{"meta":{"query_hash":"c67a6f5045a4","filters":{"topic":"Artificial Intelligence in Healthcare"},"cohort_total":843,"direct_labels_cover":7,"predictions_cover":843,"exported":843,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/c67a6f5045a4","api":"https://metacan.xera.ac/api/v1/cohort?topic=Artificial+Intelligence+in+Healthcare"},"results":[{"id":"W103825515","doi":"10.1155/2009/308710","title":"Electronic Health","year":2009,"lang":"en","type":"article","venue":"International Journal of Telemedicine and Applications","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Health care; Sociotechnical system; Health promotion; Quality (philosophy); Public health; Health technology; Public relations; Medicine; Business; Computer science; Internet privacy; Knowledge management; Political science; Nursing","score_opus":0.061659839853744215,"score_gpt":0.5077205284069615,"score_spread":0.44606068855321723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W103825515","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024770142,0.016474994,0.008622262,0.03603502,0.008269954,0.00031192385,0.009217015,0.0013885187,0.91720337],"genre_scores_gemma":[0.042917315,0.031598076,0.011796397,0.022244956,0.00761698,0.0003033345,0.014070567,0.00026655864,0.8691858],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99876606,0.00028324837,0.00009866273,0.00021033842,0.0005141478,0.0001275042],"domain_scores_gemma":[0.99719596,0.0007632364,0.00017683802,0.0006269374,0.0008655987,0.00037136668],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016078653,0.0004527822,0.00039252342,0.0021784315,0.001004357,0.0038221518,0.0011081124,0.002763716,0.30122924],"category_scores_gemma":[0.007336813,0.00020407817,0.0004174558,0.0025771065,0.00076736,0.0024902497,0.0025147446,0.0011867298,0.13403128],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000070183625,0.000058485908,0.0018232071,0.00037558723,0.000020619487,0.00016309747,0.00015599305,0.00013494038,0.00035767458,0.040026926,0.61896807,0.33784518],"study_design_scores_gemma":[0.000011963514,0.000027812132,0.0015197897,0.0002750105,0.000008557738,0.00033720644,0.00010096704,0.00009903891,0.00019148852,0.0070713265,0.99034774,0.000009144707],"about_ca_topic_score_codex":0.0016825845,"about_ca_topic_score_gemma":0.0014233746,"teacher_disagreement_score":0.30122924,"about_ca_system_score_codex":0.0009843141,"about_ca_system_score_gemma":0.001723156,"threshold_uncertainty_score":0.9967117},"labels":[],"label_agreement":null},{"id":"W127143195","doi":"10.3233/978-1-58603-979-0-519","title":"Medical Text Analytics Tools for Search and Classification","year":2009,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"","keywords":"Computer science; Analytics; Data science; Information retrieval","score_opus":0.39109821879025863,"score_gpt":0.5770917842271062,"score_spread":0.18599356543684753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W127143195","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00512617,0.0019464755,0.69703716,0.002072951,0.0002715228,0.0027477755,0.06945472,0.20850666,0.012836616],"genre_scores_gemma":[0.031139191,0.0011177902,0.8870649,0.00073373347,0.0002745134,0.003009287,0.063631885,0.0042609167,0.008767832],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951605,0.0012420497,0.001114979,0.00063585537,0.0016624313,0.00018418492],"domain_scores_gemma":[0.97984284,0.013229996,0.0014384409,0.0017648416,0.0030159024,0.0007079531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006831657,0.0026416816,0.0019060884,0.015284471,0.0010326668,0.0043953797,0.00254622,0.0014577126,0.035502583],"category_scores_gemma":[0.024122356,0.0008027251,0.0016889313,0.011674525,0.00063020684,0.005650668,0.0028422961,0.0015982935,0.022777017],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007066094,0.00035748436,0.0024835533,0.0031454472,0.00027803166,0.00071289175,0.0008944271,0.003994762,0.009058227,0.021767361,0.21821436,0.73838687],"study_design_scores_gemma":[0.0009574343,0.0005343285,0.009224119,0.0023580357,0.00035212835,0.0023155939,0.0012206362,0.16075757,0.04167148,0.12971058,0.65044844,0.00044961044],"about_ca_topic_score_codex":0.0028939147,"about_ca_topic_score_gemma":0.0024479982,"teacher_disagreement_score":0.035502583,"about_ca_system_score_codex":0.0013068134,"about_ca_system_score_gemma":0.0021899908,"threshold_uncertainty_score":0.11876798},"labels":[],"label_agreement":null},{"id":"W1527947811","doi":"10.1002/9780470987605.ch3","title":"Graphics to Display the Data Distribution","year":2008,"lang":"en","type":"other","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Geological Survey of Canada","funders":"","keywords":"Histogram; Plot (graphics); Scatter plot; Graphics; TRACE (psycholinguistics); Mathematics; Pattern recognition (psychology); Computer science; Artificial intelligence; Statistics; Computer graphics (images); Image (mathematics)","score_opus":0.32643623993173815,"score_gpt":0.5318138613214639,"score_spread":0.20537762138972576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1527947811","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00095791166,0.001840846,0.14814714,0.007748112,0.011478694,0.0030778502,0.2897169,0.19939728,0.3376353],"genre_scores_gemma":[0.011948971,0.0055781403,0.23003137,0.0099996375,0.0038839662,0.006144542,0.15198249,0.09582254,0.48460838],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979588,0.0004826588,0.00024087584,0.00022080539,0.0009787156,0.000118076634],"domain_scores_gemma":[0.9894996,0.0052873045,0.00038358168,0.0012336448,0.0032659555,0.00032977026],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024864564,0.002580807,0.0021226862,0.003781464,0.0007909208,0.004808516,0.0021697062,0.0017195654,0.6860949],"category_scores_gemma":[0.02919114,0.0012629902,0.0012826193,0.005126788,0.0006640276,0.002841322,0.0020107364,0.0038700637,0.45481423],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003577245,0.000022156295,0.00010507883,0.00020694474,0.000007973384,0.000026407279,0.000053725445,0.0003692327,0.00038381165,0.0024598266,0.96997976,0.026349239],"study_design_scores_gemma":[0.00007834328,0.000027218008,0.0006971569,0.00017269244,0.000011592202,0.000076868295,0.000068644884,0.0019051939,0.0005645377,0.0044976715,0.99186534,0.000034764256],"about_ca_topic_score_codex":0.005240656,"about_ca_topic_score_gemma":0.0041948673,"teacher_disagreement_score":0.6860949,"about_ca_system_score_codex":0.0012166835,"about_ca_system_score_gemma":0.0021144866,"threshold_uncertainty_score":0.44774753},"labels":[],"label_agreement":null},{"id":"W1603920668","doi":"10.1109/meco.2015.7181948","title":"An intelligent system for diabetes prediction","year":2015,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ministère de l'Économie, de la Science et de l'Innovation - Québec; Heart and Stroke Foundation of Canada","keywords":"Computer science; Support vector machine; Naive Bayes classifier; Reliability (semiconductor); Machine learning; Process (computing); Artificial intelligence; Bayes' theorem; Data mining; Outcome (game theory); The Internet; Joint (building); Bayesian probability; Engineering","score_opus":0.3119049866439406,"score_gpt":0.5105526515381021,"score_spread":0.19864766489416152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1603920668","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.120016634,0.0041029877,0.75226015,0.0021970698,0.0014073341,0.0007868471,0.008985519,0.09191815,0.018325275],"genre_scores_gemma":[0.6874802,0.0014658166,0.2908353,0.0011127235,0.0003733847,0.0004708264,0.008452856,0.00023218036,0.009576766],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995524,0.00007450276,0.000047793845,0.0001564069,0.00013191221,0.000036979873],"domain_scores_gemma":[0.99946445,0.00020023141,0.00004796415,0.00008924543,0.00016027833,0.000037764217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007207295,0.0005968141,0.00066782255,0.0010935361,0.0004553864,0.0011597018,0.0008816335,0.00071709463,0.0049174353],"category_scores_gemma":[0.0024688176,0.00018914233,0.0004531939,0.0007695584,0.00015017754,0.00085979846,0.0006217258,0.00065039675,0.0027382192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014624941,0.00060121354,0.017268516,0.00040105468,0.00023194148,0.00077592855,0.000144052,0.020727353,0.019132327,0.0041288324,0.04399907,0.8911274],"study_design_scores_gemma":[0.00023641322,0.0007034543,0.019175446,0.00012833379,0.0003945212,0.0015189354,0.00009894072,0.8785867,0.029610936,0.012268256,0.0571485,0.00012957874],"about_ca_topic_score_codex":0.0036481528,"about_ca_topic_score_gemma":0.0031432915,"teacher_disagreement_score":0.0049174353,"about_ca_system_score_codex":0.00039162824,"about_ca_system_score_gemma":0.00067319407,"threshold_uncertainty_score":0.016450465},"labels":[],"label_agreement":null},{"id":"W1777383459","doi":"","title":"Crunching big data in the cloud with Hadoop and BigInsights","year":2011,"lang":"en","type":"article","venue":"Conference of the Centre for Advanced Studies on Collaborative Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada)","funders":"","keywords":"Computer science; Big data; Cloud computing; Petabyte; The Internet; Data science; Unstructured data; Web traffic; Volume (thermodynamics); Data mining; World Wide Web","score_opus":0.7283515559636305,"score_gpt":0.575856521405224,"score_spread":0.15249503455840652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1777383459","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045163143,0.0347079,0.46005198,0.06452796,0.02060214,0.003218993,0.055289462,0.25597346,0.06046503],"genre_scores_gemma":[0.2970075,0.01759078,0.51980877,0.018243818,0.004745705,0.0029174231,0.10226882,0.019558555,0.017858608],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9906639,0.0016570262,0.0005944396,0.0013764042,0.004617058,0.0010910908],"domain_scores_gemma":[0.9857308,0.0027446938,0.0005619184,0.0049229623,0.002921806,0.0031176943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076721055,0.002992556,0.0022707614,0.0032259307,0.0040718988,0.008163747,0.0058882656,0.0016365079,0.0071906894],"category_scores_gemma":[0.02016081,0.0021562746,0.002753508,0.0067493194,0.003948712,0.014692013,0.012349342,0.009425108,0.005957939],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015461085,0.00034208992,0.004048416,0.0014327028,0.000847177,0.00064857857,0.0013331977,0.02470485,0.0059310356,0.04095619,0.77212167,0.14608805],"study_design_scores_gemma":[0.00091096846,0.00025637806,0.004180032,0.0008453787,0.00019809019,0.00038290746,0.0018451142,0.16561627,0.008135368,0.3387656,0.47828287,0.00058100553],"about_ca_topic_score_codex":0.013868786,"about_ca_topic_score_gemma":0.013579818,"teacher_disagreement_score":0.013868786,"about_ca_system_score_codex":0.00240266,"about_ca_system_score_gemma":0.005760301,"threshold_uncertainty_score":0.04057443},"labels":[],"label_agreement":null},{"id":"W1895464879","doi":"10.15353/joci.v9i2.3173","title":"Impact of Internet on delivery of critical cardiac health care: A case study from India","year":2012,"lang":"en","type":"article","venue":"The Journal of Community Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"The Internet; Telemedicine; General partnership; Logistic regression; Medicine; Intensive care; Business; Health care; Medical emergency; Public health; Emergency medicine; Nursing; Intensive care medicine; Computer science; Economic growth; Internal medicine; World Wide Web; Finance; Economics","score_opus":0.21517281689962167,"score_gpt":0.5320459750662858,"score_spread":0.31687315816666417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1895464879","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9974721,0.00009574058,0.00015437687,0.0002956813,0.000004345184,0.0000395378,0.000035983616,0.0000043585983,0.0018978046],"genre_scores_gemma":[0.9986053,0.00035111164,0.0003542328,0.00010954486,0.0000099792105,0.000026601789,0.000023092689,0.0000046651917,0.00051541405],"study_design_codex":"case_report","study_design_gemma":"case_report","domain_scores_codex":[0.99847156,0.0007356024,0.00009199595,0.00007882875,0.00021155507,0.000410442],"domain_scores_gemma":[0.9951336,0.0026653777,0.0009745033,0.0002103694,0.0002928499,0.0007232403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009040422,0.00039652453,0.00029764473,0.0016277884,0.0034505413,0.0016032051,0.0012869133,0.0016765553,0.0023119762],"category_scores_gemma":[0.0039479,0.0003761714,0.00048314763,0.0018581351,0.0012968088,0.0006973984,0.0013273655,0.0011786754,0.00023682644],"study_design_candidate":"case_report","study_design_consensus":"case_report","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003605171,0.004002946,0.3979263,0.00066371425,0.00014251827,0.4460213,0.11044532,0.0023869153,0.0022995865,0.003944755,0.0027408586,0.029065179],"study_design_scores_gemma":[0.00013694684,0.0025115123,0.3291496,0.00050543644,0.0002699135,0.24305871,0.3997823,0.0071254964,0.003937933,0.0007575635,0.012573806,0.00019071397],"about_ca_topic_score_codex":0.023811968,"about_ca_topic_score_gemma":0.035932668,"teacher_disagreement_score":0.023811968,"about_ca_system_score_codex":0.002696221,"about_ca_system_score_gemma":0.0015385214,"threshold_uncertainty_score":0.04734671},"labels":[],"label_agreement":null},{"id":"W1906803142","doi":"10.1155/2015/676129","title":"Ensemble Merit Merge Feature Selection for Enhanced Multinomial Classification in Alzheimer’s Dementia","year":2015,"lang":"en","type":"article","venue":"Computational and Mathematical Methods in Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; F. Hoffmann-La Roche; University of Southern California; DoD Alzheimer's Disease Neuroimaging Initiative; Pfizer; BioClinica; Biogen; Bristol-Myers Squibb; University of California, San Diego; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Feature selection; Artificial intelligence; Random forest; Support vector machine; Pattern recognition (psychology); Computer science; Naive Bayes classifier; Classifier (UML); Ensemble learning; Machine learning","score_opus":0.46031012931662146,"score_gpt":0.6029290803583585,"score_spread":0.142618951041737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1906803142","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28712976,0.0014227283,0.7088559,0.0002793725,0.00008536972,0.00007231662,0.000158516,0.0006436721,0.0013523449],"genre_scores_gemma":[0.8458669,0.00024217795,0.15179542,0.000058420017,0.00006741169,0.00007550939,0.00035733875,0.00004149238,0.0014952921],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993831,0.00020325073,0.000043757762,0.00008195775,0.00021043282,0.00007759485],"domain_scores_gemma":[0.9990835,0.00043618112,0.00006566824,0.0000708115,0.00030371608,0.000040185394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002334546,0.00048925163,0.0011970064,0.001403199,0.0004450438,0.0006479464,0.0006072512,0.00060493767,0.0007432919],"category_scores_gemma":[0.0029059902,0.00021695903,0.0008913577,0.0009812368,0.0001869062,0.0007190162,0.00058385386,0.00057399453,0.00023687205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006807805,0.0002329835,0.016835762,0.000090065034,0.00025359675,0.00026473403,0.00013817803,0.14984398,0.022677459,0.002398357,0.0032537312,0.80333036],"study_design_scores_gemma":[0.000014515071,0.00016584329,0.0063980683,0.000009486763,0.000052872303,0.00012979926,0.000031424424,0.9870231,0.0040983576,0.0011116092,0.00094959413,0.000015370233],"about_ca_topic_score_codex":0.0023609519,"about_ca_topic_score_gemma":0.003100631,"teacher_disagreement_score":0.0023609519,"about_ca_system_score_codex":0.00037068367,"about_ca_system_score_gemma":0.0005367945,"threshold_uncertainty_score":0.0123464465},"labels":[],"label_agreement":null},{"id":"W1926248049","doi":"10.1002/bimj.201100251","title":"Regression trees for predicting mortality in patients with cardiovascular disease: What improvement is achieved by using ensemble‐based methods?","year":2012,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Logistic regression; Regression; Statistics; Random forest; Regression analysis; Covariate; Predictive modelling; Population; Medicine; Machine learning; Artificial intelligence; Computer science; Mathematics","score_opus":0.22839515640652572,"score_gpt":0.5023475563129224,"score_spread":0.27395239990639664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1926248049","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6219359,0.07208856,0.2789207,0.017383527,0.0017405831,0.00016497985,0.002107289,0.0011858572,0.004472577],"genre_scores_gemma":[0.9178316,0.015502956,0.061957832,0.0010078999,0.0014436301,0.00009993388,0.0014261017,0.00007705416,0.0006530437],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99626344,0.002706943,0.00014911305,0.00031287095,0.00042610746,0.00014141847],"domain_scores_gemma":[0.98391944,0.011242692,0.0014851177,0.0013852181,0.0015463494,0.0004211531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013295764,0.001097825,0.0019384699,0.0015401549,0.0002575618,0.0010571103,0.0010351371,0.0010014767,0.00076076377],"category_scores_gemma":[0.030177986,0.00027459,0.0012375595,0.0015676088,0.00027282332,0.0026292745,0.0006462806,0.0018543891,0.00058153516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010039705,0.0003909012,0.3115988,0.00050781405,0.003122011,0.00011409228,0.0005169752,0.090571925,0.0007225252,0.0022133456,0.009634794,0.5796028],"study_design_scores_gemma":[0.0002761065,0.0018685926,0.18206415,0.0010913227,0.0019230219,0.0004453917,0.0007486237,0.77058625,0.001389566,0.030512678,0.008880073,0.00021433421],"about_ca_topic_score_codex":0.0029998445,"about_ca_topic_score_gemma":0.0046400153,"teacher_disagreement_score":0.013295764,"about_ca_system_score_codex":0.0002728103,"about_ca_system_score_gemma":0.00048000453,"threshold_uncertainty_score":0.0703156},"labels":[],"label_agreement":null},{"id":"W1966130221","doi":"10.5539/gjhs.v7n4p392","title":"Prediction of Breast Cancer Survival Through Knowledge Discovery in Databases","year":2015,"lang":"en","type":"article","venue":"Global Journal of Health Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Iran University of Medical Sciences","keywords":"Breast cancer; Context (archaeology); Medicine; IBM; Predictive modelling; Cancer; Oncology; Machine learning; Computer science; Internal medicine; Biology","score_opus":0.4373148152868181,"score_gpt":0.5608005764447357,"score_spread":0.1234857611579176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966130221","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54280806,0.007323447,0.40939474,0.0045321486,0.00021133375,0.0009910036,0.02545245,0.0030251283,0.0062617348],"genre_scores_gemma":[0.79822636,0.0033717025,0.18179873,0.0002701454,0.000104381514,0.00037962417,0.015130813,0.00003417641,0.00068403943],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967674,0.0011989548,0.00053565827,0.0005005903,0.0008005,0.0001968631],"domain_scores_gemma":[0.98877174,0.008361977,0.00092629204,0.00077724084,0.0009779115,0.00018487206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005296916,0.0005530482,0.0010248926,0.0057695033,0.00049552746,0.0026666133,0.0011489864,0.0007701864,0.0006295888],"category_scores_gemma":[0.017717991,0.00031416348,0.0011469098,0.0047302456,0.00026291903,0.001830033,0.0011809168,0.0010118387,0.00041203678],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009895703,0.0013838169,0.25394294,0.001490514,0.000900968,0.0011613123,0.0007155419,0.097961776,0.0036447612,0.007110414,0.010675731,0.62002265],"study_design_scores_gemma":[0.000109742534,0.0005253955,0.05941821,0.00047341888,0.00062182697,0.0008142628,0.00096682867,0.88555056,0.00981403,0.028955998,0.012635181,0.00011458583],"about_ca_topic_score_codex":0.005872171,"about_ca_topic_score_gemma":0.005048728,"teacher_disagreement_score":0.005872171,"about_ca_system_score_codex":0.0007209796,"about_ca_system_score_gemma":0.0018950901,"threshold_uncertainty_score":0.02801311},"labels":[],"label_agreement":null},{"id":"W1967140955","doi":"10.1145/2180796.2180809","title":"Knowledge discovery system for automated quality abstraction","year":2012,"lang":"en","type":"article","venue":"ACM SIGHIT Record","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicaid; Computer science; Transparency (behavior); Quality (philosophy); Commission; Quarter (Canadian coin); Core (optical fiber); Abstraction; Health care; Computer security; Business; Telecommunications","score_opus":0.3219959649906098,"score_gpt":0.5526751666156433,"score_spread":0.23067920162503353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967140955","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0101873595,0.0003701681,0.7658211,0.001297746,0.00014993474,0.0010661344,0.012011356,0.20035157,0.008744695],"genre_scores_gemma":[0.13505384,0.00033880037,0.82640964,0.0008825541,0.00009695867,0.0011076112,0.027704163,0.0014845504,0.0069218813],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973755,0.00046618868,0.00042367532,0.0006963991,0.000873428,0.00016485233],"domain_scores_gemma":[0.9943183,0.002614609,0.00052778557,0.0010939424,0.0012063679,0.00023891836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037103626,0.00094485667,0.0009378952,0.004051143,0.0013755523,0.0021163528,0.0025714124,0.001161464,0.009566707],"category_scores_gemma":[0.012207062,0.00071889383,0.0013700279,0.0028285636,0.00047467143,0.0027836107,0.0025684896,0.0018369351,0.005469563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010241217,0.001072056,0.011775778,0.0012723552,0.00044914984,0.0012518677,0.00082525273,0.022989297,0.021583695,0.028998964,0.17365831,0.73509914],"study_design_scores_gemma":[0.0007154454,0.00032897663,0.008053555,0.0002467165,0.00043732504,0.00096602755,0.00029861566,0.6974091,0.054757673,0.04870831,0.1878081,0.00027026143],"about_ca_topic_score_codex":0.013752341,"about_ca_topic_score_gemma":0.014357286,"teacher_disagreement_score":0.013752341,"about_ca_system_score_codex":0.00209877,"about_ca_system_score_gemma":0.0040675155,"threshold_uncertainty_score":0.03200376},"labels":[],"label_agreement":null},{"id":"W1974868900","doi":"10.1109/iccabs.2012.6182656","title":"Poster: Applying data mining algorithms to early detection of liver cancer","year":2012,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Incidence (geometry); Cancer; Liver cancer; Cancer incidence; Survivability; Computer science; Algorithm; Medicine; Data mining; Mathematics; Internal medicine","score_opus":0.39691258328588613,"score_gpt":0.5253535574290303,"score_spread":0.1284409741431442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974868900","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09177912,0.0153143825,0.7923248,0.030542403,0.02277087,0.0011473082,0.007205947,0.009569249,0.02934586],"genre_scores_gemma":[0.37161055,0.007478228,0.5628774,0.0034650196,0.0060973796,0.00038687963,0.008760095,0.00071475067,0.038609754],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907124,0.00028112062,0.00009792447,0.0002007843,0.0002845562,0.000064456915],"domain_scores_gemma":[0.9961367,0.0016944523,0.00011969049,0.0002555124,0.0015496858,0.00024391049],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034290156,0.0008667037,0.00077399466,0.0017610607,0.0006631194,0.0017572698,0.0010236504,0.00116867,0.009032051],"category_scores_gemma":[0.009359811,0.0003025044,0.0010128331,0.0012003086,0.0003183566,0.0011234473,0.00091576943,0.0017044798,0.004297816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008115057,0.00047492218,0.010032343,0.00041089667,0.00027630664,0.00031589624,0.0001009148,0.021337787,0.006950688,0.0016985663,0.113271125,0.84431916],"study_design_scores_gemma":[0.00021980009,0.0010081101,0.015658375,0.00032110457,0.00033809093,0.0010126214,0.00032483588,0.86359465,0.026941475,0.02473325,0.0657298,0.00011788884],"about_ca_topic_score_codex":0.0018387745,"about_ca_topic_score_gemma":0.002000699,"teacher_disagreement_score":0.009032051,"about_ca_system_score_codex":0.0003395466,"about_ca_system_score_gemma":0.0006197914,"threshold_uncertainty_score":0.030215204},"labels":[],"label_agreement":null},{"id":"W1980636080","doi":"10.1007/s10654-006-0005-y","title":"Applications of Artificial Intelligence Systems in the Analysis of Epidemiological Data","year":2006,"lang":"en","type":"review","venue":"European Journal of Epidemiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Epidemiology; Medicine; Data science; Artificial intelligence; Computer science; Pathology","score_opus":0.7083805879569877,"score_gpt":0.608071448142109,"score_spread":0.10030913981487866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980636080","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00030252433,0.99237025,0.00509114,0.00070163514,0.00023185923,0.000023906083,0.000024564286,0.00003079201,0.0012233263],"genre_scores_gemma":[0.0024997995,0.9898864,0.0066956957,0.00023280716,0.00033422525,0.000018691697,0.000049782626,0.0000047363383,0.00027789435],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981415,0.00057623413,0.00024676332,0.00020992741,0.0007737575,0.00005172154],"domain_scores_gemma":[0.9873769,0.010472096,0.0004714531,0.0002467106,0.0012753092,0.00015760098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003913106,0.0013488464,0.0022568388,0.00650041,0.00042887108,0.0025639543,0.0018524994,0.001962473,0.0017350999],"category_scores_gemma":[0.008019915,0.00054543855,0.0012210453,0.009496144,0.0013581216,0.0022988894,0.0012824886,0.0025594828,0.0010203857],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041099927,0.00013303888,0.00096784934,0.012389441,0.00038838116,0.00022949075,0.00013796201,0.002141854,0.0007123235,0.009156539,0.008202962,0.96549916],"study_design_scores_gemma":[0.00006151862,0.00023360003,0.0067158635,0.014739625,0.0009063823,0.0033850041,0.00041830447,0.006719544,0.0025643995,0.052530535,0.91156536,0.0001599563],"about_ca_topic_score_codex":0.0021638966,"about_ca_topic_score_gemma":0.0026461594,"teacher_disagreement_score":0.00650041,"about_ca_system_score_codex":0.0012381291,"about_ca_system_score_gemma":0.0020211604,"threshold_uncertainty_score":0.020694733},"labels":[],"label_agreement":null},{"id":"W1987331031","doi":"10.1186/cc5599","title":"ISIS program: a new tool for medical research at the bedside in critical care units","year":2007,"lang":"en","type":"article","venue":"Critical Care","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Bayer Canada","keywords":"Medicine; Critical illness; Information flow; Medical emergency; Data science; Critically ill; Intensive care medicine; Computer science","score_opus":0.549014830387155,"score_gpt":0.6809534762309367,"score_spread":0.13193864584378168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987331031","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010953119,0.00070116937,0.5684881,0.0015220965,0.00042552254,0.0014572722,0.018266093,0.3836195,0.014567073],"genre_scores_gemma":[0.06560897,0.0012115771,0.86204517,0.0011327332,0.00057659205,0.0041366187,0.030233499,0.01601649,0.019038301],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99707496,0.0009408643,0.00036425734,0.00042252455,0.0010626562,0.00013471136],"domain_scores_gemma":[0.98476636,0.010054539,0.00090004486,0.0018576178,0.001340306,0.0010811561],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060723657,0.0014194438,0.0011752397,0.005494726,0.0006427734,0.0024259167,0.0017248186,0.0008027266,0.031230923],"category_scores_gemma":[0.016704218,0.00074852037,0.0010276777,0.0034713997,0.00091202784,0.0037885339,0.0032171675,0.0014131429,0.011744783],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028464077,0.00068165275,0.009749761,0.001609959,0.00027182262,0.00060178945,0.0012644151,0.0029270994,0.02595146,0.02434339,0.2799584,0.64979386],"study_design_scores_gemma":[0.001896107,0.0015710243,0.014720167,0.00062022195,0.0005047156,0.0018672146,0.00048113905,0.088220365,0.06480513,0.05394105,0.77102613,0.00034670718],"about_ca_topic_score_codex":0.0010397884,"about_ca_topic_score_gemma":0.0010816054,"teacher_disagreement_score":0.031230923,"about_ca_system_score_codex":0.0007166533,"about_ca_system_score_gemma":0.0021779218,"threshold_uncertainty_score":0.10447788},"labels":[],"label_agreement":null},{"id":"W2020502126","doi":"10.1016/j.diabres.2013.01.023","title":"Evaluating the risk of type 2 diabetes mellitus using artificial neural network: An effective classification approach","year":2013,"lang":"en","type":"article","venue":"Diabetes Research and Clinical Practice","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":93,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire Sainte-Justine","funders":"","keywords":"Receiver operating characteristic; Medicine; Logistic regression; Artificial neural network; Multivariate statistics; Statistics; Area under the curve; Type 2 Diabetes Mellitus; Data set; Artificial intelligence; Machine learning; Diabetes mellitus; Internal medicine; Mathematics; Computer science; Endocrinology","score_opus":0.6392326485622599,"score_gpt":0.6561973894622376,"score_spread":0.01696474089997768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020502126","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8450652,0.0016447197,0.14712116,0.00088976487,0.0002075113,0.00018389025,0.0008855888,0.00025369835,0.003748391],"genre_scores_gemma":[0.97433996,0.000318709,0.023981167,0.000056500918,0.00007477985,0.000052538882,0.0004367929,0.000006728665,0.00073283317],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895144,0.00039221268,0.0001518612,0.00015064722,0.00027675516,0.00007704345],"domain_scores_gemma":[0.9972377,0.0018239203,0.0002328745,0.0001070881,0.0005024437,0.000095955176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024746563,0.0008263037,0.0011636103,0.002592969,0.00039109832,0.0014514254,0.00074780633,0.001039473,0.0010274726],"category_scores_gemma":[0.0052213194,0.0001819017,0.0008485828,0.0010614399,0.00021705651,0.00084519875,0.0004157771,0.0007176128,0.00018731279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026697095,0.0018926733,0.49165732,0.00021039613,0.0012495153,0.00038632905,0.0001235173,0.11161433,0.0058639585,0.002186736,0.0021038582,0.38004154],"study_design_scores_gemma":[0.000058518275,0.00044417917,0.05904189,0.0000381117,0.00042435763,0.0001586421,0.00014990698,0.93541217,0.0017273013,0.0021523668,0.00035513903,0.000037331774],"about_ca_topic_score_codex":0.0045163757,"about_ca_topic_score_gemma":0.0036853675,"teacher_disagreement_score":0.0045163757,"about_ca_system_score_codex":0.0005597064,"about_ca_system_score_gemma":0.00053862494,"threshold_uncertainty_score":0.013087332},"labels":[],"label_agreement":null},{"id":"W2021753742","doi":"10.5210/ojphi.v6i1.5015","title":"A Probabilistic Case-finding Algorithm for Chronic Disease Surveillance","year":2014,"lang":"en","type":"article","venue":"Online Journal of Public Health Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Logistic regression; Medicine; Cohort; Probabilistic logic; Diabetes mellitus; Data mining; Algorithm; Statistics; Artificial intelligence; Computer science; Internal medicine; Mathematics","score_opus":0.24942133364026703,"score_gpt":0.5017967445012326,"score_spread":0.25237541086096554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021753742","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049430775,0.00012170248,0.99200046,0.0001807343,0.000021924448,0.0003354196,0.00018208651,0.0019208707,0.00029375943],"genre_scores_gemma":[0.06596036,0.00010638588,0.93175936,0.00012004483,0.00003946852,0.0007323791,0.0006743606,0.00010598245,0.0005017802],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966119,0.0011666076,0.00046364628,0.00073105603,0.00085618475,0.00017050545],"domain_scores_gemma":[0.9905945,0.006606312,0.00059544254,0.0006351114,0.0013537268,0.00021485622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076052863,0.0010367058,0.0016500439,0.004085219,0.001217365,0.0017115549,0.003483335,0.0015358339,0.0042664493],"category_scores_gemma":[0.021938594,0.0008696065,0.0016663173,0.002613637,0.00070587464,0.0016040838,0.0029929697,0.0016094,0.0015232487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003636041,0.00045401818,0.0179955,0.00025442088,0.00028371764,0.00044067152,0.000276925,0.22176066,0.0018039766,0.013546927,0.008881538,0.733938],"study_design_scores_gemma":[0.00011445617,0.000044054756,0.00066614046,0.000018508385,0.00003894524,0.00025524345,0.00002033169,0.9863128,0.00051854836,0.010362925,0.0016312517,0.000016940894],"about_ca_topic_score_codex":0.011700401,"about_ca_topic_score_gemma":0.009377854,"teacher_disagreement_score":0.011700401,"about_ca_system_score_codex":0.0012155031,"about_ca_system_score_gemma":0.002902875,"threshold_uncertainty_score":0.040221095},"labels":[],"label_agreement":null},{"id":"W2025647920","doi":"10.5539/gjhs.v7n5p304","title":"Type 2 Diabetes Mellitus Screening and Risk Factors Using Decision Tree: Results of Data Mining","year":2015,"lang":"en","type":"article","venue":"Global Journal of Health Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":102,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"University of Tabriz; Tabriz University of Medical Sciences; Iran University of Medical Sciences","keywords":"C4.5 algorithm; Decision tree; Medicine; Body mass index; Diabetes mellitus; Data mining; Data pre-processing; Decision tree learning; Type 2 diabetes; Decision tree model; Identification (biology); Computer science; Machine learning; Internal medicine; Support vector machine; Naive Bayes classifier; Endocrinology","score_opus":0.44621319240515506,"score_gpt":0.548326548722445,"score_spread":0.10211335631728996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025647920","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87947255,0.002133896,0.10958664,0.0016014986,0.00012368178,0.00031087085,0.0025764012,0.00041114743,0.0037832905],"genre_scores_gemma":[0.95728576,0.0005426424,0.040316418,0.000064723165,0.000037953472,0.00008778031,0.0012792995,0.000017496257,0.000367911],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99782324,0.0012143945,0.00020452806,0.00022915013,0.00042579242,0.00010288005],"domain_scores_gemma":[0.9878995,0.010358202,0.00034395253,0.00028920098,0.00095453986,0.00015463421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057175383,0.00089054496,0.00083272427,0.002149517,0.00039456057,0.0012572459,0.00083605445,0.0005567669,0.0010669947],"category_scores_gemma":[0.013710825,0.00018900982,0.0014969705,0.0017851569,0.00017032897,0.0010935486,0.00043481676,0.0006680969,0.00022753334],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015135334,0.001390366,0.47468764,0.0007670865,0.001279058,0.0008983498,0.0005720007,0.25552213,0.0012517023,0.0027447958,0.004589602,0.25478375],"study_design_scores_gemma":[0.00008534561,0.0004403083,0.040468205,0.00015983178,0.00047794465,0.00035545716,0.00031690818,0.951072,0.0013998854,0.0040191608,0.0011757634,0.000029295365],"about_ca_topic_score_codex":0.0054976763,"about_ca_topic_score_gemma":0.0025677923,"teacher_disagreement_score":0.0057175383,"about_ca_system_score_codex":0.00059108017,"about_ca_system_score_gemma":0.0010726424,"threshold_uncertainty_score":0.030237556},"labels":[],"label_agreement":null},{"id":"W2031989156","doi":"10.2481/dsj.2.25","title":"Data integration and knowledge discovery in biomedical databases. Reliable information from unreliable sources","year":2003,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Scope (computer science); Computer science; Data science; Usability; Metadata; Transparency (behavior); Open data; Reuse; Implementation; World Wide Web; Data discovery; Data publishing; Publishing; Software engineering; Political science; Engineering","score_opus":0.2754938637313639,"score_gpt":0.5016500590355036,"score_spread":0.22615619530413972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031989156","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067679877,0.076502904,0.85501075,0.034708902,0.0013043983,0.000595469,0.0027689547,0.0018635234,0.020477086],"genre_scores_gemma":[0.1494963,0.044748392,0.7807166,0.005439686,0.0024836578,0.00087977643,0.0073523987,0.00057208166,0.0083111115],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9604355,0.018429363,0.0045870477,0.0030945528,0.0127971675,0.0006563522],"domain_scores_gemma":[0.93059564,0.047174703,0.0044741128,0.011595683,0.00530367,0.0008560392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.043434348,0.0009461007,0.0033378208,0.015827496,0.0026863944,0.017415568,0.003775336,0.003931697,0.004110878],"category_scores_gemma":[0.111411326,0.0019487641,0.002696335,0.026899697,0.0067494125,0.02651634,0.01253912,0.0036729975,0.0031759571],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002291806,0.00011085976,0.0044486756,0.0042726267,0.00059297966,0.00090350595,0.0031041272,0.008177101,0.0013139078,0.5193773,0.033527367,0.4239423],"study_design_scores_gemma":[0.000043894994,0.000046202484,0.0013132268,0.0016569921,0.0002440066,0.00089788163,0.0009914953,0.0338826,0.002417628,0.8319884,0.12643251,0.00008509575],"about_ca_topic_score_codex":0.0033346259,"about_ca_topic_score_gemma":0.0027853095,"teacher_disagreement_score":0.043434348,"about_ca_system_score_codex":0.0026365924,"about_ca_system_score_gemma":0.006708412,"threshold_uncertainty_score":0.22970557},"labels":[],"label_agreement":null},{"id":"W2034448355","doi":"10.1109/jbhi.2013.2274733","title":"Data Mining in Bone Marrow Transplant Records to Identify Patients With High Odds of Survival","year":2013,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"Mitacs; Tehran University of Medical Sciences and Health Services","keywords":"Medicine; Odds; Odds ratio; Prioritization; Confidence interval; Matching (statistics); Probabilistic logic; Bone marrow transplant; Data mining; Computer science; Internal medicine; Bone marrow; Oncology; Bone marrow transplantation; Artificial intelligence; Logistic regression; Pathology","score_opus":0.17465877003162664,"score_gpt":0.45751510830160497,"score_spread":0.28285633826997836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034448355","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9781276,0.00080619904,0.012904346,0.0007075028,0.000036124544,0.00015444914,0.00581561,0.00017982625,0.0012682657],"genre_scores_gemma":[0.98012996,0.00028412646,0.013737494,0.00008192493,0.000034891193,0.000079284124,0.005461087,0.000006899267,0.00018430156],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982626,0.000530308,0.00044537615,0.00027734693,0.00036192665,0.00012242203],"domain_scores_gemma":[0.98976666,0.006280111,0.0020909482,0.0005956204,0.000996789,0.000269913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028860003,0.0002496968,0.00060395827,0.0044969576,0.0003251496,0.0011335728,0.000547322,0.00055054366,0.0006802564],"category_scores_gemma":[0.012669572,0.00017199873,0.00061516603,0.004252327,0.00016140999,0.00057326653,0.00047054488,0.00050564477,0.00027425928],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003649433,0.00020034732,0.939664,0.00017506948,0.0002037509,0.00036340713,0.00024095687,0.0028743432,0.00089124934,0.00026235665,0.0011128379,0.053646743],"study_design_scores_gemma":[0.00006489257,0.00050755235,0.8858733,0.00025390627,0.000319038,0.0024157895,0.0012627611,0.09800952,0.004983562,0.0020392481,0.004222318,0.00004826902],"about_ca_topic_score_codex":0.0032294637,"about_ca_topic_score_gemma":0.0041934117,"teacher_disagreement_score":0.0044969576,"about_ca_system_score_codex":0.00040051158,"about_ca_system_score_gemma":0.00072241115,"threshold_uncertainty_score":0.015262783},"labels":[],"label_agreement":null},{"id":"W2040991168","doi":"10.1109/conielecomp.2009.63","title":"Tutorial III: Image Processing and Analysis with Matlab","year":2009,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"MATLAB; Computer science; Graphical user interface; Coding (social sciences); Image processing; Source code; Process (computing); Variety (cybernetics); User interface; Computer engineering; Programming language; Engineering drawing; Computer hardware; Software engineering; Human–computer interaction; Artificial intelligence; Image (mathematics); Engineering","score_opus":0.08494534414740082,"score_gpt":0.47664011037245624,"score_spread":0.3916947662250554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040991168","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006074043,0.0037684029,0.9578791,0.0012712679,0.0014213106,0.00018880625,0.0010600594,0.019394193,0.01440942],"genre_scores_gemma":[0.008311293,0.013347118,0.8998174,0.0016161792,0.0021402517,0.00095720164,0.0032180776,0.008368874,0.062223595],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99881566,0.00022475341,0.00013393215,0.00017594473,0.00058153673,0.00006819226],"domain_scores_gemma":[0.9965749,0.0013833412,0.00017664128,0.00031011147,0.0013980239,0.0001569729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016038975,0.0024240043,0.0015833193,0.002166202,0.00045906755,0.0020982937,0.0018606058,0.0013949568,0.09044949],"category_scores_gemma":[0.008117422,0.00088679255,0.0013829053,0.00144547,0.0005267732,0.002285794,0.001498408,0.002700398,0.08127549],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001572273,0.00008124472,0.00023555146,0.0014692771,0.00009481563,0.0004403838,0.0002118801,0.009928499,0.01658286,0.010832985,0.3776728,0.5822924],"study_design_scores_gemma":[0.000062116706,0.00013760352,0.0011698976,0.00072922296,0.00007005542,0.0019747247,0.00014891903,0.04817302,0.018358193,0.027262283,0.9017714,0.00014255206],"about_ca_topic_score_codex":0.0009191853,"about_ca_topic_score_gemma":0.0008677772,"teacher_disagreement_score":0.09044949,"about_ca_system_score_codex":0.00051881577,"about_ca_system_score_gemma":0.00095032156,"threshold_uncertainty_score":0.30258363},"labels":[],"label_agreement":null},{"id":"W2046099868","doi":"10.1016/j.jclinepi.2007.12.008","title":"R and S-PLUS produced different classification trees for predicting patient mortality","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research; Institute for Clinical Evaluative Sciences","keywords":"Medicine; Statistics; Mathematics","score_opus":0.8048081317288023,"score_gpt":0.6610888984722897,"score_spread":0.1437192332565126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046099868","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7136564,0.003187483,0.23405932,0.002448379,0.001588783,0.00085259945,0.017326409,0.016514892,0.01036569],"genre_scores_gemma":[0.77715224,0.0010053868,0.20238902,0.00084303285,0.0004126544,0.00047842893,0.011974106,0.0013877004,0.0043573813],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952604,0.0023853737,0.000649994,0.0009362775,0.00045432968,0.00031357523],"domain_scores_gemma":[0.9693169,0.024407467,0.0005747998,0.0018418088,0.0032074666,0.0006516364],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010589187,0.0023492365,0.0018705423,0.0025384633,0.0006611421,0.0017945536,0.0014130663,0.0020520175,0.003701034],"category_scores_gemma":[0.032332767,0.00062351103,0.003284261,0.001684904,0.0004030139,0.0015636799,0.0009754002,0.002286057,0.004015826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0063970527,0.001046746,0.1167633,0.0011368456,0.0025037366,0.0006756029,0.0005862599,0.061396196,0.014110418,0.0018971348,0.02992377,0.76356286],"study_design_scores_gemma":[0.0009708248,0.0050768596,0.09485531,0.00046609834,0.004361017,0.0012816899,0.00090818485,0.83559114,0.027789775,0.013123265,0.015194164,0.0003817802],"about_ca_topic_score_codex":0.0034111787,"about_ca_topic_score_gemma":0.004969429,"teacher_disagreement_score":0.9894108,"about_ca_system_score_codex":0.0005818634,"about_ca_system_score_gemma":0.0011831338,"threshold_uncertainty_score":0.056001604},"labels":[],"label_agreement":null},{"id":"W2060947741","doi":"10.1016/j.jclinepi.2012.11.008","title":"Using methods from the data-mining and machine-learning literature for disease classification and prediction: a case study examining classification of heart failure subtypes","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":348,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Canadian Institutes of Health Research; National Institutes of Health","keywords":"Logistic regression; Random forest; Support vector machine; Decision tree; Artificial intelligence; Machine learning; Regression; Medicine; Computer science; Statistics; Mathematics","score_opus":0.8274950577973865,"score_gpt":0.6728096974974961,"score_spread":0.15468536029989044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060947741","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73048025,0.008485929,0.22261754,0.01992858,0.00027918263,0.0008976075,0.0006170984,0.00017553313,0.01651831],"genre_scores_gemma":[0.7723947,0.0038984534,0.21935801,0.0013099907,0.00011394521,0.0002938743,0.00027160454,0.00007215407,0.0022871385],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.991931,0.0053124344,0.00064570183,0.00040063105,0.0014730595,0.0002371019],"domain_scores_gemma":[0.94435304,0.048899703,0.0017256151,0.0021118254,0.002533567,0.00037629646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018527314,0.0006182059,0.0006001076,0.0030160518,0.0015329972,0.0031303419,0.0016279372,0.0016824765,0.0013217347],"category_scores_gemma":[0.046202533,0.00027385636,0.0008308134,0.0032973206,0.0013073406,0.0019606638,0.0016756656,0.0019716395,0.00034641605],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004150624,0.0020879328,0.39968455,0.0008687035,0.0002676377,0.0067063384,0.012407293,0.00364774,0.0029171302,0.013905216,0.0044244383,0.5526679],"study_design_scores_gemma":[0.00070864893,0.0031859262,0.33227843,0.0034463042,0.0014688022,0.063092984,0.067806885,0.25096902,0.021694968,0.15401277,0.10079495,0.0005404264],"about_ca_topic_score_codex":0.0060115545,"about_ca_topic_score_gemma":0.016512604,"teacher_disagreement_score":0.018527314,"about_ca_system_score_codex":0.0009949285,"about_ca_system_score_gemma":0.0020743604,"threshold_uncertainty_score":0.097983},"labels":[],"label_agreement":null},{"id":"W2062172883","doi":"10.1504/ijbdi.2014.063835","title":"Health big data analytics: current perspectives, challenges and potential solutions","year":2014,"lang":"en","type":"article","venue":"International Journal of Big Data Intelligence","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":131,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Big data; Data science; Computer science; Process (computing); Analytics; Guideline; Health data; Data mining; Knowledge management; Health care; Medicine; Political science","score_opus":0.611332550204909,"score_gpt":0.5254841188079858,"score_spread":0.08584843139692311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062172883","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004335038,0.4093628,0.055366173,0.51768684,0.0029368708,0.00015169223,0.0003905486,0.00037833073,0.0093917865],"genre_scores_gemma":[0.09728787,0.71309716,0.1355779,0.03456942,0.015282688,0.00047664304,0.0010388129,0.00014604435,0.0025235126],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99188906,0.003867871,0.00056810497,0.0007948069,0.0023704509,0.0005097514],"domain_scores_gemma":[0.95105267,0.03521248,0.0015925711,0.0015794862,0.0072129527,0.0033497985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026975289,0.0011787231,0.0015482162,0.0036861238,0.0024130922,0.013824686,0.0049341656,0.008888633,0.004328404],"category_scores_gemma":[0.022947881,0.0011553746,0.0013605633,0.0063726767,0.00774896,0.028451476,0.007901944,0.010263462,0.0013976065],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003258512,0.0003558278,0.0060733734,0.009150329,0.00019544315,0.00035922413,0.0013298811,0.0071841124,0.0012569155,0.3800362,0.101436466,0.4922965],"study_design_scores_gemma":[0.00007097815,0.00022953669,0.001927072,0.006045783,0.0000802723,0.0006665787,0.007608718,0.02968192,0.00076341094,0.62308776,0.32965127,0.0001867238],"about_ca_topic_score_codex":0.0028509707,"about_ca_topic_score_gemma":0.003449166,"teacher_disagreement_score":0.026975289,"about_ca_system_score_codex":0.003068836,"about_ca_system_score_gemma":0.0071783867,"threshold_uncertainty_score":0.14266068},"labels":[],"label_agreement":null},{"id":"W2102419299","doi":"10.1016/j.medengphy.2003.09.005","title":"Improvement and automation of artificial neural networks to estimate medical outcomes","year":2004,"lang":"en","type":"article","venue":"Medical Engineering & Physics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Carleton University","funders":"","keywords":"Artificial neural network; Automation; Artificial intelligence; Engineering; Computer science; Machine learning; Mechanical engineering","score_opus":0.04403539195379631,"score_gpt":0.42963580541074015,"score_spread":0.38560041345694385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102419299","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08746712,0.0003724691,0.90298694,0.0003028496,0.00005229766,0.0001905929,0.00010995611,0.005939582,0.0025781917],"genre_scores_gemma":[0.58457434,0.00018861938,0.41355607,0.00010962367,0.000053583364,0.00022050757,0.00022505998,0.00019234471,0.00087987445],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962878,0.0019801012,0.0002896528,0.0005416073,0.00080447836,0.00009623943],"domain_scores_gemma":[0.9862006,0.008803986,0.0011551934,0.0017151607,0.0020495155,0.00007562614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058258143,0.0013433549,0.0006407675,0.0010920402,0.00028819757,0.0008903476,0.0009272197,0.00068980287,0.00076555193],"category_scores_gemma":[0.028849054,0.000528725,0.00035043174,0.00066603074,0.0005209789,0.001071692,0.00076152245,0.0012148387,0.00051085575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003589904,0.00023769872,0.012053614,0.000152326,0.0001655719,0.000112866415,0.0002847642,0.33534807,0.016906258,0.0022023106,0.0019602904,0.6302173],"study_design_scores_gemma":[0.000044045533,0.00009180262,0.0069033247,0.00002993958,0.00003405647,0.00007972924,0.00002517511,0.9743158,0.01378013,0.003056703,0.0016045988,0.00003463199],"about_ca_topic_score_codex":0.0046072095,"about_ca_topic_score_gemma":0.0053711846,"teacher_disagreement_score":0.0058258143,"about_ca_system_score_codex":0.0006520449,"about_ca_system_score_gemma":0.0007975891,"threshold_uncertainty_score":0.030810237},"labels":[],"label_agreement":null},{"id":"W2103289331","doi":"10.1007/s10916-010-9572-2","title":"A Novel Web-enabled Healthcare Solution on HealthVault System","year":2010,"lang":"en","type":"article","venue":"Journal of Medical Systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Health informatics; Computer science; Healthcare system; Health care; Web application; World Wide Web; Political science","score_opus":0.14417320735798422,"score_gpt":0.4778924730281015,"score_spread":0.3337192656701173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103289331","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18923321,0.0016282354,0.6403866,0.006754895,0.0015128731,0.0006581195,0.0012210968,0.092546076,0.066058904],"genre_scores_gemma":[0.712318,0.00048180766,0.22652324,0.0025155297,0.00038340478,0.00019012814,0.0018511604,0.00091611786,0.05482066],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995714,0.000097609394,0.000031778225,0.000072886774,0.00014962086,0.00007667063],"domain_scores_gemma":[0.9996402,0.00008764083,0.000018936313,0.00007687638,0.00008837581,0.00008789561],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004185185,0.00028554923,0.00042717063,0.0005134732,0.0005958938,0.0017356657,0.00097498624,0.001441299,0.011082534],"category_scores_gemma":[0.0008189471,0.0002196985,0.00035095948,0.00043759777,0.0002179235,0.0013597847,0.0014672658,0.0006317472,0.0023468405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002385394,0.0012118161,0.0061270604,0.0005044854,0.00028512668,0.0032192485,0.0007116627,0.008437936,0.109336734,0.028419128,0.1310891,0.70827234],"study_design_scores_gemma":[0.0010096645,0.0011312752,0.010877407,0.00015410916,0.00037310165,0.005060532,0.00053187716,0.5053212,0.13198234,0.018197661,0.32514858,0.00021219536],"about_ca_topic_score_codex":0.0020139876,"about_ca_topic_score_gemma":0.0024818457,"teacher_disagreement_score":0.011082534,"about_ca_system_score_codex":0.00043363086,"about_ca_system_score_gemma":0.00076468755,"threshold_uncertainty_score":0.037074745},"labels":[],"label_agreement":null},{"id":"W2110461473","doi":"10.1164/rccm.201409-1703ed","title":"Can Database Studies Be Used to Make the Tough Research Decisions?","year":2014,"lang":"en","type":"letter","venue":"American Journal of Respiratory and Critical Care Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Database; MEDLINE; Data science; Computer science","score_opus":0.5373209331426695,"score_gpt":0.605080128812804,"score_spread":0.06775919567013455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110461473","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008202286,0.001350611,0.00040616986,0.9922271,0.0050731865,0.000013548061,0.000053604475,0.000014222261,0.00077963155],"genre_scores_gemma":[0.0025236986,0.00252945,0.0032366156,0.9595302,0.031012552,0.00015082087,0.00006884179,0.000030300112,0.00091759564],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.804217,0.12144034,0.029155936,0.008102318,0.03326152,0.0038229472],"domain_scores_gemma":[0.17819393,0.6957792,0.022452742,0.024711164,0.055855863,0.023007095],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.25498205,0.0014508284,0.0056361067,0.008690343,0.007964142,0.02108646,0.009741315,0.09039722,0.01542136],"category_scores_gemma":[0.62560844,0.0027504105,0.004598534,0.006164422,0.021757903,0.039111774,0.011055455,0.061158966,0.010041106],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021794194,0.00013793894,0.003960399,0.0007282597,0.00046425912,0.0013807517,0.000575477,0.00015617686,0.00014073645,0.030286249,0.9151515,0.04680047],"study_design_scores_gemma":[0.00078471337,0.00015140763,0.00209758,0.0054375036,0.0005245751,0.0017767365,0.0030063458,0.0011557284,0.00023902423,0.31219834,0.6723174,0.0003105957],"about_ca_topic_score_codex":0.0059284046,"about_ca_topic_score_gemma":0.011836333,"teacher_disagreement_score":0.74501795,"about_ca_system_score_codex":0.007508924,"about_ca_system_score_gemma":0.022054262,"threshold_uncertainty_score":0.9187398},"labels":[],"label_agreement":null},{"id":"W2115683309","doi":"10.2196/medinform.2913","title":"Big Data and Clinicians: A Review on the State of the Science","year":2014,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":158,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Big data; Data science; Computer science; Pace; Data quality; Data mining","score_opus":0.5332844092986461,"score_gpt":0.6082372109656298,"score_spread":0.0749528016669837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115683309","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004272452,0.99798703,0.000089016,0.0011833656,0.00024038264,0.00000627345,0.000013556791,0.0000037498655,0.0004338858],"genre_scores_gemma":[0.000349876,0.99871135,0.00016995746,0.00045624122,0.00023630373,0.000009352788,0.00001285762,0.0000014037887,0.00005264208],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99708456,0.00089757965,0.0006818606,0.00025750665,0.00094601,0.00013241776],"domain_scores_gemma":[0.9735336,0.021893779,0.0012970206,0.00029010672,0.002561366,0.00042415125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00485103,0.001063867,0.002368091,0.0077579487,0.0007863756,0.002812831,0.0016699662,0.00281209,0.004042963],"category_scores_gemma":[0.012273159,0.00059161166,0.0016540823,0.012017894,0.0015816002,0.0043875994,0.0016197406,0.0029568372,0.0011671281],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007041196,0.00005215579,0.00065408007,0.09328862,0.00024824752,0.0002419545,0.00046769786,0.00030869606,0.00027916837,0.006737975,0.048072487,0.8495785],"study_design_scores_gemma":[0.000021379688,0.00008255148,0.002185551,0.107874535,0.00043307955,0.0012913167,0.00054559734,0.00015747422,0.00019301542,0.0059854463,0.8811746,0.000055401513],"about_ca_topic_score_codex":0.0030215497,"about_ca_topic_score_gemma":0.0050951582,"teacher_disagreement_score":0.0077579487,"about_ca_system_score_codex":0.0021975227,"about_ca_system_score_gemma":0.006963077,"threshold_uncertainty_score":0.025654972},"labels":[],"label_agreement":null},{"id":"W2120083095","doi":"10.1007/s11517-013-1096-8","title":"Using reduced rule base with Expert System for the diagnosis of disease in hypertension","year":2013,"lang":"en","type":"article","venue":"Medical & Biological Engineering & Computing","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Università degli Studi di Padova; York University","keywords":"Disease; Expert system; Medicine; Incidence (geometry); Human physiology; Medical emergency; Intensive care medicine; Pediatrics; Computer science; Internal medicine; Artificial intelligence; Mathematics","score_opus":0.20033524030235692,"score_gpt":0.4150317497678931,"score_spread":0.21469650946553617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120083095","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2570973,0.0038865572,0.71181804,0.00077187375,0.00058312726,0.0006915509,0.0032768317,0.008935898,0.012938837],"genre_scores_gemma":[0.70103323,0.0010497025,0.28993315,0.000397346,0.0001253428,0.00020758687,0.0032773064,0.00008063795,0.0038957188],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993554,0.00010194137,0.00010280402,0.00015920443,0.00023136003,0.000049336446],"domain_scores_gemma":[0.99852055,0.0008231735,0.000054964075,0.00012199919,0.00044082548,0.000038505863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008349089,0.00048938993,0.0009717484,0.0014970197,0.00039393446,0.001223827,0.0012787575,0.0008568333,0.0032966216],"category_scores_gemma":[0.0032961564,0.0003062863,0.00078477844,0.0005866552,0.00016297135,0.00046748642,0.00037059656,0.00071004994,0.0009594374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014709176,0.0009957213,0.011188744,0.00077710755,0.0006345471,0.005654988,0.0002558326,0.107336946,0.04800491,0.0021058882,0.0099920565,0.8115824],"study_design_scores_gemma":[0.00028170718,0.0005886594,0.010842773,0.00019940743,0.001142991,0.0020706458,0.00015317995,0.931383,0.03817996,0.0047131884,0.010362633,0.000081935665],"about_ca_topic_score_codex":0.009332518,"about_ca_topic_score_gemma":0.008760622,"teacher_disagreement_score":0.009332518,"about_ca_system_score_codex":0.0003397488,"about_ca_system_score_gemma":0.00089768524,"threshold_uncertainty_score":0.018556356},"labels":[],"label_agreement":null},{"id":"W2120701494","doi":"10.1109/icmla.2009.92","title":"Survival Prediction in Lung Cancer Treated with Radiotherapy: Bayesian Networks vs. Support Vector Machines in Handling Missing Data","year":2009,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Missing data; Support vector machine; Computer science; Bayesian network; Artificial intelligence; Domain (mathematical analysis); Bayesian probability; Lung cancer; Machine learning; Medicine; Oncology; Mathematics","score_opus":0.09553098012307575,"score_gpt":0.4551401833412734,"score_spread":0.3596092032181976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120701494","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68176526,0.0053919107,0.3039843,0.0055556344,0.00014523877,0.00013837848,0.0005803305,0.00043318997,0.0020057503],"genre_scores_gemma":[0.9723555,0.00068222097,0.02599975,0.00017893342,0.00010690075,0.000063095395,0.00027169837,0.000016516573,0.00032548537],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99551564,0.003570372,0.00017602125,0.00022093175,0.0003752903,0.0001418382],"domain_scores_gemma":[0.98042554,0.01674474,0.0010597256,0.00049830915,0.0008899185,0.00038185995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015698094,0.0005561061,0.0009694319,0.0017949612,0.00031954737,0.0010223706,0.0006851292,0.0011962992,0.0006070704],"category_scores_gemma":[0.039017994,0.00037599987,0.00063262053,0.0009921456,0.0003901015,0.0022210293,0.00072564615,0.0012635425,0.0002288409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002940075,0.00043634436,0.15678865,0.00035168196,0.00061403745,0.0001637395,0.00037790812,0.500389,0.0012012972,0.0059033255,0.0022709868,0.32856306],"study_design_scores_gemma":[0.00007244927,0.00023270088,0.009595974,0.00007303575,0.000055272416,0.00006204993,0.000066368266,0.9792876,0.00042092346,0.009773878,0.00033270076,0.000027032067],"about_ca_topic_score_codex":0.006006123,"about_ca_topic_score_gemma":0.0055175805,"teacher_disagreement_score":0.015698094,"about_ca_system_score_codex":0.0008261269,"about_ca_system_score_gemma":0.0008764601,"threshold_uncertainty_score":0.08302045},"labels":[],"label_agreement":null},{"id":"W2138528847","doi":"10.1109/iembs.2008.4650165","title":"Bayesian-based diagnostic decision-support for pediatrics","year":2008,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Carleton University","funders":"","keywords":"Medical diagnosis; Diagnostic test; Decision support system; Test (biology); Medicine; Pediatrics; Computer science; Family medicine; Artificial intelligence; Pathology","score_opus":0.16463160274716557,"score_gpt":0.4809518236082018,"score_spread":0.3163202208610363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138528847","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022775384,0.0016341485,0.9667918,0.002312922,0.000095660944,0.00015790368,0.0005608179,0.0017628662,0.003908517],"genre_scores_gemma":[0.55264086,0.0014341377,0.4421645,0.0005067331,0.00014149223,0.0002775875,0.00090546295,0.000072626215,0.001856567],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985336,0.0007212817,0.00011886942,0.0001499368,0.00041865985,0.00005755253],"domain_scores_gemma":[0.9931195,0.0053188303,0.00036387573,0.00015256878,0.0008622846,0.0001829485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028657955,0.00042293523,0.00058132847,0.0011425627,0.0004961854,0.0012287701,0.000959815,0.00086597406,0.002448646],"category_scores_gemma":[0.0153829185,0.0004274533,0.0004025123,0.00073930377,0.00039237432,0.0012950994,0.0006484511,0.001024383,0.00062308245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059934077,0.00034629702,0.006192968,0.0005290351,0.00015016233,0.0003930516,0.00026837297,0.5053224,0.0031826724,0.037297957,0.01321871,0.43249902],"study_design_scores_gemma":[0.00006588954,0.000043591343,0.0007237386,0.00006302701,0.000028970959,0.00008391799,0.000025028225,0.9594136,0.0011104089,0.034069046,0.004350836,0.000021919917],"about_ca_topic_score_codex":0.010686178,"about_ca_topic_score_gemma":0.010420477,"teacher_disagreement_score":0.010686178,"about_ca_system_score_codex":0.0010659513,"about_ca_system_score_gemma":0.0020219993,"threshold_uncertainty_score":0.021247983},"labels":[],"label_agreement":null},{"id":"W2151782034","doi":"10.2196/medinform.4226","title":"Metadata Correction: Making Big Data Useful for Health Care: A Summary of the Inaugural MIT Critical Data Conference","year":2015,"lang":"en","type":"erratum","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"George (robot); Library science; Art history; Art; Computer science","score_opus":0.45633847551006174,"score_gpt":0.5521788620702676,"score_spread":0.09584038656020583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151782034","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00065068516,0.04590946,0.010982347,0.59126896,0.3352566,0.00049093016,0.0017506784,0.001400904,0.012289434],"genre_scores_gemma":[0.018996673,0.14902058,0.06603453,0.3188374,0.32828274,0.0014426631,0.010535771,0.003990345,0.10285928],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9478801,0.012446351,0.009666324,0.002619785,0.02542415,0.0019632673],"domain_scores_gemma":[0.6526957,0.08419705,0.014711367,0.017556388,0.22038156,0.010457914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0872603,0.0018163016,0.0018659232,0.010626933,0.006787765,0.01655268,0.0054528965,0.006841992,0.019731382],"category_scores_gemma":[0.23625569,0.0009963936,0.0020346204,0.0077982666,0.005854452,0.013456338,0.0073558646,0.010744636,0.00984555],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029297033,0.000023480738,0.00044695055,0.0005472519,0.000014320317,0.000098958146,0.00021585607,0.000084870764,0.00014218288,0.0035693867,0.9250131,0.06981435],"study_design_scores_gemma":[0.0000114504455,0.000020080048,0.00064046826,0.0017053819,0.000020197933,0.00013319022,0.0004544286,0.00019998358,0.00045023693,0.0023979659,0.99392325,0.000043434124],"about_ca_topic_score_codex":0.023312738,"about_ca_topic_score_gemma":0.036927886,"teacher_disagreement_score":0.0872603,"about_ca_system_score_codex":0.008923959,"about_ca_system_score_gemma":0.037771117,"threshold_uncertainty_score":0.4614821},"labels":[],"label_agreement":null},{"id":"W2154023152","doi":"10.1109/iembs.1999.804406","title":"Methodologies for predicting coronary surgery outcomes","year":2003,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Ottawa","funders":"Medical Research Council; Natural Sciences and Engineering Research Council of Canada; Medical Research Council Canada","keywords":"Bypass grafting; Computer science; Artificial neural network; Representation (politics); Artery; Binary number; Grafting; Artificial intelligence; Database; Cardiology; Medicine; Mathematics; Materials science","score_opus":0.6586239730434724,"score_gpt":0.5984644631936672,"score_spread":0.060159509849805226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154023152","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052799277,0.003938871,0.9357027,0.0008792489,0.00023415074,0.00032194745,0.0013107905,0.0008558137,0.0039573503],"genre_scores_gemma":[0.48192975,0.0031428759,0.5087618,0.00024552396,0.00045138918,0.0005481981,0.0020382265,0.0000612865,0.0028209526],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980388,0.00067121256,0.00019194467,0.00046282716,0.0005604748,0.00007477345],"domain_scores_gemma":[0.9943487,0.00310417,0.0008378722,0.00034195714,0.0012339696,0.00013324532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004203968,0.0010924366,0.0006415613,0.0043886867,0.0003557873,0.0019256355,0.0012296553,0.00090047624,0.001366764],"category_scores_gemma":[0.014949093,0.00033136737,0.00075360306,0.0025675576,0.00029081362,0.0011313973,0.0006335854,0.00078861223,0.0005807066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016913326,0.00024305463,0.040015902,0.00044633067,0.00062819413,0.00017702985,0.00020845968,0.2606873,0.0029785854,0.011571924,0.0043019936,0.6785721],"study_design_scores_gemma":[0.000033912645,0.00014102645,0.009923463,0.00010707078,0.00010495018,0.00016865236,0.00009472692,0.95244545,0.001925741,0.031135509,0.003873428,0.000046114466],"about_ca_topic_score_codex":0.0034668404,"about_ca_topic_score_gemma":0.0037999735,"teacher_disagreement_score":0.0043886867,"about_ca_system_score_codex":0.0007046662,"about_ca_system_score_gemma":0.0008988853,"threshold_uncertainty_score":0.02223301},"labels":[],"label_agreement":null},{"id":"W2159258553","doi":"10.1109/embc.2012.6346501","title":"Muscle categorization using PDF estimation and Naive Bayes classification","year":2012,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Naive Bayes classifier; Categorization; Artificial intelligence; Computer science; Bayes' theorem; Pattern recognition (psychology); Bayes error rate; Machine learning; Support vector machine; Bayes classifier; Bayesian probability","score_opus":0.28424279454596907,"score_gpt":0.5072090445670916,"score_spread":0.22296625002112253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159258553","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019882152,0.0009873242,0.97474515,0.00039256437,0.0001860643,0.00032381466,0.00021038072,0.0018408573,0.001431723],"genre_scores_gemma":[0.36661083,0.00068149285,0.6277031,0.0004376045,0.00045891287,0.00045214052,0.0008637318,0.00013566726,0.002656511],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995567,0.0014306325,0.00064548635,0.0009331228,0.0011580966,0.00026560223],"domain_scores_gemma":[0.98773706,0.008843806,0.000654456,0.00052860845,0.0020764023,0.00015968083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0071684774,0.0013496167,0.0021321967,0.0049989345,0.0010757999,0.0023938084,0.0024306977,0.0023663165,0.0032587969],"category_scores_gemma":[0.020096948,0.0007212452,0.0016599811,0.0019116111,0.00081776915,0.002645037,0.00085322943,0.0018957648,0.0017567481],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005895589,0.0002837141,0.008845176,0.00037806615,0.0002698411,0.00023356163,0.00024450498,0.115159385,0.002497876,0.0080456985,0.005908625,0.857544],"study_design_scores_gemma":[0.000039917555,0.00006590154,0.001210261,0.00008301384,0.00005416841,0.00017824378,0.00008555705,0.9768893,0.001468828,0.018700069,0.001185058,0.000039759805],"about_ca_topic_score_codex":0.008762672,"about_ca_topic_score_gemma":0.005179681,"teacher_disagreement_score":0.008762672,"about_ca_system_score_codex":0.0015076934,"about_ca_system_score_gemma":0.0016960341,"threshold_uncertainty_score":0.03791094},"labels":[],"label_agreement":null},{"id":"W2161299495","doi":"10.2196/medinform.3447","title":"Making Big Data Useful for Health Care: A Summary of the Inaugural MIT Critical Data Conference","year":2014,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Big data; Data science; Statement (logic); Computer science; Data mining; Epistemology; Philosophy","score_opus":0.46997211351663104,"score_gpt":0.5640014367907548,"score_spread":0.09402932327412372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161299495","genre_codex":"review","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006421647,0.5111488,0.0049679796,0.4230734,0.05154107,0.00017744598,0.00022761407,0.00016296377,0.0080585955],"genre_scores_gemma":[0.010819663,0.7922339,0.011857996,0.077903606,0.09323668,0.0004677597,0.0007975942,0.0003527756,0.012329976],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9759941,0.009575333,0.0027133538,0.0013968893,0.008844531,0.0014758059],"domain_scores_gemma":[0.89374846,0.04804389,0.00338223,0.0027794733,0.039968915,0.012077063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07103489,0.0022158753,0.0018059674,0.0074669668,0.0048003104,0.019908095,0.0027302708,0.007304389,0.0056719165],"category_scores_gemma":[0.068088114,0.0012124128,0.0017526937,0.0074213375,0.005708123,0.020865226,0.008028147,0.018230373,0.0026795708],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010126553,0.00011926307,0.0008332589,0.0027612643,0.00007334898,0.00015445023,0.0011034082,0.0005037547,0.00035453137,0.023395894,0.7505391,0.22006036],"study_design_scores_gemma":[0.000012645237,0.000052970023,0.0010623126,0.0043098326,0.000028350107,0.000102839025,0.0007721284,0.00022035048,0.00014341543,0.009095771,0.98413867,0.00006080803],"about_ca_topic_score_codex":0.0054745213,"about_ca_topic_score_gemma":0.0094209835,"teacher_disagreement_score":0.07103489,"about_ca_system_score_codex":0.008179542,"about_ca_system_score_gemma":0.016307212,"threshold_uncertainty_score":0.37567294},"labels":[],"label_agreement":null},{"id":"W2171815584","doi":"10.1186/1756-0381-7-22","title":"Applications of the MapReduce programming framework to clinical big data analysis: current landscape and future trends","year":2014,"lang":"en","type":"review","venue":"BioData Mining","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":147,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Calgary Laboratory Services; University of Calgary","funders":"","keywords":"Computer science; Big data; Scalability; Programming paradigm; Data-intensive computing; Distributed computing; Data processing; Node (physics); Distributed File System; Grid computing; Grid; Database; Data mining; Operating system; Programming language","score_opus":0.5193724130788084,"score_gpt":0.6095661319612116,"score_spread":0.09019371888240313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171815584","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047118533,0.8185324,0.11895419,0.033237852,0.0028795374,0.00024145596,0.0002460678,0.001315565,0.019881023],"genre_scores_gemma":[0.026760148,0.84430104,0.111452326,0.006766128,0.006480271,0.0002045863,0.0005551095,0.00035504217,0.0031253293],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997127,0.00080060627,0.00023627856,0.0004828221,0.0011601048,0.0001931875],"domain_scores_gemma":[0.9915741,0.004479284,0.0003651902,0.00034944568,0.002591527,0.0006405295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072562657,0.0007438996,0.00092666864,0.0027752947,0.00057909294,0.0035711962,0.0030910405,0.0017437913,0.0023321572],"category_scores_gemma":[0.007740624,0.0007642454,0.001118306,0.004328601,0.0022616228,0.0051590847,0.002272269,0.004667703,0.0012571561],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014198683,0.00024176002,0.0036925804,0.0064220694,0.00011299608,0.00026171698,0.0006658817,0.004262401,0.0021302626,0.04976753,0.047156096,0.88514465],"study_design_scores_gemma":[0.000050569866,0.00031566978,0.003609128,0.0031631049,0.000098076096,0.0017387796,0.0009926399,0.016245501,0.0028554052,0.07175822,0.89897114,0.00020169599],"about_ca_topic_score_codex":0.0035041128,"about_ca_topic_score_gemma":0.0025070915,"teacher_disagreement_score":0.0072562657,"about_ca_system_score_codex":0.0017959465,"about_ca_system_score_gemma":0.0038722942,"threshold_uncertainty_score":0.03837526},"labels":[],"label_agreement":null},{"id":"W2173730923","doi":"10.5815/ijisa.2015.12.08","title":"Heart Diseases Diagnosis Using Neural Networks Arbitration","year":2015,"lang":"en","type":"article","venue":"International Journal of Intelligent Systems and Applications","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":150,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Support vector machine; Heart disease; Artificial intelligence; Artificial neural network; Machine learning; Multilayer perceptron; Medical diagnosis; Set (abstract data type); Perceptron; Feedforward neural network; Medicine; Cardiology; Pathology","score_opus":0.19667113230557318,"score_gpt":0.4811983888718895,"score_spread":0.2845272565663163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2173730923","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33756685,0.004327375,0.6309492,0.0025504832,0.0007394224,0.000366173,0.0006935111,0.0036748538,0.0191321],"genre_scores_gemma":[0.95759696,0.0003541188,0.03801737,0.00017953862,0.000076271164,0.00008036443,0.00028332986,0.000021656295,0.003390371],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994394,0.00012748216,0.00006849493,0.00016172465,0.000121601646,0.000081265534],"domain_scores_gemma":[0.9988751,0.0005671454,0.00012471595,0.00005650499,0.00033336785,0.00004322392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011913236,0.0006245649,0.00072966673,0.00086113485,0.0005480549,0.0011059784,0.0009045364,0.0008787199,0.0030552724],"category_scores_gemma":[0.0034597027,0.00029978435,0.0005909872,0.0006149887,0.0003352814,0.0010067722,0.00070444256,0.00088409916,0.00045882675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009661668,0.00063946383,0.014019432,0.00022724547,0.00024181204,0.00042804962,0.00016123231,0.57772547,0.006321269,0.005008981,0.0042825458,0.38997838],"study_design_scores_gemma":[0.000011888576,0.000053581694,0.0007470566,0.0000103594175,0.000019592875,0.000034953533,0.000012623766,0.9954261,0.0012375128,0.0020592862,0.0003794547,0.0000075166317],"about_ca_topic_score_codex":0.007812547,"about_ca_topic_score_gemma":0.006030606,"teacher_disagreement_score":0.007812547,"about_ca_system_score_codex":0.0008903201,"about_ca_system_score_gemma":0.00087297126,"threshold_uncertainty_score":0.0155341625},"labels":[],"label_agreement":null},{"id":"W2176091603","doi":"10.1109/pacrim.2015.7334888","title":"Proteus: A scalable, flexible and extensible multi-classifier framework","year":2015,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Machine learning; Random forest; Artificial intelligence; Naive Bayes classifier; Support vector machine; Scalability; Classifier (UML); Extensibility; Software deployment; Plug-in; Software engineering; Operating system","score_opus":0.4215122571643154,"score_gpt":0.5299480613231621,"score_spread":0.10843580415884668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2176091603","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006484424,0.00032893804,0.80283004,0.00032331943,0.00011850942,0.00035691314,0.0012354079,0.18677017,0.001552307],"genre_scores_gemma":[0.15321416,0.00048752717,0.8155398,0.00081190583,0.000111748435,0.0009038555,0.010174151,0.013242389,0.00551444],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99787927,0.00041174627,0.00022368587,0.0004735335,0.0007631762,0.00024862032],"domain_scores_gemma":[0.99767286,0.00081444177,0.00016989233,0.0005172238,0.0005455535,0.00028007358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004152137,0.0014627812,0.0012132238,0.001731242,0.00074139354,0.0019760947,0.005012524,0.0015271832,0.004593853],"category_scores_gemma":[0.007925649,0.002036235,0.0022602289,0.001056158,0.00082304486,0.0036288523,0.0034673016,0.0028464766,0.005051699],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00324624,0.0008703435,0.012014572,0.0013244139,0.001485984,0.0020269102,0.0008086663,0.15689598,0.029571952,0.039591648,0.18385284,0.5683104],"study_design_scores_gemma":[0.0002677314,0.00019150713,0.0019643065,0.0001278181,0.00012446048,0.0006827144,0.000069062924,0.85730004,0.017381135,0.043762308,0.07792417,0.0002046987],"about_ca_topic_score_codex":0.008276611,"about_ca_topic_score_gemma":0.0066827782,"teacher_disagreement_score":0.008276611,"about_ca_system_score_codex":0.0009870356,"about_ca_system_score_gemma":0.002605396,"threshold_uncertainty_score":0.021958828},"labels":[],"label_agreement":null},{"id":"W2197437548","doi":"10.1371/journal.pone.0104859.t001","title":"Montreal Classification Scheme.","year":2015,"lang":"en","type":"paratext","venue":"Figshare","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Classification scheme; Computer science; Information retrieval","score_opus":0.5196553185799689,"score_gpt":0.543044712144778,"score_spread":0.02338939356480907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2197437548","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009908436,0.0053013843,0.003923808,0.007849334,0.0036732156,0.0008820161,0.7564043,0.0011937047,0.21978146],"genre_scores_gemma":[0.011596439,0.008145571,0.009441304,0.0024154389,0.0010926111,0.0015669032,0.69505167,0.001362127,0.26932797],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971631,0.0004294673,0.00060037995,0.0004919628,0.0007098087,0.00060522184],"domain_scores_gemma":[0.9902119,0.001053593,0.00078280485,0.0008238236,0.0060244985,0.0011032982],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002483499,0.0015868834,0.001563726,0.011068131,0.0016730082,0.0037433377,0.0035503455,0.0018855634,0.4637135],"category_scores_gemma":[0.015321453,0.00063407293,0.0014938164,0.01599302,0.0008298683,0.004237366,0.0021045173,0.002601382,0.31380478],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051896084,0.0000101518735,0.0012361936,0.00025670574,0.0000135496575,0.00003186267,0.000055349883,0.000096141994,0.000035891873,0.0048391735,0.9675811,0.025791906],"study_design_scores_gemma":[0.00004248939,0.000022667924,0.0054801977,0.00048633447,0.000017181745,0.00012706686,0.00014903299,0.00015786242,0.00006460916,0.0037644936,0.9896678,0.000020356696],"about_ca_topic_score_codex":0.07319061,"about_ca_topic_score_gemma":0.0799422,"teacher_disagreement_score":0.4637135,"about_ca_system_score_codex":0.0043669427,"about_ca_system_score_gemma":0.010624626,"threshold_uncertainty_score":0.7649476},"labels":[],"label_agreement":null},{"id":"W2288555432","doi":"10.5539/mas.v10n3p66","title":"Predicting Heart Attacks in Patients Using Artificial Intelligence Methods","year":2016,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Field (mathematics); Class (philosophy); Knowledge extraction; Heart disease; Table (database); Artificial intelligence; Data mining; Machine learning; Medicine; Internal medicine; Mathematics","score_opus":0.27871079507203844,"score_gpt":0.5383043451027737,"score_spread":0.25959355003073525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2288555432","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32142565,0.011175779,0.60245705,0.0097338185,0.0018133471,0.0013885308,0.01018881,0.0055403737,0.036276568],"genre_scores_gemma":[0.8265674,0.0039245808,0.15608692,0.00082936883,0.00064125855,0.00043607305,0.006246634,0.00007130356,0.005196449],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988599,0.00038693668,0.00017448238,0.00019145038,0.000311579,0.0000756411],"domain_scores_gemma":[0.9975458,0.0017560805,0.00020519004,0.00011593182,0.0003014922,0.00007562859],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015436603,0.00082380284,0.00075086043,0.0039282828,0.00032883591,0.001749752,0.0009449085,0.001023332,0.0029821869],"category_scores_gemma":[0.007048804,0.00025811762,0.0012786321,0.0022798858,0.00026157958,0.00079161866,0.00047116517,0.0012025704,0.0010903099],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004632323,0.0011355478,0.15282863,0.0005674277,0.00062677206,0.00068342313,0.000283047,0.16984211,0.0014165887,0.0054017426,0.022256669,0.6444948],"study_design_scores_gemma":[0.000037025515,0.00017858777,0.015306424,0.0001378512,0.00011175375,0.0002527907,0.00018995708,0.97024494,0.001069129,0.0070385183,0.005390529,0.000042515592],"about_ca_topic_score_codex":0.0056649554,"about_ca_topic_score_gemma":0.0046954695,"teacher_disagreement_score":0.0056649554,"about_ca_system_score_codex":0.00058266555,"about_ca_system_score_gemma":0.0006895251,"threshold_uncertainty_score":0.011263967},"labels":[],"label_agreement":null},{"id":"W2291439604","doi":"10.1145/2808797.2809367","title":"Importance of Data Mining in Healthcare","year":2015,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Health care; Data mining; Data science; Computer science; Health data; Quality (philosophy); Data quality; Business","score_opus":0.6643480662487644,"score_gpt":0.6019096089615764,"score_spread":0.062438457287188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2291439604","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011900141,0.3732837,0.31844664,0.25013003,0.005948082,0.00077716564,0.0019403026,0.0008713252,0.036702577],"genre_scores_gemma":[0.176284,0.3285254,0.44229895,0.03512417,0.009898975,0.00070807105,0.0031031638,0.00030643854,0.0037509094],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9634801,0.019027887,0.0038339936,0.002661078,0.010564888,0.0004320631],"domain_scores_gemma":[0.80415994,0.16179273,0.0057741385,0.009671947,0.016590336,0.0020109683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.039791945,0.0008261698,0.0017084138,0.006648985,0.001557829,0.007184758,0.0026987547,0.0028815386,0.002198736],"category_scores_gemma":[0.10157598,0.0007984609,0.0012511106,0.011388645,0.0035784845,0.012881792,0.0034900894,0.0060211984,0.0012960945],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016970698,0.00025202413,0.018521033,0.007411114,0.0003234835,0.0003668101,0.0010963368,0.0045497725,0.0008784032,0.14474426,0.050272845,0.7714142],"study_design_scores_gemma":[0.00006101153,0.0001901743,0.010744551,0.011230581,0.00019050739,0.0020854007,0.0029854998,0.021726841,0.0022593017,0.36740425,0.5809594,0.00016262916],"about_ca_topic_score_codex":0.0014908598,"about_ca_topic_score_gemma":0.0009567891,"teacher_disagreement_score":0.039791945,"about_ca_system_score_codex":0.0025227054,"about_ca_system_score_gemma":0.004854203,"threshold_uncertainty_score":0.21044242},"labels":[],"label_agreement":null},{"id":"W2296534876","doi":"10.1109/icter.2013.6761203","title":"Medical informatics","year":2013,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Health informatics; Computer science; Informatics; Medical imaging; Data science; Artificial intelligence; Engineering; Medicine; Nursing","score_opus":0.17988295246877517,"score_gpt":0.5244987985178574,"score_spread":0.34461584604908224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2296534876","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002609331,0.03180664,0.09583922,0.053145852,0.01098285,0.00095994165,0.011553847,0.005236248,0.7878661],"genre_scores_gemma":[0.10162,0.09991676,0.18206157,0.038304254,0.021334738,0.0017490246,0.03612027,0.0015723149,0.517321],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952878,0.001581965,0.0004776565,0.00062683615,0.0018118173,0.00021380544],"domain_scores_gemma":[0.9915364,0.00283323,0.000503636,0.0019178191,0.002566651,0.00064236386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004418687,0.00084918534,0.0008522203,0.0052315732,0.001498909,0.008180807,0.0021525056,0.0026482202,0.13110799],"category_scores_gemma":[0.017680874,0.00041796354,0.00066256576,0.0045558047,0.0014826801,0.004017272,0.0040119486,0.0023255763,0.07818426],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008717047,0.00007253033,0.0011508093,0.0011018135,0.00004672017,0.00022623726,0.0003701171,0.00048751623,0.00067125255,0.13585462,0.4417063,0.41822496],"study_design_scores_gemma":[0.00001613188,0.000025330724,0.0004859134,0.00039050923,0.0000117325335,0.00037502154,0.000114497336,0.00048446193,0.0003252782,0.034015924,0.96374154,0.000013623262],"about_ca_topic_score_codex":0.0010033293,"about_ca_topic_score_gemma":0.0005393501,"teacher_disagreement_score":0.13110799,"about_ca_system_score_codex":0.0018094426,"about_ca_system_score_gemma":0.003927391,"threshold_uncertainty_score":0.43859988},"labels":[],"label_agreement":null},{"id":"W2301645172","doi":"10.14288/1.0045259","title":"How do various fugitive literature searching methods impact the comprehensiveness of literature uncovered for systematic review?","year":2014,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Systematic review; Computer science; Political science; MEDLINE","score_opus":0.04315446355718581,"score_gpt":0.3822912214715636,"score_spread":0.33913675791437775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2301645172","genre_codex":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23560731,0.45961398,0.15949713,0.04105286,0.00416011,0.07644743,0.007581247,0.0013678179,0.014672124],"genre_scores_gemma":[0.5715914,0.055520326,0.2888826,0.01082351,0.0012537445,0.06867107,0.0022543876,0.00044348685,0.0005594556],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.12163319,0.51607555,0.257475,0.01809561,0.08389266,0.002828064],"domain_scores_gemma":[0.027066855,0.8553482,0.07283766,0.017991144,0.02572764,0.0010284082],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7978771,0.003576997,0.00886954,0.05878936,0.0050548324,0.020321472,0.0061074644,0.006774569,0.0028862746],"category_scores_gemma":[0.94616127,0.004581439,0.018877827,0.04312832,0.0102974195,0.022100285,0.013217199,0.0037334103,0.0006321721],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0065682335,0.0006286413,0.14771187,0.23460141,0.07480823,0.0006796649,0.049625985,0.0029013269,0.0031369927,0.011208648,0.007856473,0.4602725],"study_design_scores_gemma":[0.011435875,0.0091905715,0.21186155,0.40124202,0.1472463,0.003352061,0.038989592,0.013261629,0.016100645,0.08325754,0.06114788,0.0029142823],"about_ca_topic_score_codex":0.0047207903,"about_ca_topic_score_gemma":0.011404567,"teacher_disagreement_score":0.20212293,"about_ca_system_score_codex":0.01724698,"about_ca_system_score_gemma":0.024587274,"threshold_uncertainty_score":0.24925363},"labels":[],"label_agreement":null},{"id":"W2316093659","doi":"10.7748/ns.29.12.33.s40","title":"Stroke Risk Calculator app","year":2014,"lang":"en","type":"article","venue":"Nursing Standard","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services","funders":"","keywords":"Calculator; Stroke (engine); Medicine; Stroke risk; Medical emergency; Ischemic stroke; Computer science; Engineering; Psychiatry","score_opus":0.0669366383227845,"score_gpt":0.4716580574960077,"score_spread":0.4047214191732232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2316093659","genre_codex":"other","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048141308,0.015384578,0.04690792,0.010011874,0.0029170613,0.0034616424,0.21371199,0.26507375,0.39438987],"genre_scores_gemma":[0.21123335,0.018556027,0.088381425,0.021180829,0.0042262687,0.006872632,0.19575039,0.025167389,0.42863172],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995974,0.000047959,0.00006555737,0.000058192996,0.00020302093,0.000027855],"domain_scores_gemma":[0.9978021,0.0011548804,0.00027782112,0.000120106764,0.00043851812,0.00020649082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045652385,0.0010973561,0.00091840397,0.0027702725,0.00037741728,0.001689754,0.0010377943,0.0010493761,0.13063733],"category_scores_gemma":[0.0060320124,0.0005465937,0.0006127765,0.0009429627,0.00012070545,0.0011659698,0.0015247058,0.0009951058,0.0618285],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010389907,0.0002407049,0.008177822,0.0009111551,0.00012932581,0.00058390107,0.00013290237,0.00020426081,0.00088689587,0.0015188542,0.7762174,0.2099578],"study_design_scores_gemma":[0.0011484036,0.00047143045,0.05215767,0.001572245,0.00060394447,0.0052948627,0.00016050287,0.0059101083,0.008598641,0.013137094,0.91055477,0.00039017393],"about_ca_topic_score_codex":0.0012606797,"about_ca_topic_score_gemma":0.0024619189,"teacher_disagreement_score":0.13063733,"about_ca_system_score_codex":0.00022132542,"about_ca_system_score_gemma":0.00055032515,"threshold_uncertainty_score":0.43702543},"labels":[],"label_agreement":null},{"id":"W2365112007","doi":"","title":"Development of Health Decision Support System(HDSS) in Canada and its Enlightenments to China","year":2012,"lang":"en","type":"article","venue":"Zhongguo xunzheng yixue zazhi","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"China; Government (linguistics); Decision support system; Business; Information system; Function (biology); Quality (philosophy); Clinical decision support system; Knowledge management; Enlightenment; Control (management); Computer science; Engineering; Political science; Data mining; Artificial intelligence","score_opus":0.11166355116763609,"score_gpt":0.4288798167230403,"score_spread":0.3172162655554042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2365112007","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55965525,0.0139534995,0.110804245,0.098583356,0.0023174386,0.0031730928,0.005449717,0.004329638,0.20173381],"genre_scores_gemma":[0.789418,0.008713394,0.1057862,0.0035072977,0.00018757944,0.0003610935,0.0038133108,0.0001238606,0.08808941],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980574,0.00025575788,0.000096018666,0.00016297895,0.0009342182,0.00049355824],"domain_scores_gemma":[0.99517304,0.00016952468,0.000093217895,0.000108972585,0.0033897338,0.0010655595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003396472,0.0004944114,0.00027149115,0.0014857167,0.002562957,0.0028230436,0.00094125856,0.0006859096,0.0029222216],"category_scores_gemma":[0.0036335536,0.00024622463,0.0004965698,0.0019511052,0.0014405127,0.0009329177,0.0015448447,0.00090360525,0.00046279104],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052695494,0.0003354654,0.055514555,0.0006380422,0.00009332726,0.0011896922,0.0036228918,0.020936728,0.0095936535,0.16374558,0.10447367,0.6393294],"study_design_scores_gemma":[0.00034721603,0.00055269524,0.08274604,0.00048329888,0.00010278233,0.00022096152,0.003929673,0.07659583,0.014587064,0.0101369945,0.8101078,0.00018972311],"about_ca_topic_score_codex":0.94808394,"about_ca_topic_score_gemma":0.85664463,"teacher_disagreement_score":0.051916063,"about_ca_system_score_codex":0.036610983,"about_ca_system_score_gemma":0.17339928,"threshold_uncertainty_score":0.2656325},"labels":[],"label_agreement":null},{"id":"W2367630464","doi":"","title":"Study of medical effectiveness of provincial stroke care delivery:based on Logistic regression","year":2014,"lang":"en","type":"article","venue":"Journal of Guangzhou University","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Logistic regression; Inflection point; Regression analysis; Statistics; Stroke (engine); Regression; Segmented regression; Medicine; Econometrics; Mathematics; Engineering; Nonlinear regression","score_opus":0.112343878237889,"score_gpt":0.4441245728425358,"score_spread":0.3317806946046468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2367630464","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98356277,0.0007416709,0.009920088,0.0010450701,0.000029191187,0.00014818825,0.0010408488,0.00006312763,0.003449029],"genre_scores_gemma":[0.99743086,0.00012012909,0.0015603065,0.0000226017,0.000014240759,0.00003723726,0.00031735183,0.000011694696,0.00048551563],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9842929,0.010024435,0.000835374,0.0012875233,0.0025669343,0.0009928356],"domain_scores_gemma":[0.8990882,0.083721176,0.009605774,0.0020634248,0.0042005638,0.0013207983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013791829,0.0004710082,0.00096736464,0.002118284,0.0005736762,0.0015397201,0.0019933633,0.000569849,0.0028789737],"category_scores_gemma":[0.09013837,0.00028777833,0.0022173538,0.004055944,0.00067696226,0.0015345352,0.0010267841,0.0014371277,0.0002472588],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004717924,0.00023583154,0.95767766,0.00020093058,0.0016003901,0.0003238303,0.0008280692,0.01910954,0.00014827748,0.002425694,0.000679532,0.016298521],"study_design_scores_gemma":[0.000052561034,0.00085314375,0.75252175,0.000095891024,0.0011676326,0.00029041345,0.0020140982,0.23947394,0.00037191945,0.001456966,0.0016486262,0.000053041826],"about_ca_topic_score_codex":0.12005184,"about_ca_topic_score_gemma":0.04192848,"teacher_disagreement_score":0.12005184,"about_ca_system_score_codex":0.0038446488,"about_ca_system_score_gemma":0.004187804,"threshold_uncertainty_score":0.23870611},"labels":[],"label_agreement":null},{"id":"W2395746999","doi":"10.20381/ruor-9700","title":"Predicting patient knowledge of cardiac risk factors: A comparison of two approaches","year":2004,"lang":"en","type":"dissertation","venue":"uO Research (University of Ottawa)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Data science; Psychology; Computer science","score_opus":0.3575262482641947,"score_gpt":0.5091140802904672,"score_spread":0.15158783202627252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395746999","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9424425,0.004595873,0.03517056,0.0025542905,0.00034313794,0.00131697,0.0024015931,0.00063262775,0.010542535],"genre_scores_gemma":[0.94140357,0.0023375095,0.05003472,0.0005371682,0.00014067769,0.00090875605,0.0024960556,0.000071974304,0.0020695217],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9876533,0.0071849837,0.0008886022,0.0013286795,0.0024524988,0.00049191207],"domain_scores_gemma":[0.9495987,0.04361241,0.0012486911,0.0010519768,0.0034764814,0.0010116674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016558891,0.0013570614,0.0020019542,0.006223964,0.0007028871,0.0035794403,0.0018476828,0.0020598194,0.002735421],"category_scores_gemma":[0.04222466,0.0005532146,0.002022856,0.0035356644,0.000673001,0.0023642362,0.0026952534,0.0018435961,0.00084430724],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009960294,0.0032243389,0.48479939,0.0013365909,0.0038939826,0.000119754965,0.0032601398,0.011035492,0.0010894797,0.0020288636,0.0034105484,0.47584105],"study_design_scores_gemma":[0.002417552,0.011998114,0.6134783,0.00089396554,0.0037301427,0.0007741041,0.011471202,0.33597693,0.0029700235,0.0081447195,0.007658414,0.00048653688],"about_ca_topic_score_codex":0.014443303,"about_ca_topic_score_gemma":0.017177828,"teacher_disagreement_score":0.016558891,"about_ca_system_score_codex":0.0022384163,"about_ca_system_score_gemma":0.0024763355,"threshold_uncertainty_score":0.08757281},"labels":[],"label_agreement":null},{"id":"W2395778099","doi":"10.3233/978-1-61499-289-9-1053","title":"Statistical Text Classifier to Detect Specific Type of Medical Incidents","year":2013,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Classifier (UML); Patient safety; Computer science; Incident report; Logistic regression; Artificial intelligence; Natural language processing; Machine learning; Computer security","score_opus":0.25586062668188125,"score_gpt":0.5441202189768841,"score_spread":0.28825959229500286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395778099","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48937404,0.0022741556,0.4570527,0.0022082732,0.0012690562,0.0014083354,0.013848158,0.013876628,0.018688696],"genre_scores_gemma":[0.81260574,0.0005155543,0.16903967,0.00025875238,0.00037963322,0.00048727187,0.010963487,0.00011659568,0.0056332494],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99831593,0.00032356227,0.00028869926,0.00033113174,0.00060678524,0.0001339074],"domain_scores_gemma":[0.99214727,0.004537038,0.0005681778,0.00036523354,0.0021694459,0.00021281437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020857658,0.00069788407,0.0007350273,0.005815845,0.00045383332,0.0013289985,0.00067098555,0.0011409502,0.0030089384],"category_scores_gemma":[0.008343334,0.00012588802,0.0008602898,0.0024458496,0.0001838631,0.0011653285,0.00041832804,0.00079175556,0.0032914118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010147811,0.0009417813,0.06625116,0.0005524859,0.0002973457,0.0010811858,0.00028044506,0.029860312,0.030292591,0.002601361,0.026661735,0.8401647],"study_design_scores_gemma":[0.00005251927,0.00076258025,0.03385288,0.00012141469,0.0001577854,0.0011942107,0.00040179273,0.9257911,0.024059873,0.0036073911,0.009934546,0.0000638304],"about_ca_topic_score_codex":0.0018946733,"about_ca_topic_score_gemma":0.0014179891,"teacher_disagreement_score":0.005815845,"about_ca_system_score_codex":0.0005913253,"about_ca_system_score_gemma":0.0008406623,"threshold_uncertainty_score":0.011030674},"labels":[],"label_agreement":null},{"id":"W2397312999","doi":"","title":"Remote patient monitoring to improve health: challenges and opportunities","year":2015,"lang":"en","type":"article","venue":"Computer Science and Software Engineering","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); University of Ottawa; Memorial University of Newfoundland","funders":"","keywords":"Health care; Focus (optics); Health promotion; Business; Risk analysis (engineering); Public relations; Computer science; Political science; Economic growth; Economics","score_opus":0.2751156655471302,"score_gpt":0.40869899947750304,"score_spread":0.13358333393037286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2397312999","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019320928,0.25563127,0.10082688,0.57385904,0.0053681936,0.00018895086,0.00040500952,0.00085761654,0.043542158],"genre_scores_gemma":[0.5224208,0.27726617,0.13653065,0.031352673,0.018250594,0.0004122892,0.00051148573,0.00022367759,0.013031657],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962261,0.002047085,0.00014806453,0.00038675035,0.00094373635,0.00024817482],"domain_scores_gemma":[0.9817463,0.011992011,0.0007152392,0.0009382922,0.0031060367,0.0015021774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009425798,0.001081994,0.0010301841,0.0011430689,0.0011084556,0.004760445,0.002803144,0.0045491573,0.0069878623],"category_scores_gemma":[0.013440276,0.00034962653,0.0005167067,0.0015066104,0.0028967878,0.008978251,0.0041622557,0.004160752,0.0016164383],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002443919,0.00038100177,0.0075375424,0.002186181,0.000103252365,0.00039176558,0.0013557909,0.0039555887,0.002571231,0.06697347,0.08597485,0.8283249],"study_design_scores_gemma":[0.00015794415,0.0010156746,0.014346318,0.006565407,0.00015584136,0.003075312,0.013603622,0.0486486,0.0031461807,0.37638304,0.5325964,0.00030556635],"about_ca_topic_score_codex":0.0018924437,"about_ca_topic_score_gemma":0.0021761802,"teacher_disagreement_score":0.009425798,"about_ca_system_score_codex":0.00085034367,"about_ca_system_score_gemma":0.0025338964,"threshold_uncertainty_score":0.049849033},"labels":[],"label_agreement":null},{"id":"W2407757632","doi":"10.1016/j.jval.2016.03.1791","title":"A NOVEL METHOD USING PRESCRIPTION TREATMENT PATTERNS TO ESTIMATE HEART FAILURE PREVALENCE IN CANADA","year":2016,"lang":"en","type":"article","venue":"Value in Health","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Merck Canada Inc. (Canada); Novartis (Canada)","funders":"","keywords":"Medicine; Medical prescription; Referral; Heart failure; Diagnosis code; Emergency medicine; Database; Internal medicine; Family medicine; Population; Environmental health","score_opus":0.2582645712173075,"score_gpt":0.5084803843387173,"score_spread":0.25021581312140984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2407757632","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8069143,0.0024598772,0.14095962,0.0028149276,0.00029313425,0.00062429626,0.030766577,0.0019657596,0.013201508],"genre_scores_gemma":[0.8743213,0.0005763727,0.1127948,0.00021714988,0.00006509695,0.00019278598,0.0060271053,0.00006350317,0.0057418835],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992465,0.00011825447,0.000067620254,0.00017635516,0.00028262028,0.000108655586],"domain_scores_gemma":[0.9967114,0.000699697,0.00021207216,0.00011256516,0.0021177495,0.00014648931],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011685698,0.00046689637,0.00069390755,0.00439901,0.0014261703,0.0019205359,0.001482575,0.00078400486,0.0021574898],"category_scores_gemma":[0.0077324607,0.00033881806,0.00076673983,0.005275871,0.00030070925,0.00053597614,0.0005561904,0.0007174361,0.00036327116],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037942026,0.00030903815,0.6946941,0.0001940618,0.00076345936,0.00024434066,0.00032129153,0.043157496,0.0016290379,0.002711116,0.017661443,0.23793516],"study_design_scores_gemma":[0.00015972495,0.000059191243,0.32034266,0.0000908819,0.0002480703,0.00021114439,0.0006346725,0.66559535,0.0018799283,0.0018721643,0.0088048475,0.00010136376],"about_ca_topic_score_codex":0.9756359,"about_ca_topic_score_gemma":0.9739768,"teacher_disagreement_score":0.024364114,"about_ca_system_score_codex":0.009470756,"about_ca_system_score_gemma":0.019668123,"threshold_uncertainty_score":0.06871551},"labels":[],"label_agreement":null},{"id":"W2412875092","doi":"10.3233/978-1-60750-949-3-736","title":"Comparison of Machine Learning Techniques with Classical Statistical Models in Predicting Health Outcomes","year":2004,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":110,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre","funders":"","keywords":"Logistic regression; Perceptron; Multilayer perceptron; Machine learning; Artificial intelligence; Support vector machine; Artificial neural network; Computer science; Sample (material); Population; Data mining; Medicine; Environmental health","score_opus":0.21781344370158545,"score_gpt":0.546464264265972,"score_spread":0.3286508205643866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2412875092","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35288954,0.016245985,0.6184992,0.002325172,0.0005711937,0.0003050087,0.000768107,0.0020049205,0.006390837],"genre_scores_gemma":[0.75839174,0.005122787,0.23332216,0.00034437547,0.00041651315,0.00018883341,0.000729696,0.00010202734,0.0013818571],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9932648,0.0041831983,0.00042117457,0.0005170735,0.0014638936,0.00014993157],"domain_scores_gemma":[0.9592285,0.03658963,0.0007960192,0.0010051548,0.0021670582,0.00021366171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0126942,0.0013449781,0.0010033733,0.0038490067,0.0002879468,0.0011429084,0.0012061921,0.0011224685,0.00080130855],"category_scores_gemma":[0.02976651,0.0002816211,0.0010637363,0.0030487436,0.00045384132,0.0024018772,0.0011139234,0.0011190323,0.00045196438],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020581798,0.0007722839,0.03928958,0.0010808746,0.0018133302,0.00016145351,0.00024169574,0.34896827,0.0013497873,0.005626335,0.0027717466,0.5958664],"study_design_scores_gemma":[0.00006740251,0.0004893707,0.005103466,0.000050342966,0.00009172547,0.00005706303,0.00006766109,0.9887085,0.0005198238,0.004253838,0.00057062396,0.000020234023],"about_ca_topic_score_codex":0.003032505,"about_ca_topic_score_gemma":0.0028319545,"teacher_disagreement_score":0.0126942,"about_ca_system_score_codex":0.0006262834,"about_ca_system_score_gemma":0.00068582105,"threshold_uncertainty_score":0.06713414},"labels":[],"label_agreement":null},{"id":"W2416493286","doi":"10.3233/978-1-61499-101-4-584","title":"Assessing the Feasibility of Data Mining Techniques for Early Liver Cancer Detection","year":2012,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Liver cancer; Cancer detection; Data mining; Data science; Cancer; Medicine; Internal medicine","score_opus":0.5970707674831072,"score_gpt":0.6255198258717298,"score_spread":0.02844905838862266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2416493286","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61176074,0.0022400033,0.37647024,0.0024352847,0.00012929166,0.00075507455,0.0008376921,0.001995808,0.003375877],"genre_scores_gemma":[0.6506926,0.0005002961,0.34764037,0.00011411255,0.00005361758,0.00019490311,0.00044528057,0.000042532065,0.0003163222],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9851399,0.008224826,0.0012253558,0.00100101,0.0041134586,0.000295431],"domain_scores_gemma":[0.80878085,0.17481165,0.0043040435,0.0032709155,0.008248976,0.0005835905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02268159,0.00091585855,0.0008353366,0.0038181574,0.00071464176,0.0020737278,0.0012763938,0.0016246042,0.0006615294],"category_scores_gemma":[0.10227984,0.0004830707,0.0009650895,0.0024248797,0.00052085996,0.0030131538,0.00093237695,0.0011667385,0.00045522134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004677097,0.0017199352,0.27564275,0.001036818,0.00093870173,0.0005039183,0.00089981576,0.0862547,0.02183132,0.0030405906,0.0017071798,0.60174716],"study_design_scores_gemma":[0.00021884142,0.0031536,0.0426272,0.00020481851,0.00040097465,0.001020532,0.0009351301,0.9248621,0.018499374,0.00480995,0.0031813849,0.00008616222],"about_ca_topic_score_codex":0.0017833835,"about_ca_topic_score_gemma":0.0015649251,"teacher_disagreement_score":0.02268159,"about_ca_system_score_codex":0.00047469517,"about_ca_system_score_gemma":0.0013613935,"threshold_uncertainty_score":0.119953156},"labels":[],"label_agreement":null},{"id":"W2420838781","doi":"10.3233/978-1-60750-563-1-101","title":"Design and Implementation of a Health Data Interoperability Mediator","year":2010,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Interoperability; Mediator; Computer science; Process management; World Wide Web; Business; Medicine","score_opus":0.33081446634390554,"score_gpt":0.5813753051763113,"score_spread":0.25056083883240576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2420838781","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020572234,0.00017970863,0.96936774,0.00057353516,0.00009270558,0.0015471721,0.00010959679,0.0039096563,0.003647691],"genre_scores_gemma":[0.1667482,0.00025271025,0.8261768,0.00038772137,0.000037359427,0.0011138854,0.0006969364,0.00027236165,0.004314053],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967033,0.001018752,0.0005478737,0.0006978927,0.0007358938,0.00029623942],"domain_scores_gemma":[0.9964598,0.0009428965,0.00027766786,0.0008409677,0.0010734109,0.00040523143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010428953,0.00044084468,0.0008947746,0.0010619537,0.0011652835,0.0039099753,0.0038398616,0.0020574245,0.003501257],"category_scores_gemma":[0.0067448434,0.00069693703,0.0008531205,0.00077875477,0.000943367,0.0034121806,0.003287136,0.0017515153,0.0013936575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030413403,0.0033646452,0.021250524,0.0018049151,0.00076893455,0.004909706,0.00785853,0.046773586,0.18514857,0.3048643,0.013825006,0.40638995],"study_design_scores_gemma":[0.0013211132,0.0014156476,0.0042524,0.00040010028,0.0006291149,0.0022747829,0.0025173498,0.46958363,0.27708095,0.032290217,0.20795223,0.00028245608],"about_ca_topic_score_codex":0.0013933331,"about_ca_topic_score_gemma":0.0006038662,"teacher_disagreement_score":0.010428953,"about_ca_system_score_codex":0.0011053907,"about_ca_system_score_gemma":0.0041625523,"threshold_uncertainty_score":0.055154204},"labels":[],"label_agreement":null},{"id":"W2435034583","doi":"","title":"Accelerating adoption. When it comes to getting everyone on board with RIS and PACS, sometimes a new model is all that's needed.","year":2007,"lang":"en","type":"article","venue":"PubMed","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Miller Group (Canada)","funders":"","keywords":"Business; Computer science; Internet privacy; Public relations; Knowledge management; Political science","score_opus":0.2890147882637094,"score_gpt":0.42088099412493296,"score_spread":0.13186620586122355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2435034583","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021023873,0.019912945,0.04878612,0.71798426,0.010420771,0.0009069836,0.0013210687,0.005433265,0.17421065],"genre_scores_gemma":[0.36367276,0.050220806,0.2555003,0.21505395,0.007932918,0.0012818847,0.0031553311,0.0017073728,0.10147468],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98822963,0.004528301,0.0008785543,0.0007890793,0.004309,0.0012653643],"domain_scores_gemma":[0.9493119,0.01670212,0.0035621468,0.0049540955,0.01773191,0.0077378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019563364,0.00066439004,0.0003552169,0.0013608354,0.0012713289,0.005053864,0.0015269803,0.004254258,0.034317184],"category_scores_gemma":[0.058118805,0.00038546507,0.0010805303,0.0014951328,0.0012004045,0.010131134,0.0038349712,0.0050126216,0.017477505],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011283936,0.00026625048,0.009366112,0.0015237659,0.000048414462,0.00023983944,0.0010215257,0.00032153956,0.0021045865,0.01950758,0.32738975,0.6380979],"study_design_scores_gemma":[0.00013419145,0.00050317735,0.02680879,0.002094476,0.00014663154,0.0010363633,0.0026153203,0.00091155805,0.0027612224,0.018352479,0.9445413,0.000094436546],"about_ca_topic_score_codex":0.0072529796,"about_ca_topic_score_gemma":0.011721107,"teacher_disagreement_score":0.034317184,"about_ca_system_score_codex":0.0019286613,"about_ca_system_score_gemma":0.009452014,"threshold_uncertainty_score":0.11480248},"labels":[],"label_agreement":null},{"id":"W2440920042","doi":"10.1016/s0197-2510(08)70211-0","title":"10.1016/s0197-2510(08)70211-0","year":2000,"lang":"en","type":"editorial","venue":"Time to knit","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Revolving door; Computer science; History; Archaeology","score_opus":0.04594413969875952,"score_gpt":0.38044083648117644,"score_spread":0.3344966967824169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2440920042","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010187727,0.0055370783,0.00043618272,0.009530346,0.064904414,0.00018032614,0.0006643819,0.0011177225,0.9175277],"genre_scores_gemma":[0.00026401985,0.0016218228,0.00020316015,0.003785433,0.013098023,0.0000771618,0.0002457516,0.00010963264,0.98059505],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99876595,0.00010154193,0.00011657238,0.00017213698,0.0007176856,0.00012618263],"domain_scores_gemma":[0.9946242,0.0015660225,0.00043842784,0.0003719881,0.0014854898,0.0015137782],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018291267,0.002265459,0.0023656208,0.0024396551,0.0014671792,0.005304118,0.0026078732,0.0103839375,0.85523754],"category_scores_gemma":[0.006861766,0.00079368596,0.0013967674,0.0020875004,0.0015126042,0.0039604413,0.0020594785,0.005576553,0.9123577],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006410898,0.00002776606,0.000046469388,0.0003501133,0.000011579097,0.00007125126,0.0000100216575,0.000057011064,0.00014090982,0.0009576418,0.9029521,0.095311046],"study_design_scores_gemma":[0.000016283833,0.000010348591,0.00006785726,0.00012896613,0.0000033840608,0.000032888005,0.0000075509865,0.000016531372,0.00001805346,0.0001603536,0.9995333,0.0000045426173],"about_ca_topic_score_codex":0.0030763508,"about_ca_topic_score_gemma":0.0048437016,"teacher_disagreement_score":0.14476246,"about_ca_system_score_codex":0.001371392,"about_ca_system_score_gemma":0.001405883,"threshold_uncertainty_score":0.2064861},"labels":[],"label_agreement":null},{"id":"W2492698696","doi":"10.5539/cis.v9n3p26","title":"Chest-Pain Consultation System Based on Fuzzy Semantic Rules","year":2016,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Zarqa University; University of Jordan","keywords":"Computer science; Ontology; Fuzzy logic; Domain (mathematical analysis); Chest pain; Reliability (semiconductor); Stage (stratigraphy); Artificial intelligence; Medicine; Surgery","score_opus":0.06978289935882236,"score_gpt":0.3928840608986889,"score_spread":0.3231011615398665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2492698696","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35610497,0.0019718662,0.56090117,0.0011443292,0.0002967724,0.0016708164,0.0068732146,0.03818486,0.03285196],"genre_scores_gemma":[0.7832906,0.00044279493,0.20326568,0.0003480393,0.00006398807,0.00039858365,0.0034768498,0.00015472544,0.008558733],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995547,0.000079048725,0.00007233946,0.00012239967,0.00013865587,0.00003284301],"domain_scores_gemma":[0.99961543,0.00013251405,0.000026705833,0.000037070906,0.00015709891,0.000031237916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039871963,0.00034986876,0.0005211885,0.0009968465,0.00049785443,0.0006574926,0.00058154936,0.000497164,0.0048386888],"category_scores_gemma":[0.001212358,0.00015828855,0.00047161969,0.00054466573,0.0001300224,0.0006648749,0.00040830323,0.00028986527,0.0011714548],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018995997,0.0012027195,0.016138026,0.0013244785,0.00021278685,0.0033954785,0.00091007724,0.020403212,0.087119125,0.005806472,0.03676546,0.8248225],"study_design_scores_gemma":[0.00078988663,0.00064875267,0.031969517,0.0002463651,0.0006796542,0.0047534993,0.00088915194,0.8113111,0.074473254,0.01062101,0.063330464,0.00028730519],"about_ca_topic_score_codex":0.005238496,"about_ca_topic_score_gemma":0.0052947705,"teacher_disagreement_score":0.005238496,"about_ca_system_score_codex":0.00041471404,"about_ca_system_score_gemma":0.00089554477,"threshold_uncertainty_score":0.016186953},"labels":[],"label_agreement":null},{"id":"W2524084843","doi":"","title":"Study of Hospital Community Awareness through Patient Informatics","year":2006,"lang":"en","type":"article","venue":"The Journal of Internet Banking and Commerce","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Health care; Scope (computer science); Service (business); Health informatics; Medical prescription; Informatics; Medicine; Function (biology); Business; Nursing; Medical emergency; Knowledge management; Computer science; Marketing; Public health; Engineering","score_opus":0.11714861026182356,"score_gpt":0.42443493363637597,"score_spread":0.3072863233745524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2524084843","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97906345,0.00016972705,0.00077930087,0.0006224827,0.000013199479,0.00015216267,0.00015309584,0.000029131457,0.019017378],"genre_scores_gemma":[0.99844766,0.00009400778,0.0003559083,0.000093956965,0.000007950382,0.000052565883,0.00007245532,0.0000030740357,0.00087235845],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972573,0.0016936864,0.00011933567,0.00014265715,0.0004309443,0.00035604835],"domain_scores_gemma":[0.9850427,0.0092977695,0.0019091131,0.0005551239,0.001740008,0.0014552537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036169463,0.00015882224,0.00025429818,0.0038345924,0.0011228722,0.00253082,0.0005102421,0.00053356594,0.0050366437],"category_scores_gemma":[0.017222853,0.00016093174,0.00027807418,0.002391318,0.0006823861,0.0020904716,0.0017492132,0.00079913647,0.00034584472],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024491342,0.0025885114,0.805019,0.00018527418,0.00006319473,0.00020470601,0.053559378,0.00017653781,0.00026612624,0.0041548987,0.0018019078,0.13173552],"study_design_scores_gemma":[0.000059882284,0.0012260168,0.7958319,0.00016608593,0.00012520143,0.00041015886,0.1855314,0.0023532507,0.00075956143,0.0028994116,0.010586518,0.00005057264],"about_ca_topic_score_codex":0.004741967,"about_ca_topic_score_gemma":0.0037004836,"teacher_disagreement_score":0.0050366437,"about_ca_system_score_codex":0.0016389989,"about_ca_system_score_gemma":0.002321291,"threshold_uncertainty_score":0.019128442},"labels":[],"label_agreement":null},{"id":"W2526948241","doi":"10.1007/978-3-319-47157-0_23","title":"Tree-Based Transforms for Privileged Learning","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Modalities; Random forest; Artificial intelligence; Classifier (UML); Decision tree; Feature (linguistics); Machine learning; Modality (human–computer interaction); Tree (set theory); Training set; Variety (cybernetics); Pattern recognition (psychology)","score_opus":0.09751452332840772,"score_gpt":0.41116680946165246,"score_spread":0.31365228613324475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2526948241","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004989648,0.00025913233,0.9908529,0.0001288466,0.00008672068,0.000020078129,0.000074916774,0.0008076507,0.0027801942],"genre_scores_gemma":[0.24092829,0.0006590384,0.7444196,0.00016702253,0.0002017555,0.0001417656,0.0007641072,0.00071060885,0.01200782],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987839,0.00033713834,0.00009579466,0.00018613382,0.00048392286,0.00011313104],"domain_scores_gemma":[0.9974891,0.0013235164,0.000094416755,0.00055970036,0.000434843,0.000098438715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015195207,0.0004519189,0.0007525893,0.0010151699,0.0005232939,0.0014975087,0.0014145472,0.0010643495,0.009165096],"category_scores_gemma":[0.00810617,0.0003120435,0.000624893,0.0012972702,0.0011581354,0.0037347616,0.002431794,0.0024670428,0.0028856283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001948605,0.000087744025,0.0002697218,0.000095045165,0.000019503908,0.000079413134,0.0001740926,0.03852279,0.0043815863,0.3597584,0.008716027,0.5877008],"study_design_scores_gemma":[0.000021947479,0.000054613705,0.00011500128,0.000038854505,0.000010920054,0.00014160786,0.000043256183,0.53706896,0.0045304406,0.4462386,0.011720009,0.000015748528],"about_ca_topic_score_codex":0.0011002399,"about_ca_topic_score_gemma":0.0012123574,"teacher_disagreement_score":0.009165096,"about_ca_system_score_codex":0.0005269781,"about_ca_system_score_gemma":0.00077453913,"threshold_uncertainty_score":0.030660331},"labels":[],"label_agreement":null},{"id":"W2537243181","doi":"10.1016/j.jalz.2016.06.1717","title":"P3‐059: Does Synthetic Data Oversampling in Feature Selection Improve the Classification Rate in Alzheimer's Disease?","year":2016,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; McGill Genome Centre","funders":"","keywords":"Undersampling; Oversampling; Feature selection; Bootstrapping (finance); Artificial intelligence; Overfitting; Computer science; Pattern recognition (psychology); Machine learning; Feature (linguistics); Normalization (sociology); Artificial neural network; Mathematics","score_opus":0.16469581241702383,"score_gpt":0.4325401594097006,"score_spread":0.2678443469926768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2537243181","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76608354,0.002286336,0.21988967,0.0033749228,0.00061291433,0.00033993676,0.0021350693,0.0020223963,0.0032552148],"genre_scores_gemma":[0.944919,0.00024274107,0.050892558,0.00033763185,0.00011468934,0.00014412742,0.002392807,0.00012025977,0.00083627034],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99736506,0.0019024888,0.00011797061,0.00028873916,0.00023538146,0.00009038049],"domain_scores_gemma":[0.9852975,0.0107250195,0.00055094244,0.001791887,0.0013818202,0.00025272707],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014593155,0.0005643898,0.00065923156,0.00040873996,0.00033698816,0.0008260171,0.000730084,0.00082813634,0.0020642134],"category_scores_gemma":[0.037003025,0.00018518195,0.00066402287,0.0003649098,0.00049548066,0.00094996946,0.0006406539,0.00063435244,0.00049702084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013156296,0.0012174348,0.100229025,0.00082475983,0.0012302652,0.0003755082,0.0004465471,0.20421486,0.013691809,0.0047941217,0.026568932,0.6332504],"study_design_scores_gemma":[0.0004143237,0.0019435759,0.021835783,0.00009411635,0.00019490672,0.00029239772,0.00015540459,0.95632416,0.009355416,0.0049156197,0.0044348277,0.000039346316],"about_ca_topic_score_codex":0.001638201,"about_ca_topic_score_gemma":0.0015307954,"teacher_disagreement_score":0.014593155,"about_ca_system_score_codex":0.0003577341,"about_ca_system_score_gemma":0.00062426523,"threshold_uncertainty_score":0.07717687},"labels":[],"label_agreement":null},{"id":"W2540310836","doi":"10.5539/gjhs.v9n6p33","title":"Applications of Cloud Computing in Health Systems","year":2016,"lang":"en","type":"article","venue":"Global Journal of Health Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cloud computing; Health care; Services computing; Computer science; Clinical decision support system; HRHIS; Health policy; Data science; Public health; World Wide Web; Medicine; Web service; Decision support system; Data mining; Nursing; Political science","score_opus":0.13430320515479158,"score_gpt":0.5227209282220983,"score_spread":0.3884177230673067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2540310836","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027696105,0.5839152,0.10108498,0.061693832,0.0034802863,0.0005681257,0.0010900458,0.00047267607,0.21999872],"genre_scores_gemma":[0.5910382,0.3307355,0.060901877,0.004702887,0.004274243,0.0003574625,0.0007154939,0.000077786426,0.007196522],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99690706,0.0014423201,0.00024005426,0.0002454123,0.0009839539,0.00018117671],"domain_scores_gemma":[0.99042964,0.007233729,0.0006937135,0.00042787835,0.0009999855,0.00021491451],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028775423,0.00037893598,0.0005272097,0.0025211785,0.0008219265,0.003407891,0.0008271813,0.0013529087,0.0067306836],"category_scores_gemma":[0.008927865,0.00020776935,0.0007167137,0.006645333,0.0012080162,0.0029455984,0.0018906199,0.0012414013,0.0009604192],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011531685,0.000108628934,0.012090434,0.010371089,0.00032191369,0.001123301,0.0012672768,0.017086098,0.0015714914,0.44916493,0.052771315,0.45400816],"study_design_scores_gemma":[0.000067662775,0.00016739257,0.0132584125,0.0075858687,0.00020629016,0.0020510003,0.001487985,0.033646397,0.0021066754,0.46197978,0.47735515,0.00008729491],"about_ca_topic_score_codex":0.0029064654,"about_ca_topic_score_gemma":0.0017758362,"teacher_disagreement_score":0.0067306836,"about_ca_system_score_codex":0.0021479863,"about_ca_system_score_gemma":0.0026771482,"threshold_uncertainty_score":0.02251637},"labels":[],"label_agreement":null},{"id":"W2546602784","doi":"10.21013/jmss.v5.n1.p11","title":"Quality of life of Persons with Diabetes Mellitus","year":2016,"lang":"en","type":"article","venue":"IRA-International Journal of Management & Social Sciences (ISSN 2455-2267)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Toronto","keywords":"Nonprobability sampling; Diabetes mellitus; Quality of life (healthcare); Gerontology; Population; Medicine; Blood sugar; Psychology; Environmental health; Endocrinology; Nursing","score_opus":0.18093036954902056,"score_gpt":0.48323729571295726,"score_spread":0.30230692616393673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2546602784","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98710537,0.004625419,0.00017155173,0.001375802,0.00006290743,0.000035083318,0.0008767693,0.0000072116536,0.005739801],"genre_scores_gemma":[0.9978254,0.0010754039,0.00014668185,0.00016722528,0.000014247369,0.000016990056,0.00036974202,0.0000010635812,0.00038328182],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993228,0.00019917828,0.00008973123,0.00005299492,0.00021811086,0.000117211755],"domain_scores_gemma":[0.99886155,0.00017669641,0.00048949785,0.00002941493,0.00019893282,0.00024384474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072004605,0.000121109435,0.0002778987,0.00077454397,0.00038438902,0.00072008587,0.00018280254,0.0002926599,0.002655579],"category_scores_gemma":[0.0033643337,0.000077105506,0.00047497355,0.0008522454,0.00018516836,0.00048900757,0.0005781507,0.00059390115,0.00016596913],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014247495,0.0002814941,0.95002437,0.00024898243,0.0001997732,0.00023679485,0.0020778289,0.00017005605,0.00026172987,0.00030863468,0.0022543864,0.043793492],"study_design_scores_gemma":[0.000010233071,0.00032422514,0.9922289,0.00016598903,0.00006311996,0.00046265972,0.0026895057,0.00022359901,0.00008155766,0.00026910272,0.003465981,0.000015054772],"about_ca_topic_score_codex":0.00179361,"about_ca_topic_score_gemma":0.002039282,"teacher_disagreement_score":0.002655579,"about_ca_system_score_codex":0.0004059341,"about_ca_system_score_gemma":0.00024378659,"threshold_uncertainty_score":0.008883774},"labels":[],"label_agreement":null},{"id":"W2547447314","doi":"10.32920/ryerson.14660673","title":"Comparative analysis of classification models for diagnosis Type 2 Diabetes","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Hospital for Sick Children; McMaster University","keywords":"C4.5 algorithm; Machine learning; Computer science; Decision tree; Artificial intelligence; Data mining; Medical diagnosis; Expert system; Multilayer perceptron; Support vector machine; Perceptron; Naive Bayes classifier; Artificial neural network; Medicine","score_opus":0.5582518129913863,"score_gpt":0.567110148366119,"score_spread":0.008858335374732684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2547447314","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67648804,0.016503956,0.28925052,0.0022900116,0.00054264284,0.00041761162,0.0022186728,0.0011661202,0.011122474],"genre_scores_gemma":[0.937105,0.0022447798,0.057487167,0.00014457329,0.00010264832,0.00016010835,0.0015654487,0.000050463805,0.0011397182],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965659,0.0018839849,0.00025811605,0.00036397245,0.00076460984,0.0001634457],"domain_scores_gemma":[0.962208,0.03387756,0.0006479588,0.00063187256,0.002452632,0.00018202851],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009718485,0.0008629058,0.0014579652,0.0038610243,0.00047055137,0.0017295575,0.00093281997,0.0011082714,0.0015940312],"category_scores_gemma":[0.02815826,0.00019586715,0.0016409563,0.0020468263,0.00023337225,0.0011808127,0.00047487102,0.00082320994,0.00031883863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029562511,0.0007054198,0.0842296,0.0008138302,0.0017496294,0.00025857537,0.00038979796,0.49050394,0.0013086022,0.008773057,0.0050768526,0.40323448],"study_design_scores_gemma":[0.000031768734,0.00029917926,0.0127859805,0.000082248735,0.0002321965,0.000081657476,0.00014959456,0.9821699,0.00072662794,0.002649107,0.0007682885,0.000023530969],"about_ca_topic_score_codex":0.008840141,"about_ca_topic_score_gemma":0.0046548606,"teacher_disagreement_score":0.009718485,"about_ca_system_score_codex":0.0018174682,"about_ca_system_score_gemma":0.0010837694,"threshold_uncertainty_score":0.051396906},"labels":[],"label_agreement":null},{"id":"W2547710899","doi":"","title":"Study of diagnosis of diabetes mellitus under healthcare","year":2016,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity College","funders":"","keywords":"Diabetes mellitus; Disease; Process (computing); Risk analysis (engineering); Health care; Intensive care medicine; Medicine; Health problems; Expert system; Computer science; Gerontology; Artificial intelligence; Economics; Economic growth","score_opus":0.24630529080720306,"score_gpt":0.4985447371949906,"score_spread":0.2522394463877875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2547710899","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8307663,0.032514147,0.007248172,0.040650763,0.0008664794,0.00012536888,0.001240258,0.000041618026,0.08654694],"genre_scores_gemma":[0.9855262,0.00870009,0.0017588339,0.00085526664,0.00043359338,0.000021301586,0.00023407346,0.0000041756125,0.002466408],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983707,0.00075111515,0.00013158309,0.00021659429,0.00040272952,0.000127285],"domain_scores_gemma":[0.9936289,0.003694776,0.0010489894,0.00010391523,0.0011657887,0.00035759088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013486699,0.00014163955,0.00024242737,0.002071761,0.00064401946,0.001959274,0.0003840123,0.0005829439,0.0033516563],"category_scores_gemma":[0.010988923,0.000081638194,0.00028823165,0.002114201,0.0006706662,0.0017180338,0.00056798384,0.0005454375,0.00031098],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001496046,0.00022047422,0.8257794,0.00037693162,0.000095263575,0.0016662098,0.0055522393,0.0005304278,0.00045106336,0.036228787,0.0073214048,0.12162819],"study_design_scores_gemma":[0.000022276088,0.0004239179,0.8480728,0.001174059,0.00021883588,0.00743616,0.048159074,0.010001181,0.0008525969,0.034757476,0.04881919,0.00006237],"about_ca_topic_score_codex":0.007570095,"about_ca_topic_score_gemma":0.0043613655,"teacher_disagreement_score":0.007570095,"about_ca_system_score_codex":0.0013789797,"about_ca_system_score_gemma":0.0014952567,"threshold_uncertainty_score":0.015052021},"labels":[],"label_agreement":null},{"id":"W2549346488","doi":"10.2196/medinform.5359","title":"Challenges and Opportunities of Big Data in Health Care: A Systematic Review","year":2016,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":405,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Big data; Health care; CINAHL; Data science; Analytics; Standardization; Data governance; Data quality; Computer science; Data management; MEDLINE; Medicine; Knowledge management; Business; Political science; Data mining; Marketing","score_opus":0.6379363503337271,"score_gpt":0.576138637263599,"score_spread":0.061797713070128046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2549346488","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00030871827,0.99849236,0.00013306456,0.0005947212,0.000095900694,0.00008303265,0.00006439204,0.000003053399,0.00022466996],"genre_scores_gemma":[0.004024701,0.9946818,0.00051066326,0.0004496724,0.00006121046,0.00017055997,0.000052735024,0.0000020139466,0.00004679368],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.98990554,0.003964592,0.0029756168,0.0005107265,0.0023230598,0.00032045477],"domain_scores_gemma":[0.9388221,0.04925437,0.0058160233,0.000617407,0.004843516,0.0006465194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013284553,0.0011338665,0.0040619792,0.011965692,0.0009700772,0.0033857566,0.00188513,0.002316663,0.0026674492],"category_scores_gemma":[0.051524043,0.00089902704,0.004370052,0.015803507,0.0011043204,0.004633662,0.0022298268,0.0015770985,0.00030494307],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000079354846,0.000021417238,0.0010026451,0.857328,0.0024578741,0.00017412416,0.00079217413,0.00015579507,0.00013219105,0.0010723791,0.004619669,0.13216452],"study_design_scores_gemma":[0.000044068805,0.00008873079,0.0020331389,0.9336239,0.009422631,0.0004633695,0.0010680942,0.00010148665,0.000120855264,0.0008302428,0.052165803,0.000037684986],"about_ca_topic_score_codex":0.006878088,"about_ca_topic_score_gemma":0.02416387,"teacher_disagreement_score":0.013284553,"about_ca_system_score_codex":0.0039441776,"about_ca_system_score_gemma":0.023278184,"threshold_uncertainty_score":0.07025623},"labels":[],"label_agreement":null},{"id":"W2564914920","doi":"10.1111/ajt.14164","title":"Elementary, My Dear Watson—The Era of Natural Language Processing in Transplantation","year":2016,"lang":"en","type":"letter","venue":"American Journal of Transplantation","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Medicine; Transplantation; Unstructured data; Big data; Kidney transplantation; Analytics; Data extraction; Computer science; Data science; Artificial intelligence; Data mining; MEDLINE; Internal medicine","score_opus":0.03558542084464109,"score_gpt":0.41200919946127346,"score_spread":0.37642377861663234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2564914920","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001629321,0.14436369,0.018525185,0.79567444,0.030618861,0.000036109646,0.00031044325,0.00032220967,0.008519683],"genre_scores_gemma":[0.060553312,0.31354368,0.049813293,0.43777716,0.11357858,0.00027510733,0.0005773532,0.0011265101,0.02275498],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99168676,0.0042325645,0.000666303,0.0010364751,0.0019972709,0.00038065168],"domain_scores_gemma":[0.9291206,0.055304617,0.0022535434,0.0035533991,0.007241983,0.00252581],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020299008,0.0006211702,0.00096068735,0.0034893302,0.0024090987,0.010904004,0.0016588949,0.0052072285,0.009663287],"category_scores_gemma":[0.064408936,0.00054691336,0.001372121,0.0027427557,0.012732217,0.026472772,0.0042026327,0.017387018,0.0043291007],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020874602,0.0000816611,0.0021791842,0.0012723707,0.00009239351,0.00037802928,0.0025479493,0.00037339446,0.000659899,0.12467674,0.51553,0.3519996],"study_design_scores_gemma":[0.00002837751,0.00007250868,0.0010342498,0.0024646285,0.00003009814,0.00097031175,0.0017667371,0.0007510043,0.00048309393,0.14963908,0.8426852,0.00007469052],"about_ca_topic_score_codex":0.0029302922,"about_ca_topic_score_gemma":0.0027912997,"teacher_disagreement_score":0.020299008,"about_ca_system_score_codex":0.0030818603,"about_ca_system_score_gemma":0.004851101,"threshold_uncertainty_score":0.107352674},"labels":[],"label_agreement":null},{"id":"W2575420350","doi":"10.1109/ftc.2016.7821702","title":"Application of multilayer perceptron neural networks and support vector machines in classification of healthcare data","year":2016,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Support vector machine; Computer science; Artificial intelligence; Machine learning; Multilayer perceptron; Artificial neural network; Field (mathematics); Data mining; Perceptron; Data classification; Structured support vector machine; Decision support system; Pattern recognition (psychology)","score_opus":0.22089744636295658,"score_gpt":0.49749454727842535,"score_spread":0.27659710091546874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2575420350","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.514451,0.0113115,0.46440366,0.0017228283,0.00054056634,0.00014317752,0.00056906225,0.0012504378,0.005607837],"genre_scores_gemma":[0.923361,0.0010696162,0.07419031,0.00009586867,0.00008436338,0.00003941999,0.00023060926,0.000012777212,0.0009161088],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979107,0.0008965619,0.0002163174,0.00018355013,0.00065859454,0.00013434885],"domain_scores_gemma":[0.9971942,0.0018933534,0.00022888668,0.00014711173,0.00047564617,0.00006091041],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00293855,0.00043221246,0.00054583175,0.0013547144,0.00019563944,0.00077706866,0.00034982574,0.0006935159,0.00074985327],"category_scores_gemma":[0.0081737265,0.00015031322,0.00045670298,0.0012374311,0.00028308955,0.00084208127,0.00042661882,0.000576167,0.00020423779],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009749443,0.00041480243,0.022967264,0.00034846817,0.00035021678,0.00030246974,0.00020499989,0.27803922,0.007991166,0.003685206,0.0024895528,0.6822316],"study_design_scores_gemma":[0.000016966134,0.00030178748,0.007376216,0.000051743224,0.000038581526,0.00010468979,0.000075645796,0.98452455,0.0035336849,0.0028872194,0.0010640654,0.000024727475],"about_ca_topic_score_codex":0.0028380705,"about_ca_topic_score_gemma":0.001758027,"teacher_disagreement_score":0.00293855,"about_ca_system_score_codex":0.00036917586,"about_ca_system_score_gemma":0.00037285252,"threshold_uncertainty_score":0.015540719},"labels":[],"label_agreement":null},{"id":"W2588263610","doi":"10.1093/eurpub/ckv167.043","title":"Integrating evidence into practice: examples from the Slovenia National Program on CVDs Prevention","year":2015,"lang":"en","type":"article","venue":"European Journal of Public Health","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Evidence-based practice; Environmental health; Medicine; Family medicine; Alternative medicine","score_opus":0.6679378439588496,"score_gpt":0.5920794090752761,"score_spread":0.07585843488357347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588263610","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1359807,0.39732382,0.0242314,0.11874972,0.0023562282,0.009262733,0.008961268,0.00077010103,0.30236405],"genre_scores_gemma":[0.45619386,0.3179665,0.16437565,0.028941216,0.00048140652,0.0063356473,0.008020688,0.0005169981,0.017168043],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9647189,0.022097569,0.005088609,0.0007487772,0.005459635,0.0018864989],"domain_scores_gemma":[0.9423851,0.037777323,0.0033547063,0.0018071112,0.011618637,0.0030571062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036680054,0.00056257343,0.0007433571,0.007791761,0.001871173,0.0042294282,0.0014039763,0.0025544395,0.004493979],"category_scores_gemma":[0.05172219,0.00043685132,0.0010374014,0.014234128,0.001394156,0.0017426137,0.0042812955,0.0021558253,0.0011419202],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044204813,0.000663187,0.017265342,0.033341955,0.0002615695,0.0028628826,0.017064257,0.0010582126,0.00075030635,0.014672995,0.08519901,0.82641816],"study_design_scores_gemma":[0.0003053036,0.00039013135,0.10535107,0.07755412,0.000412196,0.0025226697,0.0151064955,0.0005449348,0.00068492524,0.0053377426,0.79169357,0.00009684742],"about_ca_topic_score_codex":0.019386409,"about_ca_topic_score_gemma":0.047764838,"teacher_disagreement_score":0.036680054,"about_ca_system_score_codex":0.008652342,"about_ca_system_score_gemma":0.027775208,"threshold_uncertainty_score":0.19398499},"labels":[],"label_agreement":null},{"id":"W2603008931","doi":"10.1109/csci.2016.0014","title":"Machine Learning Application to Predict the Risk of Coronary Artery Atherosclerosis","year":2016,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Imputation (statistics); Computer science; Expectation–maximization algorithm; Maximization; Artificial intelligence; Missing data; Coronary artery disease; Pattern recognition (psychology); Machine learning; Cardiology; Maximum likelihood; Statistics; Medicine; Mathematics","score_opus":0.09352734841443064,"score_gpt":0.4098723615359309,"score_spread":0.3163450131215002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2603008931","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.110671274,0.0033242996,0.87490225,0.0015667599,0.0002215089,0.00014428314,0.0006327913,0.0026035816,0.0059333243],"genre_scores_gemma":[0.73583925,0.0012543843,0.25898698,0.00020388597,0.00016083027,0.000100889294,0.00079590536,0.000038379836,0.0026195275],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931526,0.00027520335,0.00006180727,0.00011233072,0.00019509574,0.000040221134],"domain_scores_gemma":[0.99811506,0.0012173597,0.00012944311,0.00012456189,0.00037393326,0.000039575854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016254568,0.00043768348,0.0006333004,0.0010886769,0.00027314658,0.00048230047,0.0005765183,0.00062416174,0.0012989461],"category_scores_gemma":[0.004748768,0.00014401495,0.00045109878,0.0011750242,0.00016881074,0.00035212762,0.00036595808,0.00070079626,0.0005852579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017580923,0.0005036334,0.032985263,0.00017847549,0.0001879329,0.00032597344,0.00010078712,0.23238485,0.0057742824,0.0037159317,0.0060794447,0.7175877],"study_design_scores_gemma":[0.0000109145085,0.00008400295,0.0040893243,0.000020295669,0.0000249042,0.00019002294,0.000025700087,0.98637354,0.003297833,0.0034522847,0.0024192035,0.000012013438],"about_ca_topic_score_codex":0.0019512381,"about_ca_topic_score_gemma":0.0015941429,"teacher_disagreement_score":0.0019512381,"about_ca_system_score_codex":0.0002538031,"about_ca_system_score_gemma":0.00058636564,"threshold_uncertainty_score":0.008596361},"labels":[],"label_agreement":null},{"id":"W2604204979","doi":"10.3233/978-1-61499-742-9-1","title":"What We Can Learn from Amazon for Clinical Decision Support Systems","year":2017,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; SNC-Lavalin (Canada)","funders":"","keywords":"Amazon rainforest; Computer science; Clinical decision support system; Data science; Decision support system; Artificial intelligence; Biology","score_opus":0.42940782789367377,"score_gpt":0.6091081733350611,"score_spread":0.1797003454413873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604204979","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017280165,0.054674316,0.021604914,0.8215958,0.0052388865,0.00012947127,0.0020218075,0.0015049133,0.075949825],"genre_scores_gemma":[0.44207633,0.12112979,0.15289932,0.20243828,0.021129658,0.00040773014,0.005234495,0.00188743,0.052796923],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945738,0.0024330346,0.0004404759,0.0004345855,0.0016393798,0.000478822],"domain_scores_gemma":[0.9684607,0.016976492,0.0010837998,0.0033750457,0.006781951,0.003321973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009773695,0.0006360197,0.0004880955,0.0012126103,0.0017264441,0.011541095,0.001962511,0.004099898,0.021387672],"category_scores_gemma":[0.044062518,0.0004367093,0.0010185048,0.0023446165,0.0026738287,0.02486347,0.0033197275,0.0041936506,0.007414281],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002669875,0.00023632565,0.009179349,0.002541237,0.00010630344,0.0008147549,0.0039781234,0.00067221606,0.0019495287,0.10838877,0.46860167,0.40326473],"study_design_scores_gemma":[0.000052068608,0.00020880245,0.0051147807,0.0023461676,0.000073812625,0.0008300564,0.00581713,0.0023721273,0.001674589,0.10035775,0.8810473,0.00010539204],"about_ca_topic_score_codex":0.006352503,"about_ca_topic_score_gemma":0.009704337,"teacher_disagreement_score":0.021387672,"about_ca_system_score_codex":0.0022962508,"about_ca_system_score_gemma":0.0031581228,"threshold_uncertainty_score":0.07154888},"labels":[],"label_agreement":null},{"id":"W2613901005","doi":"10.20286/jeas.v3i4.27","title":"Prediction of Workplace Accidents with Knowledge Discovery Approach Using Weka Software","year":2016,"lang":"en","type":"article","venue":"Nova Journal of Engineering and Applied Sciences","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Engineering; Population; Occupational safety and health; Order (exchange); Occupational accident; Forensic engineering; Operations management; Business; Risk analysis (engineering); Environmental health; Occupational medicine; Medicine","score_opus":0.17608578707034006,"score_gpt":0.39842769143161516,"score_spread":0.2223419043612751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2613901005","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35596648,0.0008565096,0.60742503,0.0011563458,0.00013780087,0.0026187256,0.012301023,0.013403075,0.006134976],"genre_scores_gemma":[0.6046594,0.00075560034,0.3808273,0.00012241612,0.000028117604,0.0019354199,0.009886318,0.00009656697,0.0016888891],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990402,0.00019956128,0.00025396803,0.0001850794,0.00023935937,0.00008190041],"domain_scores_gemma":[0.9954568,0.003423539,0.00040109653,0.00017973859,0.0004885582,0.000050254253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012262331,0.00097201957,0.00077003,0.004820922,0.00071270816,0.0012219627,0.0009981589,0.000561944,0.0021572637],"category_scores_gemma":[0.006670343,0.0005063641,0.0019971319,0.0020717788,0.0002637825,0.000732524,0.0006491739,0.00085773924,0.0005995947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058105844,0.0013333167,0.058885623,0.0029618128,0.0011532321,0.0014991104,0.00079735194,0.4898118,0.008767443,0.0032937229,0.011748978,0.41916654],"study_design_scores_gemma":[0.00007947842,0.00031340605,0.014682765,0.00025376957,0.00048981,0.00032823224,0.00046839062,0.96271783,0.010188967,0.0043619084,0.0060431194,0.00007236406],"about_ca_topic_score_codex":0.015146019,"about_ca_topic_score_gemma":0.010615743,"teacher_disagreement_score":0.015146019,"about_ca_system_score_codex":0.0008180077,"about_ca_system_score_gemma":0.002233121,"threshold_uncertainty_score":0.030115724},"labels":[],"label_agreement":null},{"id":"W2621304421","doi":"","title":"Dataset Descriptions: HCLS Community Profile","year":2015,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Computer vision","score_opus":0.6792525543304674,"score_gpt":0.5844529803168492,"score_spread":0.09479957401361816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2621304421","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00085263327,0.0001362801,0.0002742065,0.00016397917,0.000070764996,0.00011193719,0.996046,0.00088549143,0.001458708],"genre_scores_gemma":[0.00087947823,0.00007087628,0.0009543469,0.00009745144,0.000014472741,0.00021215841,0.9968714,0.00010535487,0.00079450407],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981857,0.00036084253,0.00029816234,0.00048167515,0.0004397557,0.0002337974],"domain_scores_gemma":[0.9949373,0.0013982074,0.0003180879,0.0012399007,0.0015005097,0.0006059573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00173655,0.0022144113,0.001109243,0.0059557934,0.0015707816,0.0020283195,0.0031010718,0.0027218575,0.075645015],"category_scores_gemma":[0.011562933,0.0005471094,0.0018267445,0.005978984,0.0005757882,0.0017124629,0.0021009212,0.0016639505,0.073106155],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018730361,0.000108148786,0.0013036168,0.00090722326,0.00003650521,0.00004232999,0.000032214935,0.00049267773,0.0004099816,0.00031158509,0.98962885,0.006539593],"study_design_scores_gemma":[0.00086289895,0.00013962133,0.0077125244,0.0006528462,0.00009159911,0.00021527978,0.00031565805,0.00287311,0.0016332205,0.002038335,0.9833724,0.000092535156],"about_ca_topic_score_codex":0.027904337,"about_ca_topic_score_gemma":0.05709025,"teacher_disagreement_score":0.075645015,"about_ca_system_score_codex":0.0012001375,"about_ca_system_score_gemma":0.0034233793,"threshold_uncertainty_score":0.25305778},"labels":[],"label_agreement":null},{"id":"W2642221425","doi":"10.1515/9783110559040-023","title":"Cancer Trends Predication Based on an Intelligent Method","year":2017,"lang":"en","type":"book-chapter","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Cancer; Artificial intelligence; Medicine; Internal medicine","score_opus":0.3485404483654838,"score_gpt":0.5816911137573542,"score_spread":0.23315066539187035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2642221425","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010697331,0.0073351986,0.9220934,0.0014388291,0.0008907117,0.00019436414,0.0005400379,0.0015822662,0.055227835],"genre_scores_gemma":[0.18988495,0.010768998,0.7299544,0.0007412185,0.0006713059,0.00037165356,0.0011764878,0.00025877042,0.06617214],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99960405,0.00006304038,0.00003860879,0.000118534175,0.00015331418,0.000022398179],"domain_scores_gemma":[0.99959,0.00018836922,0.00002631162,0.00003054117,0.00015395948,0.000010821772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006553281,0.0007444084,0.0005736994,0.0019982136,0.00032242204,0.0014313312,0.0008615038,0.00068567396,0.0043041566],"category_scores_gemma":[0.0016483763,0.00026992708,0.0009638389,0.0019780018,0.0003332972,0.0014882073,0.00044090525,0.0006184967,0.0013780554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009414777,0.00010670252,0.004005064,0.00057775696,0.00013833257,0.00039245115,0.00030224468,0.071118556,0.005314256,0.08358367,0.027744528,0.80662227],"study_design_scores_gemma":[0.000039157872,0.00010997776,0.0050578895,0.00026757253,0.00022233096,0.0007968685,0.00016382326,0.7869253,0.008073432,0.07322013,0.12500139,0.0001221152],"about_ca_topic_score_codex":0.002338077,"about_ca_topic_score_gemma":0.002307011,"teacher_disagreement_score":0.0043041566,"about_ca_system_score_codex":0.00072184653,"about_ca_system_score_gemma":0.0006892078,"threshold_uncertainty_score":0.014398873},"labels":[],"label_agreement":null},{"id":"W2724709825","doi":"10.15171/jcvtr.2017.16","title":"Comparison of coronary artery disease guidelines with extracted knowledge from data mining","year":2017,"lang":"en","type":"article","venue":"Journal of Cardiovascular and Thoracic Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Guideline; Coronary artery disease; CAD; Medicine; Disease; Chest pain; Data mining; Internal medicine; Computer science; Pathology; Engineering","score_opus":0.7308694972981719,"score_gpt":0.6669575360507893,"score_spread":0.06391196124738252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2724709825","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9636754,0.0030154167,0.013974136,0.00066831487,0.00009808768,0.0005237153,0.014566967,0.00026975336,0.0032082603],"genre_scores_gemma":[0.9498371,0.0008860595,0.02950687,0.00009804254,0.00004367918,0.00022929731,0.019127332,0.000011638149,0.00025999942],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941461,0.0014201567,0.0017474589,0.000881807,0.0015747775,0.00022968327],"domain_scores_gemma":[0.9671561,0.023406051,0.0031690008,0.0014289174,0.004461594,0.0003782912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059413337,0.00048149892,0.0007061713,0.007816777,0.0004088037,0.001634219,0.0006436454,0.00068760966,0.0007903362],"category_scores_gemma":[0.04072952,0.00014197516,0.0010815643,0.004892883,0.00024172365,0.0012548843,0.00075520156,0.0004908422,0.00023352228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016646473,0.0006801038,0.78063625,0.0022780094,0.0015096623,0.00065204623,0.00081442454,0.0091187265,0.0022879743,0.00084421417,0.0036423635,0.1958715],"study_design_scores_gemma":[0.00033802894,0.0025330773,0.7956985,0.002123502,0.0037503133,0.0022620186,0.004546634,0.15055303,0.014982154,0.0062403264,0.0168208,0.00015152455],"about_ca_topic_score_codex":0.0029927834,"about_ca_topic_score_gemma":0.0049654953,"teacher_disagreement_score":0.007816777,"about_ca_system_score_codex":0.00067312893,"about_ca_system_score_gemma":0.0015736619,"threshold_uncertainty_score":0.031421125},"labels":[],"label_agreement":null},{"id":"W2729440683","doi":"10.4018/978-1-5225-2515-8","title":"Handbook of Research on Data Science for Effective Healthcare Practice and Administration","year":2017,"lang":"en","type":"book","venue":"Advances in healthcare information systems and administration book series","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Calgary","funders":"","keywords":"Administration (probate law); Health care; Psychology; Medicine; Data science; Engineering ethics; Computer science; Political science; Engineering","score_opus":0.22808273230104062,"score_gpt":0.5736741326559185,"score_spread":0.3455914003548779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2729440683","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00102713,0.3354896,0.1498897,0.061949793,0.01594286,0.0006990358,0.0088519035,0.0047552544,0.42139474],"genre_scores_gemma":[0.014630758,0.4264129,0.23907763,0.029817598,0.0104987025,0.0019066563,0.008786734,0.0023747364,0.2664942],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953884,0.0013302697,0.00047320608,0.0003793198,0.0023296252,0.00009915018],"domain_scores_gemma":[0.9710443,0.022721726,0.00073342025,0.001521867,0.00343064,0.000548129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005929442,0.0008694639,0.0014453069,0.0036662417,0.0009584977,0.008072679,0.0017115705,0.0016310029,0.04148925],"category_scores_gemma":[0.021349581,0.0008474571,0.0007220432,0.0062357867,0.0018614279,0.006166107,0.0020021447,0.005343748,0.025997745],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010417516,0.00003111864,0.00017394961,0.0013444521,0.00003498756,0.00002742745,0.00035860625,0.00037997024,0.00020245627,0.105757274,0.6654891,0.22619031],"study_design_scores_gemma":[0.0000064387095,0.000011145577,0.00036548518,0.0011837106,0.000010318734,0.00009495848,0.000121760146,0.0004265784,0.000088390996,0.038729493,0.95894575,0.000016009717],"about_ca_topic_score_codex":0.0024756382,"about_ca_topic_score_gemma":0.003569305,"teacher_disagreement_score":0.04148925,"about_ca_system_score_codex":0.0022078876,"about_ca_system_score_gemma":0.009639727,"threshold_uncertainty_score":0.13879538},"labels":[],"label_agreement":null},{"id":"W2730393743","doi":"10.1145/3059009.3072977","title":"A 12 Week Full Stack Web Course in 2017","year":2017,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Course (navigation); Computer science; Stack (abstract data type); World Wide Web; Multimedia; Operating system; Engineering","score_opus":0.36704157212606114,"score_gpt":0.5564227916633853,"score_spread":0.18938121953732412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2730393743","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14753167,0.0028078288,0.04508113,0.069216624,0.04666747,0.005726422,0.008034421,0.008575223,0.6663591],"genre_scores_gemma":[0.11914149,0.002006844,0.024331016,0.016701352,0.0041541667,0.0024027275,0.006440933,0.0009923065,0.8238291],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987399,0.00010921536,0.00005037097,0.00018338005,0.0003795855,0.0005376353],"domain_scores_gemma":[0.9960737,0.000091898335,0.00011048106,0.000096614596,0.000558185,0.003069169],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028328246,0.0017682061,0.0011750847,0.0011471125,0.0041171904,0.005860861,0.0024558944,0.0023252536,0.1110528],"category_scores_gemma":[0.0026023586,0.00055442046,0.0008337255,0.00061615766,0.0012649285,0.0025919962,0.0068490687,0.0042115864,0.07147152],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005358086,0.005672773,0.0033542472,0.00027824382,0.000017041559,0.0006310855,0.0010242254,0.0014741617,0.0053370623,0.01457596,0.7989433,0.16815616],"study_design_scores_gemma":[0.00010082967,0.0015093838,0.0112166805,0.00037824467,0.000012018855,0.00036915424,0.0018983694,0.0017814789,0.0031515884,0.017281858,0.9622484,0.00005208211],"about_ca_topic_score_codex":0.0028865081,"about_ca_topic_score_gemma":0.009768085,"teacher_disagreement_score":0.1110528,"about_ca_system_score_codex":0.0043275184,"about_ca_system_score_gemma":0.008076903,"threshold_uncertainty_score":0.37150866},"labels":[],"label_agreement":null},{"id":"W2732108610","doi":"10.1177/096228020401300507","title":"Book Review: Analyzing medical data using S-PLUS","year":2004,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Data science","score_opus":0.7380944379549161,"score_gpt":0.7792716709767741,"score_spread":0.04117723302185794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2732108610","genre_codex":"review","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035272145,0.53310835,0.2400955,0.066222906,0.09888222,0.0006400182,0.005945801,0.0152184805,0.036359522],"genre_scores_gemma":[0.014809521,0.34511068,0.22202303,0.050381403,0.09213092,0.000802454,0.0069516418,0.009960379,0.25783],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979882,0.0005878333,0.00014827918,0.00023952776,0.0009855548,0.00005058816],"domain_scores_gemma":[0.97944605,0.011912117,0.00076873665,0.000695539,0.0065267286,0.0006508523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022771498,0.0013102132,0.0026363013,0.0045523066,0.00046325795,0.0017053003,0.0011662362,0.0013061943,0.025217773],"category_scores_gemma":[0.014549082,0.0007007833,0.0013209959,0.00694867,0.0008042641,0.0017113474,0.00068868906,0.002213024,0.022171127],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033205553,0.000025325086,0.00022045318,0.00068699813,0.000063319996,0.000043771597,0.0000133002395,0.00033836442,0.00032759755,0.000572848,0.8411946,0.15648022],"study_design_scores_gemma":[0.000044618668,0.00014787508,0.0022239562,0.000661807,0.00015888238,0.0008560373,0.000025510528,0.003536435,0.0013571287,0.0042036055,0.98672473,0.000059351783],"about_ca_topic_score_codex":0.0027801925,"about_ca_topic_score_gemma":0.0076244744,"teacher_disagreement_score":0.025217773,"about_ca_system_score_codex":0.00079075573,"about_ca_system_score_gemma":0.0020813954,"threshold_uncertainty_score":0.08436185},"labels":[],"label_agreement":null},{"id":"W2737306180","doi":"10.4018/978-1-5225-2515-8.ch012","title":"Application of Data Mining Techniques in Clinical Decision Making","year":2017,"lang":"en","type":"book-chapter","venue":"Advances in healthcare information systems and administration book series","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Clinical decision making; Medical decision making; Data mining; Medicine; Computer science; Intensive care medicine; Medical emergency","score_opus":0.17742833689900842,"score_gpt":0.5300307289739543,"score_spread":0.3526023920749459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2737306180","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004222361,0.67826694,0.2454826,0.017656026,0.0028787053,0.0006199807,0.0022264703,0.00066779996,0.047979113],"genre_scores_gemma":[0.04226663,0.5304614,0.4069102,0.0041198977,0.0026398038,0.0007993918,0.0020908401,0.00014509397,0.010566882],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.994892,0.0020326949,0.0006624473,0.00045569736,0.0018694365,0.00008774984],"domain_scores_gemma":[0.98642665,0.011373206,0.0005033884,0.0003529123,0.0012413365,0.00010246028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068609472,0.0009732803,0.0011008385,0.005249157,0.00046863419,0.0035152861,0.0015786686,0.0013218632,0.005852335],"category_scores_gemma":[0.018192284,0.00050898327,0.0015915334,0.007894535,0.0008708191,0.0028079972,0.0013406313,0.0027001104,0.003086106],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005977767,0.00008280081,0.0018120139,0.009284986,0.00042642598,0.00030221985,0.0005010974,0.004359156,0.00068044494,0.046839967,0.054598767,0.88105226],"study_design_scores_gemma":[0.000057556346,0.00021079194,0.0040779132,0.018056275,0.00038599098,0.0018105021,0.0008481143,0.01881004,0.002722585,0.2152567,0.73760194,0.00016162873],"about_ca_topic_score_codex":0.001384595,"about_ca_topic_score_gemma":0.0019672764,"teacher_disagreement_score":0.0068609472,"about_ca_system_score_codex":0.0013498964,"about_ca_system_score_gemma":0.0024352218,"threshold_uncertainty_score":0.036284566},"labels":[],"label_agreement":null},{"id":"W2738045462","doi":"10.4018/978-1-5225-2515-8.ch015","title":"Leveraging Applications of Data Mining in Healthcare Using Big Data Analytics","year":2017,"lang":"en","type":"book-chapter","venue":"Advances in healthcare information systems and administration book series","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Big data; Data science; Leverage (statistics); Computer science; Analytics; Data analysis; Scalability; Health care; Data mining; Data quality; Data set; Set (abstract data type); Database; Artificial intelligence; Engineering","score_opus":0.3738997594153554,"score_gpt":0.4895918567705111,"score_spread":0.11569209735515568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2738045462","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065425523,0.21352328,0.39925325,0.027650582,0.009093845,0.00044811587,0.0010165612,0.0030342124,0.33943757],"genre_scores_gemma":[0.04772171,0.2687393,0.4736169,0.010525057,0.009224239,0.00036488264,0.0019606485,0.0010855882,0.18676169],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993507,0.000108586944,0.000036205398,0.00009568518,0.00038039763,0.000028435348],"domain_scores_gemma":[0.99879813,0.0008389552,0.00003876383,0.00010228388,0.00015724689,0.000064468484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011029888,0.00095297367,0.00058296253,0.00211581,0.00048290959,0.0040878346,0.0011428751,0.0009616566,0.008007308],"category_scores_gemma":[0.0023624112,0.00053079,0.0008357458,0.003542532,0.0007815005,0.0044774893,0.001963935,0.0023292124,0.0064480016],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034549095,0.00008226766,0.00071354315,0.0013309121,0.00007370896,0.00028459437,0.0008621728,0.0035264166,0.0042320266,0.10743969,0.1698099,0.7116103],"study_design_scores_gemma":[0.000010373852,0.000046977384,0.0008805937,0.001079804,0.000032671098,0.0008996359,0.00027877477,0.008766777,0.002102861,0.11928127,0.8665791,0.000041139047],"about_ca_topic_score_codex":0.00053388416,"about_ca_topic_score_gemma":0.0013006465,"teacher_disagreement_score":0.008007308,"about_ca_system_score_codex":0.00054711517,"about_ca_system_score_gemma":0.0010213557,"threshold_uncertainty_score":0.026787162},"labels":[],"label_agreement":null},{"id":"W2752925099","doi":"10.6000/1927-5129.2017.13.77","title":"Analyzing Diabetes Datasets using Data Mining","year":2017,"lang":"en","type":"article","venue":"Journal of Basic & Applied Sciences","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Naive Bayes classifier; Computer science; Diabetes mellitus; Data mining; Domain (mathematical analysis); Random forest; Data set; Data science; Medicine; Artificial intelligence; Machine learning; Support vector machine; Mathematics","score_opus":0.4432978032849009,"score_gpt":0.5419335777827297,"score_spread":0.09863577449782873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752925099","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35810295,0.0046232757,0.03113708,0.0041801445,0.00093433796,0.002389608,0.5809017,0.00598338,0.011747479],"genre_scores_gemma":[0.3295758,0.0022297867,0.08003198,0.0007421711,0.00028428072,0.0017363302,0.58181703,0.00011533573,0.0034673049],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826425,0.00019324652,0.00039640698,0.00039441072,0.00054381276,0.00020790772],"domain_scores_gemma":[0.99753606,0.0009739941,0.00034528816,0.00039846485,0.0005752561,0.0001708215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015967329,0.00087480695,0.0009175718,0.005708876,0.0008159081,0.0017017445,0.0013959589,0.0012714148,0.0029323297],"category_scores_gemma":[0.0050017694,0.0002111559,0.0013568636,0.006195118,0.00023309852,0.000765001,0.0009023675,0.0012531207,0.0015231299],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029152073,0.0037315737,0.25098258,0.0034693556,0.0010296442,0.00302865,0.00039134387,0.034938727,0.0064833155,0.003698086,0.15476051,0.534571],"study_design_scores_gemma":[0.00071767677,0.0018604364,0.30892155,0.0012842821,0.0007409005,0.0048773405,0.003022489,0.28513187,0.03319493,0.014216013,0.34568778,0.00034480813],"about_ca_topic_score_codex":0.006255427,"about_ca_topic_score_gemma":0.0075008585,"teacher_disagreement_score":0.006255427,"about_ca_system_score_codex":0.0010490493,"about_ca_system_score_gemma":0.0013762586,"threshold_uncertainty_score":0.012437999},"labels":[],"label_agreement":null},{"id":"W2753236721","doi":"10.6000/1927-5129.2017.13.79","title":"Huge and Real-Time Database Systems: A Comparative Study and Review for SQL Server 2016, Oracle 12c &amp; MySQL 5.7 for Personal Computer","year":2017,"lang":"en","type":"article","venue":"Journal of Basic & Applied Sciences","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Oracle; Database; SQL; Relational database; Database server; Object (grammar); Data Transformation Services; Relational database management system; View; Database tuning; Database design; World Wide Web; Query by Example; Software engineering","score_opus":0.3354903277727136,"score_gpt":0.5249143818696304,"score_spread":0.18942405409691676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2753236721","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035249736,0.998159,0.000334396,0.0004518453,0.00008992716,0.00000546688,0.000014652106,0.0000042612214,0.00058800937],"genre_scores_gemma":[0.004080914,0.99406683,0.0009339652,0.00039594635,0.00022972058,0.0000134034635,0.000052094878,0.0000055980404,0.00022145972],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979728,0.0003877624,0.00043743628,0.00028366406,0.0008384923,0.000079864076],"domain_scores_gemma":[0.9898671,0.006674644,0.0008240792,0.00017885378,0.0021954048,0.0002598337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041519674,0.00049372594,0.0010524553,0.006731879,0.00050026336,0.002246264,0.0011390527,0.0010528669,0.0017259095],"category_scores_gemma":[0.0060766577,0.00051181274,0.0008736723,0.010676021,0.0012573891,0.0044601616,0.0008284963,0.0013984098,0.00051562116],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015454431,0.00010345962,0.0021939687,0.032204326,0.00022605396,0.00018395593,0.00051782327,0.0005357756,0.0011453935,0.011002764,0.025540048,0.9261918],"study_design_scores_gemma":[0.000022140319,0.0004568591,0.009938779,0.019279132,0.0006989154,0.003112843,0.0014728056,0.0008416977,0.001385058,0.005158652,0.95751107,0.00012207872],"about_ca_topic_score_codex":0.0022418203,"about_ca_topic_score_gemma":0.0032127944,"teacher_disagreement_score":0.006731879,"about_ca_system_score_codex":0.0013444101,"about_ca_system_score_gemma":0.0024693368,"threshold_uncertainty_score":0.021957994},"labels":[],"label_agreement":null},{"id":"W2754051415","doi":"10.1136/jech-2017-209608","title":"A glossary for big data in population and public health: discussion and commentary on terminology and research methods","year":2017,"lang":"en","type":"article","venue":"Journal of Epidemiology & Community Health","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; Memorial University of Newfoundland","funders":"","keywords":"Big data; Glossary; Terminology; Data science; Analytics; Population; Population health; Public health; Data analysis; Computer science; Medicine; Data mining; Environmental health","score_opus":0.8980856379065626,"score_gpt":0.7287880736224875,"score_spread":0.16929756428407505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2754051415","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018504063,0.121478066,0.012299579,0.7659726,0.07648539,0.00050025835,0.003840931,0.00018823352,0.019049978],"genre_scores_gemma":[0.0050362074,0.11071762,0.02425222,0.7753182,0.059864335,0.004533931,0.0039630844,0.000925364,0.015389029],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9188785,0.035487045,0.021406664,0.0046971384,0.017596107,0.0019345565],"domain_scores_gemma":[0.66048414,0.27497524,0.0098530445,0.011009232,0.040769085,0.0029092703],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10153676,0.0029433698,0.0054681776,0.016354911,0.008614379,0.0153604,0.014788457,0.024286807,0.020414537],"category_scores_gemma":[0.24983703,0.0021681953,0.006647322,0.025538322,0.021200018,0.026549527,0.014343392,0.041967414,0.009109246],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021034908,0.000008078965,0.000052123254,0.0028578367,0.000022352799,0.00010811907,0.0022532411,0.00010712759,0.00009573293,0.10892333,0.874904,0.010647031],"study_design_scores_gemma":[0.000017491571,0.000011039173,0.00023872475,0.0131801255,0.00002494056,0.00018967708,0.00105038,0.00010184743,0.000055611425,0.029294463,0.9557779,0.000057825404],"about_ca_topic_score_codex":0.0369254,"about_ca_topic_score_gemma":0.03222983,"teacher_disagreement_score":0.89846325,"about_ca_system_score_codex":0.020157248,"about_ca_system_score_gemma":0.022308765,"threshold_uncertainty_score":0.5369841},"labels":[],"label_agreement":null},{"id":"W2760488410","doi":"10.1016/j.cjca.2017.07.163","title":"DEVELOPING A CASE DEFINITION FOR CONGESTIVE HEART FAILURE USING PRIMARY CARE EMR DATA","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Cardiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Heart failure; Medical emergency; Medical record; Intensive care medicine; Health care; Identification (biology); Best practice; Family medicine; Emergency medicine; Cardiology; Internal medicine","score_opus":0.5272351720173516,"score_gpt":0.5090941169199376,"score_spread":0.01814105509741404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2760488410","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12810993,0.0005804315,0.8368061,0.0047864714,0.00035149395,0.0036970782,0.007154073,0.002609151,0.015905254],"genre_scores_gemma":[0.3165225,0.00020195918,0.6742058,0.00043435418,0.00007153594,0.0007266022,0.006261597,0.00015037172,0.001425249],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9945022,0.0013573276,0.0013994324,0.0008941223,0.001450917,0.000396146],"domain_scores_gemma":[0.9865219,0.0066437027,0.0017113382,0.0009493555,0.0035287905,0.00064484694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047229417,0.0008949664,0.000576971,0.005727237,0.0013656763,0.0039224415,0.001962527,0.0017463838,0.0035903838],"category_scores_gemma":[0.021465007,0.0005333371,0.001561846,0.0022247084,0.0008918912,0.003399485,0.0030797734,0.0015595744,0.00086534047],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005903309,0.0008764103,0.37347624,0.0014328845,0.00041728257,0.018647062,0.0062361183,0.0539958,0.020028982,0.115768686,0.072765484,0.33576474],"study_design_scores_gemma":[0.00017486195,0.00036085254,0.06729061,0.0012166208,0.0003997987,0.016928378,0.012279884,0.69329995,0.023565978,0.059517153,0.12476444,0.00020147228],"about_ca_topic_score_codex":0.012185606,"about_ca_topic_score_gemma":0.015459401,"teacher_disagreement_score":0.012185606,"about_ca_system_score_codex":0.0017825306,"about_ca_system_score_gemma":0.0029089693,"threshold_uncertainty_score":0.024977565},"labels":[],"label_agreement":null},{"id":"W2766393601","doi":"10.5334/ijic.3357","title":"Using etechnology to create quality care for seniors","year":2017,"lang":"en","type":"article","venue":"International Journal of Integrated Care","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Alberta Health Services","funders":"","keywords":"Quality (philosophy); Field (mathematics); Computer science; World Wide Web","score_opus":0.2675886979538853,"score_gpt":0.5860242466837916,"score_spread":0.3184355487299063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766393601","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19515872,0.0138011,0.18717785,0.20487165,0.006513563,0.0007964955,0.00024203726,0.0013132541,0.39012527],"genre_scores_gemma":[0.7405935,0.010623677,0.19045895,0.020934677,0.0011023107,0.00048104703,0.00025516053,0.00021757618,0.03533301],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.985537,0.008049005,0.0007651481,0.00082538446,0.0036340374,0.001189438],"domain_scores_gemma":[0.9904152,0.0023837509,0.0014037191,0.0014247892,0.0017062547,0.0026662722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015789866,0.0004671412,0.0003354958,0.0019379521,0.0027410267,0.008182869,0.0012280506,0.0017529015,0.005344863],"category_scores_gemma":[0.019266803,0.00022527046,0.0005791434,0.0015463614,0.0041695554,0.005775696,0.0112337675,0.0022088427,0.0016539736],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008269624,0.00096115173,0.02984866,0.00091351476,0.0001264387,0.0005194146,0.029010208,0.0008685502,0.0020735352,0.09970435,0.061085977,0.77480555],"study_design_scores_gemma":[0.0002079873,0.0016139896,0.039427537,0.0037514786,0.00012492375,0.0013989564,0.034499627,0.00316356,0.00267537,0.18405668,0.7289507,0.00012913128],"about_ca_topic_score_codex":0.0021961106,"about_ca_topic_score_gemma":0.0047422666,"teacher_disagreement_score":0.015789866,"about_ca_system_score_codex":0.0029341397,"about_ca_system_score_gemma":0.010991063,"threshold_uncertainty_score":0.08350581},"labels":[],"label_agreement":null},{"id":"W2768710815","doi":"","title":"Framework for development of Information Technology Infrastructure for Health (ITIH) care in India – a critical study","year":2017,"lang":"en","type":"article","venue":"Qualitative and Quantitative Methods in Libraries","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"La Cité Collégiale","funders":"","keywords":"Health care; Business; Interoperability; Health informatics; Stakeholder; Government (linguistics); Population; Information infrastructure; Knowledge management; Information system; HRHIS; Medicine; Public relations; Health policy; Computer science; Political science; Environmental health; World Wide Web","score_opus":0.38286685303719686,"score_gpt":0.6728693411259936,"score_spread":0.29000248808879675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768710815","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04644865,0.018727021,0.1579976,0.17205784,0.0011620645,0.004961765,0.0017236347,0.000711565,0.59620994],"genre_scores_gemma":[0.62100196,0.017409595,0.29595223,0.009445057,0.00035838303,0.0028494038,0.0017266446,0.00015319689,0.05110353],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99294007,0.0033032645,0.0007151752,0.0005173747,0.0013147193,0.0012093732],"domain_scores_gemma":[0.99373156,0.0022007746,0.0005038724,0.00035816777,0.0021662936,0.001039387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009179154,0.0006701263,0.00035393424,0.0062251114,0.00432645,0.013926043,0.0022018817,0.0031461453,0.005143245],"category_scores_gemma":[0.0045832894,0.00045707318,0.00092490844,0.0053277058,0.0077590267,0.0066065276,0.0056869127,0.0029172504,0.00096024625],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008922301,0.00006359462,0.0014594061,0.00054621155,0.000007462886,0.0007966644,0.0054934225,0.0012220704,0.0003079198,0.9542872,0.011240813,0.024566334],"study_design_scores_gemma":[0.000022204935,0.00015779368,0.009415501,0.0045531495,0.000048563863,0.002008074,0.047062196,0.006581135,0.0011089679,0.26478237,0.66416115,0.00009882653],"about_ca_topic_score_codex":0.038021006,"about_ca_topic_score_gemma":0.0250817,"teacher_disagreement_score":0.038021006,"about_ca_system_score_codex":0.02134111,"about_ca_system_score_gemma":0.050552163,"threshold_uncertainty_score":0.1548413},"labels":[],"label_agreement":null},{"id":"W2782967258","doi":"","title":"Big data analytics: challenges and applications to health care.","year":2017,"lang":"en","type":"article","venue":"Conference of the Centre for Advanced Studies on Collaborative Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Big data; Data science; Computer science; Analytics; Health care; Data mining; Political science","score_opus":0.7539364936114901,"score_gpt":0.6379185107689496,"score_spread":0.1160179828425405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2782967258","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008771545,0.26839888,0.14602076,0.5447509,0.011625668,0.00028410507,0.002251047,0.001117941,0.016779156],"genre_scores_gemma":[0.24568717,0.33069035,0.33498493,0.041322324,0.029189568,0.0006975395,0.004632907,0.00062789966,0.012167342],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9880581,0.006197277,0.0011055913,0.0007857537,0.003385777,0.00046768013],"domain_scores_gemma":[0.87619907,0.103153065,0.0017783602,0.005088306,0.008363356,0.0054178326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04270963,0.0010109661,0.0017807159,0.0037683842,0.0018588789,0.016499499,0.0029209405,0.004321806,0.0052301367],"category_scores_gemma":[0.059869844,0.0012493553,0.0009654316,0.0070285853,0.0068065613,0.020448783,0.006700368,0.007970485,0.0016001444],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019423249,0.0001908985,0.008417927,0.0027819893,0.00031765434,0.00031971218,0.0018640762,0.004193294,0.001479967,0.19268018,0.40047568,0.3870844],"study_design_scores_gemma":[0.000035665194,0.00008192727,0.005165091,0.0026480264,0.000074560776,0.00044490522,0.0065590087,0.024304328,0.0010447614,0.42154738,0.5380055,0.00008891263],"about_ca_topic_score_codex":0.0032285398,"about_ca_topic_score_gemma":0.006337663,"teacher_disagreement_score":0.04270963,"about_ca_system_score_codex":0.0019239134,"about_ca_system_score_gemma":0.0050379895,"threshold_uncertainty_score":0.22587281},"labels":[],"label_agreement":null},{"id":"W2783818711","doi":"10.2196/resprot.8879","title":"Correction for: Opening the Black Box of Electronic Health: Collecting, Analyzing, and Interpreting Log Data","year":2018,"lang":"en","type":"erratum","venue":"JMIR Research Protocols","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Data science; Black box; Health records; Computer science; Electronic health record; Information retrieval; Data mining; World Wide Web; Health care; Political science; Artificial intelligence","score_opus":0.5803280795752249,"score_gpt":0.6833053812800682,"score_spread":0.10297730170484332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783818711","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001311201,0.00054286805,0.00098358,0.08548328,0.90608674,0.00019031271,0.0035858827,0.00076581386,0.0022304943],"genre_scores_gemma":[0.013036677,0.007316513,0.021696389,0.3656701,0.35708195,0.00476102,0.010484249,0.00559911,0.214354],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9629449,0.008621994,0.011576378,0.0025464883,0.012132183,0.0021780087],"domain_scores_gemma":[0.71634454,0.08953952,0.012406186,0.016987506,0.15867852,0.006043767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022258118,0.00272498,0.0034165566,0.007736911,0.0069890767,0.0086883465,0.0050450093,0.010921555,0.13472056],"category_scores_gemma":[0.329967,0.00263542,0.0029278202,0.0059163556,0.0053282008,0.004814786,0.0046036053,0.01984733,0.06765459],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047884667,0.0000106256075,0.00005078664,0.00019740516,0.000011917561,0.000096490876,0.000058536898,0.00001181802,0.000020880732,0.00038743272,0.9957455,0.0033606582],"study_design_scores_gemma":[0.00019902017,0.0000493269,0.0015354087,0.0021128375,0.00008561286,0.0004488457,0.00050101185,0.00022191086,0.00043685985,0.0031940646,0.9910944,0.000120576995],"about_ca_topic_score_codex":0.025756156,"about_ca_topic_score_gemma":0.034100197,"teacher_disagreement_score":0.13472056,"about_ca_system_score_codex":0.008346124,"about_ca_system_score_gemma":0.017395305,"threshold_uncertainty_score":0.4506852},"labels":[],"label_agreement":null},{"id":"W2784109320","doi":"10.1109/glocom.2017.8254451","title":"Performance Assessment of Decision Tree-Based Predictive Classifiers for Risk Pregnancy Care","year":2017,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Decision tree; Computer science; Classifier (UML); Decision tree learning; Statistic; Cohen's kappa; Data mining; Decision support system; Machine learning; Artificial intelligence; Health care; Statistics; Mathematics","score_opus":0.17711224189837033,"score_gpt":0.530289256404475,"score_spread":0.35317701450610467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784109320","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84026927,0.008899133,0.13523114,0.0017213569,0.0008886381,0.00037138036,0.0027794116,0.0014403791,0.00839933],"genre_scores_gemma":[0.9658991,0.001101828,0.02914435,0.00011889725,0.00011884215,0.00013666145,0.0022830502,0.000035109744,0.0011620156],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99710375,0.001173862,0.00033544365,0.00036591874,0.00071152044,0.00030952832],"domain_scores_gemma":[0.98870325,0.008004357,0.0004240461,0.0003842758,0.002151616,0.00033246406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076694335,0.0013902971,0.001530495,0.0029756862,0.0007894472,0.0013869368,0.0010468833,0.0012843651,0.0013613967],"category_scores_gemma":[0.015359427,0.0002515501,0.0012518115,0.0015492397,0.0002440601,0.0012637464,0.00072744733,0.0011952707,0.0007778747],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00447579,0.0012685088,0.10370856,0.0006362545,0.00089583825,0.00038158655,0.0004073462,0.37859836,0.0032686938,0.0022663607,0.009282361,0.49481034],"study_design_scores_gemma":[0.000033831042,0.00046906498,0.007881812,0.00008619736,0.00018056674,0.000107319465,0.0001390349,0.98707193,0.002133631,0.0009848827,0.00088589755,0.000025918214],"about_ca_topic_score_codex":0.011549153,"about_ca_topic_score_gemma":0.0045420113,"teacher_disagreement_score":0.011549153,"about_ca_system_score_codex":0.001225407,"about_ca_system_score_gemma":0.0016583572,"threshold_uncertainty_score":0.040560305},"labels":[],"label_agreement":null},{"id":"W2784952320","doi":"10.1373/clinchem.2017.278853","title":"A Q&amp;A with the Qualcomm Tricorder XPRIZE Winners","year":2018,"lang":"en","type":"article","venue":"Clinical Chemistry","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Oakville-Trafalgar Memorial Hospital","funders":"","keywords":"Competition (biology); Innovator; Frontier; Health care; EPIC; Competitor analysis; Marketing; Medical diagnosis; Cloud computing; Health technology; Business; Medicine; Computer science; Economics; Political science","score_opus":0.4057774283539361,"score_gpt":0.6025777847775058,"score_spread":0.1968003564235697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784952320","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019231346,0.0017277602,0.008226509,0.11580612,0.06997146,0.0017111759,0.0035128065,0.0077411835,0.7893798],"genre_scores_gemma":[0.004070227,0.0008213178,0.0024123427,0.019745601,0.009646533,0.00034926878,0.0017796417,0.0014254441,0.95974964],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9880911,0.00093905925,0.0005192411,0.0013726194,0.0074588577,0.0016191204],"domain_scores_gemma":[0.95857096,0.0021358824,0.0012744017,0.0021710596,0.016595488,0.019252189],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008872718,0.0013595031,0.0010527776,0.0024609717,0.004664124,0.02145242,0.002734343,0.007915349,0.6727754],"category_scores_gemma":[0.028715959,0.0007423162,0.0015385154,0.0016400963,0.0021067555,0.0075125396,0.0062610195,0.0066449204,0.56849784],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029099032,0.000064437234,0.00012909027,0.000032711396,0.000002292405,0.00006869304,0.000019610887,0.00002762289,0.00017962673,0.0022483116,0.9689103,0.028288214],"study_design_scores_gemma":[0.000028846429,0.000053478492,0.0003597452,0.00004741272,0.0000019658944,0.00008332158,0.0000562668,0.00012897114,0.000117838244,0.001149493,0.99795675,0.000015824548],"about_ca_topic_score_codex":0.0040298128,"about_ca_topic_score_gemma":0.006584252,"teacher_disagreement_score":0.6727754,"about_ca_system_score_codex":0.0035242792,"about_ca_system_score_gemma":0.0145641025,"threshold_uncertainty_score":0.46674615},"labels":[],"label_agreement":null},{"id":"W2788244638","doi":"10.5206/wurjhns.2017-18.19","title":"Western Faculty Profile: Dr. Dan Lizotte","year":2017,"lang":"en","type":"article","venue":"Western Undergraduate Research Journal Health and Natural Sciences","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Western University","funders":"","keywords":"Bachelor; Biostatistics; Interview; Pleasure; Medical education; Library science; Health science; Advice (programming); Undergraduate research; Psychology; Sociology; Medicine; Computer science; Political science; Public health; Nursing","score_opus":0.4211628616270388,"score_gpt":0.6118183270629524,"score_spread":0.19065546543591355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788244638","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034617686,0.009898706,0.0012412136,0.6454848,0.11622647,0.00034707252,0.0011684523,0.0016185375,0.22055301],"genre_scores_gemma":[0.005503018,0.004396557,0.0003338376,0.095472544,0.012468582,0.00011287616,0.00027098684,0.00027776338,0.8811638],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993395,0.00006602792,0.000033466073,0.00011187118,0.00032917288,0.00011988698],"domain_scores_gemma":[0.99159735,0.00023879278,0.00017341341,0.00011340865,0.002466536,0.005410597],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00105615,0.00044405853,0.0007069349,0.0008389993,0.0024116002,0.0030255485,0.000914057,0.0028868814,0.35248268],"category_scores_gemma":[0.005412804,0.0003466336,0.00025618466,0.0007411844,0.00060662674,0.0020162726,0.0022294342,0.003018166,0.2015962],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000059475583,0.000011700881,0.000089235036,0.00001501164,4.283884e-7,0.00004138918,0.000029396637,0.0000044502817,0.000040794665,0.00011830225,0.99348783,0.006155653],"study_design_scores_gemma":[0.000007729099,0.000022176437,0.0005869693,0.000062060266,0.0000017579406,0.00021552239,0.0003942479,0.000033335662,0.000075276694,0.00019476119,0.9983973,0.000008814727],"about_ca_topic_score_codex":0.0056947884,"about_ca_topic_score_gemma":0.016887698,"teacher_disagreement_score":0.35248268,"about_ca_system_score_codex":0.0016167222,"about_ca_system_score_gemma":0.0053390483,"threshold_uncertainty_score":0.92360485},"labels":[],"label_agreement":null},{"id":"W2792030527","doi":"10.5539/cis.v11n2p11","title":"Finding Nutritional Deficiency and Disease Pattern of Rural People Using Fuzzy Logic and Big Data Techniques on Hadoop","year":2018,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Fuzzy logic; Computer science; Malnutrition; Habit; Big data; Classifier (UML); Rural area; Calorie; Data mining; Disease; Artificial intelligence; Data science; Machine learning; Medicine; Psychology; Pathology","score_opus":0.27461188807378495,"score_gpt":0.4700055835139864,"score_spread":0.19539369544020146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792030527","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.724214,0.0008025714,0.24334364,0.0032624048,0.00027687382,0.0011448788,0.013891686,0.0072196163,0.005844344],"genre_scores_gemma":[0.8394311,0.00027059848,0.15466218,0.00017482383,0.000033840923,0.00032057107,0.0042837746,0.000043337306,0.0007798139],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99932826,0.00012438973,0.00012616171,0.00013966055,0.00020250573,0.00007909393],"domain_scores_gemma":[0.9986349,0.00050700683,0.00012423328,0.00018161228,0.0003919628,0.00016019784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010893127,0.0005894919,0.0007192903,0.002474435,0.0010496955,0.001304977,0.0008655021,0.00042746597,0.0008883426],"category_scores_gemma":[0.0022970026,0.00030683723,0.001027338,0.0019791035,0.00039689534,0.001304893,0.0009060782,0.000468943,0.00019340155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015136615,0.00156968,0.1280482,0.0012617112,0.00093630806,0.002382656,0.0022595073,0.45128718,0.022914037,0.0056089135,0.016893944,0.36532426],"study_design_scores_gemma":[0.00005823025,0.00017766365,0.019463435,0.000051165905,0.00008650744,0.00026138138,0.00181049,0.95620245,0.0054297405,0.012568826,0.0038315721,0.000058626316],"about_ca_topic_score_codex":0.021396033,"about_ca_topic_score_gemma":0.024050144,"teacher_disagreement_score":0.021396033,"about_ca_system_score_codex":0.0010221769,"about_ca_system_score_gemma":0.0016033768,"threshold_uncertainty_score":0.042542994},"labels":[],"label_agreement":null},{"id":"W2794398035","doi":"10.1093/jcag/gwy008.188","title":"A187 OBSERVATIONAL RETROSPECTIVE ANALYSIS OF PATIENTS IN THE CANADIAN ABBVIECARE (AC) HCV PATIENT SUPPORT PROGRAM","year":2018,"lang":"en","type":"article","venue":"Journal of the Canadian Association of Gastroenterology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"ABB (Canada)","funders":"","keywords":"Medicine; Discontinuation; Internal medicine; Medical prescription; Logistic regression; Observational study; Retrospective cohort study; Epidemiology; Ribavirin; Hepatitis C; Hepatitis C virus; Pediatrics; Virus; Immunology","score_opus":0.06486835491211462,"score_gpt":0.3896123569665626,"score_spread":0.324744002054448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794398035","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99518776,0.00023667111,0.00010104306,0.00006784648,0.0000071011928,0.00017759723,0.003078589,0.0000066764273,0.0011366298],"genre_scores_gemma":[0.9965233,0.00019648255,0.00018598513,0.00017713077,0.00001548404,0.00009322731,0.0025165384,0.000004689004,0.00028707954],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99787843,0.00022016399,0.00015323148,0.00045012266,0.00064821163,0.00064990297],"domain_scores_gemma":[0.9967174,0.00046288705,0.0010331047,0.00022676773,0.0007703194,0.00078952726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010899839,0.0005113639,0.00067731395,0.0019230135,0.0026662215,0.0013484963,0.0012053783,0.0005757103,0.0027283733],"category_scores_gemma":[0.00277913,0.0007239494,0.00054664706,0.005162064,0.001021309,0.0005233934,0.0011489508,0.001079176,0.0004232587],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016228201,0.00012552482,0.9972567,0.000031612675,0.000033889773,0.00015850324,0.00040280377,0.000026634863,0.00010264949,0.00003908263,0.00054015004,0.0011201523],"study_design_scores_gemma":[0.000023535684,0.00018398375,0.9976968,0.000016535372,0.000031245618,0.00021969629,0.0010603712,0.0001693243,0.000035731086,0.000015914276,0.000535976,0.000010922877],"about_ca_topic_score_codex":0.7537608,"about_ca_topic_score_gemma":0.78287154,"teacher_disagreement_score":0.24623919,"about_ca_system_score_codex":0.00964788,"about_ca_system_score_gemma":0.011686052,"threshold_uncertainty_score":0.49537867},"labels":[],"label_agreement":null},{"id":"W2800590228","doi":"","title":"International workshop on Artificial Intelligence in Medical Applications","year":2013,"lang":"en","type":"article","venue":"Federated Conference on Computer Science and Information Systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.13139806587794886,"score_gpt":0.4230634241239552,"score_spread":0.29166535824600637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2800590228","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027991438,0.06256653,0.43393883,0.051536888,0.041793697,0.0006698623,0.0025989662,0.004764828,0.374139],"genre_scores_gemma":[0.1445952,0.031199766,0.23406816,0.0061489865,0.0058761677,0.00038798683,0.0066524292,0.00069925404,0.5703721],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99867,0.0004361765,0.000108071996,0.00018106974,0.00043822743,0.00016650536],"domain_scores_gemma":[0.99782664,0.00042623264,0.00006304019,0.0003988882,0.00096677756,0.0003182884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051938505,0.0006530387,0.00077575207,0.0014851127,0.00079643045,0.003919538,0.001611707,0.0015150959,0.042321574],"category_scores_gemma":[0.0033755056,0.00027865113,0.0009244115,0.0011304908,0.00068035163,0.002683325,0.0022991246,0.0021440408,0.014216999],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023633242,0.00044824477,0.0011975659,0.0004148875,0.000077326426,0.00019558278,0.00023870698,0.001186019,0.005932157,0.038420897,0.23415715,0.71749514],"study_design_scores_gemma":[0.000031968244,0.00016658402,0.0033983837,0.0004196816,0.000081748054,0.0005110679,0.00027451004,0.013585085,0.006407976,0.0265414,0.94855297,0.000028561284],"about_ca_topic_score_codex":0.0019652515,"about_ca_topic_score_gemma":0.0028926493,"teacher_disagreement_score":0.042321574,"about_ca_system_score_codex":0.0009229678,"about_ca_system_score_gemma":0.0028179449,"threshold_uncertainty_score":0.14157975},"labels":[],"label_agreement":null},{"id":"W2801048895","doi":"10.1007/s11548-018-1773-z","title":"IPCAI 2018 Special Issue: Information Processing for Computer-Assisted Interventions, 9th International Conference 2018—Part 1","year":2018,"lang":"en","type":"editorial","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Health informatics; Psychological intervention; Data science; Multimedia; World Wide Web; Medicine; Nursing; Public health","score_opus":0.1316393795347542,"score_gpt":0.4490712929658164,"score_spread":0.3174319134310622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801048895","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029971829,0.013320158,0.00039736088,0.014403177,0.9695143,0.000029902249,0.00006774693,0.00009500513,0.002142419],"genre_scores_gemma":[0.000375161,0.014423443,0.0004210186,0.0070075244,0.964904,0.0000465315,0.00010829086,0.00008801827,0.012625897],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99345535,0.00077209127,0.00081276725,0.0006881604,0.0038500517,0.00042158572],"domain_scores_gemma":[0.9733976,0.007429959,0.0017488009,0.0007954937,0.013477386,0.0031507758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006466954,0.0037172276,0.0054834723,0.008289195,0.0034281895,0.013784335,0.0033828428,0.013017445,0.027727554],"category_scores_gemma":[0.020033175,0.0011604942,0.002972666,0.0039917473,0.0028909622,0.006735719,0.002861659,0.016885078,0.017163327],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035693523,0.000026638007,0.000025392965,0.0005176639,0.000020382253,0.00005592537,0.0000097645825,0.000038830214,0.00009815106,0.00034828784,0.98183286,0.016990487],"study_design_scores_gemma":[0.000043110806,0.000047184014,0.00023883196,0.00067145907,0.00005152597,0.00020336243,0.000027681312,0.0002431155,0.00022124183,0.0016495042,0.99658406,0.000018946452],"about_ca_topic_score_codex":0.0017554264,"about_ca_topic_score_gemma":0.0044159708,"teacher_disagreement_score":0.027727554,"about_ca_system_score_codex":0.0034834046,"about_ca_system_score_gemma":0.0053948513,"threshold_uncertainty_score":0.09275788},"labels":[],"label_agreement":null},{"id":"W2802566692","doi":"10.5539/gjhs.v10n6p114","title":"Prospects of Big Data Analytics in Africa Healthcare System","year":2018,"lang":"en","type":"article","venue":"Global Journal of Health Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Big data; Health care; Data science; Analytics; Healthcare system; Business; The Internet; Computer science; Political science; World Wide Web","score_opus":0.42139605417184095,"score_gpt":0.5290515110681718,"score_spread":0.10765545689633088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2802566692","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053360485,0.25065657,0.02336962,0.5673998,0.004321358,0.00032352578,0.0027269349,0.00029158377,0.097550124],"genre_scores_gemma":[0.5690251,0.33911657,0.044851243,0.023625424,0.0035755918,0.00043118477,0.0019692546,0.00013494928,0.017270636],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985353,0.00072061707,0.000083532315,0.000126058,0.00024485294,0.0002896566],"domain_scores_gemma":[0.9946043,0.0023669733,0.00052303175,0.00019234768,0.0015910297,0.00072231336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003588677,0.0005498496,0.00031420126,0.002315525,0.0014453846,0.0051421328,0.0009693806,0.0019630662,0.0055045313],"category_scores_gemma":[0.0078387335,0.0002790023,0.00057079125,0.0031802969,0.001105456,0.008834001,0.0027365517,0.0017971805,0.0013648578],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030922744,0.00017484569,0.02417585,0.005057285,0.00013653927,0.0028347892,0.003142003,0.004921732,0.002638693,0.3576363,0.14310388,0.4558688],"study_design_scores_gemma":[0.000040884748,0.0001404515,0.010535847,0.0058253324,0.000064172586,0.0011579185,0.009743825,0.009328788,0.0019850445,0.13292246,0.8281616,0.00009358487],"about_ca_topic_score_codex":0.0036487596,"about_ca_topic_score_gemma":0.0023231513,"teacher_disagreement_score":0.0055045313,"about_ca_system_score_codex":0.002290719,"about_ca_system_score_gemma":0.0069973515,"threshold_uncertainty_score":0.018978953},"labels":[],"label_agreement":null},{"id":"W2807783632","doi":"10.2196/resprot.9466","title":"Validating a Machine Learning Algorithm to Predict 30-Day Re-Admissions in Patients With Heart Failure: Protocol for a Prospective Cohort Study","year":2018,"lang":"en","type":"article","venue":"JMIR Research Protocols","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Protocol (science); Prospective cohort study; Computer science; Medicine; Cohort; Cohort study; Machine learning; Artificial intelligence; Algorithm; Alternative medicine; Internal medicine","score_opus":0.33725779352354224,"score_gpt":0.6377325955866979,"score_spread":0.3004748020631557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807783632","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008805437,0.00012919895,0.006825482,0.00022230734,0.00019082225,0.98035324,0.0025642554,0.000082579834,0.00082658784],"genre_scores_gemma":[0.0042967256,0.000055696026,0.004052822,0.000103327446,0.000020536354,0.9905663,0.0007556415,0.000009167545,0.00013964932],"study_design_codex":"randomized_trial","study_design_gemma":"observational","domain_scores_codex":[0.9444998,0.03341338,0.008778009,0.0036774713,0.007534791,0.0020965065],"domain_scores_gemma":[0.92467195,0.015545902,0.010208849,0.019026758,0.027245583,0.0033009327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11723451,0.0030695521,0.003526844,0.0018901206,0.0042320616,0.003185692,0.004758378,0.0047701714,0.0172215],"category_scores_gemma":[0.09233732,0.0022691975,0.005926671,0.002486953,0.0045792884,0.0024779802,0.003635914,0.0071021155,0.0060230596],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.5021942,0.11491634,0.05679035,0.02019748,0.0062406696,0.0025692384,0.0039301156,0.04912145,0.017744672,0.015024211,0.07389325,0.13737807],"study_design_scores_gemma":[0.35524875,0.3007352,0.08524663,0.0129345115,0.003475221,0.001145407,0.0023694371,0.03073579,0.021705447,0.009333634,0.17577763,0.001292403],"about_ca_topic_score_codex":0.0030368895,"about_ca_topic_score_gemma":0.0035646528,"teacher_disagreement_score":0.11723451,"about_ca_system_score_codex":0.005248943,"about_ca_system_score_gemma":0.023537837,"threshold_uncertainty_score":0.62000275},"labels":[],"label_agreement":null},{"id":"W2870292154","doi":"10.1007/978-981-13-0755-3_2","title":"Using Open Clinical Data to Create an Embeddable Prediction System for Hospital Stay","year":2018,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thunder Bay Regional Research Institute; Lakehead University","funders":"","keywords":"Computer science; Bayesian network; Naive Bayes classifier; Tree (set theory); Classifier (UML); Medicine; Medical emergency; Data mining; Data science; Artificial intelligence; Mathematics","score_opus":0.683785439408603,"score_gpt":0.6109856988445617,"score_spread":0.07279974056404137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2870292154","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.112259835,0.0010713355,0.73984087,0.002125426,0.0012905777,0.0003899079,0.026778154,0.09986076,0.016383165],"genre_scores_gemma":[0.44689572,0.0006946587,0.502235,0.0006808825,0.00031833805,0.00026437844,0.027515814,0.0019102998,0.019484982],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99970895,0.00004019514,0.000025888256,0.00010874341,0.000095356045,0.000020920112],"domain_scores_gemma":[0.9986557,0.0007274286,0.000078615565,0.00026177414,0.00022093137,0.000055529505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000609763,0.00050849956,0.00030561423,0.0011198043,0.00020730018,0.0011756008,0.0007878893,0.00052372675,0.0059550535],"category_scores_gemma":[0.0034162595,0.00028451008,0.0004153158,0.001084559,0.00017479733,0.0017294348,0.0010180916,0.00063391734,0.0027163583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000657642,0.00032669457,0.017420957,0.00032596604,0.00016547718,0.00081933633,0.0006380885,0.03149069,0.017780209,0.006004119,0.06379857,0.8605723],"study_design_scores_gemma":[0.000118033204,0.00030133623,0.018384902,0.00017383762,0.00020460019,0.00080061704,0.0003800759,0.7798292,0.056821857,0.032591548,0.11025554,0.0001385238],"about_ca_topic_score_codex":0.003982595,"about_ca_topic_score_gemma":0.0064627733,"teacher_disagreement_score":0.0059550535,"about_ca_system_score_codex":0.0003890225,"about_ca_system_score_gemma":0.00036523765,"threshold_uncertainty_score":0.0199216},"labels":[],"label_agreement":null},{"id":"W2886522935","doi":"10.1111/joim.12822","title":"<scp>eD</scp>octor: machine learning and the future of medicine","year":2018,"lang":"en","type":"review","venue":"Journal of Internal Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":923,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Medicine; Personalized medicine; Field (mathematics); Alternative medicine; Precision medicine; MEDLINE; Artificial intelligence; Health care; Data science; Medical education; Bioinformatics; Computer science; Pathology","score_opus":0.14147224027197783,"score_gpt":0.5221836019344029,"score_spread":0.38071136166242514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886522935","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034967624,0.86480826,0.0011999133,0.03942534,0.019084252,0.00007511835,0.00092708063,0.00022842486,0.07390189],"genre_scores_gemma":[0.0038349645,0.91078156,0.0011355035,0.019338606,0.018205458,0.00008123898,0.0011943423,0.00008825845,0.04534008],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99938655,0.00011004138,0.00005623999,0.000067879664,0.00031979752,0.00005953386],"domain_scores_gemma":[0.9971733,0.0010717248,0.00027611296,0.000113951464,0.00104227,0.00032254134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082650216,0.00059147127,0.00087146903,0.0032741947,0.00072767027,0.0026551308,0.0013505046,0.002331423,0.07911279],"category_scores_gemma":[0.0040912176,0.00019406248,0.00071179826,0.0040894058,0.00078444125,0.002369474,0.0014902317,0.0035445914,0.03571264],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036715766,0.00002398656,0.00016293027,0.0056337416,0.00003841656,0.00015549526,0.000086323744,0.00012378048,0.00031049928,0.010644759,0.6083223,0.37446102],"study_design_scores_gemma":[0.0000054337183,0.000010090357,0.00048410075,0.003647007,0.000016514896,0.00035008328,0.000044755518,0.000050056067,0.00009428575,0.003587026,0.9917013,0.000009306237],"about_ca_topic_score_codex":0.0024893356,"about_ca_topic_score_gemma":0.0050724777,"teacher_disagreement_score":0.07911279,"about_ca_system_score_codex":0.0011726627,"about_ca_system_score_gemma":0.002748606,"threshold_uncertainty_score":0.2646587},"labels":[],"label_agreement":null},{"id":"W2887581276","doi":"10.11159/icbes18.156","title":"Monitoring System for Glycemic Control in Patients with Type 2 Diabetes Mellitus, Based on Mobile Technology, Telemetry, and Health Education","year":2018,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Glycemic; Telemetry; Type 2 Diabetes Mellitus; Diabetes mellitus; Medicine; Computer science; Endocrinology; Telecommunications","score_opus":0.016028352324070568,"score_gpt":0.31529393519887217,"score_spread":0.2992655828748016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887581276","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.767395,0.017282143,0.07883754,0.0054554455,0.0021939408,0.003518,0.035093356,0.030812072,0.059412584],"genre_scores_gemma":[0.94390005,0.0028431213,0.034060184,0.0017326993,0.0006191005,0.0012234261,0.00736083,0.00018920505,0.00807146],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9992576,0.00014242582,0.000117871394,0.00020250396,0.00022914626,0.0000502787],"domain_scores_gemma":[0.9991517,0.00021380073,0.00017429383,0.00005787445,0.00031008033,0.00009228162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079954095,0.000747349,0.0008176472,0.0019277089,0.0005309524,0.0011518027,0.0005104294,0.00061059115,0.004599335],"category_scores_gemma":[0.0023432416,0.00014058223,0.00037095323,0.0011005806,0.000097154305,0.00053104653,0.00059548905,0.0006186671,0.0020914695],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00372771,0.0016785474,0.35526952,0.0009605986,0.00046422397,0.0013677215,0.0010177827,0.0013879251,0.019250555,0.00086639536,0.06756219,0.5464468],"study_design_scores_gemma":[0.0010447545,0.003131769,0.79192483,0.00084624684,0.0013885212,0.0051531177,0.0010721164,0.0756921,0.042597886,0.0018836716,0.07490974,0.0003552116],"about_ca_topic_score_codex":0.0031669769,"about_ca_topic_score_gemma":0.0032821046,"teacher_disagreement_score":0.004599335,"about_ca_system_score_codex":0.0003949271,"about_ca_system_score_gemma":0.0006061303,"threshold_uncertainty_score":0.015386283},"labels":[],"label_agreement":null},{"id":"W2889261985","doi":"10.1093/eurheartj/ehy566.6152","title":"6152A novel model for prediction of ischemic stroke in patients without atrial fibrillation","year":2018,"lang":"en","type":"article","venue":"European Heart Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Medicine; Atrial fibrillation; Cardiology; Ischemic stroke; Internal medicine; Stroke (engine); Ischemia","score_opus":0.24528244022613183,"score_gpt":0.4576297053959338,"score_spread":0.21234726516980196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889261985","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82734954,0.0014575243,0.15174639,0.0038589938,0.00064176985,0.00034278486,0.0070465645,0.0015955465,0.005960817],"genre_scores_gemma":[0.9773812,0.00024409013,0.013663068,0.0001993513,0.00017415229,0.00032988907,0.004021883,0.00003527781,0.0039510257],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905294,0.0003407686,0.00006393218,0.00030297978,0.00009666534,0.00014266442],"domain_scores_gemma":[0.99697065,0.0020656604,0.00024505213,0.00011255322,0.00045360465,0.00015242108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032288178,0.0010946696,0.0014735914,0.0013059549,0.00054237334,0.0015452588,0.0013635098,0.001370999,0.007615742],"category_scores_gemma":[0.0056155375,0.0004166315,0.001397142,0.0005969626,0.00032721908,0.0006389594,0.00077988574,0.0014516292,0.0017728396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028315154,0.0019324586,0.24679574,0.00017325148,0.0011465359,0.00082945067,0.00019788695,0.6147254,0.0011731768,0.0033641134,0.013821974,0.11300859],"study_design_scores_gemma":[0.000089038054,0.00012129297,0.007476949,0.000021501639,0.000060354676,0.00006557564,0.000011595316,0.9907541,0.000055674875,0.0010436577,0.00028982182,0.000010366404],"about_ca_topic_score_codex":0.014143834,"about_ca_topic_score_gemma":0.0067678755,"teacher_disagreement_score":0.014143834,"about_ca_system_score_codex":0.0008473477,"about_ca_system_score_gemma":0.0015192919,"threshold_uncertainty_score":0.028123021},"labels":[],"label_agreement":null},{"id":"W2889321397","doi":"10.1093/eurheartj/ehy563.4348","title":"4348Cluster analysis of cardiovascular risk phenotypes in patients with type 2 diabetes and established atherosclerotic cardiovascular disease: a potential approach to precision medicine","year":2018,"lang":"en","type":"article","venue":"European Heart Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian VIGOUR Centre","funders":"","keywords":"Medicine; Atherosclerotic cardiovascular disease; Disease; Type 2 diabetes; Diabetes mellitus; Internal medicine; Phenotype; Cardiology; Endocrinology; Genetics","score_opus":0.05811392888851367,"score_gpt":0.3377155400031247,"score_spread":0.279601611114611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889321397","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73761237,0.0052847206,0.24296322,0.0033478353,0.00028464603,0.00032573217,0.0051647103,0.0010118422,0.004004955],"genre_scores_gemma":[0.9400452,0.0003369644,0.05642873,0.00032231826,0.0001525819,0.00012891753,0.0021413695,0.000055313696,0.0003885819],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968477,0.0018428969,0.00022516081,0.00068427273,0.0002875194,0.00011230712],"domain_scores_gemma":[0.9910535,0.004682499,0.0016710107,0.0017203196,0.00062760146,0.00024502855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006343696,0.00068204256,0.001543844,0.0025354947,0.0006108572,0.0021427271,0.00097023905,0.00068771583,0.0016784118],"category_scores_gemma":[0.014090628,0.00034845492,0.001519399,0.0023537155,0.0006474933,0.00062854163,0.0012172125,0.0011274714,0.000326344],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017180817,0.00031691123,0.83386827,0.0002967164,0.0029606698,0.00021037804,0.0005093337,0.025753697,0.004199419,0.00454609,0.003992316,0.12162811],"study_design_scores_gemma":[0.00045696768,0.00080000714,0.6206952,0.00021634005,0.0013292896,0.00054781424,0.0005938865,0.29832166,0.003104387,0.06513756,0.008647542,0.00014950258],"about_ca_topic_score_codex":0.0035441099,"about_ca_topic_score_gemma":0.0034809704,"teacher_disagreement_score":0.006343696,"about_ca_system_score_codex":0.0007447099,"about_ca_system_score_gemma":0.0010830857,"threshold_uncertainty_score":0.03354907},"labels":[],"label_agreement":null},{"id":"W2892370045","doi":"10.1038/s41746-018-0058-9","title":"Health intelligence: how artificial intelligence transforms population and personalized health","year":2018,"lang":"en","type":"editorial","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":256,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Health care; Data science; Analytics; Clinical decision support system; Big data; Computer science; Geocoding; Artificial intelligence; Visualization; Decision support system; Knowledge management; Data mining","score_opus":0.1329808311194993,"score_gpt":0.48456641142171236,"score_spread":0.3515855803022131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2892370045","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011996227,0.08076071,0.0070278402,0.18707876,0.71754736,0.00003132998,0.00018915544,0.00026209617,0.006982835],"genre_scores_gemma":[0.0043200864,0.06902225,0.0034307032,0.05340561,0.8546732,0.00008357699,0.00009538641,0.00017330558,0.014795896],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99677914,0.0011855939,0.00029001405,0.00043423648,0.0011954989,0.00011547179],"domain_scores_gemma":[0.98282087,0.013665951,0.00034790643,0.0004962834,0.0021633443,0.0005056983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005648362,0.001586687,0.0013986789,0.0024303233,0.0014749231,0.00822623,0.0034461417,0.01263112,0.0073538865],"category_scores_gemma":[0.024779502,0.0006046909,0.0016021255,0.0012443276,0.007016269,0.005895192,0.0022255576,0.016622359,0.00397974],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003136187,0.00001393135,0.00010167614,0.0007424794,0.0000754002,0.0001599134,0.00016993286,0.00036545732,0.00009056856,0.045658845,0.8962806,0.056309856],"study_design_scores_gemma":[0.000022737555,0.0000161702,0.00014169063,0.0005595366,0.000040464125,0.00018529246,0.00006635024,0.0006567165,0.00010712549,0.045771148,0.9524061,0.000026735566],"about_ca_topic_score_codex":0.0020070032,"about_ca_topic_score_gemma":0.0028367888,"teacher_disagreement_score":0.01263112,"about_ca_system_score_codex":0.0022564428,"about_ca_system_score_gemma":0.002169762,"threshold_uncertainty_score":0.029871762},"labels":[],"label_agreement":null},{"id":"W2896454345","doi":"10.1109/innovate-data.2018.00013","title":"Application of Data Mining Techniques to Predict the Length of Stay of Hospitalized Patients with Diabetes","year":2018,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Diabetes mellitus; Computer science; Scheduling (production processes); Machine learning; Artificial intelligence; Health care; Ensemble learning; Field (mathematics); Medicine; Mathematical optimization; Mathematics","score_opus":0.1063093475163977,"score_gpt":0.4561719970376963,"score_spread":0.3498626495212986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896454345","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91136694,0.0010932912,0.08258718,0.0009895429,0.00015758965,0.000080210215,0.0017759702,0.00047255144,0.001476686],"genre_scores_gemma":[0.97689146,0.00026243107,0.021525977,0.0000641821,0.000047797723,0.00003427867,0.0009821363,0.000008131151,0.00018365266],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994998,0.00015096326,0.00008234245,0.00009741902,0.000109995715,0.000059528797],"domain_scores_gemma":[0.9972915,0.0015070726,0.00036237945,0.00014933,0.000552036,0.00013769144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010713608,0.0006436945,0.0006977288,0.002136206,0.00027645956,0.0006659298,0.000526996,0.0006202727,0.00038161667],"category_scores_gemma":[0.005316924,0.00019414687,0.00088715047,0.0012423149,0.000079100166,0.00050832826,0.00040045375,0.000868578,0.00013564956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058016565,0.00085946167,0.53685457,0.000113901435,0.00076784805,0.00041246132,0.00017637834,0.20766333,0.0023196847,0.0004827347,0.0032076451,0.24656177],"study_design_scores_gemma":[0.000009663988,0.00014294434,0.044694632,0.000028106206,0.000095632065,0.00013199038,0.00012370954,0.9520922,0.0012950519,0.0008339269,0.0005318566,0.000020247558],"about_ca_topic_score_codex":0.007564941,"about_ca_topic_score_gemma":0.007171777,"teacher_disagreement_score":0.007564941,"about_ca_system_score_codex":0.00044739284,"about_ca_system_score_gemma":0.0007063103,"threshold_uncertainty_score":0.015041828},"labels":[],"label_agreement":null},{"id":"W2896846189","doi":"10.1016/j.jdiacomp.2018.10.010","title":"Prognostic tools for cardiovascular disease in patients with type 2 diabetes: A systematic review and meta-analysis of C-statistics","year":2018,"lang":"en","type":"review","venue":"Journal of Diabetes and its Complications","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":59,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Medicine; Meta-analysis; Diabetes mellitus; Statistic; Disease; Population; Statistics; Predictive modelling; Risk assessment; Type 2 diabetes; Internal medicine; Computer science; Environmental health","score_opus":0.2864020857111843,"score_gpt":0.45715163226711797,"score_spread":0.17074954655593366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896846189","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006412588,0.9923388,0.0005213368,0.00011202561,0.00011120556,0.00006999814,0.00030155928,0.000021881224,0.00011059257],"genre_scores_gemma":[0.35351065,0.6374412,0.0055614747,0.0013606845,0.00046341468,0.00036423528,0.0010143636,0.000044756438,0.00023913413],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.98715657,0.005749182,0.003464062,0.0018056252,0.0014348029,0.00038965384],"domain_scores_gemma":[0.9685593,0.024242803,0.004576199,0.0011319701,0.0012005437,0.00028914347],"candidate_categories":["metaepi_broad"],"consensus_categories":[],"category_scores_codex":[0.0119511215,0.0028106503,0.015225597,0.00545495,0.0006534387,0.0026674897,0.0028475404,0.0025884656,0.002863611],"category_scores_gemma":[0.037828505,0.0016166336,0.035830006,0.0068561174,0.0009329066,0.002373981,0.002089827,0.0026491813,0.0002076244],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021495358,0.000051654377,0.018334586,0.15551998,0.7997894,0.00008746434,0.00011495699,0.0004613291,0.00015667896,0.0001435427,0.0006657234,0.022525111],"study_design_scores_gemma":[0.00079740485,0.00020477566,0.009726209,0.01082801,0.97659904,0.00009649652,0.00006896217,0.00026079742,0.000079268306,0.0002659749,0.0010238563,0.00004927785],"about_ca_topic_score_codex":0.0064105936,"about_ca_topic_score_gemma":0.018429842,"teacher_disagreement_score":0.9847744,"about_ca_system_score_codex":0.0013916516,"about_ca_system_score_gemma":0.0029094643,"threshold_uncertainty_score":0.06320429},"labels":[],"label_agreement":null},{"id":"W2896927272","doi":"10.2196/10212","title":"Prediction of Glucose Metabolism Disorder Risk Using a Machine Learning Algorithm: Pilot Study","year":2018,"lang":"en","type":"article","venue":"JMIR Diabetes","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Machine learning; Computer science; Artificial intelligence; Algorithm","score_opus":0.13948922105321357,"score_gpt":0.43684388561490384,"score_spread":0.29735466456169024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896927272","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9945205,0.00008900839,0.004661525,0.000080956386,0.0000150599835,0.00022428088,0.00012897386,0.00007299835,0.00020681141],"genre_scores_gemma":[0.9883051,0.00009825862,0.010643935,0.000046685418,0.000030984094,0.0002324676,0.0003744647,0.00000868854,0.0002593764],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989586,0.00070551404,0.000052299933,0.00013521282,0.00007204462,0.000076362616],"domain_scores_gemma":[0.9914916,0.0061611705,0.00026368306,0.00064698205,0.0010569858,0.00037953563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004800408,0.000860314,0.00081320107,0.00054005865,0.00025949575,0.00036099777,0.0005802446,0.0006963056,0.0013302459],"category_scores_gemma":[0.00853963,0.00025119542,0.0008015033,0.00036926247,0.00032002234,0.0006410225,0.00038640862,0.00085419865,0.0004008273],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.021464968,0.040258035,0.6122223,0.00032718552,0.001082845,0.0008911077,0.00063515676,0.0824677,0.0071344865,0.0003879136,0.0026450003,0.23048325],"study_design_scores_gemma":[0.0026895793,0.05428022,0.21642467,0.000038911778,0.00037165784,0.00045902326,0.0002825201,0.72096735,0.0032444252,0.00045162326,0.00072192185,0.0000680596],"about_ca_topic_score_codex":0.0030339686,"about_ca_topic_score_gemma":0.0012347902,"teacher_disagreement_score":0.004800408,"about_ca_system_score_codex":0.00032592393,"about_ca_system_score_gemma":0.000550156,"threshold_uncertainty_score":0.025387287},"labels":[],"label_agreement":null},{"id":"W2901863036","doi":"10.2196/12577","title":"Medication Use for Childhood Pneumonia at a Children’s Hospital in Shanghai, China: Analysis of Pattern Mining Algorithms","year":2018,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China; Shanghai Science and Technology Development Foundation","keywords":"Pneumonia; Data mining; Computer science; Medicine; Medical record; Data science; Medical emergency; Algorithm","score_opus":0.049606703899535434,"score_gpt":0.4224179444331129,"score_spread":0.3728112405335775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901863036","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.997323,0.00028377667,0.000986997,0.00014634608,0.0000072172406,0.000037302823,0.0009743535,0.000022752667,0.00021822518],"genre_scores_gemma":[0.99442863,0.00021881986,0.0026663842,0.00003052078,0.000008458584,0.00003869936,0.0024995352,0.0000039944625,0.000105000625],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874085,0.00031844512,0.00024477165,0.000251195,0.00028881387,0.00015593036],"domain_scores_gemma":[0.9955603,0.0023344448,0.00092908373,0.00017685904,0.0007712684,0.00022810994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022849631,0.00051894144,0.0005226633,0.0040949867,0.0003383542,0.00083507237,0.0004487487,0.00035982064,0.00050118193],"category_scores_gemma":[0.005764678,0.00017128239,0.0010762218,0.0032826678,0.00025184025,0.0004970967,0.000408012,0.00037098414,0.00011546218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008337437,0.00005656374,0.9847757,0.000061646955,0.00013977822,0.0001718262,0.000080317644,0.0031258503,0.00021195174,0.000075579344,0.00040894764,0.010808446],"study_design_scores_gemma":[0.000017964901,0.00012514718,0.92995656,0.00002811517,0.00010356136,0.00035934258,0.0003137331,0.068207815,0.000330056,0.00018106813,0.00036415271,0.000012508245],"about_ca_topic_score_codex":0.024226004,"about_ca_topic_score_gemma":0.018810792,"teacher_disagreement_score":0.024226004,"about_ca_system_score_codex":0.0013086979,"about_ca_system_score_gemma":0.0018538091,"threshold_uncertainty_score":0.04816997},"labels":[],"label_agreement":null},{"id":"W2904290041","doi":"10.1016/j.cogsys.2018.12.001","title":"A novel machine learning approach for early detection of hepatocellular carcinoma patients","year":2018,"lang":"en","type":"article","venue":"Cognitive Systems Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":126,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Feature selection; Support vector machine; Hepatocellular carcinoma; Preprocessor; Normalization (sociology); Artificial intelligence; Machine learning; Computer science; Liver cancer; Data pre-processing; Selection (genetic algorithm); Feature (linguistics); Genetic algorithm; Medicine; Internal medicine","score_opus":0.3858015286476613,"score_gpt":0.5059562624752874,"score_spread":0.12015473382762604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904290041","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25729132,0.0023341011,0.7274315,0.001974197,0.00035901368,0.00044470953,0.0008058093,0.0019199444,0.0074395183],"genre_scores_gemma":[0.8704461,0.0005053374,0.12362872,0.00025127231,0.00014336713,0.00025989118,0.0006902731,0.000023715536,0.004051329],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99958307,0.00009546312,0.000033221782,0.00012182888,0.00011238816,0.000053985863],"domain_scores_gemma":[0.9996171,0.00012980418,0.00003571137,0.000016685626,0.00018092731,0.000019684207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070032256,0.000473021,0.00062453037,0.0011623772,0.00033943183,0.0006560864,0.00079511973,0.0007153538,0.001093881],"category_scores_gemma":[0.0013712327,0.00015520997,0.0006542653,0.0006856276,0.00016684309,0.0005868585,0.00036890162,0.0005957743,0.00047563165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004290772,0.0009281649,0.053863265,0.0002000122,0.00032039086,0.0005443064,0.00019964822,0.14181085,0.011266461,0.003711198,0.008189039,0.7785377],"study_design_scores_gemma":[0.00001810035,0.0001596704,0.0076062735,0.000019533145,0.00006148784,0.00022702181,0.000035332534,0.9862099,0.0024136452,0.0015266982,0.0017028552,0.000019498695],"about_ca_topic_score_codex":0.004420785,"about_ca_topic_score_gemma":0.0037203864,"teacher_disagreement_score":0.004420785,"about_ca_system_score_codex":0.00059184403,"about_ca_system_score_gemma":0.00091042253,"threshold_uncertainty_score":0.008790135},"labels":[],"label_agreement":null},{"id":"W2906027675","doi":"10.1109/access.2018.2884249","title":"Metabolic Syndrome and Development of Diabetes Mellitus: Predictive Modeling Based on Machine Learning Techniques","year":2018,"lang":"en","type":"article","venue":"IEEE Access","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Logistic regression; Diabetes mellitus; Naive Bayes classifier; Decision tree; Machine learning; Metabolic syndrome; Random forest; C4.5 algorithm; Artificial intelligence; Medicine; Oversampling; Computer science; Bayes' theorem; Sampling (signal processing); Statistics; Internal medicine; Mathematics; Endocrinology; Support vector machine; Bayesian probability; Filter (signal processing)","score_opus":0.14694016180176755,"score_gpt":0.4541550147678001,"score_spread":0.30721485296603257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906027675","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20587999,0.0029698098,0.7867983,0.001609676,0.00013052857,0.00015107986,0.00037753777,0.0003394726,0.0017436796],"genre_scores_gemma":[0.89149624,0.0019425955,0.10503993,0.00012724492,0.00017571876,0.00014218078,0.0004111339,0.000015361251,0.00064955803],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998869,0.00069581723,0.00005919637,0.00012833951,0.00019919779,0.00004843526],"domain_scores_gemma":[0.9962882,0.0031503162,0.0002035861,0.0001299925,0.0001872492,0.000040688024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002832865,0.0005168045,0.0006515498,0.0015195336,0.0002877429,0.0010006402,0.00056682545,0.0005537793,0.0004268867],"category_scores_gemma":[0.008742908,0.00020647405,0.00070779107,0.0012444811,0.00026201265,0.0007775456,0.0005370964,0.0009949176,0.00014122108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023298872,0.00039149323,0.07974239,0.00019763013,0.00036720152,0.00024633566,0.00019694472,0.698935,0.001127245,0.010786418,0.001408834,0.20636757],"study_design_scores_gemma":[0.0000049285386,0.00004399181,0.0034042841,0.00002695785,0.000022955588,0.00004032583,0.000022104678,0.9914996,0.0001591596,0.0044887504,0.00027902814,0.000007957486],"about_ca_topic_score_codex":0.0050247028,"about_ca_topic_score_gemma":0.0038206398,"teacher_disagreement_score":0.0050247028,"about_ca_system_score_codex":0.00046373362,"about_ca_system_score_gemma":0.00072402804,"threshold_uncertainty_score":0.014981747},"labels":[],"label_agreement":null},{"id":"W2906811739","doi":"10.1136/bmj.k5357","title":"What’s holding up the big data revolution in healthcare?","year":2018,"lang":"en","type":"editorial","venue":"BMJ","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Vector Institute","funders":"","keywords":"Big data; Health care; Internet privacy; Data science; Business; Computer science; Political science; Law; Data mining","score_opus":0.4293378091917153,"score_gpt":0.5615388281352214,"score_spread":0.13220101894350605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906811739","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020498423,0.015879711,0.000081185644,0.100433566,0.8827819,0.00001494109,0.00004438448,0.000038027578,0.0007057029],"genre_scores_gemma":[0.00031394756,0.010342974,0.00013412499,0.05919062,0.92732275,0.000028349736,0.000024670078,0.00004115377,0.0026014773],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.968246,0.0071433405,0.0037018221,0.0019609532,0.017525312,0.001422592],"domain_scores_gemma":[0.84708625,0.08740201,0.007062734,0.003434259,0.039080083,0.015934566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03381863,0.0041236533,0.006225194,0.0084987655,0.007363664,0.021728354,0.0059578484,0.04097016,0.014540265],"category_scores_gemma":[0.13309702,0.001765715,0.004440927,0.004981218,0.00893377,0.014122236,0.003368847,0.040948868,0.008539274],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003325525,0.000015475869,0.000025196736,0.0007558541,0.00004813747,0.000056872275,0.00004248717,0.000017038756,0.000025450507,0.0006987655,0.992847,0.0054343683],"study_design_scores_gemma":[0.00014869137,0.000043022053,0.00027505256,0.0029351981,0.00016622497,0.00013502542,0.00023250094,0.000110862835,0.00008034075,0.005500291,0.99032354,0.0000492524],"about_ca_topic_score_codex":0.0053819735,"about_ca_topic_score_gemma":0.012496311,"teacher_disagreement_score":0.04097016,"about_ca_system_score_codex":0.006852602,"about_ca_system_score_gemma":0.016441451,"threshold_uncertainty_score":0.17885214},"labels":[],"label_agreement":null},{"id":"W2907723909","doi":"10.1186/s12874-018-0644-1","title":"Machine learning methodologies versus cardiovascular risk scores, in predicting disease risk","year":2018,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":113,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"Horizon 2020; Hellenic Cardiological Society; European Commission; World Health Organization","keywords":"Random forest; Machine learning; Bootstrapping (finance); Artificial intelligence; Decision tree; Predictive value; Predictive modelling; Computer science; Medicine; Statistics; Econometrics; Internal medicine; Mathematics","score_opus":0.8049045884280996,"score_gpt":0.6719449449497101,"score_spread":0.1329596434783895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907723909","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53419816,0.12340928,0.31822252,0.0073806844,0.0015707446,0.00079341617,0.001928738,0.00044263032,0.01205371],"genre_scores_gemma":[0.8817291,0.010780733,0.10480419,0.00070460694,0.00062519324,0.00030148702,0.00039501503,0.00003624998,0.0006233179],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98395765,0.012489387,0.0009004789,0.00084326963,0.0016293256,0.00017980694],"domain_scores_gemma":[0.94556814,0.04715717,0.0038561183,0.001215894,0.0019177138,0.00028486334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029918188,0.0009464045,0.0010464146,0.0025942074,0.00023678307,0.0020628308,0.00057226175,0.0011285342,0.0010523665],"category_scores_gemma":[0.042943776,0.00017773327,0.0009366919,0.0022527312,0.0006811117,0.0014152298,0.0008112562,0.0011877844,0.00041248364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003229879,0.00039199548,0.27482623,0.003716754,0.0028914344,0.00025711858,0.00048271473,0.041242927,0.0024164724,0.0077154413,0.0027493336,0.66007966],"study_design_scores_gemma":[0.0010785667,0.016157208,0.38059142,0.008302463,0.0037491363,0.0029559673,0.0018587788,0.4431834,0.013769703,0.094312645,0.03357819,0.00046262392],"about_ca_topic_score_codex":0.0006509592,"about_ca_topic_score_gemma":0.0007532042,"teacher_disagreement_score":0.029918188,"about_ca_system_score_codex":0.0005322724,"about_ca_system_score_gemma":0.00079695164,"threshold_uncertainty_score":0.1582244},"labels":[],"label_agreement":null},{"id":"W2912710021","doi":"10.1145/2896338","title":"Proceedings of the 6th International Conference on Digital Health Conference","year":2016,"lang":"en","type":"paratext","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Digital health; eHealth; Health informatics; Public health; Library science; Analytics; Public health informatics; Political science; Computer science; Public relations; Health care; International health; Data science; Medicine; Health promotion","score_opus":0.2725396194562867,"score_gpt":0.5069295026614679,"score_spread":0.23438988320518117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912710021","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005628611,0.0775359,0.01834706,0.074515104,0.15810324,0.0006912668,0.008410077,0.0049828435,0.65178597],"genre_scores_gemma":[0.029483508,0.037893433,0.009514788,0.013480735,0.025308937,0.00040114837,0.015668074,0.0009772287,0.8672722],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99743253,0.00059950503,0.0001838419,0.0004569146,0.0009709916,0.00035621555],"domain_scores_gemma":[0.99427384,0.00096017367,0.00016719021,0.0006173759,0.002135791,0.0018456065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003072313,0.0009784522,0.0010644357,0.0019147951,0.0014955179,0.008721821,0.0015962351,0.0024757632,0.29025006],"category_scores_gemma":[0.0063056583,0.00029101138,0.0007954263,0.0016942703,0.00085200387,0.005624254,0.003629904,0.0031683363,0.16744334],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007441494,0.00006568305,0.000456423,0.0003130534,0.00001622571,0.00009014854,0.0001596659,0.00006286868,0.0005962343,0.0044867257,0.8652075,0.128471],"study_design_scores_gemma":[0.0000049363643,0.000016757578,0.00045214343,0.00012498572,0.0000072480398,0.000074097996,0.00014498293,0.00012601717,0.00015466401,0.00088151667,0.9980034,0.000009307874],"about_ca_topic_score_codex":0.0018264019,"about_ca_topic_score_gemma":0.00284313,"teacher_disagreement_score":0.29025006,"about_ca_system_score_codex":0.001271774,"about_ca_system_score_gemma":0.0023141373,"threshold_uncertainty_score":0.9709832},"labels":[],"label_agreement":null},{"id":"W2913699606","doi":"10.1007/978-3-030-04506-7_4","title":"Healthcare Analytics Applications","year":2019,"lang":"en","type":"book-chapter","venue":"SpringerBriefs in health care management and economics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Health care; Analytics; Data science; Computer science; Political science","score_opus":0.07924098111654782,"score_gpt":0.38539991241309846,"score_spread":0.30615893129655064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913699606","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021069997,0.013020735,0.08672559,0.011647471,0.0042650863,0.000466395,0.0065017245,0.0115603525,0.86370564],"genre_scores_gemma":[0.03828523,0.018992595,0.06483189,0.007928686,0.0038506764,0.00052162417,0.019177543,0.0018719108,0.8445398],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99902713,0.00021195396,0.00006623978,0.00014266891,0.00048643595,0.00006571547],"domain_scores_gemma":[0.998953,0.00034045434,0.000037417452,0.0002315213,0.0003419057,0.00009572905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011684379,0.0012114818,0.00058531924,0.0022414322,0.0007084399,0.004849143,0.00132808,0.0012678596,0.1642236],"category_scores_gemma":[0.0035691506,0.00041970692,0.000678386,0.0028226704,0.00035185515,0.0026272573,0.0029526604,0.001241565,0.10888227],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033056687,0.000052667743,0.00029990377,0.00032375898,0.000020338694,0.00009650878,0.00011474875,0.00050715107,0.0010090704,0.02945911,0.55682904,0.41125458],"study_design_scores_gemma":[0.0000083654695,0.000013016635,0.00031871698,0.00014605446,0.000009200894,0.0001509807,0.000067461864,0.0020566212,0.0006342783,0.021248473,0.97533876,0.000008152783],"about_ca_topic_score_codex":0.001047174,"about_ca_topic_score_gemma":0.0013183911,"teacher_disagreement_score":0.1642236,"about_ca_system_score_codex":0.0005339839,"about_ca_system_score_gemma":0.0009386788,"threshold_uncertainty_score":0.5493827},"labels":[],"label_agreement":null},{"id":"W2916599650","doi":"10.1109/isspit.2018.8642650","title":"A Comparative Analysis of Unsupervised Machine Techniques for Liver Disease Prediction","year":2018,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Silhouette; Field (mathematics); Unsupervised learning; Computational complexity theory; Computational intelligence; Set (abstract data type); Data set; Data mining; Pattern recognition (psychology); Algorithm; Mathematics","score_opus":0.23549331482326918,"score_gpt":0.5256213340002522,"score_spread":0.29012801917698305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2916599650","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5056045,0.011368565,0.46920803,0.0008017635,0.00020165107,0.0002221901,0.0008982631,0.0014754299,0.010219533],"genre_scores_gemma":[0.7798864,0.0035507793,0.21287246,0.00008653507,0.00014351665,0.00013235427,0.0013530772,0.00009239817,0.001882441],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976568,0.00083290384,0.00016258248,0.0002385356,0.0010174128,0.0000917326],"domain_scores_gemma":[0.984294,0.010968216,0.0006257886,0.00080098293,0.0031882226,0.0001228441],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025280397,0.00051333394,0.0006286219,0.0033218046,0.00038021768,0.000617048,0.0005032557,0.0005768709,0.00072504993],"category_scores_gemma":[0.010880285,0.00012961018,0.0007722144,0.002532418,0.00021562682,0.00087757537,0.00040992527,0.00045937244,0.00024119252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077291206,0.00040343887,0.040594827,0.00057942676,0.00048021783,0.0001519051,0.00029099267,0.13078411,0.007328327,0.0052566035,0.0032769458,0.81008035],"study_design_scores_gemma":[0.000026347612,0.0007598971,0.049809504,0.00008109802,0.00015818793,0.00032138117,0.00023277478,0.93314254,0.008243982,0.00375028,0.0034213574,0.000052654257],"about_ca_topic_score_codex":0.00401092,"about_ca_topic_score_gemma":0.0047754194,"teacher_disagreement_score":0.00401092,"about_ca_system_score_codex":0.00051259494,"about_ca_system_score_gemma":0.0007773075,"threshold_uncertainty_score":0.013369739},"labels":[],"label_agreement":null},{"id":"W2917067128","doi":"10.1007/978-3-030-06109-8_5","title":"Big Data Challenges from a Healthcare Administration Perspective","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in bioengineering","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Health care; Public relations; Big data; Corporate governance; Competence (human resources); Business; Administration (probate law); Service delivery framework; Nexus (standard); Public administration; Service (business); Political science; Management; Engineering; Marketing; Computer science","score_opus":0.2789616718755794,"score_gpt":0.4337358722839842,"score_spread":0.15477420040840478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2917067128","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016503138,0.07947613,0.07634232,0.7965415,0.009408009,0.00006463514,0.0006751941,0.00028081393,0.03556108],"genre_scores_gemma":[0.1768801,0.24034594,0.20066954,0.2282335,0.092953384,0.00059098087,0.0017658275,0.00066147716,0.05789925],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99470794,0.0024843705,0.00030779996,0.00043579965,0.0018012819,0.00026275025],"domain_scores_gemma":[0.96238226,0.030234616,0.00062794285,0.001605751,0.0031592736,0.001990193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014984053,0.00081840175,0.0013836827,0.0022262735,0.00166751,0.012447648,0.0028662346,0.0054479907,0.007446392],"category_scores_gemma":[0.019207008,0.0008758511,0.00074971037,0.003998373,0.0065797213,0.023047091,0.0053644152,0.013640299,0.002188488],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038256094,0.00006357815,0.0005410173,0.00063614873,0.0000541488,0.00019376533,0.00033498558,0.0022654498,0.00030033238,0.66082966,0.25412914,0.08061345],"study_design_scores_gemma":[0.000011591403,0.000019578792,0.0002683181,0.0004325476,0.000015321999,0.00027125774,0.00082268874,0.00624274,0.00029328096,0.6452035,0.34639138,0.0000277031],"about_ca_topic_score_codex":0.002159515,"about_ca_topic_score_gemma":0.0027404127,"teacher_disagreement_score":0.014984053,"about_ca_system_score_codex":0.0028512704,"about_ca_system_score_gemma":0.004290308,"threshold_uncertainty_score":0.0792442},"labels":[],"label_agreement":null},{"id":"W2939022260","doi":"10.5281/zenodo.1474792","title":"Design Of A Pneumonia Ontology For Diagnosis Decision Support System","year":2018,"lang":"en","type":"preprint","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Ontology; Pneumonia; Intensive care medicine; Medicine; Decision support system; Computer science; Artificial intelligence; Internal medicine; Philosophy; Epistemology","score_opus":0.2507651162425904,"score_gpt":0.4358583321826903,"score_spread":0.18509321594009992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2939022260","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016271707,0.0002428756,0.9652021,0.0012981828,0.00013286229,0.0010032435,0.0020823812,0.0082090525,0.005557647],"genre_scores_gemma":[0.098995164,0.00032991072,0.89125574,0.0004643236,0.00005229552,0.00053524977,0.0044222423,0.00037399936,0.0035710707],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99842167,0.00023667922,0.00031662176,0.00030499208,0.0005660606,0.00015402891],"domain_scores_gemma":[0.99883467,0.00031503316,0.000100816906,0.00015583156,0.00046122738,0.00013229378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018500172,0.00051811256,0.0007656526,0.0019876228,0.0010499717,0.0026893022,0.0014616457,0.0013678636,0.0040445263],"category_scores_gemma":[0.0037121628,0.0005879079,0.0013407845,0.0012258155,0.0005142145,0.0022374943,0.002390133,0.0013152268,0.0015428109],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006233723,0.0012518923,0.011657885,0.0018960703,0.0004977575,0.0039802548,0.002494638,0.06325018,0.09473833,0.12167338,0.03765845,0.66027784],"study_design_scores_gemma":[0.00022207054,0.00018281802,0.0058650947,0.00043457825,0.000553751,0.0020610509,0.0009729817,0.605922,0.051312476,0.060626786,0.27166557,0.00018081482],"about_ca_topic_score_codex":0.0070893867,"about_ca_topic_score_gemma":0.0064310087,"teacher_disagreement_score":0.0070893867,"about_ca_system_score_codex":0.0014695744,"about_ca_system_score_gemma":0.0038029116,"threshold_uncertainty_score":0.0140962005},"labels":[],"label_agreement":null},{"id":"W2942012903","doi":"10.3233/978-1-61499-951-5-229","title":"A Hadoop/MapReduce Based Platform for Supporting Health Big Data Analytics","year":2019,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Island Health; University of Victoria","funders":"","keywords":"Big data; Computer science; Metadata; Benchmark (surveying); Raw data; Analytics; Database; Data science; World Wide Web; Data mining","score_opus":0.47891036392850317,"score_gpt":0.555944042977733,"score_spread":0.07703367904922986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942012903","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17116795,0.00096553593,0.7311009,0.006143536,0.001700972,0.0041616326,0.0063384227,0.0401303,0.03829068],"genre_scores_gemma":[0.35822895,0.00038052874,0.6264189,0.00077160797,0.00016790154,0.0005311644,0.0055837426,0.00081821426,0.0070990203],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987301,0.0002776338,0.000083923944,0.00021869884,0.00050718524,0.00018246712],"domain_scores_gemma":[0.9977743,0.0003755493,0.000080878606,0.00042026892,0.00072696334,0.0006220476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028959063,0.00043554668,0.00028781453,0.0005978212,0.0015181538,0.0017696173,0.0018439656,0.0003950438,0.0027615447],"category_scores_gemma":[0.0027247441,0.00039832928,0.0006505914,0.00076017494,0.00071945274,0.0016627231,0.0021844015,0.0012853722,0.0012018925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029145589,0.0025191335,0.030171188,0.0018332716,0.00053964974,0.0031048346,0.004097479,0.05789119,0.11385325,0.045135986,0.1984918,0.5394476],"study_design_scores_gemma":[0.0007470222,0.0022488008,0.02317666,0.00031910327,0.00023900802,0.0021960184,0.0039444957,0.42166916,0.07378467,0.05542135,0.41572237,0.0005313067],"about_ca_topic_score_codex":0.010964975,"about_ca_topic_score_gemma":0.011681085,"teacher_disagreement_score":0.010964975,"about_ca_system_score_codex":0.0008639856,"about_ca_system_score_gemma":0.0039106533,"threshold_uncertainty_score":0.021802306},"labels":[],"label_agreement":null},{"id":"W2943089774","doi":"10.1109/ccoms.2019.8821633","title":"Performance Improvement of Decision Trees for Diagnosis of Coronary Artery Disease Using Multi Filtering Approach","year":2019,"lang":"en","type":"article","venue":"2019 IEEE 4th International Conference on Computer and Communication Systems (ICCCS)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"C4.5 algorithm; Circumflex; Decision tree; Cardiology; Computer science; Coronary artery disease; Tree (set theory); Decision tree learning; Right coronary artery; Internal medicine; Medicine; Artery; Pattern recognition (psychology); Artificial intelligence; Mathematics; Myocardial infarction; Coronary angiography; Support vector machine","score_opus":0.25327351197550113,"score_gpt":0.4370091264381438,"score_spread":0.1837356144626427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943089774","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60407275,0.010131515,0.37153366,0.0017537393,0.0008512304,0.00021998897,0.0029580414,0.0029851536,0.0054937694],"genre_scores_gemma":[0.895532,0.0009838819,0.09761299,0.00027774088,0.00019933569,0.00007061656,0.004021083,0.000055176482,0.0012472343],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99795026,0.0006954583,0.00027571476,0.00041546646,0.00041188553,0.00025123803],"domain_scores_gemma":[0.9958753,0.0026269262,0.0001943487,0.00017853193,0.000901057,0.00022387624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047897883,0.0012729325,0.0015209529,0.003362302,0.0008072839,0.0012496492,0.0009587763,0.0015917821,0.0011629437],"category_scores_gemma":[0.008096119,0.00027686445,0.0017941848,0.0016207463,0.00020436285,0.0012012001,0.0006233354,0.0010540647,0.0006239601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002273872,0.0007922505,0.040794574,0.00036449867,0.00071139156,0.00035024353,0.00028224432,0.28159204,0.008136106,0.0014163951,0.009356562,0.65392977],"study_design_scores_gemma":[0.00003856179,0.00026782864,0.005903426,0.000045230066,0.00012114736,0.000109194174,0.00008606067,0.9889044,0.0022273955,0.0012623941,0.0010132092,0.000021174474],"about_ca_topic_score_codex":0.014132051,"about_ca_topic_score_gemma":0.008662835,"teacher_disagreement_score":0.014132051,"about_ca_system_score_codex":0.00088979385,"about_ca_system_score_gemma":0.0013125945,"threshold_uncertainty_score":0.028099597},"labels":[],"label_agreement":null},{"id":"W2945314865","doi":"10.1177/0840470419846134","title":"Intelligent health data analytics: A convergence of artificial intelligence and big data","year":2019,"lang":"en","type":"article","venue":"Healthcare Management Forum","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Big data; Data science; Analytics; Computer science; Health care; Data analysis; Business intelligence; Data quality; Knowledge management; Data mining; Engineering","score_opus":0.4275021929463665,"score_gpt":0.4861191591299544,"score_spread":0.058616966183587915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945314865","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0120561365,0.090985484,0.714571,0.1425826,0.0020512668,0.0005240514,0.00071139244,0.0012075605,0.035310596],"genre_scores_gemma":[0.22035696,0.0938094,0.64643973,0.023354823,0.009758886,0.0006480874,0.00117479,0.00045559046,0.0040016654],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98259556,0.007654519,0.0013896768,0.0015902948,0.0063790763,0.0003909167],"domain_scores_gemma":[0.93841344,0.050130215,0.0017066909,0.005117722,0.0032354454,0.0013965939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023259858,0.0014061286,0.00273629,0.00995889,0.001593919,0.01880593,0.003351153,0.003529243,0.0015974224],"category_scores_gemma":[0.03218296,0.0011042383,0.0015508832,0.008989386,0.01341377,0.021547353,0.009353371,0.0074705086,0.0007582107],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011747591,0.0002661405,0.0068528582,0.0038695286,0.00056726893,0.000366667,0.0035411497,0.009888305,0.0025487852,0.6227294,0.022865327,0.32638717],"study_design_scores_gemma":[0.000022960776,0.000054396092,0.0012734418,0.0012785827,0.00006176889,0.00018940329,0.0012524191,0.022120293,0.0007176512,0.9008536,0.07208446,0.000091034824],"about_ca_topic_score_codex":0.0015825522,"about_ca_topic_score_gemma":0.0017386317,"teacher_disagreement_score":0.023259858,"about_ca_system_score_codex":0.0032772305,"about_ca_system_score_gemma":0.005590463,"threshold_uncertainty_score":0.12301141},"labels":[],"label_agreement":null},{"id":"W2946016028","doi":"10.1177/0840470419848428","title":"A population health perspective on artificial intelligence","year":2019,"lang":"en","type":"article","venue":"Healthcare Management Forum","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Public Health Ontario; University of Toronto; Institute of Population and Public Health; McGill University","funders":"","keywords":"Perspective (graphical); Population; Computer science; Data science; Psychology; Artificial intelligence; Medicine; Environmental health","score_opus":0.12241100344908791,"score_gpt":0.48208000227081005,"score_spread":0.35966899882172215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946016028","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004915474,0.10789858,0.033049703,0.6042474,0.0029777926,0.000060223432,0.0003502699,0.00007675497,0.24642374],"genre_scores_gemma":[0.5535664,0.21250755,0.0201407,0.1598915,0.028423175,0.00048284268,0.00036310742,0.000087712746,0.024536947],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9952767,0.0031327566,0.00012605145,0.00044081075,0.00072018564,0.0003035203],"domain_scores_gemma":[0.9922884,0.0063166744,0.00025574653,0.00022880411,0.0005799826,0.00033037498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005500654,0.0006743094,0.0006114434,0.003665495,0.0017325364,0.0051290477,0.0013326311,0.0047834665,0.006012098],"category_scores_gemma":[0.008812425,0.00023437437,0.0007599722,0.002833257,0.014159047,0.005413648,0.0025698694,0.007889144,0.0007540262],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053099516,0.00002046629,0.00054009474,0.00010997918,0.000013875854,0.000060083825,0.0005443578,0.00053833507,0.000026455864,0.9738666,0.010362132,0.013912341],"study_design_scores_gemma":[0.000007818447,0.000029249904,0.0010259792,0.00048214523,0.000014764804,0.00019231159,0.0008022438,0.0010795261,0.000054882228,0.8435892,0.1527076,0.0000143005245],"about_ca_topic_score_codex":0.0074998364,"about_ca_topic_score_gemma":0.0042251768,"teacher_disagreement_score":0.0074998364,"about_ca_system_score_codex":0.0055765556,"about_ca_system_score_gemma":0.0033866756,"threshold_uncertainty_score":0.040460885},"labels":[],"label_agreement":null},{"id":"W2949767632","doi":"10.1109/access.2019.2923707","title":"Effective Heart Disease Prediction Using Hybrid Machine Learning Techniques","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1871,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"China Medical University","keywords":"Computer science; Machine learning; Random forest; Heart disease; Artificial intelligence; Predictive modelling; Disease; Internet of Things; Support vector machine; The Internet; Data mining; Medicine","score_opus":0.11509027832121588,"score_gpt":0.4976392046669986,"score_spread":0.38254892634578275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949767632","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1789822,0.0020137643,0.8128726,0.0005896054,0.00012633506,0.00005632552,0.00036330492,0.0029093747,0.0020864827],"genre_scores_gemma":[0.8838042,0.0003673173,0.11400976,0.00014210181,0.000094628806,0.00004620028,0.00036127804,0.000035646714,0.0011389225],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999559,0.00014297687,0.000024612791,0.00008977401,0.00013401009,0.000049547667],"domain_scores_gemma":[0.9992029,0.0004811635,0.000071979615,0.000068407964,0.00015083095,0.00002479794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010125055,0.0005996342,0.0007660741,0.0012310663,0.00023039707,0.000521186,0.0006273617,0.00074671494,0.0009159697],"category_scores_gemma":[0.0015407783,0.00019654812,0.00077002967,0.000732546,0.00016265636,0.00082674756,0.00038932133,0.0005070618,0.0005229087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034420606,0.0003302056,0.012049953,0.00009146749,0.00018657242,0.00021251178,0.000053771633,0.4951442,0.013742101,0.001462571,0.0023075405,0.47407493],"study_design_scores_gemma":[0.0000081740445,0.00006711386,0.0012055968,0.0000057033776,0.000018573237,0.000057477784,0.00000640357,0.9961541,0.0013840962,0.0008580176,0.00022580143,0.000008887483],"about_ca_topic_score_codex":0.0028887226,"about_ca_topic_score_gemma":0.003246181,"teacher_disagreement_score":0.0028887226,"about_ca_system_score_codex":0.000247675,"about_ca_system_score_gemma":0.0003285329,"threshold_uncertainty_score":0.005743861},"labels":[],"label_agreement":null},{"id":"W2953505302","doi":"10.1016/j.compbiomed.2019.103346","title":"Machine learning-based coronary artery disease diagnosis: A comprehensive review","year":2019,"lang":"en","type":"review","venue":"Computers in Biology and Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":269,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Université du Québec à Montréal","funders":"","keywords":"CAD; Coronary artery disease; Feature selection; Computer science; Machine learning; Artificial intelligence; Feature (linguistics); Sample size determination; Coronary angiography; Selection (genetic algorithm); Sample (material); Medicine; Stenosis; Radiology; Data mining; Internal medicine; Statistics; Myocardial infarction; Mathematics; Engineering drawing","score_opus":0.2605775293194842,"score_gpt":0.5359636585444464,"score_spread":0.2753861292249622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953505302","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007721093,0.99930775,0.0001479905,0.00015103347,0.000088868896,0.0000057471907,0.000032646927,0.00000493738,0.00018383146],"genre_scores_gemma":[0.0006017794,0.9985593,0.00029995324,0.00023615605,0.00013565218,0.0000069226794,0.000050351347,0.0000012386081,0.00010872282],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99960774,0.000067739595,0.00009825186,0.00008837353,0.00011335315,0.00002454833],"domain_scores_gemma":[0.998711,0.0007603851,0.0001724221,0.000025831725,0.0002756569,0.000054740285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013269692,0.0008857606,0.0023456807,0.002755732,0.00020705405,0.0011727092,0.0012251099,0.0011348611,0.0031417753],"category_scores_gemma":[0.0026187007,0.0003506366,0.0013728654,0.0024460019,0.00038277454,0.0013230918,0.0007342093,0.0013567003,0.0011594346],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000118444106,0.000103588776,0.0005600202,0.053399503,0.0005916857,0.00013116757,0.00004328712,0.00041079213,0.0007433687,0.0011252876,0.02317227,0.9196006],"study_design_scores_gemma":[0.0002186378,0.00057337905,0.006085036,0.05104629,0.0057724155,0.0027460384,0.00020640659,0.0010471211,0.0011585059,0.0036177444,0.9273774,0.0001510842],"about_ca_topic_score_codex":0.0018821079,"about_ca_topic_score_gemma":0.0037391768,"teacher_disagreement_score":0.0031417753,"about_ca_system_score_codex":0.0005106749,"about_ca_system_score_gemma":0.001792062,"threshold_uncertainty_score":0.010510266},"labels":[],"label_agreement":null},{"id":"W2954431181","doi":"10.1016/j.jval.2019.04.534","title":"PCV99 BAYESIAN NETWORKS AS AN EMERGING TOOL FOR DISEASE RISK ESTIMATION AND CLINICAL DECISION-MAKING: A REAL-WORLD EXAMPLE IN CORONARY ARTERY DISEASE","year":2019,"lang":"en","type":"article","venue":"Value in Health","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Toronto Public Health","funders":"","keywords":"Interpretability; Coronary artery disease; Logistic regression; Machine learning; CAD; Bayesian network; Disease; Artificial intelligence; Receiver operating characteristic; Computer science; Missing data; Medicine; Bayesian probability; Risk assessment; Data mining; Internal medicine; Engineering","score_opus":0.1502559212390691,"score_gpt":0.508387657659241,"score_spread":0.3581317364201719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954431181","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052178193,0.002226647,0.9166557,0.006489631,0.00021744496,0.00021719294,0.002094496,0.001699886,0.018220818],"genre_scores_gemma":[0.46595165,0.0013771477,0.52590126,0.00053522445,0.00011950322,0.0001865481,0.0011791209,0.00023489112,0.00451469],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964307,0.002321075,0.0001505455,0.0003086437,0.00070626143,0.000082770544],"domain_scores_gemma":[0.96467286,0.030907106,0.0008130609,0.001182903,0.0020220948,0.00040196534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007478588,0.00086483435,0.0008383668,0.002450918,0.00094651047,0.0033908484,0.0015795896,0.0023264496,0.0073309005],"category_scores_gemma":[0.04163921,0.0004891006,0.000697934,0.0024530957,0.000772691,0.0025016991,0.0013016125,0.002620738,0.001061936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059996545,0.00032141167,0.011499084,0.00030447426,0.00025330155,0.00042031112,0.0003889267,0.52062297,0.0006701178,0.08108224,0.014795111,0.36904204],"study_design_scores_gemma":[0.00005476441,0.00005086042,0.0011434044,0.00011410683,0.000049842023,0.00013261691,0.000067711364,0.9070553,0.0005723377,0.082412586,0.008312548,0.000033966142],"about_ca_topic_score_codex":0.026461642,"about_ca_topic_score_gemma":0.029131183,"teacher_disagreement_score":0.026461642,"about_ca_system_score_codex":0.0017572221,"about_ca_system_score_gemma":0.0025821456,"threshold_uncertainty_score":0.052615225},"labels":[],"label_agreement":null},{"id":"W2957345146","doi":"10.1109/icc.2019.8761985","title":"Fetal Birth Weight Estimation in High-Risk Pregnancies Through Machine Learning Techniques","year":2019,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Gestation; Fetus; Gestational age; Obstetrics; Birth weight; Pregnancy; Medicine; Intervention (counseling); Estimation; Low birth weight; Infant mortality; Fetal weight; Computer science; Population; Engineering; Environmental health; Biology","score_opus":0.057874753212135144,"score_gpt":0.41619630352178116,"score_spread":0.358321550309646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2957345146","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5991318,0.0026367255,0.39497113,0.00032705587,0.00006932877,0.00004805443,0.00028068075,0.00051877956,0.0020163858],"genre_scores_gemma":[0.9619731,0.0006349893,0.03671509,0.000024577384,0.000022882177,0.000018536526,0.00018579188,0.0000111552545,0.00041396395],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996069,0.00018485232,0.00003216801,0.000056459416,0.00007766125,0.000041898296],"domain_scores_gemma":[0.99857724,0.0010164418,0.00016580304,0.000052127678,0.0001533806,0.00003507813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00112402,0.00041244668,0.00040574413,0.0016055254,0.0001525817,0.0005750807,0.00036523782,0.00051187596,0.00038750106],"category_scores_gemma":[0.004693866,0.00016202185,0.0003888354,0.0007973865,0.0001358971,0.00051472645,0.00034542178,0.00043329308,0.0001863398],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045466662,0.00024090394,0.29307064,0.0001254052,0.00021448152,0.0005772695,0.00016685543,0.24564043,0.0063425084,0.0013154171,0.0009352011,0.4509162],"study_design_scores_gemma":[0.000007928724,0.00011647742,0.045686334,0.000039759365,0.00004992995,0.000326793,0.000096198724,0.94923705,0.0023444083,0.0015442028,0.000532081,0.00001889857],"about_ca_topic_score_codex":0.0032014423,"about_ca_topic_score_gemma":0.0024804105,"teacher_disagreement_score":0.0032014423,"about_ca_system_score_codex":0.0002458514,"about_ca_system_score_gemma":0.00028507703,"threshold_uncertainty_score":0.006365657},"labels":[],"label_agreement":null},{"id":"W2958091182","doi":"10.18280/rces.050301","title":"Classification of heart disease using multiple classifiers","year":2019,"lang":"en","type":"article","venue":"Review of Computer Engineering Studies","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology)","score_opus":0.21728973428642065,"score_gpt":0.4831938412163425,"score_spread":0.26590410692992184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2958091182","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26418492,0.012730938,0.69945526,0.0014134294,0.0016869301,0.00071877654,0.0024612052,0.0056082495,0.011740348],"genre_scores_gemma":[0.75125957,0.0033456406,0.23665263,0.00039386796,0.00075673795,0.00026149084,0.002256654,0.00008586544,0.004987514],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969915,0.0005201049,0.0004104426,0.00078792014,0.0010494231,0.00024057951],"domain_scores_gemma":[0.9972584,0.00076153304,0.0002964177,0.00024876342,0.0013337532,0.000101160345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003056394,0.0010331288,0.0019295316,0.0040900796,0.00072918745,0.0016022284,0.0011035438,0.001096305,0.0012934512],"category_scores_gemma":[0.005848621,0.0003343095,0.0013565065,0.0022405034,0.0001804678,0.0015440844,0.00095891015,0.00098471,0.0014647222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048709163,0.00043934112,0.04495987,0.00029882728,0.00068986946,0.00029131235,0.0001293031,0.01400052,0.010547924,0.0007019232,0.006674005,0.9207801],"study_design_scores_gemma":[0.00007517305,0.00097145844,0.06632969,0.00040795156,0.0012593445,0.0017675678,0.00041354605,0.8809617,0.026688907,0.0054656398,0.015497023,0.00016194586],"about_ca_topic_score_codex":0.0025221282,"about_ca_topic_score_gemma":0.0024359839,"teacher_disagreement_score":0.0040900796,"about_ca_system_score_codex":0.0005283225,"about_ca_system_score_gemma":0.00070476753,"threshold_uncertainty_score":0.016163945},"labels":[],"label_agreement":null},{"id":"W2958769551","doi":"","title":"A STUDY ON ASSOCIATION RULE MINING FOR VARIOUS HEART DISEASES MEDICAL DATA","year":2019,"lang":"en","type":"article","venue":"International journal of advance research and innovative ideas in education","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Association rule learning; Angina; Chest pain; Disease; Medicine; Asymptomatic; Apriori algorithm; Set (abstract data type); Heart disease; Data mining; Medical emergency; Cardiology; Internal medicine; Computer science; Myocardial infarction","score_opus":0.2528641631724724,"score_gpt":0.6388507355504573,"score_spread":0.38598657237798495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2958769551","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44222313,0.04172853,0.47196883,0.0059939837,0.0010859495,0.0011386994,0.0035740992,0.0010926969,0.031193905],"genre_scores_gemma":[0.62119323,0.015363981,0.35433784,0.0015486791,0.00053903094,0.0003967748,0.002923418,0.00013114464,0.0035659806],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9871634,0.0055895415,0.0017524849,0.001396795,0.0038827055,0.00021504682],"domain_scores_gemma":[0.89810896,0.089013085,0.0018127847,0.0026651763,0.007933413,0.00046658897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01490142,0.00042154072,0.0006457154,0.0065169553,0.0007986732,0.0024135858,0.00086322316,0.00080147386,0.0013088575],"category_scores_gemma":[0.046181504,0.00027431472,0.0015824272,0.0100492705,0.0006558654,0.0029359316,0.00055529416,0.0012931469,0.0006032464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005206564,0.0006123521,0.13361356,0.0017499742,0.0005160763,0.0014837469,0.0017454755,0.008296803,0.004884428,0.021603843,0.006418665,0.8185544],"study_design_scores_gemma":[0.0002865382,0.0043297433,0.22261421,0.0035202894,0.0015769337,0.024618909,0.008895998,0.39147568,0.049417417,0.06113212,0.23175159,0.00038059542],"about_ca_topic_score_codex":0.0017651174,"about_ca_topic_score_gemma":0.0013748785,"teacher_disagreement_score":0.01490142,"about_ca_system_score_codex":0.00073435315,"about_ca_system_score_gemma":0.0008440965,"threshold_uncertainty_score":0.078807175},"labels":[],"label_agreement":null},{"id":"W2963565281","doi":"10.1016/j.cmpb.2019.104992","title":"A new machine learning technique for an accurate diagnosis of coronary artery disease","year":2019,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":340,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Machine learning; CAD; Artificial intelligence; Normalization (sociology); Particle swarm optimization; Preprocessor; Classifier (UML); Support vector machine; Coronary artery disease; Feature selection; Data pre-processing; Data mining; Medicine","score_opus":0.247954431720299,"score_gpt":0.53739828263951,"score_spread":0.289443850919211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963565281","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010468822,0.0016218302,0.9833171,0.0004117346,0.00063984154,0.00006831318,0.00014577358,0.0008528036,0.0024737776],"genre_scores_gemma":[0.11317162,0.0016073369,0.8745164,0.00047350055,0.000721337,0.00013767982,0.00028696304,0.000091669055,0.008993474],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951124,0.00007489434,0.000036647845,0.000097908196,0.00025102866,0.000028219],"domain_scores_gemma":[0.99908495,0.00044219033,0.00005491642,0.00009287916,0.00029239903,0.00003269554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007521288,0.0004579334,0.0005327239,0.0012434202,0.000400237,0.0006900307,0.00064927764,0.0008898354,0.0029246663],"category_scores_gemma":[0.0020852021,0.00023751432,0.00053149724,0.00093550474,0.0003428493,0.0011847527,0.000638704,0.0009747396,0.0015698583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017419316,0.00013398986,0.0020478698,0.00019613118,0.00010641828,0.00020835888,0.00006767894,0.009518446,0.06008061,0.0072715515,0.0073968857,0.912798],"study_design_scores_gemma":[0.000090172216,0.0004091945,0.0065708444,0.00009156497,0.00025614433,0.00268026,0.000062718806,0.85822004,0.06216664,0.015310473,0.054049287,0.000092707414],"about_ca_topic_score_codex":0.0008006758,"about_ca_topic_score_gemma":0.0013922701,"teacher_disagreement_score":0.0029246663,"about_ca_system_score_codex":0.00021019009,"about_ca_system_score_gemma":0.00045119022,"threshold_uncertainty_score":0.009784043},"labels":[],"label_agreement":null},{"id":"W2967935744","doi":"10.5220/0007949902960303","title":"Classification of Alzheimer’s Disease using Machine Learning Techniques","year":2019,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":115,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Machine learning; Naive Bayes classifier; Decision tree; Disease; Artificial intelligence; Computer science; Health care; Support vector machine; Medicine","score_opus":0.30543317996183605,"score_gpt":0.5218391048121328,"score_spread":0.21640592485029675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967935744","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56840605,0.019225158,0.37313548,0.004015497,0.0017206797,0.001033523,0.017194515,0.005105674,0.010163437],"genre_scores_gemma":[0.80597585,0.004036123,0.16895866,0.00041143998,0.00044746784,0.00039509725,0.016960122,0.000052581658,0.0027627056],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837744,0.000276483,0.00032880265,0.0003293946,0.00050298433,0.00018486298],"domain_scores_gemma":[0.99795854,0.0008625633,0.00027160998,0.00016105502,0.0006645221,0.00008170648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019435689,0.0012391366,0.0013438988,0.0063888077,0.0004963663,0.0014675655,0.0011519535,0.0013343043,0.0009042141],"category_scores_gemma":[0.0047099795,0.00019986591,0.0015791346,0.00302733,0.00033385723,0.0010487989,0.00065950997,0.0014225636,0.00095080334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005377073,0.0013715192,0.08317767,0.00064570864,0.00053912605,0.0009231345,0.00023148072,0.084523976,0.005687072,0.001687456,0.022049036,0.7986262],"study_design_scores_gemma":[0.00004598917,0.00033462446,0.03471582,0.0002445227,0.00014563806,0.0007131224,0.00038720007,0.94407505,0.005357229,0.0067105438,0.0071968744,0.00007332324],"about_ca_topic_score_codex":0.0068700123,"about_ca_topic_score_gemma":0.0051543196,"teacher_disagreement_score":0.0068700123,"about_ca_system_score_codex":0.0007945982,"about_ca_system_score_gemma":0.0010190319,"threshold_uncertainty_score":0.013660014},"labels":[],"label_agreement":null},{"id":"W2968147120","doi":"10.1097/tp.0000000000002923","title":"Seeing the Forest for the Trees: Random Forest Models for Predicting Survival in Kidney Transplant Recipients","year":2019,"lang":"en","type":"review","venue":"Transplantation","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Random forest; Machine learning; Computer science; Artificial intelligence; Decision tree; Recursive partitioning; Regression; Statistics; Mathematics","score_opus":0.3192333719941502,"score_gpt":0.4885849999815572,"score_spread":0.169351627987407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2968147120","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012553099,0.015240463,0.94987345,0.010938413,0.001756913,0.0004169259,0.0035222506,0.0025237612,0.003174718],"genre_scores_gemma":[0.30944738,0.02306954,0.6361995,0.0047933673,0.0060600373,0.0016872104,0.0091943,0.0014593926,0.008089355],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973431,0.0016687202,0.0001138035,0.00039798053,0.0003581249,0.000118345495],"domain_scores_gemma":[0.9885626,0.009571357,0.00051736383,0.00040894217,0.00066677487,0.00027293962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0082350345,0.0021222571,0.0023144863,0.0018997896,0.0010023286,0.0022694676,0.0032789037,0.002679697,0.0047962707],"category_scores_gemma":[0.019441446,0.00089692685,0.0022570547,0.0026362087,0.00078986597,0.003524073,0.0017479347,0.005595911,0.0020845602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006824501,0.00024136704,0.012557635,0.00068315165,0.00065513357,0.00026885027,0.00025311616,0.5123218,0.00044800216,0.030609421,0.12015738,0.3211216],"study_design_scores_gemma":[0.00008077783,0.00011165884,0.00088432967,0.00023464471,0.00009951841,0.00007875422,0.00003622744,0.90988636,0.00018893002,0.074635275,0.013697798,0.00006568575],"about_ca_topic_score_codex":0.011665984,"about_ca_topic_score_gemma":0.02171636,"teacher_disagreement_score":0.011665984,"about_ca_system_score_codex":0.0010669611,"about_ca_system_score_gemma":0.0017428651,"threshold_uncertainty_score":0.043551564},"labels":[],"label_agreement":null},{"id":"W2968723729","doi":"10.1145/3357514.3357515","title":"EuroGP 2019 panel discussion","year":2019,"lang":"en","type":"article","venue":"ACM SIGEVOlution","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"The Internet; World Wide Web; Computer science; Everyday life; Set (abstract data type); Synonym (taxonomy); Internet privacy; Political science","score_opus":0.15943510150069157,"score_gpt":0.45366451172691624,"score_spread":0.2942294102262247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2968723729","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001470295,0.011423982,0.0011663937,0.57995623,0.17359638,0.0007226938,0.010337012,0.00034810978,0.22097898],"genre_scores_gemma":[0.011401494,0.0047366642,0.0013084206,0.6275337,0.044393465,0.0016669392,0.004201259,0.00034068836,0.3044174],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99428695,0.0010917725,0.0002796925,0.0009964003,0.0017867002,0.0015585007],"domain_scores_gemma":[0.99340856,0.0020019775,0.00037461423,0.00034960886,0.0022545424,0.001610768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014891653,0.0013561117,0.00095029845,0.001699032,0.003157611,0.011149911,0.0035714183,0.03597422,0.10504864],"category_scores_gemma":[0.016858296,0.0006292927,0.0024181216,0.0019348384,0.0015902345,0.0052508204,0.0046612914,0.014573537,0.04855416],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000093875235,0.00002751197,0.00016285486,0.0001807916,0.000009569512,0.00010439314,0.000029430304,0.00006149546,0.00009734707,0.0052952836,0.988565,0.005372351],"study_design_scores_gemma":[0.00003029021,0.000012538616,0.00061150134,0.0002749238,0.000008007139,0.000025833586,0.000049815295,0.00002682044,0.00007413685,0.0015280509,0.99734855,0.000009544282],"about_ca_topic_score_codex":0.010544204,"about_ca_topic_score_gemma":0.0122510465,"teacher_disagreement_score":0.10504864,"about_ca_system_score_codex":0.005621865,"about_ca_system_score_gemma":0.012226357,"threshold_uncertainty_score":0.35142273},"labels":[],"label_agreement":null},{"id":"W2971382582","doi":"10.1016/j.eswa.2020.113408","title":"An Efficient Convolutional Neural Network for Coronary Heart Disease Prediction","year":2019,"lang":"en","type":"preprint","venue":"Expert Systems with Applications","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Queen's University; University of Pittsburgh","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Machine learning; Deep learning; Artificial neural network; Test data; Data mining; Pattern recognition (psychology)","score_opus":0.10109723894667501,"score_gpt":0.4392184916486733,"score_spread":0.33812125270199833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971382582","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17668398,0.00366588,0.8036273,0.0010799567,0.0005455333,0.000112102454,0.0024076926,0.0042510354,0.0076265363],"genre_scores_gemma":[0.7720768,0.0010663887,0.19846575,0.00031191666,0.00023168563,0.00010303769,0.0039545083,0.0001371123,0.023652846],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99984956,0.000017930859,0.000008744071,0.000041468676,0.000044200635,0.000038147613],"domain_scores_gemma":[0.9997608,0.00008182516,0.000013797478,0.00003442851,0.00009454689,0.000014551223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041212223,0.0005960944,0.0005178252,0.00052198867,0.00023682666,0.00041778488,0.0010072538,0.00083519565,0.003239019],"category_scores_gemma":[0.00089882483,0.00039021438,0.00044403953,0.00048712132,0.00015129735,0.0005531049,0.0006569386,0.000603739,0.00096059905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004171508,0.0002470036,0.003099965,0.00010963771,0.00019824822,0.00021128081,0.000027826647,0.24025168,0.0192745,0.004522944,0.017331071,0.7143086],"study_design_scores_gemma":[0.000008995033,0.000016166126,0.00057988835,0.0000045458582,0.000023150724,0.000025015483,0.000002658744,0.99542373,0.0023073226,0.00091249734,0.00069267134,0.000003330096],"about_ca_topic_score_codex":0.018084478,"about_ca_topic_score_gemma":0.027004529,"teacher_disagreement_score":0.018084478,"about_ca_system_score_codex":0.00048708066,"about_ca_system_score_gemma":0.0009949148,"threshold_uncertainty_score":0.03595841},"labels":[],"label_agreement":null},{"id":"W2971510668","doi":"10.26685/urncst.151","title":"Palliative Care Management System","year":2019,"lang":"en","type":"article","venue":"Undergraduate Research in Natural and Clinical Science and Technology (URNCST) Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Questionnaire; Process (computing); Computer science; Focus group; Quality (philosophy); Information system; Palliative care; World Wide Web; Knowledge management; Medicine; Nursing; Engineering; Business","score_opus":0.2037151274555779,"score_gpt":0.5657689026314043,"score_spread":0.36205377517582643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971510668","genre_codex":"software","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06623845,0.003774342,0.29111525,0.008075528,0.002002604,0.0063211676,0.069006756,0.3095421,0.24392383],"genre_scores_gemma":[0.47463566,0.0033338685,0.21547249,0.0065648668,0.0010195061,0.0038140677,0.16414468,0.0072924052,0.123722434],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99923897,0.00014251581,0.00013925602,0.00019397444,0.00021463948,0.000070636546],"domain_scores_gemma":[0.9981293,0.00036286624,0.000111871326,0.0004349551,0.0007185604,0.0002425316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001403473,0.00044990046,0.0005546038,0.001387043,0.0010759148,0.0021036442,0.0014819143,0.00076054595,0.037084304],"category_scores_gemma":[0.003333046,0.0003092731,0.00043027397,0.0010357768,0.00022035513,0.0021765935,0.0017935511,0.0008145824,0.020271579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007342854,0.00040143053,0.013821,0.001274279,0.00008951016,0.0009358416,0.0013222267,0.0020862927,0.009971412,0.011912165,0.52791923,0.42953226],"study_design_scores_gemma":[0.00024696853,0.00022857917,0.011077094,0.00028725946,0.00007967601,0.0012916159,0.00042739985,0.021508008,0.011441227,0.00613847,0.9471585,0.000115284165],"about_ca_topic_score_codex":0.0017006043,"about_ca_topic_score_gemma":0.00094678515,"teacher_disagreement_score":0.037084304,"about_ca_system_score_codex":0.0007604681,"about_ca_system_score_gemma":0.0011250253,"threshold_uncertainty_score":0.12405938},"labels":[],"label_agreement":null},{"id":"W2972258955","doi":"10.28924/2291-8639","title":"International Journal of Analysis and Applications","year":2017,"lang":"en","type":"paratext","venue":"International Journal of Analysis and Applications","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":177,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics","score_opus":0.09053165552389525,"score_gpt":0.5195714330547074,"score_spread":0.4290397775308122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972258955","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016853288,0.12077574,0.3667216,0.017341455,0.018110812,0.00032245545,0.001263365,0.0011233687,0.45748794],"genre_scores_gemma":[0.40118295,0.11495317,0.17326987,0.00381051,0.012781547,0.0015182734,0.0026317355,0.00064048276,0.28921145],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99832183,0.00031069064,0.00015380992,0.00034224146,0.00076789537,0.00010364125],"domain_scores_gemma":[0.99831605,0.0003905485,0.00014369375,0.00031605674,0.0007024475,0.00013135336],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018077967,0.0011743434,0.0013774814,0.0017490317,0.0010830428,0.005213875,0.0009969648,0.0016571451,0.035563577],"category_scores_gemma":[0.005105185,0.00029931168,0.0011175473,0.0023439005,0.0017691979,0.001973949,0.002386686,0.0027381761,0.009718512],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008599884,0.000100097386,0.0015370707,0.0009476099,0.00015931454,0.0004560157,0.00029807832,0.007445778,0.0027320446,0.6113069,0.06978081,0.30515012],"study_design_scores_gemma":[0.00003252331,0.0000905308,0.0020578657,0.00043561877,0.00007239902,0.00075433886,0.00029782738,0.04069787,0.001039311,0.5142818,0.44019845,0.000041420517],"about_ca_topic_score_codex":0.0010951989,"about_ca_topic_score_gemma":0.0004609676,"teacher_disagreement_score":0.9644364,"about_ca_system_score_codex":0.0012353396,"about_ca_system_score_gemma":0.002159103,"threshold_uncertainty_score":0.11897206},"labels":[],"label_agreement":null},{"id":"W2972893922","doi":"10.1177/0840470419874356","title":"Artificial intelligence in healthcare: A Canadian context","year":2019,"lang":"en","type":"review","venue":"Healthcare Management Forum","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Western University; CARE Canada","funders":"","keywords":"Health care; Context (archaeology); Investment (military); Business; Knowledge management; Capital investment; Public relations; Engineering ethics; Political science; Computer science; Engineering; Finance; History","score_opus":0.29157530356633454,"score_gpt":0.5094065603643754,"score_spread":0.21783125679804083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972893922","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013820168,0.99113363,0.00005413552,0.004073013,0.0002958893,0.000003788732,0.000031467636,0.0000034217117,0.004266456],"genre_scores_gemma":[0.0032141446,0.99434966,0.00014789167,0.0013236428,0.00012893118,0.0000036351987,0.00002094216,0.0000017196078,0.00080944225],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99898857,0.00015556201,0.00006839961,0.000082795515,0.0005657714,0.0001389529],"domain_scores_gemma":[0.9971397,0.00071427925,0.00013793845,0.00003667991,0.001697945,0.00027352868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019312422,0.00061093376,0.00088530715,0.0046217134,0.0016136074,0.00335459,0.0008544221,0.0016024077,0.0043862225],"category_scores_gemma":[0.0033175994,0.00021839775,0.00047481305,0.012172917,0.0024566653,0.0015742853,0.0011598411,0.002574676,0.0005366077],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009002854,0.000054400643,0.0007383625,0.021773864,0.00011515462,0.0003454148,0.0010623581,0.0008058208,0.000509883,0.11736613,0.17423645,0.6829021],"study_design_scores_gemma":[0.000007359189,0.000013289018,0.0019070036,0.0077615534,0.00006625969,0.00020454002,0.00037133932,0.000083604624,0.00007002743,0.0032785055,0.9862164,0.00002003184],"about_ca_topic_score_codex":0.7803844,"about_ca_topic_score_gemma":0.8642045,"teacher_disagreement_score":0.21961558,"about_ca_system_score_codex":0.030560806,"about_ca_system_score_gemma":0.08121493,"threshold_uncertainty_score":0.44181782},"labels":[],"label_agreement":null},{"id":"W2975743880","doi":"10.18280/isi.240305","title":"Robust Cluster-then-label (RCTL) Approach for Heart Disease Prediction","year":2019,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cluster (spacecraft); Artificial intelligence; Computer science; Pattern recognition (psychology)","score_opus":0.09116106326604012,"score_gpt":0.3500119309632207,"score_spread":0.2588508676971806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2975743880","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018471127,0.000731779,0.9729653,0.000728746,0.00018115323,0.00025807563,0.00088086585,0.0038945167,0.0018883198],"genre_scores_gemma":[0.40754294,0.0003850424,0.57702774,0.00088415656,0.00043328758,0.0005238489,0.0047859135,0.0005868486,0.0078301495],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99650735,0.0009034347,0.0001615043,0.0010461807,0.00097499473,0.00040639404],"domain_scores_gemma":[0.9956026,0.0017737584,0.0005099436,0.0006635403,0.0012542853,0.0001958638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031668204,0.0012921459,0.0026558659,0.0027132393,0.0016957476,0.0018204993,0.004261147,0.0029133304,0.0034696998],"category_scores_gemma":[0.007644705,0.0004880348,0.0017529123,0.0024690703,0.00079164427,0.0016993452,0.0020208566,0.002705062,0.0027437925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010971382,0.0011972603,0.011157316,0.00033417658,0.00044499146,0.0004054148,0.00030438823,0.26836136,0.005215227,0.011614565,0.03867931,0.66118884],"study_design_scores_gemma":[0.000031384952,0.00007427921,0.0007477061,0.000019232646,0.000029458983,0.00007721726,0.000047319274,0.9870429,0.0015295229,0.008079626,0.0022907425,0.00003065222],"about_ca_topic_score_codex":0.016165147,"about_ca_topic_score_gemma":0.01808911,"teacher_disagreement_score":0.016165147,"about_ca_system_score_codex":0.0016740097,"about_ca_system_score_gemma":0.0026470718,"threshold_uncertainty_score":0.032142103},"labels":[],"label_agreement":null},{"id":"W2976252475","doi":"10.1038/s41598-019-49563-6","title":"Prognostic Modeling and Prevention of Diabetes Using Machine Learning Technique","year":2019,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University; University of Toronto; Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hidden Markov model; Framingham Risk Score; Medicine; Population; Receiver operating characteristic; Computer science; Artificial intelligence; Machine learning; Diabetes mellitus; Sample (material); Disease; Internal medicine; Environmental health","score_opus":0.11955813067904178,"score_gpt":0.4412827382406808,"score_spread":0.321724607561639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2976252475","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23496133,0.0019623244,0.75678426,0.0015257215,0.00013768236,0.000110404166,0.0006989007,0.0011688316,0.0026505217],"genre_scores_gemma":[0.92365134,0.0008587338,0.07416517,0.00010222969,0.000078107776,0.000055522094,0.00041109003,0.000013895317,0.00066397624],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993612,0.00032720852,0.000056132256,0.00008933345,0.00010933438,0.000056765657],"domain_scores_gemma":[0.99736816,0.0019142306,0.0003047153,0.00015396737,0.00021538032,0.00004352352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025421446,0.00041816177,0.00051408535,0.0015442498,0.00027849444,0.00076797674,0.00041244252,0.0004839233,0.00093682396],"category_scores_gemma":[0.0077880197,0.00017490536,0.0006343697,0.00080401695,0.00023626148,0.0006029463,0.0003686348,0.00072592736,0.00029764615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003274422,0.0003540018,0.22953571,0.0002151748,0.00044044878,0.00034104448,0.00025436177,0.43638486,0.0032960665,0.0072424,0.00232426,0.31928423],"study_design_scores_gemma":[0.000014634084,0.00012936642,0.014586524,0.00004643496,0.00006454109,0.0001223431,0.00004320931,0.9771828,0.00096330117,0.0060357666,0.00078999234,0.000021082931],"about_ca_topic_score_codex":0.0084331855,"about_ca_topic_score_gemma":0.005748289,"teacher_disagreement_score":0.0084331855,"about_ca_system_score_codex":0.00051572314,"about_ca_system_score_gemma":0.0009869467,"threshold_uncertainty_score":0.016768217},"labels":[],"label_agreement":null},{"id":"W2979103454","doi":"10.1109/iccchina.2019.8855897","title":"A High Accuracy Integrated Bagging-Fuzzy-GBDT Prediction Algorithm for Heart Disease Diagnosis","year":2019,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Boosting (machine learning); Fuzzy logic; Machine learning; Artificial intelligence; Heart disease; Computational intelligence; Data mining; Decision tree; Algorithm; Precision and recall; Medicine; Internal medicine","score_opus":0.09117491431252392,"score_gpt":0.4437618975627365,"score_spread":0.35258698325021254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979103454","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042204686,0.00062514725,0.9551746,0.00022467236,0.000115269446,0.000072496805,0.00009185367,0.00054941495,0.0009418516],"genre_scores_gemma":[0.68459195,0.00046608123,0.31135067,0.0002822201,0.00011449392,0.00018264819,0.0004253012,0.000044595392,0.0025420126],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992779,0.00009984717,0.00007477367,0.00016692003,0.00029179052,0.00008880304],"domain_scores_gemma":[0.99912363,0.00032823978,0.00006310569,0.000050597584,0.0003859033,0.000048532238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012515892,0.0007272831,0.0011971022,0.0011106478,0.0008234999,0.0008679516,0.0014442606,0.001080972,0.0009379221],"category_scores_gemma":[0.003062275,0.00033982995,0.0009120521,0.00096653594,0.00030014498,0.0010999888,0.0008480412,0.0009458101,0.00033096233],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028827798,0.000219709,0.007546695,0.000094273695,0.00012491392,0.0001776428,0.00014416744,0.44638538,0.0068874178,0.0034999382,0.0036323746,0.5309992],"study_design_scores_gemma":[0.000010478684,0.000028628656,0.00047763894,0.000005700771,0.00001685946,0.000035917077,0.000007359209,0.9974381,0.00073321623,0.00090863014,0.00032998537,0.00000733626],"about_ca_topic_score_codex":0.014208653,"about_ca_topic_score_gemma":0.011004086,"teacher_disagreement_score":0.014208653,"about_ca_system_score_codex":0.00084478647,"about_ca_system_score_gemma":0.0013008664,"threshold_uncertainty_score":0.028251886},"labels":[],"label_agreement":null},{"id":"W2979692716","doi":"10.12927/cjnl.2019.25964","title":"Big Data: Why Should Canadian Nurse Leaders Care?","year":2019,"lang":"en","type":"article","venue":"Nursing leadership","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Western University","funders":"","keywords":"Nursing; Nurse Administrator; Psychology; Health care; MEDLINE; Political science; Medicine","score_opus":0.7778908196865937,"score_gpt":0.5136869156546251,"score_spread":0.2642039040319686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979692716","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0091949385,0.005528872,0.0005204997,0.9624698,0.0031002748,0.000056676905,0.00061862555,0.000052753974,0.018457463],"genre_scores_gemma":[0.4639648,0.031969387,0.005597524,0.45346445,0.00446619,0.00027960056,0.0019556803,0.0003102497,0.03799202],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9884465,0.0024584814,0.0003870994,0.0009250305,0.0042579253,0.0035249519],"domain_scores_gemma":[0.9528743,0.0051876702,0.0019361065,0.0010517037,0.01725531,0.021694958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010622786,0.00046310216,0.0005580226,0.001961668,0.01856269,0.013874546,0.0029897557,0.004993743,0.011924552],"category_scores_gemma":[0.049463637,0.0004550215,0.000612322,0.005098437,0.008728535,0.0065452033,0.006343696,0.008381523,0.00173019],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013647157,0.00007377692,0.027880706,0.0006253265,0.000054371372,0.00058602425,0.01590076,0.00024865492,0.00022286734,0.03413599,0.79535943,0.12477572],"study_design_scores_gemma":[0.000120590084,0.00006984492,0.040382378,0.0029990196,0.000067630914,0.00028938628,0.09825092,0.0007457533,0.0002865408,0.033879098,0.8226591,0.0002497401],"about_ca_topic_score_codex":0.92423886,"about_ca_topic_score_gemma":0.9664873,"teacher_disagreement_score":0.9167368,"about_ca_system_score_codex":0.0832632,"about_ca_system_score_gemma":0.27570057,"threshold_uncertainty_score":0.60411966},"labels":[],"label_agreement":null},{"id":"W2980705747","doi":"10.1177/0272989x19879095","title":"Probabilistic Graphical Modeling for Estimating Risk of Coronary Artery Disease: Applications of a Flexible Machine-Learning Method","year":2019,"lang":"en","type":"article","venue":"Medical Decision Making","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Public Health Ontario; University of Toronto; University of Calgary","funders":"","keywords":"Machine learning; Bayesian network; Artificial intelligence; Coronary artery disease; Missing data; CAD; Computer science; Receiver operating characteristic; Probabilistic logic; Logistic regression; Risk assessment; Artificial neural network; Support vector machine; Medicine; Internal medicine; Engineering","score_opus":0.10613431735221995,"score_gpt":0.5019966610811613,"score_spread":0.3958623437289413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980705747","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038138595,0.00019529267,0.99529016,0.00018138105,0.000014995123,0.000023496808,0.000053022122,0.0001344024,0.00029328844],"genre_scores_gemma":[0.42230555,0.00094561774,0.5745377,0.00022878397,0.00015440592,0.00036309139,0.000364408,0.00010203564,0.0009983977],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969983,0.002007978,0.00012660048,0.00033454562,0.00044471837,0.000087889],"domain_scores_gemma":[0.98655486,0.011350486,0.00084425585,0.00057854,0.00051551097,0.00015637073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006414297,0.001023584,0.0010248413,0.0021075276,0.0005487611,0.0009991952,0.0016807794,0.0011732359,0.0015179862],"category_scores_gemma":[0.021580957,0.000737625,0.0015624468,0.001380078,0.0013322048,0.0014784836,0.0016370892,0.0018797724,0.00030575445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000379342,0.000034606044,0.0029097588,0.00006569567,0.000088053675,0.0000779194,0.00008130038,0.9162179,0.00037973924,0.0345636,0.0005699028,0.044973664],"study_design_scores_gemma":[0.000006975666,0.0000072254934,0.00023041906,0.000012849879,0.0000063701664,0.000020807267,0.00000388908,0.97748965,0.000055415185,0.021914944,0.000243557,0.000007898406],"about_ca_topic_score_codex":0.008831222,"about_ca_topic_score_gemma":0.0053865802,"teacher_disagreement_score":0.008831222,"about_ca_system_score_codex":0.0012205674,"about_ca_system_score_gemma":0.0011610483,"threshold_uncertainty_score":0.033922434},"labels":[],"label_agreement":null},{"id":"W2981121978","doi":"10.1186/s12902-019-0436-6","title":"Predictive models for diabetes mellitus using machine learning techniques","year":2019,"lang":"en","type":"article","venue":"BMC Endocrine Disorders","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":294,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University; Fields Institute for Research in Mathematical Sciences; University of Toronto; York University","funders":"Division of Mathematical Sciences; Natural Sciences and Engineering Research Council of Canada; Fields Institute for Research in Mathematical Sciences","keywords":"Logistic regression; Medicine; Decision tree; Diabetes mellitus; Random forest; Receiver operating characteristic; Machine learning; Artificial intelligence; Sensitivity (control systems); Body mass index; Predictive modelling; Decision tree model; Internal medicine; Statistics; Computer science; Mathematics; Endocrinology; Engineering","score_opus":0.09883913857235904,"score_gpt":0.43600004627983135,"score_spread":0.3371609077074723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981121978","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07006589,0.0024523034,0.91724294,0.001786698,0.0001783466,0.00026316775,0.0014699479,0.0033569413,0.0031838187],"genre_scores_gemma":[0.7889043,0.0020752442,0.20359291,0.00042806182,0.00028096253,0.000423036,0.0021471917,0.00011063585,0.0020376474],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99923587,0.00030659186,0.000055423534,0.00012570427,0.00020374941,0.00007270758],"domain_scores_gemma":[0.9938186,0.0050525814,0.00038813203,0.00014033502,0.00053181645,0.000068582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027611023,0.0013380088,0.0009897405,0.0029940614,0.0004696444,0.0012614484,0.0012011216,0.0007750294,0.001866194],"category_scores_gemma":[0.010911896,0.00035139272,0.0011057457,0.0017503893,0.00036977587,0.00084826705,0.00064895436,0.0017924366,0.0006894489],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012133798,0.00018466263,0.024248479,0.00018495659,0.00029996692,0.0002403017,0.00008982759,0.83256525,0.00037731073,0.0042271405,0.0041414546,0.13331926],"study_design_scores_gemma":[0.000009336032,0.000018774332,0.0010575515,0.000034458746,0.000037156206,0.000043003656,0.000015835634,0.99203026,0.00018218126,0.0058834334,0.0006784007,0.000009554113],"about_ca_topic_score_codex":0.026422067,"about_ca_topic_score_gemma":0.01429421,"teacher_disagreement_score":0.026422067,"about_ca_system_score_codex":0.0012658162,"about_ca_system_score_gemma":0.0015516639,"threshold_uncertainty_score":0.052536547},"labels":[],"label_agreement":null},{"id":"W2981521947","doi":"10.1038/s41597-019-0206-3","title":"A database for using machine learning and data mining techniques for coronary artery disease diagnosis","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":107,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Université du Québec à Montréal","funders":"","keywords":"Coronary artery disease; Computer science; Disease; Database; Artificial intelligence; Information retrieval; Medicine; Internal medicine","score_opus":0.40365149775140063,"score_gpt":0.5364813959138394,"score_spread":0.13282989816243873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981521947","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060756025,0.005208482,0.04531861,0.0012917422,0.00055427215,0.0010386026,0.9109825,0.018450595,0.011079582],"genre_scores_gemma":[0.01353913,0.0033531322,0.07228238,0.0007155453,0.00026414447,0.001248894,0.9051983,0.0009517363,0.002446703],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.994635,0.0008093518,0.0024661375,0.00066245307,0.0012454385,0.00018167181],"domain_scores_gemma":[0.9731609,0.009836222,0.004136905,0.0054460336,0.0055704103,0.0018494779],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042694667,0.0016115268,0.0021023874,0.01746431,0.0010741748,0.0042375973,0.0030226216,0.0019246322,0.019554254],"category_scores_gemma":[0.029260108,0.0007162143,0.0013054662,0.016613677,0.00041005327,0.004147949,0.0029596288,0.0019529818,0.017536106],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010529552,0.00046233786,0.016082054,0.005355937,0.00048739393,0.00074452243,0.000299118,0.0032151486,0.0045253253,0.011396864,0.7047892,0.2515892],"study_design_scores_gemma":[0.00043884257,0.00023300486,0.015580898,0.0011151579,0.00035036833,0.001148636,0.00025952925,0.006093452,0.004523474,0.012908207,0.95715624,0.00019222416],"about_ca_topic_score_codex":0.0040205186,"about_ca_topic_score_gemma":0.006017657,"teacher_disagreement_score":0.019554254,"about_ca_system_score_codex":0.00094199425,"about_ca_system_score_gemma":0.004167208,"threshold_uncertainty_score":0.0654155},"labels":[],"label_agreement":null},{"id":"W2990041205","doi":"10.1007/s12065-019-00327-1","title":"RETRACTED ARTICLE: Hybrid genetic algorithm and a fuzzy logic classifier for heart disease diagnosis","year":2019,"lang":"en","type":"article","venue":"Evolutionary Intelligence","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":407,"is_retracted":true,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Classifier (UML); Heart disease; Fuzzy logic; Artificial intelligence; Machine learning; Genetic algorithm; Feature selection; Disease; Rough set; Data mining; Pattern recognition (psychology); Medicine; Pathology","score_opus":0.0866876389067494,"score_gpt":0.4130774936949667,"score_spread":0.3263898547882173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990041205","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019226695,0.003751819,0.0061135422,0.2186483,0.7662819,0.000038401973,0.0006517179,0.00043989846,0.0021518578],"genre_scores_gemma":[0.038665593,0.0075819353,0.011517943,0.1867664,0.65482914,0.000097449556,0.0013334078,0.00052839174,0.09867973],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986161,0.00024335069,0.00026198503,0.0001901949,0.0005591115,0.0001292072],"domain_scores_gemma":[0.9885266,0.0047409507,0.00035019993,0.00041166885,0.005171948,0.00079861644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020715385,0.0007476813,0.0012886181,0.001612774,0.0012321186,0.0020927058,0.0021493102,0.009026932,0.01178084],"category_scores_gemma":[0.029327545,0.000370277,0.0011964024,0.0006763036,0.0012941775,0.0013951629,0.00092888257,0.0058189915,0.008620107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018829637,0.000049204948,0.00057571067,0.00018092197,0.00005745799,0.0027572038,0.00004888698,0.0002683446,0.00040063093,0.00069459423,0.95929193,0.035486918],"study_design_scores_gemma":[0.00018600251,0.00022499758,0.0044002295,0.0003455958,0.00023870122,0.010892071,0.00022214587,0.0061293347,0.0029197056,0.0055440958,0.9688136,0.00008365747],"about_ca_topic_score_codex":0.0054678195,"about_ca_topic_score_gemma":0.00797772,"teacher_disagreement_score":0.01178084,"about_ca_system_score_codex":0.0015264694,"about_ca_system_score_gemma":0.0015465403,"threshold_uncertainty_score":0.03941077},"labels":[],"label_agreement":null},{"id":"W2990291356","doi":"10.1007/s42452-019-1759-7","title":"A robust voting approach for diabetes prediction using traditional machine learning techniques","year":2019,"lang":"en","type":"article","venue":"SN Applied Sciences","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":47,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Khulna University; University of Engineering and Technology, Lahore","keywords":"Machine learning; Artificial intelligence; Naive Bayes classifier; Random forest; Computer science; Support vector machine; Artificial neural network; Voting; Classifier (UML); Boosting (machine learning); Data mining","score_opus":0.32519314910952574,"score_gpt":0.4232375905150691,"score_spread":0.09804444140554336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990291356","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03001061,0.0006388809,0.9668159,0.00023975152,0.00020663359,0.00008117123,0.00012564854,0.00067040685,0.0012110054],"genre_scores_gemma":[0.6034244,0.00034301478,0.38797936,0.00030767667,0.0003413067,0.00014156858,0.00074854435,0.00011247762,0.006601812],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983157,0.00045848032,0.0001365375,0.0004047869,0.00047649254,0.00020807276],"domain_scores_gemma":[0.99795073,0.0008928691,0.00010270007,0.00022848284,0.0007439107,0.00008133787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029611445,0.0006577489,0.0018607086,0.0011464199,0.0006900652,0.00102729,0.0027600203,0.0012901612,0.002409376],"category_scores_gemma":[0.004642617,0.00044415484,0.0011189508,0.0010398345,0.0003864799,0.0010508262,0.0011244682,0.001061169,0.00082006917],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075465895,0.00041257573,0.0043745697,0.000105854284,0.000331397,0.00013938855,0.00004827123,0.16911669,0.015455606,0.005763805,0.0051517086,0.7983455],"study_design_scores_gemma":[0.000019101264,0.00006230281,0.00052287756,0.0000050867116,0.00003973255,0.00003290487,0.0000080687705,0.99520135,0.0020160407,0.0014863879,0.00059795036,0.000008206731],"about_ca_topic_score_codex":0.005669341,"about_ca_topic_score_gemma":0.0074784607,"teacher_disagreement_score":0.005669341,"about_ca_system_score_codex":0.00046817004,"about_ca_system_score_gemma":0.0011341943,"threshold_uncertainty_score":0.015660226},"labels":[],"label_agreement":null},{"id":"W2990726790","doi":"10.1109/access.2019.2953920","title":"NE-nu-SVC: A New Nested Ensemble Clinical Decision Support System for Effective Diagnosis of Coronary Artery Disease","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":102,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Université du Québec à Montréal","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"CAD; Computer science; Support vector machine; Coronary artery disease; Artificial intelligence; Kernel (algebra); Machine learning; Algorithm; Pattern recognition (psychology); Medicine; Internal medicine; Mathematics","score_opus":0.20445339930139322,"score_gpt":0.5413087781162608,"score_spread":0.33685537881486755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990726790","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1283797,0.0011039674,0.86393845,0.00063390075,0.0002144474,0.00023662529,0.0007924916,0.0029262286,0.0017742084],"genre_scores_gemma":[0.78455186,0.00044236818,0.21182571,0.00034897143,0.00013216231,0.00022251309,0.0011120817,0.000058830694,0.0013055963],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992648,0.00019720843,0.000075678036,0.00015475848,0.00024320056,0.00006434421],"domain_scores_gemma":[0.998912,0.0004351175,0.000090843416,0.00009125282,0.00038337073,0.0000874628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018721439,0.0005547302,0.0011439768,0.0010939649,0.0004312846,0.00071483146,0.0010372249,0.0008325787,0.0010571757],"category_scores_gemma":[0.004499255,0.00020540097,0.0005874349,0.0006135172,0.00018101274,0.000870591,0.00085050013,0.00081237627,0.0003246503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00087658584,0.00059795275,0.020830648,0.000102429374,0.00035682885,0.00032019487,0.00012582749,0.20180285,0.006868202,0.0020047415,0.009112392,0.75700134],"study_design_scores_gemma":[0.00002050665,0.00013844397,0.0012087823,0.000010041816,0.000033358792,0.00009014695,0.000009561493,0.99568284,0.0010430042,0.00090712897,0.0008407978,0.00001546089],"about_ca_topic_score_codex":0.005828939,"about_ca_topic_score_gemma":0.006230612,"teacher_disagreement_score":0.005828939,"about_ca_system_score_codex":0.0005023712,"about_ca_system_score_gemma":0.0010318392,"threshold_uncertainty_score":0.011590064},"labels":[],"label_agreement":null},{"id":"W2991813872","doi":"10.1111/exsy.12485","title":"Hybrid particle swarm optimization for rule discovery in the diagnosis of coronary artery disease","year":2019,"lang":"en","type":"article","venue":"Expert Systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Particle swarm optimization; Computer science; CAD; Categorical variable; Set (abstract data type); Data mining; Rule-based system; Feature selection; Metaheuristic; Artificial intelligence; Algorithm; Mathematical optimization; Machine learning; Mathematics","score_opus":0.11739570015047476,"score_gpt":0.42817261360710035,"score_spread":0.3107769134566256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991813872","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.100817725,0.0009203738,0.8943041,0.0004610835,0.000110756635,0.0002176088,0.00016087141,0.0007050552,0.002302383],"genre_scores_gemma":[0.71758497,0.00029949454,0.2802541,0.00015749806,0.000043616626,0.00018220139,0.00030248353,0.00003223427,0.0011433455],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988696,0.00039101875,0.0001466007,0.00020935074,0.00030705085,0.00007635086],"domain_scores_gemma":[0.99646074,0.0025304283,0.0002166511,0.0001222266,0.00060644303,0.00006356278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025834353,0.0007226989,0.0015657932,0.001812356,0.0004888878,0.0012077206,0.0009772554,0.0010249263,0.0008788506],"category_scores_gemma":[0.005815045,0.00045474898,0.00093513855,0.00090988394,0.00046542418,0.00057086744,0.00047481895,0.00068160746,0.00018211447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002574138,0.00019759276,0.004972304,0.00016837698,0.00020460087,0.0002458036,0.000113876995,0.8583936,0.0027482137,0.0022302074,0.0011052721,0.1293627],"study_design_scores_gemma":[0.00001097123,0.000022043103,0.00033081483,0.00000592404,0.000011199691,0.000016147455,0.0000066204843,0.99871397,0.00043577512,0.0003238639,0.00011989115,0.0000028129195],"about_ca_topic_score_codex":0.011155307,"about_ca_topic_score_gemma":0.0047172876,"teacher_disagreement_score":0.011155307,"about_ca_system_score_codex":0.0007714759,"about_ca_system_score_gemma":0.0010098101,"threshold_uncertainty_score":0.022180736},"labels":[],"label_agreement":null},{"id":"W2991899257","doi":"10.1007/s12553-019-00396-3","title":"New hybrid method for heart disease diagnosis utilizing optimization algorithm in feature selection","year":2019,"lang":"en","type":"article","venue":"Health and Technology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":107,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Feature selection; Selection (genetic algorithm); Computer science; Feature (linguistics); Genetic algorithm; Heuristic; k-nearest neighbors algorithm; Data mining; Algorithm; Pattern recognition (psychology); Artificial intelligence; Optimization algorithm; Machine learning; Mathematical optimization; Mathematics","score_opus":0.062335902038009657,"score_gpt":0.46140930993918905,"score_spread":0.3990734079011794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991899257","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020104427,0.0005787201,0.9772076,0.00015320252,0.000080148726,0.00008134081,0.00005950453,0.00056281453,0.0011722189],"genre_scores_gemma":[0.5039496,0.0006225138,0.48905364,0.00021105465,0.0001785261,0.00047184704,0.0004601209,0.00009757788,0.00495509],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994467,0.00010157394,0.00004848505,0.00013072089,0.0002203036,0.00005222897],"domain_scores_gemma":[0.9996388,0.00013068393,0.000032228883,0.000018415869,0.00016427368,0.000015613596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007018419,0.0007415776,0.0013263078,0.0016183632,0.00046506632,0.0008252127,0.00088229903,0.0006571828,0.0019034395],"category_scores_gemma":[0.0010910035,0.00030845773,0.00091494137,0.0013999989,0.00023372365,0.0006278732,0.00047797276,0.00040885824,0.0003687977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002669542,0.00025050633,0.0045083985,0.00022109994,0.0002865011,0.00026300602,0.00011804328,0.28814343,0.020345816,0.003861658,0.0052599274,0.67647463],"study_design_scores_gemma":[0.000024958803,0.000055645254,0.0010578331,0.0000075643293,0.00002898833,0.000096970616,0.000012573854,0.9955836,0.0015355344,0.0006461475,0.00093987066,0.000010308406],"about_ca_topic_score_codex":0.0043747034,"about_ca_topic_score_gemma":0.0025615762,"teacher_disagreement_score":0.0043747034,"about_ca_system_score_codex":0.00039996902,"about_ca_system_score_gemma":0.0007327456,"threshold_uncertainty_score":0.008698523},"labels":[],"label_agreement":null},{"id":"W2992733197","doi":"10.1007/978-3-030-36778-7_53","title":"A Novel Effective Ensemble Model for Early Detection of Coronary Artery Disease","year":2019,"lang":"en","type":"book-chapter","venue":"Learning and analytics in intelligent systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Coronary artery disease; Cardiology; Medicine; Internal medicine; Computer science","score_opus":0.11383906074383944,"score_gpt":0.39792373010308496,"score_spread":0.28408466935924553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2992733197","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04020729,0.0019870147,0.953293,0.00047646186,0.0003331237,0.00003802228,0.00040768058,0.0009558782,0.0023015202],"genre_scores_gemma":[0.6897522,0.0018341356,0.29198,0.00064559357,0.0006838582,0.00017389831,0.0024432577,0.00017649049,0.012310523],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99968743,0.00006703241,0.000020452544,0.00008795008,0.000088028115,0.000049060112],"domain_scores_gemma":[0.99946934,0.00021194165,0.000024968838,0.00004885646,0.00022209005,0.000022809678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009681508,0.00074583635,0.0012090253,0.000681028,0.00042476677,0.000682591,0.0012419546,0.0010019991,0.001277239],"category_scores_gemma":[0.0014774955,0.00027150929,0.0007978532,0.0007244069,0.00018081574,0.0012375442,0.00073432055,0.0012168527,0.00066008465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019815438,0.0002703541,0.0037182306,0.000056898738,0.00028640992,0.00012099738,0.000062133244,0.34479988,0.0080197165,0.004557555,0.013350656,0.62455904],"study_design_scores_gemma":[0.0000023691682,0.000021829766,0.00038863774,0.000003191228,0.000025948397,0.000025537263,0.000003559787,0.99761766,0.00049597473,0.0009889973,0.00042129657,0.000004975573],"about_ca_topic_score_codex":0.006037267,"about_ca_topic_score_gemma":0.008039357,"teacher_disagreement_score":0.006037267,"about_ca_system_score_codex":0.0003337821,"about_ca_system_score_gemma":0.00059334835,"threshold_uncertainty_score":0.012004256},"labels":[],"label_agreement":null},{"id":"W2994036840","doi":"10.12688/f1000research.20498.1","title":"Evidence-based Clinical Decision Support Systems for the prediction and detection of three disease states in critical care: A systematic literature review","year":2019,"lang":"en","type":"preprint","venue":"F1000Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Rijksuniversiteit Groningen; Philips","keywords":"Open peer review; Plant biology; Disease; Medicine; Intensive care medicine; Physiology; Neuroscience; Computer science; Biology; Internal medicine","score_opus":0.49861987485475995,"score_gpt":0.6202115122777582,"score_spread":0.12159163742299822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994036840","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00090936606,0.99694103,0.0002928669,0.000464087,0.000105409665,0.0005955135,0.0003864584,0.000011217959,0.00029403978],"genre_scores_gemma":[0.018315814,0.9771962,0.001902551,0.0007933724,0.00011543891,0.0011819912,0.00039842,0.0000069402527,0.00008923678],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9847563,0.0058069206,0.0055775153,0.0008757771,0.0026556067,0.00032787098],"domain_scores_gemma":[0.89772356,0.0840682,0.009937537,0.0010011143,0.006627615,0.0006420496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014800071,0.0017386475,0.00783414,0.012777977,0.0010457459,0.0036270632,0.0025511442,0.0028313096,0.006154736],"category_scores_gemma":[0.09528052,0.001130899,0.010749315,0.0110889645,0.0010361726,0.003281077,0.0019488354,0.0021470012,0.00048460744],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023886393,0.00003959438,0.0010343686,0.93924326,0.007031477,0.00005785245,0.00019785942,0.00018334972,0.000051309205,0.00030621054,0.0013151745,0.050300617],"study_design_scores_gemma":[0.00022338785,0.00014362528,0.00225376,0.95578223,0.033673607,0.0001313212,0.00017594112,0.00017551713,0.000072866445,0.00031941818,0.007016011,0.000032324762],"about_ca_topic_score_codex":0.012297491,"about_ca_topic_score_gemma":0.03096955,"teacher_disagreement_score":0.014800071,"about_ca_system_score_codex":0.006747498,"about_ca_system_score_gemma":0.019458048,"threshold_uncertainty_score":0.07827121},"labels":[],"label_agreement":null},{"id":"W2995525717","doi":"10.3126/njh.v3i3.26048","title":"Factors Involved In First Myocardial Infarction, Its Complications And Thrombolytic Pattern In Selected Hospitals Of Nepal","year":2004,"lang":"en","type":"article","venue":"Nepalese Heart Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Epidemiological transition; Myocardial infarction; Medicine; Developing country; Epidemiology; Coronary heart disease; Quarter (Canadian coin); Life style; Disease; Medical emergency; Environmental health; Cardiology; Internal medicine; Economic growth; Geography","score_opus":0.14253067375485468,"score_gpt":0.4300198354520224,"score_spread":0.2874891616971677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995525717","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99873334,0.00013954799,0.000023711926,0.00009640494,0.0000025701975,0.000008051466,0.00031154134,0.0000023816233,0.00068243314],"genre_scores_gemma":[0.9991862,0.0001718811,0.000022121818,0.00005598771,0.000005946425,0.000010613344,0.00023970597,0.0000016019567,0.0003059303],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99977535,0.000040535113,0.0000318573,0.000043465934,0.00002474164,0.00008405722],"domain_scores_gemma":[0.9992107,0.00019573988,0.0002662265,0.000036275185,0.00007219096,0.0002188216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019109102,0.00017700842,0.00020453909,0.00079854723,0.000745393,0.0006667973,0.0003674846,0.00040941074,0.0032266253],"category_scores_gemma":[0.0013090295,0.00031160147,0.00036138517,0.00076820876,0.00035147832,0.000506291,0.0007536232,0.0006870715,0.00046059449],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057253226,0.000048894002,0.99758434,0.000015728476,0.000017178214,0.00034053324,0.0005725943,0.000034769975,0.000110092114,0.000033617627,0.00023892899,0.0009460664],"study_design_scores_gemma":[0.000005417515,0.0000854949,0.99625933,0.000013778624,0.000012868616,0.000662806,0.0025630144,0.0001071174,0.000043380787,0.000030764284,0.00020945365,0.00000654887],"about_ca_topic_score_codex":0.016121902,"about_ca_topic_score_gemma":0.02765174,"teacher_disagreement_score":0.016121902,"about_ca_system_score_codex":0.00052651495,"about_ca_system_score_gemma":0.0007555309,"threshold_uncertainty_score":0.032056093},"labels":[],"label_agreement":null},{"id":"W2996533187","doi":"10.1007/978-3-030-32587-9_7","title":"Prediction Model for Prevalence of Type-2 Diabetes Mellitus Complications Using Machine Learning Approach","year":2019,"lang":"en","type":"book-chapter","venue":"Studies in big data","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Type 2 Diabetes Mellitus; Diabetes mellitus; Medicine; Type 2 diabetes; Machine learning; Artificial intelligence; Computer science; Endocrinology","score_opus":0.7036060933300636,"score_gpt":0.5165066646733827,"score_spread":0.18709942865668094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996533187","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6298793,0.003374114,0.34462512,0.0024556636,0.00055287825,0.00014051254,0.007425893,0.0021428047,0.009403687],"genre_scores_gemma":[0.95852906,0.00069591124,0.029249363,0.00013714861,0.0001810873,0.000111191075,0.004400632,0.00003419993,0.0066615096],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99987733,0.000027615877,0.000010335699,0.00004456422,0.000017956821,0.000022112432],"domain_scores_gemma":[0.99937516,0.00043069347,0.00004186514,0.000024606623,0.00010763938,0.000020094145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005867341,0.0005204761,0.00051879283,0.00089356827,0.00021558405,0.0006414127,0.00078806723,0.0005808015,0.002736692],"category_scores_gemma":[0.0011603776,0.00018271958,0.0008865003,0.00057220587,0.00008911823,0.0004925069,0.00019706455,0.0006759578,0.0007249401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057935,0.0008466961,0.2349708,0.00021638602,0.0006819397,0.00045247155,0.00015097538,0.46243632,0.0016309773,0.0048258933,0.016955411,0.27625272],"study_design_scores_gemma":[0.000007948785,0.000042538126,0.012860037,0.000017827177,0.00006432738,0.00005877745,0.000027701211,0.98500305,0.00020469497,0.0013182097,0.00038637198,0.000008629534],"about_ca_topic_score_codex":0.011750292,"about_ca_topic_score_gemma":0.008335534,"teacher_disagreement_score":0.011750292,"about_ca_system_score_codex":0.0004031926,"about_ca_system_score_gemma":0.00042022837,"threshold_uncertainty_score":0.023363769},"labels":[],"label_agreement":null},{"id":"W2996712851","doi":"10.1016/j.jval.2019.09.2194","title":"PNS294 REVIEW OF ANALYTICAL METHODS FOR ANALYSIS OF PATIENT REPORTED OUTCOME (PRO) DATA IN THE PRESENCE OF CENSORING DUE TO DEATH","year":2019,"lang":"en","type":"article","venue":"Value in Health","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Eli Lilly (Canada)","funders":"","keywords":"Censoring (clinical trials); Interpretability; Computer science; Statistics; Continuation; Econometrics; Data mining; Mathematics; Machine learning","score_opus":0.6611683677528487,"score_gpt":0.6394010307986849,"score_spread":0.021767336954163774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996712851","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002399854,0.54901993,0.41012686,0.011772891,0.0040350826,0.0014780657,0.0091910595,0.00091243285,0.011063798],"genre_scores_gemma":[0.018354649,0.58212453,0.3656058,0.0072325785,0.0052699605,0.0038337589,0.009421978,0.0010619482,0.007094778],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.91427535,0.058436222,0.010078544,0.0040913513,0.0126892,0.0004293984],"domain_scores_gemma":[0.7666688,0.18770672,0.009435484,0.009360267,0.026080472,0.00074815104],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09765188,0.0019410951,0.0031878643,0.009586322,0.0008065231,0.0040405425,0.0037026817,0.0019581674,0.0088989055],"category_scores_gemma":[0.1997601,0.0013195637,0.0040887413,0.01048545,0.0023217725,0.0018521256,0.0023161299,0.0036692165,0.005541896],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037655988,0.00013662224,0.00925924,0.020432228,0.002172352,0.00023311368,0.0002805577,0.0014233303,0.00077011535,0.017293192,0.061206155,0.8864165],"study_design_scores_gemma":[0.000244942,0.0010052357,0.056635123,0.051778518,0.003299631,0.0036174234,0.0003907896,0.011339967,0.0053937524,0.04646923,0.81943184,0.00039343486],"about_ca_topic_score_codex":0.0062634232,"about_ca_topic_score_gemma":0.0069229174,"teacher_disagreement_score":0.9023481,"about_ca_system_score_codex":0.0024719317,"about_ca_system_score_gemma":0.009302776,"threshold_uncertainty_score":0.51643866},"labels":[],"label_agreement":null},{"id":"W2998144608","doi":"10.1002/ima.22391","title":"Bayesian inference framework for bounded generalized Gaussian‐based mixture model and its application to biomedical images classification","year":2019,"lang":"en","type":"article","venue":"International Journal of Imaging Systems and Technology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Frequentist inference; Computer science; Mixture model; Machine learning; Artificial intelligence; Inference; Bounded function; Bayesian inference; Bayesian probability; Model selection; Data mining; Pattern recognition (psychology); Mathematics","score_opus":0.05389594740538274,"score_gpt":0.44915667149324157,"score_spread":0.39526072408785884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998144608","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045093447,0.0003598554,0.99416286,0.00025384728,0.000019026964,0.000026803904,0.000044547265,0.00015145472,0.00047231687],"genre_scores_gemma":[0.51426303,0.0018902734,0.47675598,0.0005428789,0.0003575065,0.0004426308,0.00080602214,0.00016324208,0.0047784797],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99712676,0.00120418,0.00014674854,0.0005302124,0.0008056266,0.00018643208],"domain_scores_gemma":[0.9953886,0.0032988084,0.0003217415,0.00017638826,0.00070358574,0.00011088254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053043193,0.0008565256,0.0018760024,0.0024468482,0.0007957352,0.0018314134,0.0028946467,0.002349089,0.0022039698],"category_scores_gemma":[0.012227018,0.00076731684,0.001869689,0.00173794,0.001208128,0.0018502568,0.0015032478,0.0022370152,0.00065940974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017261931,0.0001241315,0.0019651265,0.00016883589,0.00017296999,0.00016665483,0.0002709901,0.78423953,0.0023820682,0.084383875,0.0025338505,0.12341937],"study_design_scores_gemma":[0.0000044803273,0.000006847795,0.00010961635,0.000006710072,0.000009529152,0.00001085621,0.00000417755,0.9921996,0.00012144513,0.007309339,0.00021077562,0.000006672002],"about_ca_topic_score_codex":0.01787293,"about_ca_topic_score_gemma":0.011638813,"teacher_disagreement_score":0.01787293,"about_ca_system_score_codex":0.0017747307,"about_ca_system_score_gemma":0.0017491591,"threshold_uncertainty_score":0.03553778},"labels":[],"label_agreement":null},{"id":"W2998499297","doi":"","title":"Comparative Analysis of Features Selection Techniques for Classification in Healthcare.","year":2019,"lang":"en","type":"article","venue":"Machine Learning and Data Mining in Pattern Recognition","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Purdue Pharma (Canada)","funders":"","keywords":"Computer science; Selection (genetic algorithm); Health care; Artificial intelligence","score_opus":0.24097415472717743,"score_gpt":0.5102778579546496,"score_spread":0.2693037032274722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998499297","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66372716,0.046790946,0.26763082,0.0024385157,0.0007280126,0.0005253929,0.0031840098,0.0015345712,0.013440628],"genre_scores_gemma":[0.89876366,0.00553502,0.090007335,0.00018962425,0.0002240638,0.00017529835,0.0025504287,0.00009934515,0.002455251],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99793744,0.0008104128,0.00020754414,0.00018172791,0.0007147437,0.00014808992],"domain_scores_gemma":[0.9906724,0.007227492,0.00028642657,0.00031470408,0.0013853136,0.00011371227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040309136,0.00053545507,0.0007996339,0.003130486,0.00033704372,0.00087938627,0.0005195707,0.00043686878,0.002464819],"category_scores_gemma":[0.010045177,0.000121381476,0.0010312451,0.0025164052,0.0001961127,0.00083783135,0.0004066409,0.0003503457,0.00064292626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023020867,0.00031390652,0.030230043,0.000515273,0.00057120225,0.00012844655,0.00015226821,0.010177203,0.005412211,0.0012075779,0.0065649017,0.942425],"study_design_scores_gemma":[0.0007029253,0.006802326,0.30397215,0.00070025236,0.0036130135,0.0023174293,0.0020833903,0.5916046,0.043725897,0.011101685,0.033189535,0.00018672514],"about_ca_topic_score_codex":0.0019296427,"about_ca_topic_score_gemma":0.002005259,"teacher_disagreement_score":0.0040309136,"about_ca_system_score_codex":0.00039082492,"about_ca_system_score_gemma":0.000554625,"threshold_uncertainty_score":0.02131778},"labels":[],"label_agreement":null},{"id":"W3000673289","doi":"10.1109/aiam48774.2019.00091","title":"Diagnosis of Female Diabetic Patients Based on Artificial Intelligence","year":2019,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Earl Haig Secondary School","funders":"","keywords":"Support vector machine; Diabetes mellitus; Logistic regression; Artificial intelligence; Machine learning; Computer science; Set (abstract data type); Test set; Medicine; Endocrinology","score_opus":0.15335153163328988,"score_gpt":0.449016864286625,"score_spread":0.29566533265333517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000673289","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82606804,0.0067730234,0.13830632,0.0036406917,0.00043674285,0.0004489523,0.002087004,0.0014884083,0.020750845],"genre_scores_gemma":[0.95687956,0.0016214667,0.038035925,0.00036037836,0.00015703382,0.000081945094,0.000977047,0.000016743055,0.0018699489],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925786,0.00019211462,0.00010304025,0.0001275389,0.0002542141,0.000065185355],"domain_scores_gemma":[0.99932015,0.0002800474,0.0000914944,0.00005264123,0.00021263411,0.000043022617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069437956,0.0004946506,0.00058649085,0.0025676787,0.00030699407,0.00085197145,0.00042885408,0.0005155612,0.0012114068],"category_scores_gemma":[0.003254347,0.00013910476,0.00062628306,0.0008874561,0.00014162579,0.000562019,0.00044596495,0.00040679675,0.000522687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069324154,0.00040228182,0.37244695,0.00035319323,0.00022624468,0.0016975523,0.00046338484,0.007191752,0.007632184,0.0013807776,0.008009864,0.59950256],"study_design_scores_gemma":[0.00019982836,0.0015006221,0.38059962,0.0005436166,0.0010285483,0.010859492,0.0023548128,0.55117303,0.022759113,0.009327884,0.019436473,0.00021692115],"about_ca_topic_score_codex":0.002036835,"about_ca_topic_score_gemma":0.0016635053,"teacher_disagreement_score":0.0025676787,"about_ca_system_score_codex":0.000286025,"about_ca_system_score_gemma":0.00033091687,"threshold_uncertainty_score":0.0040525794},"labels":[],"label_agreement":null},{"id":"W3002855918","doi":"10.1109/access.2020.2968608","title":"Handling Irregularly Sampled Longitudinal Data and Prognostic Modeling of Diabetes Using Machine Learning Technique","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Toronto; Toronto Metropolitan University","funders":"Prince Sultan University","keywords":"Computer science; Hidden Markov model; Machine learning; Artificial intelligence; Interval (graph theory); Polynomial; Data mining; Mathematics","score_opus":0.4917977887778538,"score_gpt":0.5114198097816329,"score_spread":0.019622021003779133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3002855918","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06271695,0.00033431454,0.9359686,0.00021429351,0.00004371356,0.00001682342,0.000101468846,0.00030464542,0.0002992575],"genre_scores_gemma":[0.8573465,0.00043959363,0.14093283,0.00008006999,0.00007814763,0.00005708021,0.00037519127,0.000021520276,0.000669051],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99954176,0.00013743422,0.00004932222,0.00011105525,0.00010929367,0.00005119727],"domain_scores_gemma":[0.9986198,0.00083668233,0.00018173324,0.00014812505,0.00017327997,0.0000402503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013697741,0.00033790033,0.00055403746,0.00076019997,0.0002832367,0.000509685,0.00067372806,0.00050552737,0.00048551994],"category_scores_gemma":[0.0041718944,0.00019537492,0.0005157332,0.00073299074,0.00025792033,0.00066144805,0.00055466517,0.0008681998,0.00012841518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001705519,0.00010015152,0.024824992,0.00008497845,0.00008378266,0.0002863736,0.00018899646,0.7691976,0.0042564543,0.0043007648,0.00083153613,0.19567384],"study_design_scores_gemma":[0.0000015334114,0.00000975694,0.00076955947,0.0000026323785,0.0000038140136,0.000018282613,0.0000070942306,0.99777967,0.00031728906,0.0009528518,0.00013450594,0.0000029742234],"about_ca_topic_score_codex":0.0058091707,"about_ca_topic_score_gemma":0.0033073938,"teacher_disagreement_score":0.0058091707,"about_ca_system_score_codex":0.00037020905,"about_ca_system_score_gemma":0.0006130969,"threshold_uncertainty_score":0.011550665},"labels":[],"label_agreement":null},{"id":"W3004527153","doi":"10.3389/fgene.2019.01076","title":"A Hybrid Approach for Modeling Type 2 Diabetes Mellitus Progression","year":2020,"lang":"en","type":"article","venue":"Frontiers in Genetics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Toronto; Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hidden Markov model; Computer science; Type 2 Diabetes Mellitus; Artificial intelligence; Imputation (statistics); Diabetes mellitus; Machine learning; Medicine; Missing data","score_opus":0.15395088779090452,"score_gpt":0.4237749285812237,"score_spread":0.2698240407903192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004527153","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062247854,0.0006373257,0.93409264,0.00033923198,0.000094162875,0.000044213542,0.00027260577,0.0004276528,0.001844252],"genre_scores_gemma":[0.863513,0.0005189964,0.12993646,0.00015125176,0.00008839112,0.0001452154,0.00052933436,0.00004373304,0.0050736587],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99970895,0.00008255589,0.000019458132,0.00009122753,0.00005992029,0.000037913374],"domain_scores_gemma":[0.99936694,0.00039564286,0.000062869876,0.000028760935,0.00010922913,0.000036570746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007244159,0.00042054872,0.0005936626,0.0006604494,0.0003494756,0.00081053836,0.0011412649,0.0009540683,0.0015812049],"category_scores_gemma":[0.0018388701,0.00034404473,0.0007660168,0.0005776057,0.00028617337,0.0004640493,0.00068998465,0.000857075,0.00029396106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000069884125,0.00003992375,0.0049305395,0.0000408759,0.00006302747,0.0000957711,0.000073761184,0.95088017,0.0008478832,0.003603945,0.00041096492,0.038943168],"study_design_scores_gemma":[0.0000015750659,0.0000062750487,0.0001804075,0.0000018071571,0.0000044652343,0.000007597771,0.0000024450906,0.999089,0.000049149185,0.00052398955,0.00013115001,0.0000020890086],"about_ca_topic_score_codex":0.020283505,"about_ca_topic_score_gemma":0.012032305,"teacher_disagreement_score":0.020283505,"about_ca_system_score_codex":0.000596197,"about_ca_system_score_gemma":0.0008192819,"threshold_uncertainty_score":0.040330887},"labels":[],"label_agreement":null},{"id":"W3005508070","doi":"10.2196/15431","title":"Ensemble Learning Models Based on Noninvasive Features for Type 2 Diabetes Screening: Model Development and Validation","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Department of Science and Technology of Liaoning Province; China Association for Science and Technology","keywords":"Machine learning; Random forest; Artificial intelligence; Computer science; Ensemble learning; Linear discriminant analysis; Test set; Cross-validation; Population; Support vector machine; Predictive modelling; Ensemble forecasting; Set (abstract data type); Data mining; Medicine","score_opus":0.25917691225500517,"score_gpt":0.450187147865009,"score_spread":0.19101023561000385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005508070","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59511733,0.0032348742,0.39543805,0.00086212775,0.00019588693,0.0003533276,0.0015695229,0.0010544893,0.0021743907],"genre_scores_gemma":[0.9113525,0.0008186362,0.0849426,0.00011736798,0.0000654182,0.00036874835,0.0015375633,0.00003947599,0.0007576174],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902856,0.00049846224,0.000069546426,0.00016692837,0.00015037578,0.0000860923],"domain_scores_gemma":[0.9932121,0.0047242986,0.00035941388,0.00042300866,0.0011538157,0.00012730977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067141014,0.0012810963,0.0015483857,0.0013590953,0.00049971795,0.00075301115,0.0012009575,0.0009994197,0.0008512509],"category_scores_gemma":[0.0094392495,0.000417,0.0015452553,0.0010238385,0.00024816405,0.00096225104,0.000860587,0.0019728728,0.0002775074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020171786,0.00021083154,0.019405292,0.00006371283,0.00029224117,0.00006059633,0.000049424416,0.9169026,0.00039455475,0.0005426618,0.0012540815,0.060622245],"study_design_scores_gemma":[0.000007917916,0.00004153751,0.0011895924,0.000011858981,0.000027044907,0.000008483601,0.000007939504,0.9980234,0.00017625945,0.0003999861,0.000099608624,0.000006492895],"about_ca_topic_score_codex":0.01603287,"about_ca_topic_score_gemma":0.009637684,"teacher_disagreement_score":0.01603287,"about_ca_system_score_codex":0.00090539816,"about_ca_system_score_gemma":0.0012181016,"threshold_uncertainty_score":0.035508037},"labels":[],"label_agreement":null},{"id":"W3008157143","doi":"10.1109/bigdata47090.2019.9005488","title":"Towards comparing and using Machine Learning techniques for detecting and predicting Heart Attack and Diseases","year":2019,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Random forest; Machine learning; Artificial intelligence; Logistic regression; Computer science; Heart disease; Naive Bayes classifier; Preprocessor; Bayesian network; Decision tree; Medical record; Disease; Data pre-processing; Data mining; Medical emergency; Medicine; Support vector machine; Internal medicine","score_opus":0.22602829012778408,"score_gpt":0.5031597853022041,"score_spread":0.27713149517442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008157143","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54737216,0.021931393,0.40616044,0.002895703,0.00097515335,0.001004884,0.0013046811,0.003559974,0.014795658],"genre_scores_gemma":[0.7169492,0.0042901477,0.27415225,0.0005097284,0.00025016785,0.00023318065,0.0015716386,0.00006813868,0.001975525],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98989606,0.004520652,0.0010200691,0.0016443947,0.002558354,0.0003605338],"domain_scores_gemma":[0.986678,0.00800051,0.0008265466,0.000962267,0.003298417,0.00023420001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012017661,0.0014080361,0.0012561447,0.0047354274,0.0005830564,0.003446469,0.0014499072,0.0021724417,0.0007126307],"category_scores_gemma":[0.019029552,0.00031557225,0.0013057902,0.0022868272,0.00046118055,0.0034828815,0.0009635873,0.001398824,0.0007233846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00097381196,0.0019428349,0.13849156,0.0010781193,0.0010934739,0.00027066216,0.0005545053,0.0580333,0.016894875,0.003282523,0.004450681,0.77293366],"study_design_scores_gemma":[0.00013436662,0.0029829293,0.0761935,0.0006863093,0.0010747951,0.0006323048,0.0017987301,0.86672425,0.028717846,0.007298399,0.013531159,0.0002253802],"about_ca_topic_score_codex":0.004309725,"about_ca_topic_score_gemma":0.0031737385,"teacher_disagreement_score":0.012017661,"about_ca_system_score_codex":0.0006805566,"about_ca_system_score_gemma":0.0009611575,"threshold_uncertainty_score":0.063556254},"labels":[],"label_agreement":null},{"id":"W3008453407","doi":"","title":"Use of decision tree analysis to determine optimal stratification groups to best identify true treatment effects in clinical research in traumatic spinal cord injury","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Surgery","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; Decision tree; Spinal cord injury; Stratification (seeds); Intensive care medicine; Spinal cord; Data mining; Psychiatry","score_opus":0.6979593772023645,"score_gpt":0.6227836662919456,"score_spread":0.07517571091041886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008453407","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49763665,0.0055464995,0.48377374,0.0040889815,0.0007439234,0.0030730525,0.0016531278,0.0006545858,0.0028295508],"genre_scores_gemma":[0.8022558,0.00047999056,0.1944331,0.00051332585,0.00012351217,0.0011683659,0.0007228499,0.000055874214,0.0002473236],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9388128,0.0536903,0.0032845575,0.0015395924,0.0020686502,0.0006040837],"domain_scores_gemma":[0.80596644,0.18041554,0.0044226656,0.0031586997,0.0045041186,0.0015326296],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06060358,0.0010231814,0.0025408294,0.0026204288,0.0010127452,0.002254271,0.00091408135,0.0011187147,0.0017757735],"category_scores_gemma":[0.12692118,0.000500163,0.003072925,0.0014190017,0.0006683223,0.001951914,0.0015692613,0.0024798173,0.00023067492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.028596021,0.0026099537,0.18023741,0.002797958,0.012937875,0.00052617566,0.0020868147,0.08999328,0.004244668,0.012534764,0.007846203,0.6555889],"study_design_scores_gemma":[0.006045382,0.009247119,0.058826104,0.0012581658,0.012467667,0.00049045944,0.0009313434,0.8055423,0.0052333437,0.09377551,0.005962636,0.0002199416],"about_ca_topic_score_codex":0.0017782071,"about_ca_topic_score_gemma":0.0028864215,"teacher_disagreement_score":0.93939644,"about_ca_system_score_codex":0.0010633927,"about_ca_system_score_gemma":0.0036309513,"threshold_uncertainty_score":0.32050616},"labels":[],"label_agreement":null},{"id":"W3008627481","doi":"10.1016/j.cmpb.2020.105400","title":"Decision tree-based diagnosis of coronary artery disease: CART model","year":2020,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":295,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Cart; CAD; C4.5 algorithm; Decision tree; Artificial intelligence; Machine learning; Coronary artery disease; Computer science; Sequential minimal optimization; Feature (linguistics); Artificial neural network; Naive Bayes classifier; Tree (set theory); Decision tree learning; Pattern recognition (psychology); Medicine; Support vector machine; Internal medicine; Mathematics","score_opus":0.3161493365175906,"score_gpt":0.524511393546613,"score_spread":0.20836205702902244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008627481","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18911946,0.009404312,0.78408825,0.0021432547,0.00060291257,0.00020300975,0.0040040235,0.0030479198,0.007386927],"genre_scores_gemma":[0.876727,0.003615402,0.11257359,0.0002765409,0.00028303437,0.00014124288,0.0020766053,0.00006767477,0.004238988],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99954504,0.00016933959,0.00003543057,0.000097381075,0.00010997531,0.000042827432],"domain_scores_gemma":[0.99899346,0.0006954235,0.000045981633,0.00003779335,0.00019367374,0.000033747147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011011972,0.000632183,0.0014192193,0.0016046697,0.00034712386,0.00089790387,0.00095467677,0.0008375722,0.0024299393],"category_scores_gemma":[0.002467834,0.00032932186,0.00094715145,0.0015918995,0.00018215651,0.00069751375,0.000274978,0.00084154867,0.0006889655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007455076,0.0003899665,0.014341874,0.00039441505,0.00067769573,0.00047005664,0.00007813729,0.5702359,0.0021118072,0.0032731746,0.010145737,0.3971356],"study_design_scores_gemma":[0.000028619632,0.00008355612,0.0018221369,0.000021673373,0.00011527115,0.00014134594,0.000008218224,0.9946089,0.00036624557,0.0020622346,0.00072892354,0.000012836751],"about_ca_topic_score_codex":0.016822034,"about_ca_topic_score_gemma":0.01068132,"teacher_disagreement_score":0.016822034,"about_ca_system_score_codex":0.0004895714,"about_ca_system_score_gemma":0.0009877873,"threshold_uncertainty_score":0.03344828},"labels":[],"label_agreement":null},{"id":"W3008968780","doi":"10.2196/16850","title":"Predicting the Development of Type 2 Diabetes in a Large Australian Cohort Using Machine-Learning Techniques: Longitudinal Survey Study","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"NSW Ministry of Health; University of Melbourne; Cancer Council NSW; National Natural Science Foundation of China; National Heart Foundation of Australia","keywords":"Medicine; Machine learning; Incidence (geometry); Type 2 diabetes; Diabetes mellitus; Cohort; Logistic regression; Population; Odds ratio; Artificial intelligence; Demography; Gerontology; Internal medicine; Computer science; Mathematics; Environmental health; Endocrinology","score_opus":0.22239346354902897,"score_gpt":0.48930766859624397,"score_spread":0.26691420504721497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008968780","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99937975,0.0000423411,0.00025362655,0.000060848146,0.0000023152854,0.000018507548,0.00012759934,0.000002305973,0.00011270239],"genre_scores_gemma":[0.99872357,0.0001327088,0.0006536419,0.00004714154,0.000005748259,0.000031042862,0.00019606581,0.0000015778629,0.00020848917],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99910396,0.00045475003,0.00006279732,0.00013754274,0.00016303973,0.00007795065],"domain_scores_gemma":[0.99834967,0.00027393294,0.0005004775,0.00025871515,0.00037781947,0.00023932903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024910765,0.00030439094,0.0003110826,0.0005450828,0.0005863922,0.0005836719,0.0004564771,0.00042172745,0.0004925773],"category_scores_gemma":[0.005007751,0.00045296265,0.0005789067,0.00080703665,0.000276415,0.00059065694,0.00084970985,0.0009891669,0.00019680579],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041399097,0.00008527618,0.99777883,0.0000071165045,0.0000420786,0.000052863114,0.00031648495,0.00006709382,0.00014990392,0.000015059004,0.00009057428,0.0013533479],"study_design_scores_gemma":[0.0000060108646,0.000083008454,0.9982699,0.000008288042,0.000025541583,0.00007985,0.00022023714,0.0011050719,0.000031424835,0.00003052846,0.00013558003,0.000004556878],"about_ca_topic_score_codex":0.050420757,"about_ca_topic_score_gemma":0.046556037,"teacher_disagreement_score":0.050420757,"about_ca_system_score_codex":0.00063632644,"about_ca_system_score_gemma":0.00069549587,"threshold_uncertainty_score":0.100254536},"labels":[],"label_agreement":null},{"id":"W3010096987","doi":"10.2196/17110","title":"Predicting Metabolic Syndrome With Machine Learning Models Using a Decision Tree Algorithm: Retrospective Cohort Study","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Science Council; National Science Foundation","keywords":"Metabolic syndrome; Machine learning; Logistic regression; Random forest; Decision tree; Artificial intelligence; Computer science; Multivariate statistics; Glycated hemoglobin; Receiver operating characteristic; Decision tree learning; Medicine; Algorithm; Internal medicine; Diabetes mellitus; Obesity","score_opus":0.11848722866795972,"score_gpt":0.4353079736208758,"score_spread":0.3168207449529161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010096987","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9982948,0.0000714882,0.0012150559,0.000019895773,0.000005877024,0.000043548585,0.00022791013,0.000008572527,0.000112971196],"genre_scores_gemma":[0.99811125,0.000076606324,0.0011750673,0.000011953158,0.0000089044015,0.000046164754,0.00042830734,0.000005022607,0.0001367249],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989077,0.000513637,0.000099400015,0.00020094527,0.00018011795,0.00009808806],"domain_scores_gemma":[0.9968136,0.0016294777,0.0004171873,0.0005084875,0.00039433947,0.00023686432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038755527,0.000475265,0.0004964238,0.0010667335,0.00043275088,0.0007600953,0.0004773699,0.00058704254,0.0011747796],"category_scores_gemma":[0.0071241767,0.0004666563,0.0008934896,0.0007386848,0.00023791821,0.0006733654,0.000399808,0.000890931,0.0003101397],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077646365,0.00046403866,0.99414283,0.000010365399,0.000119265605,0.00012801739,0.00008972041,0.0007382907,0.00014782454,0.000039300336,0.00014450448,0.003199408],"study_design_scores_gemma":[0.00032380127,0.0060481126,0.93270355,0.000045891386,0.0004898967,0.0011629537,0.00076206384,0.056632265,0.0006614649,0.00037375974,0.0007415912,0.000054663047],"about_ca_topic_score_codex":0.0039287177,"about_ca_topic_score_gemma":0.0024977694,"teacher_disagreement_score":0.0039287177,"about_ca_system_score_codex":0.00034254545,"about_ca_system_score_gemma":0.00043665268,"threshold_uncertainty_score":0.02049613},"labels":[],"label_agreement":null},{"id":"W3011137403","doi":"10.1016/s0735-1097(20)32673-5","title":"AN ENSEMBLE-BASED APPROACH TO THE DEVELOPMENT OF CLINICAL PREDICTION MODELS FOR FUTURE-ONSET HEART FAILURE AND CORONARY ARTERY DISEASE USING MACHINE LEARNING","year":2020,"lang":"en","type":"article","venue":"Journal of the American College of Cardiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Medicine; Coronary artery disease; Heart failure; Cardiology; Internal medicine; Disease; CAD; Machine learning; Artificial intelligence","score_opus":0.171941110156037,"score_gpt":0.4375726465766576,"score_spread":0.26563153642062065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011137403","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061602987,0.0013872738,0.93227774,0.00082122895,0.00022799245,0.00011121144,0.0005932464,0.0010701125,0.0019082195],"genre_scores_gemma":[0.70101434,0.0009161021,0.29244646,0.00034238337,0.0003521035,0.00025268528,0.0023060648,0.00010448369,0.0022654345],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889994,0.00045997745,0.00010941302,0.00021204504,0.00022616638,0.00009247877],"domain_scores_gemma":[0.9959596,0.002455406,0.00016107691,0.000238546,0.0010673774,0.00011800822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036541042,0.0008830657,0.001455011,0.0018249769,0.0005963097,0.0010879962,0.0013469394,0.0009558098,0.0013016093],"category_scores_gemma":[0.007776326,0.0004505902,0.001256786,0.0012495148,0.0001751203,0.0010916376,0.0008957249,0.0018438613,0.00043970605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020645351,0.0004051105,0.014823075,0.00007399785,0.00095044804,0.00024335703,0.00014363667,0.5393372,0.0016457906,0.0029991034,0.0062015816,0.43297026],"study_design_scores_gemma":[0.000005574275,0.00003001954,0.0006590209,0.000010006413,0.000053797005,0.000028232476,0.000010137177,0.9967181,0.00022650401,0.0018993863,0.0003523094,0.0000068836653],"about_ca_topic_score_codex":0.009144533,"about_ca_topic_score_gemma":0.01269445,"teacher_disagreement_score":0.009144533,"about_ca_system_score_codex":0.00055711064,"about_ca_system_score_gemma":0.0012083155,"threshold_uncertainty_score":0.019325018},"labels":[],"label_agreement":null},{"id":"W3011285191","doi":"10.1016/s0735-1097(20)34169-3","title":"ARTIFICIAL INTELLIGENCE-ENABLED ECG ALGORITHM FOR THE SCREENING OF DIABETES","year":2020,"lang":"en","type":"article","venue":"Journal of the American College of Cardiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Medicine; Diabetes mellitus; Artificial intelligence; Machine learning; Endocrinology","score_opus":0.13372979641561417,"score_gpt":0.41822949667190185,"score_spread":0.2844997002562877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011285191","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18374759,0.002569367,0.79752684,0.001514688,0.0004133623,0.0002278004,0.0010306515,0.004180698,0.008789011],"genre_scores_gemma":[0.68474597,0.00069095707,0.30923468,0.00046371517,0.00014168846,0.00010626052,0.00077388046,0.000050038252,0.0037927546],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998455,0.00003013896,0.000015171753,0.000042331674,0.000047701385,0.000019167337],"domain_scores_gemma":[0.9997329,0.0001238837,0.000014429351,0.000015618194,0.000096369266,0.00001678886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035393136,0.0003524618,0.00046699095,0.0008627648,0.00025378566,0.0005986611,0.00063200673,0.0006352863,0.0019990306],"category_scores_gemma":[0.0014877298,0.00011767837,0.00036873252,0.00040573484,0.00009604992,0.00025147674,0.0002852026,0.00050248706,0.0005496193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074625335,0.0006208977,0.016878985,0.00015294283,0.00017357207,0.0006735703,0.000050596773,0.092444524,0.0221333,0.0029521931,0.0076842653,0.85548884],"study_design_scores_gemma":[0.00006982366,0.00015954013,0.0059243543,0.000026395302,0.000078429795,0.00045428865,0.000014492124,0.9819381,0.00770276,0.001618492,0.0020014835,0.000011736706],"about_ca_topic_score_codex":0.003909327,"about_ca_topic_score_gemma":0.0053407857,"teacher_disagreement_score":0.003909327,"about_ca_system_score_codex":0.00030991418,"about_ca_system_score_gemma":0.00065470627,"threshold_uncertainty_score":0.0077731013},"labels":[],"label_agreement":null},{"id":"W3012071714","doi":"10.5220/0008857302950302","title":"Advanced Analytics to Predict Survivability of Breast Cancer Patients","year":2020,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Survivability; Computer science; Breast cancer; Analytics; Cancer; Medicine; Data science; Internal medicine; Computer network","score_opus":0.15591651943234813,"score_gpt":0.4872915018489559,"score_spread":0.3313749824166078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012071714","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9200303,0.0036412526,0.037143636,0.0062883324,0.0003773021,0.00023022073,0.019923031,0.0011459743,0.011219967],"genre_scores_gemma":[0.9846156,0.00047832326,0.006554407,0.00019343119,0.00011734253,0.000032756365,0.0072080814,0.000012758109,0.0007872849],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999466,0.00013201355,0.000057579742,0.000093794646,0.00016330736,0.00008733472],"domain_scores_gemma":[0.99717027,0.0016457787,0.0003999246,0.00015940874,0.00041869635,0.00020597411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072792935,0.00045218822,0.00040500605,0.0022302628,0.00021182577,0.0011497604,0.0003691588,0.00046030764,0.0020417967],"category_scores_gemma":[0.005759187,0.000099105746,0.0004865681,0.0012682842,0.000109254506,0.00071076385,0.0005910052,0.00077318854,0.0006661247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079742586,0.0008788792,0.7004468,0.00024455567,0.00034625106,0.00035321663,0.0002681496,0.033199787,0.0019513109,0.002808347,0.019978013,0.23872735],"study_design_scores_gemma":[0.00008489542,0.0009774511,0.2487244,0.00027909313,0.00032227847,0.0008298203,0.0014993866,0.7030673,0.004348748,0.024474086,0.015332305,0.00006017456],"about_ca_topic_score_codex":0.004609587,"about_ca_topic_score_gemma":0.005523405,"teacher_disagreement_score":0.004609587,"about_ca_system_score_codex":0.00037582498,"about_ca_system_score_gemma":0.00064325513,"threshold_uncertainty_score":0.009165525},"labels":[],"label_agreement":null},{"id":"W3012330081","doi":"10.1016/s0735-1097(20)34165-6","title":"COMPARISON OF MACHINE LEARNING (ML) METHODS WITH CONVENTIONAL STATISTICAL MODELS (CSM) FOR PREDICTION OF MORTALITY IN MYOCARDIAL INFARCTION (MI) PATIENTS","year":2020,"lang":"en","type":"article","venue":"Journal of the American College of Cardiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"","keywords":"Medicine; Logistic regression; Myocardial infarction; Proportional hazards model; Regression; Internal medicine; Cardiology; Regression analysis; Predictive modelling; Statistics","score_opus":0.18548375479796658,"score_gpt":0.496391547598259,"score_spread":0.3109077928002924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012330081","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87915087,0.0072052996,0.10726765,0.001692736,0.00057118374,0.00012537888,0.0011343951,0.00074055954,0.0021118873],"genre_scores_gemma":[0.9758671,0.0007811877,0.021875128,0.00016427277,0.00021317047,0.00005360135,0.00062550855,0.000038905284,0.00038123204],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99741036,0.0017529476,0.00019379717,0.00027108283,0.00029401918,0.00007781481],"domain_scores_gemma":[0.9679979,0.02865507,0.0007019057,0.0007067425,0.0015773627,0.00036103334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008302859,0.0007502718,0.00088098727,0.0013937565,0.00024329944,0.0009799224,0.00094438187,0.00087222963,0.0011702876],"category_scores_gemma":[0.022638708,0.0001588104,0.0008638905,0.00081620674,0.00026897553,0.0010787433,0.0006308336,0.0009982069,0.00025540424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.016841607,0.0024284862,0.25063002,0.0008009283,0.0026727975,0.0001743202,0.00028925986,0.22875227,0.0021091187,0.0030764006,0.0052972096,0.4869275],"study_design_scores_gemma":[0.00025145788,0.0016952395,0.027931986,0.000044550092,0.0002753207,0.00006750834,0.00010784654,0.9664815,0.0006444275,0.0020446626,0.00042681888,0.000028618817],"about_ca_topic_score_codex":0.0036830346,"about_ca_topic_score_gemma":0.0020062688,"teacher_disagreement_score":0.008302859,"about_ca_system_score_codex":0.00055687863,"about_ca_system_score_gemma":0.0009038036,"threshold_uncertainty_score":0.043910205},"labels":[],"label_agreement":null},{"id":"W3012427759","doi":"10.5220/0008986305140521","title":"A Framework for System-level Health Data Sharing","year":2020,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University; University of Ottawa","funders":"","keywords":"Computer science; Data sharing; Medicine","score_opus":0.8226170150406564,"score_gpt":0.620148697993804,"score_spread":0.20246831704685242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012427759","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"reproducibility","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"reproducibility","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014354046,0.00010741215,0.9906641,0.0005544448,0.000084253705,0.00024178615,0.00025595247,0.005024591,0.0016321064],"genre_scores_gemma":[0.09573553,0.00020270741,0.89742506,0.000551337,0.00012171293,0.00045024493,0.001803967,0.000757007,0.0029525317],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98708725,0.0039117136,0.0018287507,0.0021410154,0.0039087343,0.001122594],"domain_scores_gemma":[0.9834821,0.00436359,0.0007271024,0.007956888,0.0021711523,0.0012991157],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018686628,0.0009842236,0.0017978743,0.0029826376,0.0030022871,0.010696204,0.006575101,0.0032236332,0.0075587034],"category_scores_gemma":[0.025738114,0.0014970511,0.003514787,0.003583027,0.0029078159,0.012705434,0.014436226,0.004715356,0.0026919611],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005205456,0.00053851324,0.0046898057,0.00056747923,0.00062391884,0.000829737,0.0023091682,0.06140305,0.0073304563,0.6713482,0.029863236,0.21997586],"study_design_scores_gemma":[0.00011497705,0.00013897187,0.000627068,0.00018959149,0.00021404357,0.00039540196,0.00056834775,0.53610176,0.009974617,0.37133998,0.080197416,0.00013781898],"about_ca_topic_score_codex":0.010634846,"about_ca_topic_score_gemma":0.01166345,"teacher_disagreement_score":0.98131335,"about_ca_system_score_codex":0.0023266696,"about_ca_system_score_gemma":0.0066736178,"threshold_uncertainty_score":0.098825514},"labels":[],"label_agreement":null},{"id":"W3012647181","doi":"10.2196/18682","title":"Retracted: Artificial Intelligence–Based Neural Network for the Diagnosis of Diabetes: Model Development","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":20,"is_retracted":true,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial neural network; Computer science; Backpropagation; Artificial intelligence; MATLAB; Machine learning; Software; Data mining","score_opus":0.24578401157576052,"score_gpt":0.4595377435315387,"score_spread":0.21375373195577818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012647181","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02456105,0.008350342,0.85047644,0.045194548,0.027452532,0.00042630278,0.0019050202,0.007472752,0.034160946],"genre_scores_gemma":[0.35221824,0.00985878,0.4343181,0.008309565,0.0060797757,0.0007377628,0.0055328803,0.0017601636,0.18118471],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992605,0.00021457064,0.00006847227,0.00012582046,0.00027964663,0.000050890536],"domain_scores_gemma":[0.99553335,0.0011988186,0.00009886293,0.00032184785,0.0026961744,0.00015084115],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0022306032,0.00083081226,0.00049490266,0.00060693786,0.00048643758,0.0009860285,0.0023908892,0.0018307336,0.014382829],"category_scores_gemma":[0.010971233,0.00024873542,0.00072030927,0.0007399621,0.00040832933,0.002240705,0.0011887883,0.0023217758,0.005762363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000400146,0.00025523885,0.0075496975,0.0011935262,0.00016851701,0.0009674792,0.00045022977,0.13816777,0.004660856,0.03285514,0.28178096,0.53155047],"study_design_scores_gemma":[0.00008223359,0.00018813998,0.0019321471,0.00028479387,0.00011039652,0.00050464965,0.00014132944,0.79795045,0.008370578,0.016316023,0.17405057,0.0000687282],"about_ca_topic_score_codex":0.015432403,"about_ca_topic_score_gemma":0.011219053,"teacher_disagreement_score":0.99816924,"about_ca_system_score_codex":0.0010307805,"about_ca_system_score_gemma":0.0021818765,"threshold_uncertainty_score":0.048115373},"labels":[],"label_agreement":null},{"id":"W3012665221","doi":"10.1186/s12911-020-1023-5","title":"Machine learning can predict survival of patients with heart failure from serum creatinine and ejection fraction alone","year":2020,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":586,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Krembil Foundation","funders":"University of Toronto","keywords":"Ejection fraction; Machine learning; Heart failure; Artificial intelligence; Feature (linguistics); Medicine; Ranking (information retrieval); Biostatistics; Creatinine; Medical record; Computer science; Fraction (chemistry); Internal medicine; Epidemiology","score_opus":0.07284056263833034,"score_gpt":0.3966208104121537,"score_spread":0.32378024777382336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012665221","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9750416,0.0012308429,0.016816169,0.0009672447,0.00012088974,0.000058464528,0.0035648618,0.00035305094,0.0018468499],"genre_scores_gemma":[0.99283266,0.0001302105,0.0040866537,0.00006664723,0.000055626875,0.000020265594,0.0025780913,0.000009198146,0.00022060124],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992015,0.00026835327,0.00007017946,0.00015993556,0.00017277135,0.0001274208],"domain_scores_gemma":[0.992646,0.0050990856,0.0008481247,0.0004227172,0.00072188047,0.0002622914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023891258,0.0009931428,0.00052911823,0.002006181,0.00023252825,0.0006131308,0.00043492933,0.0006991416,0.0013150163],"category_scores_gemma":[0.008068675,0.00009163668,0.0010400896,0.0011549311,0.00021745524,0.00068612467,0.00041656458,0.0008775644,0.00067614723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077902287,0.0006304659,0.80925345,0.00010959675,0.00048491565,0.0001324796,0.00004410908,0.09238804,0.000868576,0.00025233938,0.0042725233,0.0907846],"study_design_scores_gemma":[0.000050323724,0.00079949293,0.33389527,0.000060920578,0.00020680635,0.00025854912,0.00013713825,0.6583733,0.0022253369,0.00247501,0.0014693801,0.000048465827],"about_ca_topic_score_codex":0.0033933292,"about_ca_topic_score_gemma":0.0036716335,"teacher_disagreement_score":0.0033933292,"about_ca_system_score_codex":0.00050703814,"about_ca_system_score_gemma":0.00063430134,"threshold_uncertainty_score":0.012635112},"labels":[],"label_agreement":null},{"id":"W3013783227","doi":"10.2196/17257","title":"Accurate Prediction of Coronary Heart Disease for Patients With Hypertension From Electronic Health Records With Big Data and Machine-Learning Methods: Model Development and Performance Evaluation","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Random forest; Machine learning; Logistic regression; Receiver operating characteristic; Medicine; Artificial intelligence; Test set; Population; Computer science; Big data; Ensemble learning; Statistics; Data mining; Mathematics","score_opus":0.2766216719624265,"score_gpt":0.45821037988245383,"score_spread":0.18158870792002735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013783227","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8422743,0.005549626,0.14647415,0.0015670003,0.00018630207,0.00037936962,0.0015045627,0.00068672263,0.0013780139],"genre_scores_gemma":[0.93869466,0.0012262708,0.05800927,0.00010751517,0.00009622562,0.00020329317,0.001441104,0.000017957582,0.00020360651],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99746823,0.001384601,0.00019168259,0.00034100996,0.00049710664,0.000117321266],"domain_scores_gemma":[0.9893154,0.0074147005,0.0008468904,0.0006774034,0.0015186435,0.00022698472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013313473,0.0010700938,0.0010122196,0.0019357714,0.00036784142,0.0012162356,0.0009780318,0.00085198117,0.0003731492],"category_scores_gemma":[0.016960066,0.00031403053,0.0009597291,0.0013494408,0.00033214103,0.001431796,0.00094953727,0.0012755096,0.00018431034],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012244153,0.0011058184,0.42315093,0.0004160146,0.0010605298,0.00018424237,0.00022588596,0.3054459,0.0021027026,0.0012009323,0.0034639644,0.2604188],"study_design_scores_gemma":[0.000037036738,0.00034742465,0.0351374,0.000050416384,0.000105264626,0.000056499273,0.00005489698,0.96164817,0.0013071267,0.0008961498,0.00033859338,0.000020953774],"about_ca_topic_score_codex":0.008127068,"about_ca_topic_score_gemma":0.006460269,"teacher_disagreement_score":0.013313473,"about_ca_system_score_codex":0.0009744569,"about_ca_system_score_gemma":0.0013909845,"threshold_uncertainty_score":0.07040924},"labels":[],"label_agreement":null},{"id":"W3014966784","doi":"10.12927/hcq.2020.26143","title":"Connecting Data to Value: An Operating Model for Healthcare Advanced Analytics","year":2020,"lang":"en","type":"article","venue":"Healthcare Quarterly","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Institute of Health Economics","funders":"","keywords":"Analytics; Health care; Best practice; Value (mathematics); Data analysis; Health administration; Data science; Business; Computer science; Knowledge management; Medicine; Nursing; Data mining; Public health; Political science; Management; Economics","score_opus":0.47045888731245733,"score_gpt":0.5499700089235304,"score_spread":0.0795111216110731,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014966784","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020002803,0.00052163075,0.86779475,0.022637738,0.00028243096,0.00042459575,0.0006071014,0.0015966431,0.08613235],"genre_scores_gemma":[0.5950904,0.0010017848,0.38445857,0.001772635,0.00047758373,0.0011368957,0.0009415215,0.0005330287,0.014587641],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99357295,0.0025045264,0.00042941072,0.0007918511,0.002110273,0.0005910958],"domain_scores_gemma":[0.99036247,0.004446866,0.0006319261,0.0017749091,0.001979969,0.00080372917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00842494,0.00093648134,0.000527355,0.0033162534,0.0021368677,0.016410282,0.0026637071,0.003206015,0.008944496],"category_scores_gemma":[0.019659283,0.0006436725,0.0015066176,0.0030434076,0.006684804,0.032865968,0.006244877,0.0043499237,0.0031914772],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024856074,0.00003221951,0.0009465556,0.00002784388,0.000012290504,0.000093224364,0.00048715723,0.004276995,0.00030787333,0.97922003,0.0027184177,0.011852471],"study_design_scores_gemma":[0.000024621122,0.0000599843,0.0004631549,0.0001517194,0.000022980072,0.0002424148,0.00076017214,0.10966184,0.000828252,0.8542581,0.03346863,0.000058230005],"about_ca_topic_score_codex":0.005272091,"about_ca_topic_score_gemma":0.0025435935,"teacher_disagreement_score":0.016410282,"about_ca_system_score_codex":0.0055885096,"about_ca_system_score_gemma":0.0065412447,"threshold_uncertainty_score":0.044555843},"labels":[],"label_agreement":null},{"id":"W3015088231","doi":"10.12927/hcq.2020.26144","title":"Connecting Data to Insight: A Pan-Canadian Study on AI in Healthcare","year":2020,"lang":"en","type":"article","venue":"Healthcare Quarterly","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Institute of Health Economics","funders":"","keywords":"Health care; Healthcare policy; Public healthcare; Healthcare system; Public relations; Analytics; Health administration; State (computer science); Business; Political science; Data science; Health policy; Health care reform; Computer science","score_opus":0.37351595012499783,"score_gpt":0.5149587173955668,"score_spread":0.14144276727056893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015088231","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9390119,0.0031061873,0.00038240585,0.0152646545,0.00008843064,0.000200947,0.0019637945,0.000024464205,0.039957203],"genre_scores_gemma":[0.9900041,0.002742778,0.00038200096,0.0021268919,0.000013921558,0.00004596308,0.0005381652,0.000029813942,0.004116375],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99315053,0.0012021435,0.00029257953,0.00048490943,0.002767526,0.002102376],"domain_scores_gemma":[0.975773,0.004923096,0.0022319062,0.0008384093,0.010815364,0.0054183397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0077902935,0.00034506744,0.00060373324,0.0030137284,0.015669333,0.008367846,0.0019448634,0.0009421339,0.0051615965],"category_scores_gemma":[0.025252968,0.0005687919,0.0005607067,0.012212135,0.0049939966,0.0031146517,0.004709836,0.0035225179,0.00035027243],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022889735,0.00029853245,0.4332051,0.0003245899,0.00011584365,0.00049637514,0.4977008,0.00022333751,0.00029854427,0.0093250275,0.018778544,0.03900443],"study_design_scores_gemma":[0.000018917846,0.00005485076,0.4175119,0.0004887968,0.000056791196,0.0001795281,0.5435079,0.00042241986,0.00009705128,0.00087304885,0.036689047,0.00009974582],"about_ca_topic_score_codex":0.9972626,"about_ca_topic_score_gemma":0.9984195,"teacher_disagreement_score":0.9031015,"about_ca_system_score_codex":0.096898496,"about_ca_system_score_gemma":0.19357772,"threshold_uncertainty_score":0.7030511},"labels":[],"label_agreement":null},{"id":"W3018351107","doi":"","title":"Data Mining Applications in Clinical Implementation and Healthcare: Highlights of Findings, Interventions, and Future Directions","year":2016,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Psychological intervention; Health care; Computer science; Data science; Medicine; Nursing; Political science","score_opus":0.43270027565508684,"score_gpt":0.632015997569195,"score_spread":0.19931572191410818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3018351107","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05398492,0.42727378,0.027237764,0.4692926,0.004980523,0.0017752886,0.0006724322,0.0003420146,0.0144407395],"genre_scores_gemma":[0.34486723,0.45381132,0.15161803,0.040192846,0.0034888666,0.0026180504,0.00054452807,0.00011165571,0.0027474822],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9713225,0.021431308,0.002442371,0.0010780044,0.002804634,0.000921108],"domain_scores_gemma":[0.8320531,0.12575293,0.0054352037,0.0056518037,0.025925875,0.0051811025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0744515,0.0010323599,0.0013080026,0.0018739563,0.0017378831,0.00956771,0.0036694256,0.002445154,0.0050017033],"category_scores_gemma":[0.10911528,0.00065182743,0.0014391252,0.004563817,0.0027348655,0.009833142,0.0033722138,0.0052873446,0.0005989636],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005832804,0.0014984338,0.035603635,0.012501062,0.00041814393,0.0001499598,0.0026445838,0.0005642365,0.0004884622,0.018928457,0.017088173,0.9095316],"study_design_scores_gemma":[0.0010832604,0.00422556,0.13875198,0.20383191,0.0031415776,0.0018549507,0.08991204,0.012780885,0.006544307,0.1597483,0.3775697,0.00055551564],"about_ca_topic_score_codex":0.008648388,"about_ca_topic_score_gemma":0.018791314,"teacher_disagreement_score":0.0744515,"about_ca_system_score_codex":0.0045688,"about_ca_system_score_gemma":0.025889376,"threshold_uncertainty_score":0.39374185},"labels":[],"label_agreement":null},{"id":"W3023324954","doi":"10.1210/jendso/bvaa046.1779","title":"MON-118 Reducing Unnecessary Repeat HbA1c Testing in a Tertiary Academic Hospital","year":2020,"lang":"en","type":"article","venue":"Journal of the Endocrine Society","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; Women's College Hospital; University of Toronto","funders":"","keywords":"Medicine; Reimbursement; Glycated hemoglobin; Quality management; Primary care; Test (biology); Internal medicine; Family medicine; Emergency medicine; Diabetes mellitus; Type 2 diabetes; Health care; Operations management","score_opus":0.12361642066499771,"score_gpt":0.4365607846466116,"score_spread":0.31294436398161385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023324954","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9759251,0.0007447905,0.0018833604,0.007823204,0.00010851922,0.0013256114,0.0011230883,0.0003645786,0.0107016675],"genre_scores_gemma":[0.99237615,0.00030596202,0.0036169346,0.0010804516,0.00003746665,0.00026343123,0.0005167036,0.000016644286,0.0017861932],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99728954,0.0008099122,0.00013156513,0.00016500201,0.0005319294,0.0010720644],"domain_scores_gemma":[0.9878846,0.00067769375,0.0013280842,0.00031779154,0.0018310886,0.007960799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028533847,0.0003498139,0.00032867418,0.00069466385,0.002274854,0.0014814389,0.0015925302,0.00054187805,0.007831994],"category_scores_gemma":[0.00671317,0.00031509815,0.00052473665,0.001484965,0.0008539842,0.00045172079,0.003312928,0.00075469905,0.0005087832],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022446972,0.0050471667,0.7134103,0.0014156627,0.00025982695,0.0012710062,0.005806608,0.0059614987,0.003231769,0.0020944828,0.06175803,0.19749898],"study_design_scores_gemma":[0.0007873338,0.0046020313,0.9426268,0.00049299415,0.00018721087,0.00030769134,0.010151549,0.014544911,0.0016127686,0.00070398144,0.023905227,0.00007759153],"about_ca_topic_score_codex":0.3614269,"about_ca_topic_score_gemma":0.60548526,"teacher_disagreement_score":0.3614269,"about_ca_system_score_codex":0.030200282,"about_ca_system_score_gemma":0.074004166,"threshold_uncertainty_score":0.7186463},"labels":[],"label_agreement":null},{"id":"W3023929243","doi":"10.5539/mas.v14n5p1","title":"A Novel Method for Computationally Efficacious Linear and Polynomial Regression Analytics of Big Data in Medicine","year":2020,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Wilcoxon signed-rank test; Linear regression; Regression analysis; Computer science; Cronbach's alpha; Statistics; Predictive analytics; Polynomial regression; Regression; Analytics; Data mining; Machine learning; Mathematics; Mann–Whitney U test","score_opus":0.4711831995778118,"score_gpt":0.5371393463959103,"score_spread":0.06595614681809853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023929243","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007634515,0.000038988357,0.9981964,0.000076967975,0.00003369338,0.000036890633,0.00003749574,0.00047938648,0.0003367014],"genre_scores_gemma":[0.031680923,0.00014181303,0.9646409,0.00013508489,0.000117684795,0.00030234954,0.00023111548,0.00039258113,0.0023575488],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981536,0.00049726845,0.00011730988,0.0003119365,0.0008303453,0.0000895596],"domain_scores_gemma":[0.99738675,0.0013033948,0.0002673147,0.0003740155,0.000542661,0.00012595707],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002293256,0.0010207872,0.0009423277,0.001182018,0.0005098991,0.0013053685,0.0016291304,0.0009229079,0.006823503],"category_scores_gemma":[0.008785784,0.00056467095,0.0015139277,0.0015407659,0.0007700451,0.0014190524,0.0024051573,0.0019448652,0.0024863367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029972094,0.00028713534,0.0021662808,0.00052417227,0.00019621944,0.00040578606,0.00027777572,0.1534392,0.024659706,0.065281786,0.017231144,0.735231],"study_design_scores_gemma":[0.000032068012,0.000069176866,0.00051961653,0.000021682274,0.00002095496,0.00017789612,0.00002609275,0.9697899,0.0037138616,0.015963458,0.009638505,0.000026810416],"about_ca_topic_score_codex":0.001615396,"about_ca_topic_score_gemma":0.0024347259,"teacher_disagreement_score":0.006823503,"about_ca_system_score_codex":0.00051605975,"about_ca_system_score_gemma":0.002099732,"threshold_uncertainty_score":0.02282691},"labels":[],"label_agreement":null},{"id":"W3033642885","doi":"10.2196/18963","title":"Predicting Current Glycated Hemoglobin Levels in Adults From Electronic Health Records: Validation of Multiple Logistic Regression Algorithm","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Logistic regression; Glycated hemoglobin; Population; Computer science; Medicine; Body mass index; Statistics; Predictive modelling; Diabetes mellitus; Data mining; Machine learning; Internal medicine; Type 2 diabetes; Mathematics; Environmental health","score_opus":0.15180431417957896,"score_gpt":0.46370086905059044,"score_spread":0.3118965548710115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033642885","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9495108,0.0009973843,0.04577997,0.00064383884,0.00010830337,0.00034282936,0.001109311,0.00052673405,0.0009807629],"genre_scores_gemma":[0.95191014,0.00042251887,0.045341596,0.000085612635,0.000044043813,0.0002448033,0.0015125191,0.00003126091,0.0004074498],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9943942,0.003461161,0.00049355644,0.00089373067,0.00055990246,0.00019747371],"domain_scores_gemma":[0.9722012,0.022116054,0.0011402939,0.0014661001,0.002761104,0.00031527897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023618205,0.0013811673,0.0009179627,0.0016462903,0.00045886304,0.0011126031,0.0020480033,0.0011073474,0.0009793829],"category_scores_gemma":[0.041593872,0.00038500823,0.001769085,0.0013023503,0.00039797986,0.0012720211,0.0012335542,0.0017487602,0.00048238927],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022252775,0.0026986,0.5595231,0.00049252535,0.001597595,0.0005368325,0.0004631044,0.23944269,0.0020175376,0.0008970734,0.0030885946,0.187017],"study_design_scores_gemma":[0.00013866095,0.00076183345,0.040593248,0.00008037541,0.00020754915,0.00013896344,0.0001625081,0.955296,0.0014899526,0.00053280295,0.00056837837,0.000029622679],"about_ca_topic_score_codex":0.013192711,"about_ca_topic_score_gemma":0.005935721,"teacher_disagreement_score":0.023618205,"about_ca_system_score_codex":0.0008351034,"about_ca_system_score_gemma":0.0019020776,"threshold_uncertainty_score":0.12490648},"labels":[],"label_agreement":null},{"id":"W3036927141","doi":"10.3233/shti200121","title":"Automatic Extraction of Risk Factors for Dialysis Patients from Clinical Notes Using Natural Language Processing Techniques","year":2020,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Dialysis; Dementia; Diabetes mellitus; Medicine; Electronic health record; Intensive care medicine; Health records; Natural language processing; Computer science; Artificial intelligence; Medical emergency; Psychiatry; Internal medicine; Disease; Health care","score_opus":0.24868230903548,"score_gpt":0.5618093797721642,"score_spread":0.31312707073668417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036927141","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24686041,0.004599027,0.63733757,0.004320969,0.0006506467,0.0034389566,0.06787819,0.02862362,0.006290529],"genre_scores_gemma":[0.2672174,0.0013613154,0.6962711,0.00044176672,0.00024829537,0.0006838306,0.03191954,0.0002812721,0.001575439],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870324,0.00030150486,0.00041838607,0.00028971885,0.0002367586,0.000050356346],"domain_scores_gemma":[0.98848444,0.008030184,0.001330411,0.0005105016,0.001487327,0.00015721137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016790815,0.0011358974,0.00062891823,0.004014287,0.00048750333,0.0015728164,0.000714481,0.00065287313,0.0021633757],"category_scores_gemma":[0.011343459,0.0004217037,0.00090938515,0.0016258523,0.00025806593,0.0011024678,0.00086316606,0.0009261624,0.0013559582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008548542,0.0004856426,0.038387842,0.0030434972,0.00025919394,0.0045034825,0.002087298,0.005651327,0.06179072,0.002727987,0.031838093,0.84837],"study_design_scores_gemma":[0.0009433537,0.0012102226,0.19363767,0.002462759,0.0019266651,0.013750649,0.0060432446,0.36195588,0.18473835,0.030984329,0.2014765,0.00087041303],"about_ca_topic_score_codex":0.0039219013,"about_ca_topic_score_gemma":0.004902955,"teacher_disagreement_score":0.004014287,"about_ca_system_score_codex":0.00057773065,"about_ca_system_score_gemma":0.002169089,"threshold_uncertainty_score":0.0088799},"labels":[],"label_agreement":null},{"id":"W3043877665","doi":"10.5210/ojphi.v12i1.10611","title":"Improving Accuracy for Diabetes Mellitus Prediction by Using Deepnet","year":2020,"lang":"en","type":"article","venue":"Online Journal of Public Health Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"King Abdullah International Medical Research Center","keywords":"Machine learning; Decision tree; Artificial intelligence; Logistic regression; Computer science; Diabetes mellitus; Christian ministry; Data mining; Medicine","score_opus":0.2982121040592978,"score_gpt":0.48432667586295236,"score_spread":0.18611457180365454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043877665","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8751139,0.0037179955,0.10370826,0.0018183689,0.0006521649,0.00011868302,0.0031135888,0.0038118067,0.0079451995],"genre_scores_gemma":[0.96434,0.00057202246,0.030218964,0.00018076439,0.00006893442,0.000029523895,0.0029169905,0.000030186819,0.0016426374],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994574,0.00012611257,0.000062539904,0.00012729118,0.00011972493,0.00010693017],"domain_scores_gemma":[0.9983253,0.00078445085,0.00013467579,0.00013894914,0.0005363354,0.000080238184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021486261,0.00075930613,0.00062724546,0.001460694,0.00033455182,0.0010708811,0.0007718321,0.0007316832,0.0013679139],"category_scores_gemma":[0.005292375,0.00021150953,0.0004948942,0.0008807221,0.0001510418,0.0011217486,0.000764201,0.0010199754,0.00058986904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011191017,0.0010001147,0.13183522,0.00023006521,0.00035552986,0.00034754584,0.00014889584,0.25367773,0.0044554984,0.0013937223,0.014296097,0.5911405],"study_design_scores_gemma":[0.00001770593,0.00008500402,0.006257857,0.00003407041,0.000037528844,0.000048221646,0.00005732702,0.98925066,0.0026322089,0.0006674862,0.00089885766,0.000013073701],"about_ca_topic_score_codex":0.023255948,"about_ca_topic_score_gemma":0.022915006,"teacher_disagreement_score":0.023255948,"about_ca_system_score_codex":0.0008879174,"about_ca_system_score_gemma":0.0012974809,"threshold_uncertainty_score":0.046241164},"labels":[],"label_agreement":null},{"id":"W3045763854","doi":"","title":"Classification of thalassemia data using K-nearest neighbor and Naïve Bayes","year":2019,"lang":"en","type":"article","venue":"International Journal of Advanced Science and Technology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Naive Bayes classifier; k-nearest neighbors algorithm; Thalassemia; Computer science; Pattern recognition (psychology); Bayes' theorem; Artificial intelligence; Bayesian probability; Medicine; Internal medicine; Support vector machine","score_opus":0.14109618468935964,"score_gpt":0.509615527891392,"score_spread":0.36851934320203233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045763854","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.797307,0.0025288304,0.18869667,0.00064390904,0.00041982517,0.0005934896,0.0045657116,0.0011778887,0.0040666545],"genre_scores_gemma":[0.9119676,0.0004910239,0.08170887,0.00008158078,0.00008303122,0.00016051659,0.004041979,0.000027640315,0.0014377971],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997924,0.0003920324,0.00046221836,0.00034360733,0.0006962244,0.00018194882],"domain_scores_gemma":[0.9962049,0.001962072,0.00027528295,0.0002658842,0.0011800808,0.00011180002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024034132,0.00051215733,0.0011507674,0.0026914428,0.00065724103,0.0013765732,0.0009611693,0.00083092984,0.0013747056],"category_scores_gemma":[0.0069692153,0.00021246557,0.00083324814,0.0014210497,0.00032506126,0.0009581668,0.00049908814,0.00065943896,0.0009033533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021700128,0.0012853952,0.22086579,0.00060773914,0.0003389016,0.00076871447,0.0006255764,0.039546926,0.008176358,0.0020607759,0.0068577626,0.7166961],"study_design_scores_gemma":[0.00011180166,0.00065070664,0.06485935,0.00024523723,0.00020567219,0.0013832238,0.0011675287,0.90814847,0.008116291,0.010021349,0.0049871528,0.00010324306],"about_ca_topic_score_codex":0.006646368,"about_ca_topic_score_gemma":0.0053368253,"teacher_disagreement_score":0.006646368,"about_ca_system_score_codex":0.00063784287,"about_ca_system_score_gemma":0.0008573941,"threshold_uncertainty_score":0.013215363},"labels":[],"label_agreement":null},{"id":"W3048210222","doi":"10.1109/jbhi.2020.3003767","title":"Guest Editorial: Blockchain and Healthcare Computing","year":2020,"lang":"en","type":"editorial","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Blockchain; Health care; Special section; Computer science; Data science; Big data; Field (mathematics); Focus (optics); Knowledge management; Computer security; Political science; Engineering; Data mining","score_opus":0.09646917646777255,"score_gpt":0.46357442951501066,"score_spread":0.3671052530472381,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048210222","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000037467125,0.0057542203,0.00017040534,0.0620505,0.930058,0.000017821178,0.000049471935,0.000049684797,0.0018123906],"genre_scores_gemma":[0.00045174215,0.004640197,0.000081203696,0.026927123,0.96014905,0.000022081631,0.000029195104,0.00003356403,0.0076658265],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9950295,0.0008886294,0.0005085732,0.00059093273,0.0025676538,0.00041466454],"domain_scores_gemma":[0.9812122,0.008385551,0.0009732582,0.00045067468,0.00598799,0.002990191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005993366,0.0029281182,0.0026227965,0.0025107672,0.0030798041,0.009400571,0.00282947,0.017705439,0.016267706],"category_scores_gemma":[0.023897203,0.00088958483,0.0021187428,0.0013216491,0.0027907079,0.0059187934,0.0019721282,0.02076093,0.013857776],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027024693,0.000008368994,0.00001509053,0.00010636543,0.00000806464,0.000076015946,0.00000759593,0.00002620005,0.000031882915,0.0005268788,0.99508566,0.004080819],"study_design_scores_gemma":[0.0000565432,0.000026987203,0.00012367874,0.00036403709,0.000021574058,0.0002157094,0.00002713169,0.00018393226,0.00010405362,0.0024430158,0.99641645,0.000016908141],"about_ca_topic_score_codex":0.001130459,"about_ca_topic_score_gemma":0.002334813,"teacher_disagreement_score":0.017705439,"about_ca_system_score_codex":0.0029139498,"about_ca_system_score_gemma":0.0033211128,"threshold_uncertainty_score":0.054420948},"labels":[],"label_agreement":null},{"id":"W3051585024","doi":"10.17577/ijertv9is080128","title":"Heart Disease Prediction using Machine Learning","year":2020,"lang":"en","type":"article","venue":"International Journal of Engineering Research and","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity College","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence","score_opus":0.31267876266446365,"score_gpt":0.5388033808490724,"score_spread":0.22612461818460877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3051585024","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6142549,0.012193464,0.32248738,0.005599359,0.0012905204,0.00058563566,0.021977935,0.0051697893,0.016441071],"genre_scores_gemma":[0.9441291,0.0019218238,0.041672148,0.000263846,0.0003742291,0.00013949847,0.00883489,0.000037098962,0.0026273855],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994437,0.00011739487,0.00006226363,0.00015261219,0.00014523079,0.00007874892],"domain_scores_gemma":[0.9986094,0.0007908879,0.00017806649,0.000082587634,0.00026467032,0.00007437272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001051733,0.0006175378,0.0008022499,0.0026275394,0.00030372507,0.0012127409,0.0005673046,0.0008471645,0.0024460475],"category_scores_gemma":[0.003553804,0.0001757707,0.0009682208,0.0015193976,0.0001405912,0.00070875156,0.00044224292,0.00089195545,0.0013777005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080787373,0.0011721851,0.34812048,0.0004588951,0.0006837383,0.0007869018,0.00009120533,0.15167435,0.002551583,0.001812229,0.020120692,0.4717199],"study_design_scores_gemma":[0.000053908574,0.0004432834,0.04823583,0.00017220728,0.0001717682,0.0005010823,0.00009357749,0.93649465,0.0025116445,0.00597286,0.005298981,0.000050158113],"about_ca_topic_score_codex":0.0056006755,"about_ca_topic_score_gemma":0.004330069,"teacher_disagreement_score":0.0056006755,"about_ca_system_score_codex":0.00041742518,"about_ca_system_score_gemma":0.00055314734,"threshold_uncertainty_score":0.011136115},"labels":[],"label_agreement":null},{"id":"W3088095465","doi":"10.1080/17517575.2020.1820583","title":"IoTPulse: machine learning-based enterprise health information system to predict alcohol addiction in Punjab (India) using IoT and fog computing","year":2020,"lang":"en","type":"article","venue":"Enterprise Information Systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Queen's University; Queen's University Belfast","keywords":"Computer science; Machine learning; Artificial intelligence; Internet of Things; Latency (audio); Fog computing; Quality of service; Real-time computing; Embedded system; Computer network; Telecommunications","score_opus":0.06636740252404123,"score_gpt":0.38254388270909384,"score_spread":0.3161764801850526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088095465","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82825786,0.0011870967,0.13160324,0.0018230397,0.0004118241,0.0005787243,0.0067658927,0.016841028,0.012531312],"genre_scores_gemma":[0.96083504,0.0003269037,0.03162357,0.0003463285,0.00005317282,0.000105865845,0.0037488327,0.00003625114,0.0029240788],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998622,0.000020174615,0.000016781361,0.000037273356,0.000037444403,0.000026153073],"domain_scores_gemma":[0.99980754,0.000058307345,0.000025104668,0.000026873313,0.000055329092,0.000026909294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003074501,0.0004507921,0.0004123114,0.0006383799,0.00027897465,0.00051956007,0.0005576796,0.00047441406,0.0009918824],"category_scores_gemma":[0.00048095512,0.00014852133,0.0003344112,0.00050293654,0.00013133301,0.0005302146,0.00053817534,0.00039464372,0.000399071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019464843,0.0026675952,0.30367407,0.0006619072,0.0006451217,0.0030981293,0.0005095717,0.09139916,0.044220798,0.0026642813,0.043312613,0.5052002],"study_design_scores_gemma":[0.00014564424,0.0011740432,0.16736132,0.00008838294,0.00025415272,0.0014914239,0.0005005936,0.77828354,0.032942425,0.0021137553,0.015527991,0.00011668618],"about_ca_topic_score_codex":0.007925462,"about_ca_topic_score_gemma":0.010292492,"teacher_disagreement_score":0.007925462,"about_ca_system_score_codex":0.0003799646,"about_ca_system_score_gemma":0.00051181595,"threshold_uncertainty_score":0.015758634},"labels":[],"label_agreement":null},{"id":"W3091047733","doi":"","title":"Oxford Royal College of General Practitioners Clinical Informatics Digital Hub: Rapid innovation to deliver extended COVID-19 surveillance and trial platforms.","year":2020,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Health informatics; Informatics; Medicine; Public health; Virology; Engineering; Nursing; Outbreak; Infectious disease (medical specialty)","score_opus":0.22238509842891027,"score_gpt":0.4789438805297842,"score_spread":0.2565587821008739,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091047733","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007772004,0.048185524,0.086610295,0.43471533,0.028901406,0.003210206,0.029498441,0.025808634,0.3352982],"genre_scores_gemma":[0.11437827,0.055730514,0.23452812,0.14202492,0.01865057,0.00508281,0.034968056,0.009520311,0.3851165],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9745195,0.010899506,0.003024035,0.0025555694,0.0074639013,0.0015374621],"domain_scores_gemma":[0.8315372,0.056037236,0.009661613,0.020483276,0.028329736,0.053950988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.043026816,0.0009049027,0.0014757975,0.0031192729,0.0010953409,0.008376844,0.0022126336,0.0043269983,0.14537829],"category_scores_gemma":[0.110908054,0.0016002975,0.0011745963,0.002091983,0.0019125202,0.0046427404,0.009069262,0.0072838003,0.055222444],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005096344,0.000087786306,0.0015670263,0.00096609246,0.000068876405,0.00024954768,0.0006201419,0.00019035059,0.0010068925,0.005935015,0.7121802,0.27661836],"study_design_scores_gemma":[0.00021743379,0.00018678118,0.0037928105,0.0011425253,0.000031585405,0.00018208119,0.00028068898,0.00027560804,0.00036513695,0.0030422774,0.99043256,0.000050467217],"about_ca_topic_score_codex":0.0077604447,"about_ca_topic_score_gemma":0.014645869,"teacher_disagreement_score":0.14537829,"about_ca_system_score_codex":0.0033292738,"about_ca_system_score_gemma":0.018389614,"threshold_uncertainty_score":0.48633885},"labels":[],"label_agreement":null},{"id":"W3092004869","doi":"10.1016/j.nic.2020.08.007","title":"Overview of Machine Learning Part 1","year":2020,"lang":"en","type":"review","venue":"Neuroimaging Clinics of North America","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Victoria Hospital; Jewish General Hospital; McGill University; Royal Victoria Regional Health Centre; University of Saskatchewan; McGill University Health Centre","funders":"Fondation de l'Association des radiologistes du Québec","keywords":"Medicine; Machine learning; Artificial intelligence; Software deployment; Data science; Computer science; Medical physics; Software engineering","score_opus":0.396401193866212,"score_gpt":0.5510356472860688,"score_spread":0.15463445341985682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092004869","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010239416,0.98806596,0.0017321458,0.0012005647,0.0012936116,0.000026943571,0.00011621228,0.000050397983,0.007411621],"genre_scores_gemma":[0.0013299051,0.98722595,0.0020518235,0.0014246241,0.002689584,0.0000489178,0.0002742566,0.000021039925,0.004933823],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99937457,0.00014192761,0.00009256895,0.00011142576,0.00023095551,0.000048478363],"domain_scores_gemma":[0.998528,0.00089126616,0.00012640608,0.000063705826,0.00031172275,0.00007879593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001130676,0.0014168237,0.0015338712,0.0040086024,0.00044315867,0.0021352465,0.0013223233,0.0021376486,0.018787876],"category_scores_gemma":[0.0024967492,0.0005461718,0.0010204576,0.0041349675,0.0010224666,0.0034224666,0.0010577983,0.0032949003,0.01206875],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043472322,0.000073374766,0.00023317696,0.015139647,0.00007955259,0.000113681366,0.00007536967,0.00081978197,0.00064017845,0.01842817,0.10885456,0.8554991],"study_design_scores_gemma":[0.0000049784403,0.00004655335,0.0004636613,0.0036519729,0.000025236306,0.00042501432,0.000023230159,0.00016425659,0.00013720697,0.007739493,0.9873022,0.00001633704],"about_ca_topic_score_codex":0.00155361,"about_ca_topic_score_gemma":0.0016468461,"teacher_disagreement_score":0.018787876,"about_ca_system_score_codex":0.0012686308,"about_ca_system_score_gemma":0.0019317452,"threshold_uncertainty_score":0.06285173},"labels":[],"label_agreement":null},{"id":"W3094057148","doi":"10.5260/chara.22.2.43","title":"ProQuest Coronavirus Research Database","year":2020,"lang":"en","type":"article","venue":"The Charleston Advisor","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Coronavirus; Pandemic; Coronavirus disease 2019 (COVID-19); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Medicine; Disease; Infectious disease (medical specialty)","score_opus":0.6790202496771239,"score_gpt":0.6015163348701325,"score_spread":0.07750391480699148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094057148","genre_codex":"dataset","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028081066,0.0024919112,0.003018536,0.0035349557,0.00044128392,0.00068451953,0.9323714,0.0060713505,0.048577957],"genre_scores_gemma":[0.006762321,0.0014208634,0.007527543,0.0020277137,0.00035090055,0.0009755617,0.96905804,0.0012193231,0.010657772],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974497,0.0005857759,0.00056820415,0.00045063935,0.00077436876,0.00017128613],"domain_scores_gemma":[0.98393875,0.005623022,0.0016007664,0.002041233,0.0049475213,0.0018487906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040839384,0.00080481224,0.0015665853,0.0059603173,0.0010070226,0.004280033,0.0026592074,0.0018896061,0.17019151],"category_scores_gemma":[0.021982795,0.0005243362,0.0009755553,0.005801358,0.0003094595,0.0030789168,0.00210561,0.0020198077,0.10592755],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042272027,0.00006791362,0.0016143381,0.0009360695,0.000043046424,0.00010006446,0.00005962263,0.00019671708,0.00038005513,0.0018990791,0.97424024,0.020040153],"study_design_scores_gemma":[0.00023774322,0.000063429674,0.0028299196,0.00032432578,0.00004885383,0.0002927171,0.00006315979,0.0006577363,0.00056693685,0.0039231395,0.9909508,0.000041138657],"about_ca_topic_score_codex":0.0024505742,"about_ca_topic_score_gemma":0.0031242885,"teacher_disagreement_score":0.17019151,"about_ca_system_score_codex":0.0010556254,"about_ca_system_score_gemma":0.003246519,"threshold_uncertainty_score":0.5693473},"labels":[],"label_agreement":null},{"id":"W3094177185","doi":"10.1109/icccnt49239.2020.9225548","title":"Risk Prediction Of Chronic Kidney Disease Using Machine Learning Algorithms","year":2020,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Random forest; Python (programming language); Kidney disease; Machine learning; Computer science; Demise; Algorithm; Artificial intelligence; Data set; Medicine; Internal medicine","score_opus":0.16945370695595038,"score_gpt":0.4485674794241015,"score_spread":0.27911377246815117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094177185","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35646525,0.0031590043,0.62256634,0.0017911226,0.00036646455,0.00028382437,0.003857452,0.006668618,0.004842003],"genre_scores_gemma":[0.8085281,0.000687102,0.18455665,0.00021906919,0.0001809481,0.0001658294,0.0035408447,0.00006530709,0.0020561963],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991598,0.00023097152,0.00012182353,0.00021573431,0.0001942258,0.00007735736],"domain_scores_gemma":[0.99753666,0.0015891553,0.00024324535,0.00010048177,0.00045832837,0.00007214785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016043816,0.00069277006,0.00084195414,0.0022927304,0.00038404376,0.0009159527,0.0005847678,0.0006673021,0.0012416514],"category_scores_gemma":[0.005472196,0.00023848006,0.0008652564,0.0012445629,0.00013853055,0.00067048596,0.0003939478,0.00094544335,0.00056784856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032762953,0.0006597956,0.1279294,0.00017655571,0.00033368514,0.0003741222,0.000099554585,0.4231918,0.0025724191,0.0015367195,0.009847092,0.4329512],"study_design_scores_gemma":[0.000008031763,0.000039745686,0.0064582042,0.00002443855,0.00001893357,0.00007364377,0.000017849452,0.9900664,0.00088659837,0.001707129,0.00068398105,0.000015036997],"about_ca_topic_score_codex":0.008883279,"about_ca_topic_score_gemma":0.006070584,"teacher_disagreement_score":0.008883279,"about_ca_system_score_codex":0.0005222694,"about_ca_system_score_gemma":0.0008557918,"threshold_uncertainty_score":0.017663121},"labels":[],"label_agreement":null},{"id":"W3094280923","doi":"10.18280/ria.340401","title":"Stratification of Cardiovascular Diseases Using Deep Learning","year":2020,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Ant colony optimization algorithms; Artificial intelligence; Artificial neural network; Backpropagation; Coronary artery disease; Computer science; Pericardial effusion; Magnetic resonance imaging; Fuzzy logic; Deep learning; Machine learning; Artificial bee colony algorithm; Medicine; Pattern recognition (psychology); Cardiology; Radiology","score_opus":0.20924764509241023,"score_gpt":0.42571276532938984,"score_spread":0.2164651202369796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094280923","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53342235,0.003993636,0.44803053,0.002253901,0.00024845658,0.0002531473,0.0028171197,0.0012256022,0.007755255],"genre_scores_gemma":[0.96280134,0.00056873134,0.031322096,0.00022394295,0.00007732991,0.00007707957,0.002000977,0.000018420193,0.0029101693],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998031,0.00004080993,0.000019288096,0.00004967845,0.000044517885,0.000042470434],"domain_scores_gemma":[0.99968994,0.00009946771,0.000039778,0.00002258996,0.00010646352,0.00004177394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005250458,0.00047646384,0.00043343313,0.001404815,0.0002240482,0.0006170233,0.0005589866,0.00060193025,0.0016467575],"category_scores_gemma":[0.0011999146,0.00017088956,0.00057140284,0.00055671704,0.000150446,0.00051036687,0.00064337254,0.00063617213,0.00044487117],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058015116,0.0007478904,0.14728023,0.0001644539,0.00038311435,0.00039943002,0.00012371418,0.21750432,0.0075242897,0.0029499494,0.010015528,0.6123269],"study_design_scores_gemma":[0.000013260894,0.0001036464,0.012088406,0.000032210133,0.000043147364,0.00011535156,0.000037542748,0.9813804,0.0014383594,0.0035592727,0.0011716485,0.000016682561],"about_ca_topic_score_codex":0.005448213,"about_ca_topic_score_gemma":0.006840888,"teacher_disagreement_score":0.005448213,"about_ca_system_score_codex":0.00049357326,"about_ca_system_score_gemma":0.0006368673,"threshold_uncertainty_score":0.010833025},"labels":[],"label_agreement":null},{"id":"W3095357888","doi":"10.1136/jech-2020-215752","title":"BIG DATA … small story","year":2020,"lang":"en","type":"article","venue":"Journal of Epidemiology & Community Health","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Public Health Agency of Canada; University of Ottawa","funders":"","keywords":"Big data; Phone; Data science; The Internet; Social media; Variety (cybernetics); Internet privacy; Computer science; Medicine; World Wide Web; Data mining; Artificial intelligence","score_opus":0.8555687588414942,"score_gpt":0.6065395226525537,"score_spread":0.24902923618894046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095357888","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012755663,0.045819476,0.004711476,0.7875812,0.060670592,0.00013195489,0.0010491366,0.0006296462,0.09813095],"genre_scores_gemma":[0.058991883,0.09785008,0.008392297,0.6451246,0.07854429,0.00055599766,0.0027346096,0.0012926754,0.1065136],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9798401,0.008013674,0.00084555533,0.0016498704,0.008484633,0.0011660842],"domain_scores_gemma":[0.96362996,0.020659715,0.0013929835,0.0041504614,0.0057498887,0.004417005],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01503515,0.0016845883,0.0011399161,0.0019214564,0.0068219546,0.02455619,0.003899387,0.012781845,0.028149413],"category_scores_gemma":[0.06761397,0.0007264415,0.0012409692,0.0035362795,0.010903551,0.036929063,0.012000286,0.020144492,0.014969062],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007634658,0.000030284582,0.0003499993,0.00050609227,0.000040473304,0.0003570212,0.0013480189,0.00010794826,0.00015880539,0.0889735,0.8613597,0.04669185],"study_design_scores_gemma":[0.000010599074,0.000019846655,0.00013445405,0.000368288,0.0000075337307,0.00018772711,0.00074012246,0.00011720828,0.000092698254,0.031740807,0.96656334,0.000017383218],"about_ca_topic_score_codex":0.0020601214,"about_ca_topic_score_gemma":0.0016542855,"teacher_disagreement_score":0.98496485,"about_ca_system_score_codex":0.0039858897,"about_ca_system_score_gemma":0.0053511024,"threshold_uncertainty_score":0.0941692},"labels":[],"label_agreement":null},{"id":"W3097271252","doi":"10.2196/19739","title":"An Application of Machine Learning to Etiological Diagnosis of Secondary Hypertension: Retrospective Study Using Electronic Medical Records","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Chinese Academy of Medical Sciences","keywords":"Medicine; Receiver operating characteristic; Secondary hypertension; Retrospective cohort study; Etiology; Logistic regression; Internal medicine; Medical record; Machine learning; Blood pressure; Artificial intelligence; Computer science","score_opus":0.10374124048727128,"score_gpt":0.4585823345414205,"score_spread":0.3548410940541492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097271252","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9971175,0.00052051473,0.00061626453,0.00007442156,0.000015457026,0.000062839375,0.0011696431,0.000005484229,0.00041785784],"genre_scores_gemma":[0.9982627,0.0001767834,0.00040091522,0.00003750256,0.000015161133,0.000049086015,0.0010027179,0.000002078414,0.000053050804],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9962149,0.000967788,0.00085467333,0.0006689564,0.0009870449,0.0003066679],"domain_scores_gemma":[0.99077034,0.0030560435,0.0035493178,0.00085985695,0.0013287672,0.00043566644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041566603,0.00031557196,0.00051636336,0.002590457,0.0005277311,0.0008526836,0.00058063545,0.00048457138,0.0008292438],"category_scores_gemma":[0.010962369,0.00034072888,0.0007549389,0.0029962028,0.00036820472,0.0009280695,0.0008761637,0.00067797303,0.00023963842],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026368722,0.000019295467,0.9988287,0.00002084104,0.000031064526,0.000054204986,0.000042150357,0.00003747665,0.000029376873,0.000013274485,0.00006668358,0.0008305441],"study_design_scores_gemma":[0.000008347893,0.00013314546,0.9957359,0.000052514635,0.00009201728,0.0007237195,0.00039406153,0.0020892853,0.00016872965,0.000053549524,0.0005397014,0.000009016073],"about_ca_topic_score_codex":0.003493906,"about_ca_topic_score_gemma":0.0036928689,"teacher_disagreement_score":0.0041566603,"about_ca_system_score_codex":0.00058878947,"about_ca_system_score_gemma":0.0009795369,"threshold_uncertainty_score":0.021982789},"labels":[],"label_agreement":null},{"id":"W3106944251","doi":"","title":"REVIEW AND ANALYSIS OF INDIAN ELECTRONIC HEALTH RECORD (EHR) SYSTEM ALONG WITH DENMARK, CANADA AND AUSTRALIA","year":2020,"lang":"en","type":"article","venue":"Journal of Natural Remedies","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cloud computing; Medical record; Business; Authentication (law); Health care; Health information technology; Health informatics; Government (linguistics); Electronic health record; Internet privacy; Computer science; Computer security; Medicine; Nursing; Public health; Political science","score_opus":0.0924228004207416,"score_gpt":0.42470483986879454,"score_spread":0.33228203944805296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3106944251","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041536014,0.9766138,0.0004179479,0.0054930933,0.00075651,0.000121493074,0.0018754433,0.000028464801,0.0105395345],"genre_scores_gemma":[0.024782404,0.969463,0.0009307082,0.0021222718,0.00022166435,0.000072336195,0.0009348848,0.000020338066,0.0014523363],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9936255,0.0008012536,0.0016076542,0.00038304855,0.00332114,0.00026146002],"domain_scores_gemma":[0.9416487,0.017391503,0.0057661375,0.0007568109,0.033148535,0.0012883416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005475225,0.00041095607,0.0010650738,0.02372951,0.0010641168,0.0027666076,0.0014224707,0.00067524606,0.0043448214],"category_scores_gemma":[0.027437728,0.0003610322,0.00133761,0.034156643,0.0010012038,0.0014397139,0.0009364314,0.00092680764,0.00060376374],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015589215,0.000071482435,0.022298843,0.1480836,0.0007545993,0.0008066961,0.0018942748,0.0004306572,0.00067240064,0.0063847667,0.10653133,0.71191543],"study_design_scores_gemma":[0.000014915732,0.00009379943,0.12298785,0.107471354,0.001870919,0.001518722,0.0019989172,0.00021333987,0.0005984063,0.0004035904,0.76274997,0.00007821421],"about_ca_topic_score_codex":0.28824475,"about_ca_topic_score_gemma":0.38264972,"teacher_disagreement_score":0.9885076,"about_ca_system_score_codex":0.01149237,"about_ca_system_score_gemma":0.037783872,"threshold_uncertainty_score":0.57313395},"labels":[],"label_agreement":null},{"id":"W3107153339","doi":"10.47964/1120.9091.18871","title":"AN LTE-M OPENTHREAD MESH NETWORK FOR DISTRIBUTED REAL-TIME STRUCTURAL HEALTH MONITORING OF CRITICAL INFRASTRUCTURE IN CANADA","year":2020,"lang":"en","type":"article","venue":"EURODYN ...","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Computer network; Critical infrastructure; Distributed computing; Computer security","score_opus":0.09000905926276903,"score_gpt":0.44933385849570745,"score_spread":0.3593247992329384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107153339","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.775327,0.00073663075,0.18867554,0.0021057618,0.00042690613,0.0006705919,0.002775647,0.007520164,0.021761764],"genre_scores_gemma":[0.97948486,0.000093843024,0.01646358,0.00010135863,0.000019572026,0.00008156194,0.0006958664,0.000030298428,0.003028962],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99965656,0.000058761387,0.000011171446,0.000055932076,0.00007993826,0.00013760528],"domain_scores_gemma":[0.9993863,0.00010239878,0.000030184905,0.000060168786,0.000287555,0.00013340577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063970516,0.0003445067,0.00035553824,0.00064436847,0.0010541154,0.0007170055,0.0011620302,0.00042115254,0.0026709882],"category_scores_gemma":[0.0013455118,0.00013855855,0.0002110317,0.00059791974,0.00036778583,0.0004720656,0.0012192624,0.0002833504,0.00040374298],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034131827,0.00057997165,0.048019454,0.00020280824,0.00014248096,0.00073926355,0.0010614451,0.41934377,0.032646675,0.011625949,0.091067515,0.39115754],"study_design_scores_gemma":[0.000099577315,0.0002713833,0.0121218115,0.00001637825,0.00004336058,0.000053178144,0.0006358439,0.9708685,0.0036430315,0.0013629622,0.0108475555,0.000036455403],"about_ca_topic_score_codex":0.36103004,"about_ca_topic_score_gemma":0.42491084,"teacher_disagreement_score":0.63896996,"about_ca_system_score_codex":0.0036172986,"about_ca_system_score_gemma":0.0032585878,"threshold_uncertainty_score":0.71785724},"labels":[],"label_agreement":null},{"id":"W3107632228","doi":"10.17504/protocols.io.spmedk6","title":"UK REF 2014 Analysis Data and R Script v1","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Data file; Raw data; Syntax; File format; Set (abstract data type); Programming language; Data set; Information retrieval; Natural language processing; Artificial intelligence","score_opus":0.4184746936605389,"score_gpt":0.5652060883358335,"score_spread":0.1467313946752946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107632228","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009533708,0.0001773354,0.02156761,0.0006326953,0.0003311387,0.0010334678,0.9210848,0.046059046,0.008160486],"genre_scores_gemma":[0.010429197,0.00030647003,0.09969307,0.0022438543,0.0002611723,0.017181832,0.7280483,0.10251028,0.03932579],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946144,0.0017916473,0.0007651983,0.0013835335,0.0011036841,0.00034144556],"domain_scores_gemma":[0.9740893,0.013241972,0.0016701279,0.0058899024,0.004388176,0.00072042743],"candidate_categories":["metaresearch","bibliometrics","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008416702,0.0019848938,0.002191205,0.0035892,0.0012753888,0.0038926643,0.002990926,0.001395969,0.47336173],"category_scores_gemma":[0.05691046,0.001881293,0.0018810029,0.0040589017,0.0011715234,0.0020728053,0.0032022824,0.0028496264,0.36013722],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029697904,0.000019927877,0.000798383,0.0009444069,0.000069684196,0.000050517854,0.000094837225,0.00034891808,0.00044815175,0.0018099337,0.9845031,0.010615104],"study_design_scores_gemma":[0.00044634414,0.00009530979,0.004600397,0.0006254967,0.00010580695,0.00016479996,0.00012944885,0.0011496545,0.0023958995,0.011668161,0.97848916,0.00012952517],"about_ca_topic_score_codex":0.0065333694,"about_ca_topic_score_gemma":0.009140386,"teacher_disagreement_score":0.9964108,"about_ca_system_score_codex":0.0015971959,"about_ca_system_score_gemma":0.0053539155,"threshold_uncertainty_score":0.75118554},"labels":[],"label_agreement":null},{"id":"W3108111691","doi":"10.18280/ria.340510","title":"A Deep Learning Method for Prediction of Cardiovascular Disease Using Convolutional Neural Network","year":2020,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Support vector machine; Artificial intelligence; Machine learning; Computer science; Naive Bayes classifier; Logistic regression; Artificial neural network; Deep learning; Disease; Heart disease; Bayes' theorem; Pattern recognition (psychology); Medicine; Bayesian probability; Pathology","score_opus":0.24900864140864157,"score_gpt":0.4351172495910777,"score_spread":0.18610860818243616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108111691","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14813532,0.004448626,0.8324273,0.0011273136,0.0006070594,0.00018043314,0.003350907,0.0053806235,0.0043423506],"genre_scores_gemma":[0.84226567,0.0016174613,0.14129406,0.00026747468,0.00016375586,0.00020230561,0.00471188,0.00010007226,0.009377308],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998286,0.000018435794,0.000015342885,0.00005227275,0.000049105704,0.000036145695],"domain_scores_gemma":[0.9997614,0.00006791153,0.000023394135,0.000017359032,0.00011311387,0.000016827007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053332443,0.00090461614,0.00054417254,0.0010273517,0.00032493577,0.00041469507,0.00090549875,0.00070105377,0.0016374454],"category_scores_gemma":[0.0009465754,0.00038170323,0.0006330567,0.00067924935,0.00014913511,0.00055308087,0.00043783497,0.0008885039,0.00053287524],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042041484,0.00041383988,0.01776349,0.00012035884,0.00023257414,0.00031033714,0.00004804412,0.3718532,0.008939338,0.0020993468,0.01576221,0.58203685],"study_design_scores_gemma":[0.000007195471,0.000020923795,0.0010783186,0.000007836171,0.000013704675,0.000025312867,0.000002891056,0.99674326,0.0011887058,0.00044699645,0.00045887538,0.00000601164],"about_ca_topic_score_codex":0.033484664,"about_ca_topic_score_gemma":0.030354133,"teacher_disagreement_score":0.033484664,"about_ca_system_score_codex":0.00079067744,"about_ca_system_score_gemma":0.0011042962,"threshold_uncertainty_score":0.06657952},"labels":[],"label_agreement":null},{"id":"W3108372494","doi":"10.1109/tem.2020.3024363","title":"Editorial: Special Section on Services Computing Management for Artificial Intelligence and Machine Learning","year":2020,"lang":"en","type":"editorial","venue":"IEEE Transactions on Engineering Management","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Taipei University of Technology; University of Ontario Institute of Technology; University of Washington","keywords":"Special section; Section (typography); Computer science; Engineering management; Artificial intelligence; Knowledge management; Engineering; Operating system","score_opus":0.052182627065336974,"score_gpt":0.35710873490935524,"score_spread":0.30492610784401825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108372494","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020255713,0.0022667137,0.00009633133,0.015874432,0.9799692,0.000018860264,0.000027374344,0.000048427944,0.0016783571],"genre_scores_gemma":[0.00016402044,0.0018378398,0.00006519238,0.007822612,0.98350406,0.000016220842,0.000022114566,0.000031062908,0.0065369257],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99418986,0.0006157386,0.00061489944,0.0007431739,0.0034065794,0.0004298335],"domain_scores_gemma":[0.9808997,0.005512532,0.001172094,0.0005343746,0.0077181174,0.0041632107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005507835,0.0045300764,0.0040455847,0.004744718,0.0043870993,0.011388532,0.0038019756,0.016678274,0.023929559],"category_scores_gemma":[0.01916176,0.0012943872,0.003603579,0.002075653,0.0031637992,0.0069128447,0.0019009735,0.019301767,0.024761563],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019951234,0.0000137114175,0.000019049821,0.00011560964,0.000007951331,0.000082201615,0.000008091866,0.00002192644,0.00004272522,0.00026439066,0.9953496,0.0040548523],"study_design_scores_gemma":[0.00003377863,0.000025737429,0.00016060649,0.0002800359,0.000022139726,0.00027030596,0.000029487912,0.000137633,0.00008424327,0.0009533859,0.9979868,0.000015890992],"about_ca_topic_score_codex":0.0014482216,"about_ca_topic_score_gemma":0.0043113152,"teacher_disagreement_score":0.023929559,"about_ca_system_score_codex":0.0037093738,"about_ca_system_score_gemma":0.0036915147,"threshold_uncertainty_score":0.080052376},"labels":[],"label_agreement":null},{"id":"W3118457748","doi":"10.21203/rs.3.rs-132385/v1","title":"Economic Evaluation of Remote Patient Monitoring System in Patients With Type 2 Diabetes","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Population; Type 2 diabetes; Diabetes mellitus; Quarter (Canadian coin); Health care; Emergency medicine; Medical emergency; Intensive care medicine; Environmental health; Geography","score_opus":0.3030091439683779,"score_gpt":0.5509304578491391,"score_spread":0.24792131388076116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118457748","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95567125,0.013528993,0.014098495,0.0023519835,0.00027631485,0.0015626594,0.0016701568,0.00004921954,0.010791002],"genre_scores_gemma":[0.9967179,0.001058112,0.0014565805,0.00007927806,0.000023031727,0.00015828985,0.00020562872,0.0000031225036,0.0002980091],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99082524,0.007577846,0.0002151189,0.0002852886,0.0006386738,0.0004578362],"domain_scores_gemma":[0.98512924,0.012374217,0.0010108878,0.00025895305,0.0007636326,0.000462978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009125387,0.0010189095,0.0014324561,0.0012788969,0.0003148087,0.0018937528,0.0009164211,0.0010835484,0.005353395],"category_scores_gemma":[0.020979617,0.0003270167,0.0031012031,0.001253674,0.00043526635,0.0013184487,0.001056553,0.0015575463,0.000117213596],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0257345,0.0042000012,0.06260952,0.0063837823,0.0064819134,0.0010661336,0.00020814537,0.77743405,0.001659001,0.014362764,0.0040594647,0.095800735],"study_design_scores_gemma":[0.004601853,0.022610694,0.07386216,0.0022721374,0.010925127,0.0010028572,0.0011769036,0.86473566,0.0032468894,0.009552754,0.0057627982,0.00025009044],"about_ca_topic_score_codex":0.0043808953,"about_ca_topic_score_gemma":0.0019680257,"teacher_disagreement_score":0.009125387,"about_ca_system_score_codex":0.0042076847,"about_ca_system_score_gemma":0.002362827,"threshold_uncertainty_score":0.048260212},"labels":[],"label_agreement":null},{"id":"W3120982506","doi":"10.1109/comnet47917.2020.9306071","title":"Diabetes Analytics and Recommendation Engine (DARE)","year":2020,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Context (archaeology); Computer science; Diabetes mellitus; Analytics; Architecture; Anomaly detection; Modular design; Data science; Medicine; Artificial intelligence","score_opus":0.24813304479851767,"score_gpt":0.47742745514180523,"score_spread":0.22929441034328757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120982506","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047893412,0.005678387,0.7489741,0.0044776923,0.0008576806,0.0017789013,0.030624507,0.13125886,0.028456531],"genre_scores_gemma":[0.3359236,0.0049590557,0.57837665,0.0036564267,0.00029742095,0.0005776872,0.055121277,0.0009777973,0.020110078],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990742,0.000113076334,0.00014560389,0.00020793478,0.0003791318,0.0000800382],"domain_scores_gemma":[0.99809664,0.00061970117,0.00012569201,0.0004319434,0.0005710068,0.00015503675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017143184,0.0008357363,0.0009955586,0.0023141748,0.00032247862,0.0015801317,0.0016782479,0.0011877782,0.0051511806],"category_scores_gemma":[0.0044266023,0.0004735538,0.00084000686,0.0016662587,0.00012890174,0.0012535021,0.0010039777,0.0014834646,0.0041039772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000936333,0.0012069946,0.03045407,0.0010048854,0.0008991849,0.00073080347,0.00021956638,0.021773301,0.012005012,0.010756852,0.10765581,0.8123572],"study_design_scores_gemma":[0.00041557764,0.00065899413,0.018864518,0.00034630927,0.00054333353,0.0016789205,0.00020119906,0.6789087,0.042211693,0.017382694,0.23848692,0.00030116833],"about_ca_topic_score_codex":0.0077971113,"about_ca_topic_score_gemma":0.010073045,"teacher_disagreement_score":0.0077971113,"about_ca_system_score_codex":0.00046076905,"about_ca_system_score_gemma":0.0008583602,"threshold_uncertainty_score":0.017232418},"labels":[],"label_agreement":null},{"id":"W3123604007","doi":"10.4018/ijeach.2021010101","title":"Prediction of Heart Cancer Data Using Hybrid Optimization and Machine Learning Techniques","year":2021,"lang":"en","type":"article","venue":"International Journal of Extreme Automation and Connectivity in Healthcare","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Overfitting; Particle swarm optimization; Computer science; Identification (biology); Artificial intelligence; Data set; Machine learning; Cancer; Set (abstract data type); Hybrid algorithm (constraint satisfaction); Data mining; Artificial neural network; Medicine","score_opus":0.3281206292536224,"score_gpt":0.47586000656531546,"score_spread":0.14773937731169307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123604007","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5559998,0.0013824092,0.43781132,0.0005182121,0.000083188344,0.00011974026,0.0007016356,0.0017000932,0.0016836053],"genre_scores_gemma":[0.92718446,0.00021822199,0.07068421,0.0000640988,0.000021820002,0.00010263327,0.0007682802,0.00004478122,0.00091152644],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996455,0.00012265772,0.000033796267,0.00009004511,0.00007083059,0.000037136637],"domain_scores_gemma":[0.9988568,0.00077234034,0.00010752856,0.0000553155,0.00017733756,0.000030716885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012846488,0.0008005099,0.0010303544,0.0012928761,0.00020947526,0.00075005984,0.00048753218,0.0008168879,0.0006340472],"category_scores_gemma":[0.0022081113,0.00028446506,0.0009572606,0.0008874468,0.00024472183,0.00042477786,0.0003717427,0.0005681628,0.00016368883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019876982,0.000117195144,0.0066351644,0.00006244247,0.00007602688,0.00008436823,0.000027744692,0.953459,0.0019696066,0.00030200175,0.00056125113,0.03650649],"study_design_scores_gemma":[0.0000028182735,0.000015159656,0.0007193221,0.0000016366027,0.0000030059678,0.0000060570796,0.0000039514166,0.99879104,0.00031748772,0.00010214804,0.000035108806,0.0000023214632],"about_ca_topic_score_codex":0.0075876215,"about_ca_topic_score_gemma":0.0034007344,"teacher_disagreement_score":0.0075876215,"about_ca_system_score_codex":0.00048569927,"about_ca_system_score_gemma":0.000586279,"threshold_uncertainty_score":0.015086889},"labels":[],"label_agreement":null},{"id":"W3123859422","doi":"10.18280/ria.340609","title":"Prediction of Brain Stroke Severity Using Machine Learning","year":2020,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":91,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Stroke (engine); Subarachnoid hemorrhage; Intracerebral hemorrhage; Medicine; Random forest; Machine learning; Predictive modelling; Ischemic stroke; Artificial intelligence; Computer science; Physical medicine and rehabilitation; Medical emergency; Cardiology; Internal medicine; Ischemia; Engineering","score_opus":0.273635845607109,"score_gpt":0.428870314001659,"score_spread":0.15523446839454996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123859422","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6526876,0.0054277196,0.325682,0.0019441092,0.00053276797,0.00033867068,0.004122499,0.0023769732,0.0068877474],"genre_scores_gemma":[0.96997976,0.0010740695,0.024959471,0.00010904545,0.00016783255,0.00007378821,0.0022070108,0.000017319835,0.0014117791],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99941576,0.00014503738,0.00007208474,0.00012476051,0.00017546344,0.00006693065],"domain_scores_gemma":[0.9984894,0.00087291043,0.0001715934,0.00007719421,0.00032840078,0.000060501396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011012644,0.0006286372,0.00062821584,0.002598564,0.00020766121,0.00079718605,0.00040743,0.0005447444,0.0010478916],"category_scores_gemma":[0.004443458,0.00014900774,0.0006921481,0.0012987624,0.00017010809,0.00070262625,0.00029311114,0.0007550544,0.0005132043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035980943,0.00054142234,0.21898119,0.00020947984,0.00032239748,0.0002846623,0.00008260847,0.25568318,0.0019371114,0.0011475172,0.006910502,0.5135401],"study_design_scores_gemma":[0.000011716142,0.00015431577,0.023279658,0.000033993078,0.00004836157,0.00011387585,0.000037150046,0.9716884,0.0010738067,0.002447589,0.0010893206,0.000021843174],"about_ca_topic_score_codex":0.0058648493,"about_ca_topic_score_gemma":0.004713586,"teacher_disagreement_score":0.0058648493,"about_ca_system_score_codex":0.00035046917,"about_ca_system_score_gemma":0.00058478786,"threshold_uncertainty_score":0.01166147},"labels":[],"label_agreement":null},{"id":"W3126212382","doi":"10.1504/ijeh.2020.10035568","title":"A causal model for type 2 diabetes and its comparison with other modelling methods","year":2020,"lang":"en","type":"article","venue":"International Journal of Electronic Healthcare","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Graphical model; Bayesian network; Logistic regression; Computer science; Probabilistic logic; Causal model; Machine learning; Type 2 diabetes; Artificial intelligence; Statistical model; Bayesian probability; Econometrics; Data mining; Diabetes mellitus; Mathematics; Statistics; Medicine","score_opus":0.3932977189982348,"score_gpt":0.5759837825025731,"score_spread":0.1826860635043383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126212382","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010437761,0.0021520003,0.9825248,0.0014810023,0.000119032506,0.0001137555,0.0012386687,0.00047512716,0.0014577953],"genre_scores_gemma":[0.39023998,0.0071760598,0.59143025,0.001023364,0.0005507225,0.00075191975,0.0053082393,0.00027408067,0.0032452836],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99653494,0.002169952,0.00016641518,0.00056309317,0.00048024362,0.00008523944],"domain_scores_gemma":[0.9822061,0.015600487,0.0007430101,0.0006267271,0.00063433975,0.00018920096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006960357,0.0010159885,0.00079073885,0.0032273557,0.00054071075,0.0014161107,0.0020468272,0.0013828968,0.0040371916],"category_scores_gemma":[0.025077883,0.0005060201,0.0021580379,0.003196631,0.0005313202,0.0025100806,0.0010485691,0.0019378997,0.00073165674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037773873,0.0003079041,0.02291034,0.0008276511,0.000953545,0.00033895136,0.00033410688,0.64043427,0.0005006447,0.11459219,0.007594646,0.21082804],"study_design_scores_gemma":[0.00004993527,0.000040236548,0.0018094787,0.00009577434,0.00012803364,0.00018049512,0.000034835684,0.91139776,0.000099991725,0.08141197,0.004723241,0.000028160692],"about_ca_topic_score_codex":0.013364036,"about_ca_topic_score_gemma":0.011960163,"teacher_disagreement_score":0.013364036,"about_ca_system_score_codex":0.0013171824,"about_ca_system_score_gemma":0.0020267032,"threshold_uncertainty_score":0.03681034},"labels":[],"label_agreement":null},{"id":"W3126552704","doi":"10.17762/pae.v58i2.1885","title":"COVID-19 and Diabetes Mellitus","year":2021,"lang":"en","type":"article","venue":"Psychology and Education Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Comorbidity; Diabetes mellitus; 2019-20 coronavirus outbreak; Quarter (Canadian coin); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Psychology; Pandemic; Gerontology; Obesity; Type 2 diabetes; Medicine; Disease; Psychiatry; Outbreak; Virology; History; Infectious disease (medical specialty); Pathology","score_opus":0.19780541180764274,"score_gpt":0.5708097302482882,"score_spread":0.3730043184406454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126552704","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17543796,0.4252111,0.0012518145,0.24091277,0.005984103,0.000111657006,0.0059662643,0.000076354336,0.14504796],"genre_scores_gemma":[0.7267886,0.22029765,0.0020415008,0.016514478,0.007858596,0.000082100116,0.0033174863,0.00002294719,0.023076653],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990269,0.000381389,0.00009436818,0.00013050284,0.00019225878,0.00017462426],"domain_scores_gemma":[0.99515885,0.0016473456,0.001502096,0.000121002915,0.000642763,0.00092787965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00109145,0.0002102717,0.00026245016,0.0010557093,0.00082974177,0.0020347135,0.00040148562,0.0009070794,0.020441191],"category_scores_gemma":[0.004741571,0.00013733657,0.0006044141,0.0021323753,0.00049623364,0.0006946483,0.0009071901,0.0018019464,0.0012523553],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010621401,0.0003263205,0.6499145,0.001985594,0.00040628505,0.0022848684,0.0010360174,0.00027848658,0.0002595929,0.019353485,0.098034196,0.2250585],"study_design_scores_gemma":[0.00006237232,0.00027448504,0.78281087,0.0038712528,0.00045337528,0.005145498,0.0027929605,0.0005069052,0.00023446692,0.015190519,0.18859556,0.00006182552],"about_ca_topic_score_codex":0.013400174,"about_ca_topic_score_gemma":0.012491759,"teacher_disagreement_score":0.020441191,"about_ca_system_score_codex":0.0010324061,"about_ca_system_score_gemma":0.0013594093,"threshold_uncertainty_score":0.06838262},"labels":[],"label_agreement":null},{"id":"W3129619312","doi":"10.1109/access.2021.3059343","title":"Detection and Prediction of Diabetes Using Data Mining: A Comprehensive Review","year":2021,"lang":"en","type":"review","venue":"IEEE Access","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":108,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Diabetes mellitus; Computer science; Predictive modelling; Field (mathematics); Data mining; Glycemic; Machine learning; Domain (mathematical analysis); Diabetes management; Artificial intelligence; Data science; Medicine; Type 2 diabetes","score_opus":0.7197744249508764,"score_gpt":0.61216332414228,"score_spread":0.10761110080859637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129619312","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002842428,0.9972373,0.0010841369,0.00060244766,0.00015625938,0.00001637663,0.00006984934,0.000019558602,0.00052983296],"genre_scores_gemma":[0.0018643114,0.99583215,0.0016041724,0.00025988647,0.00018630033,0.000017404866,0.000105924206,0.000003906961,0.00012590237],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9991393,0.00018886948,0.00018289666,0.00014312254,0.00030626944,0.00003946431],"domain_scores_gemma":[0.99567056,0.0030390539,0.00033189927,0.00007678375,0.00079093664,0.00009075526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022070664,0.00088500086,0.0015188082,0.0036768527,0.00025507255,0.0011613369,0.0013516537,0.0010379589,0.0013413612],"category_scores_gemma":[0.0053164046,0.00035496405,0.0013433901,0.0041762292,0.00033213056,0.0014385517,0.00064810144,0.0012926494,0.00081662403],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006137933,0.000088965695,0.0014380686,0.017167551,0.0002794451,0.000092214344,0.00005669319,0.00069573167,0.0004055207,0.0018837056,0.012636331,0.9651944],"study_design_scores_gemma":[0.00004590416,0.00054462365,0.008968877,0.043883152,0.0019643472,0.0027037817,0.0003224755,0.0037020422,0.0020705499,0.010187945,0.9254521,0.00015416912],"about_ca_topic_score_codex":0.0020174216,"about_ca_topic_score_gemma":0.0021173218,"teacher_disagreement_score":0.0036768527,"about_ca_system_score_codex":0.00059900834,"about_ca_system_score_gemma":0.001682458,"threshold_uncertainty_score":0.011672258},"labels":[],"label_agreement":null},{"id":"W3130588842","doi":"10.1016/j.matpr.2020.12.079","title":"WITHDRAWN: Improving the accuracy of heart attack risk prediction based on information gain feature selection technique","year":2021,"lang":"en","type":"article","venue":"Materials Today Proceedings","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":24,"is_retracted":true,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Feature selection; Random forest; Support vector machine; Naive Bayes classifier; Computer science; Artificial intelligence; Information gain ratio; Machine learning; Decision tree; Logistic regression; Feature (linguistics); Information gain; Redundancy (engineering); Predictive modelling; Data mining; Pattern recognition (psychology)","score_opus":0.041042785177698236,"score_gpt":0.3733155511004604,"score_spread":0.33227276592276217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3130588842","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21688738,0.041936018,0.07877058,0.1761442,0.29397413,0.0016619036,0.069270864,0.013908082,0.107446834],"genre_scores_gemma":[0.5913783,0.012426107,0.044591427,0.021509567,0.044888936,0.00042371426,0.034554314,0.001104862,0.24912278],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993585,0.000089226014,0.00007118251,0.000082576466,0.00034486887,0.000053596068],"domain_scores_gemma":[0.99555075,0.0009303206,0.0001373789,0.00021789412,0.0029531794,0.00021044393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010987028,0.0005564423,0.000726129,0.0009676947,0.0004883547,0.00092226453,0.00090429466,0.0010742735,0.039325196],"category_scores_gemma":[0.00831198,0.00015527125,0.0006110126,0.0008201939,0.00025260763,0.0006157341,0.00032145833,0.0010159266,0.012252471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023620683,0.00020133566,0.005357841,0.0008265451,0.00016980698,0.0005666612,0.000056258363,0.0012686757,0.013076352,0.0014920452,0.5994856,0.37513694],"study_design_scores_gemma":[0.0030134525,0.0031886569,0.13145202,0.0008557056,0.0012220514,0.0034469217,0.0004264866,0.08047262,0.10654246,0.009941976,0.6590821,0.00035555736],"about_ca_topic_score_codex":0.0060268543,"about_ca_topic_score_gemma":0.00654831,"teacher_disagreement_score":0.039325196,"about_ca_system_score_codex":0.000482466,"about_ca_system_score_gemma":0.001065964,"threshold_uncertainty_score":0.13155591},"labels":[],"label_agreement":null},{"id":"W3134235683","doi":"10.1016/j.cjca.2021.03.003","title":"Machine Learning, Predictive Analytics, and the Emperor's New Clothes: Why Artificial Intelligence Has Not Yet Replaced Conventional Approaches","year":2021,"lang":"en","type":"letter","venue":"Canadian Journal of Cardiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Calgary","funders":"","keywords":"Medicine; Scopus; Big data; Analytics; Precision medicine; Artificial intelligence; Predictive analytics; MEDLINE; Machine learning; Data science; Computer science; Data mining; Pathology","score_opus":0.28494094693898747,"score_gpt":0.3769469177029889,"score_spread":0.09200597076400141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134235683","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009763793,0.00076092075,0.0000671548,0.9964329,0.0018600995,0.0000015691446,0.0000095463465,0.0000041595267,0.0007659922],"genre_scores_gemma":[0.0037550281,0.001828447,0.0004906708,0.97179484,0.01762394,0.000016170248,0.000011230816,0.000018288792,0.004461356],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9905759,0.0029939294,0.0008809989,0.0010934715,0.003665349,0.00079020445],"domain_scores_gemma":[0.93652874,0.04890136,0.0015814656,0.0010815505,0.0069321627,0.0049747955],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014364609,0.0006215397,0.001464018,0.0009131847,0.0053561814,0.008916173,0.0020710316,0.05916601,0.006267137],"category_scores_gemma":[0.052722845,0.0006182949,0.0009713794,0.0009878987,0.01116012,0.011811935,0.0026493287,0.06938917,0.0033499955],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049116326,0.000056710956,0.00077020464,0.00007075072,0.000014888313,0.00058128923,0.0004863097,0.000088525565,0.00012187147,0.023940876,0.9522858,0.021533586],"study_design_scores_gemma":[0.00009512133,0.000050845923,0.0011566787,0.00065257546,0.000017391907,0.0009242469,0.0019749478,0.0013959793,0.0001395023,0.08358635,0.90991545,0.000090953006],"about_ca_topic_score_codex":0.021371685,"about_ca_topic_score_gemma":0.042106476,"teacher_disagreement_score":0.9856354,"about_ca_system_score_codex":0.0057239146,"about_ca_system_score_gemma":0.010933531,"threshold_uncertainty_score":0.075968266},"labels":[],"label_agreement":null},{"id":"W3134332400","doi":"10.29337/ijdh.24","title":"Digital Health, Big Data and Connectivity: 5G and Beyond for Patient-Centred Care","year":2021,"lang":"en","type":"article","venue":"International Journal of Digital Health","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Big data; Digital health; Health care; Data science; Computer science; Psychology; Political science; Data mining","score_opus":0.1846319181436164,"score_gpt":0.46019321696863497,"score_spread":0.27556129882501856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134332400","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038327717,0.8178304,0.017363783,0.10922754,0.007624488,0.000053806085,0.00022798179,0.00015010744,0.043689135],"genre_scores_gemma":[0.06808675,0.87908685,0.010422402,0.023809686,0.012740393,0.00006244678,0.00014869495,0.000033830263,0.005608899],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987588,0.00054984033,0.0000762686,0.00011103568,0.0003964799,0.000107576896],"domain_scores_gemma":[0.99679416,0.0022621239,0.00018259828,0.00012269571,0.00042121124,0.0002171067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001937979,0.00040448093,0.00047469678,0.0015401343,0.00058089674,0.0035607796,0.00060289464,0.0023370353,0.005016268],"category_scores_gemma":[0.002749342,0.00015436558,0.0005595034,0.0018241735,0.0018376056,0.004590206,0.0020522166,0.0030036587,0.00081822474],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009120717,0.000052011717,0.001549587,0.005467548,0.0001007836,0.00042915152,0.00067371613,0.0019166915,0.0018320333,0.38680577,0.08948186,0.51159966],"study_design_scores_gemma":[0.000008305608,0.000087211,0.0016417927,0.0060536694,0.000049034068,0.00082635495,0.0009042092,0.0020927705,0.000582637,0.12331194,0.86439466,0.000047411413],"about_ca_topic_score_codex":0.0013438648,"about_ca_topic_score_gemma":0.0013960606,"teacher_disagreement_score":0.005016268,"about_ca_system_score_codex":0.0013278319,"about_ca_system_score_gemma":0.0016551205,"threshold_uncertainty_score":0.016781092},"labels":[],"label_agreement":null},{"id":"W3137300000","doi":"10.1109/confluence51648.2021.9377174","title":"Organ Risk Prediction for Parkinson’s Disease using Deep Learning Techniques","year":2021,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Machine learning; Computer science; Artificial neural network; Deep learning; Disease; Perceptron; Parkinson's disease; Construct (python library); Medical diagnosis; Data science; Medicine; Pathology","score_opus":0.14454644583917717,"score_gpt":0.47841227125040214,"score_spread":0.333865825411225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137300000","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6518399,0.0017589096,0.33967003,0.002223905,0.00013329463,0.00007248209,0.0012548644,0.0006529351,0.002393663],"genre_scores_gemma":[0.9822751,0.0002200096,0.01607517,0.00010295056,0.0000301987,0.000021414127,0.0005392567,0.000010669649,0.0007252113],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997284,0.00007265725,0.00002941492,0.00006275788,0.0000650703,0.000041687752],"domain_scores_gemma":[0.99895084,0.0005657671,0.00015963521,0.000053216936,0.00020309328,0.00006738378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095356716,0.0005386105,0.00042848304,0.0008774039,0.00019900753,0.0005879348,0.00050205283,0.0007035274,0.0007392161],"category_scores_gemma":[0.0029049087,0.00021393038,0.00064890244,0.0004673289,0.00020683286,0.0006037002,0.0005740438,0.0011203422,0.00017285268],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038965454,0.0003407724,0.1254847,0.00008995586,0.0002178854,0.0005654801,0.000115704606,0.71630967,0.0030009558,0.001719442,0.0035800813,0.14818574],"study_design_scores_gemma":[0.0000032331832,0.000025332487,0.0037590184,0.000008681261,0.000008827225,0.00003896839,0.0000110151805,0.99443734,0.0004037161,0.0011688806,0.0001301456,0.0000048441816],"about_ca_topic_score_codex":0.0084082335,"about_ca_topic_score_gemma":0.00994225,"teacher_disagreement_score":0.0084082335,"about_ca_system_score_codex":0.00062689313,"about_ca_system_score_gemma":0.0004938836,"threshold_uncertainty_score":0.016718626},"labels":[],"label_agreement":null},{"id":"W3139599754","doi":"10.11575/prism/38706","title":"Develop a comprehensive hypertension prediction model and risk score in population-based data applying conventional statistical and machine learning approaches","year":2021,"lang":"en","type":"dissertation","venue":"PRISM (University of Calgary)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Machine learning; Computer science; Artificial intelligence; Predictive modelling; Statistical learning; Data mining","score_opus":0.20012381965032322,"score_gpt":0.3503871853614008,"score_spread":0.15026336571107757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139599754","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12534283,0.06094945,0.7677065,0.012457041,0.0007311682,0.0050596944,0.020561304,0.0015613228,0.005630647],"genre_scores_gemma":[0.605159,0.022763038,0.34722936,0.0024365664,0.0004468573,0.0059529226,0.0136931,0.00010331659,0.0022159172],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99556327,0.0022693058,0.00071813696,0.00059075793,0.00070915406,0.00014938132],"domain_scores_gemma":[0.9853276,0.011462873,0.0009125447,0.0003394855,0.0018050293,0.00015245892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014185436,0.0014187234,0.0031746093,0.0054863156,0.00044625538,0.0022737451,0.0019873297,0.0014702477,0.002079178],"category_scores_gemma":[0.034564126,0.0005763796,0.007276112,0.004850975,0.0004376566,0.0014155201,0.0013107943,0.001795679,0.0006570078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011296194,0.00060393754,0.22844289,0.01743797,0.032633066,0.00088416936,0.0006954826,0.24444717,0.0014329071,0.012582121,0.024079567,0.4356312],"study_design_scores_gemma":[0.0009218195,0.001215418,0.06705718,0.0055327844,0.029156655,0.00063854514,0.0004711737,0.8314047,0.0011029482,0.039238147,0.022953074,0.00030763628],"about_ca_topic_score_codex":0.05792879,"about_ca_topic_score_gemma":0.04337527,"teacher_disagreement_score":0.05792879,"about_ca_system_score_codex":0.0022826162,"about_ca_system_score_gemma":0.008025786,"threshold_uncertainty_score":0.115183234},"labels":[],"label_agreement":null},{"id":"W3140656083","doi":"10.18280/ria.350104","title":"A Weight Based Labeled Classifier Using Machine Learning Technique for Classification of Medical Data","year":2021,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Classifier (UML); Pattern recognition (psychology); Machine learning","score_opus":0.38367131558946654,"score_gpt":0.5023137194165473,"score_spread":0.1186424038270808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3140656083","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025829123,0.000735779,0.96871287,0.0005367759,0.0003723686,0.00020031902,0.00021842314,0.0012971614,0.002097269],"genre_scores_gemma":[0.4540857,0.000817921,0.5334299,0.00056165433,0.00040782968,0.00044902376,0.0013572158,0.00009434944,0.008796402],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832684,0.00032476994,0.0001592889,0.0003258303,0.0007242987,0.00013908511],"domain_scores_gemma":[0.99844223,0.00050930236,0.00012469865,0.00013722831,0.00073251803,0.000054029315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015047765,0.00058668765,0.0011884889,0.001573542,0.00084304874,0.0012306507,0.0018019257,0.0016576248,0.0016543083],"category_scores_gemma":[0.0036868546,0.00026167286,0.0009798453,0.0014661519,0.00040301026,0.0016396358,0.00065996643,0.00148262,0.0012341182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027878815,0.0005808486,0.0068957484,0.00019513363,0.00014966093,0.0002767598,0.00016126744,0.0873422,0.012071637,0.0058687464,0.009145664,0.8770336],"study_design_scores_gemma":[0.00001008883,0.00010743812,0.0006622549,0.000028376624,0.000023897881,0.000098479686,0.00003218858,0.9909679,0.0035407767,0.0023589402,0.0021518413,0.000017684813],"about_ca_topic_score_codex":0.005766963,"about_ca_topic_score_gemma":0.005194841,"teacher_disagreement_score":0.005766963,"about_ca_system_score_codex":0.00084366347,"about_ca_system_score_gemma":0.0013533224,"threshold_uncertainty_score":0.011466801},"labels":[],"label_agreement":null},{"id":"W3142047004","doi":"10.1109/trpms.2021.3071148","title":"Risk Assessment of Computer-Aided Diagnostic Software for Hepatic Resection","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Radiation and Plasma Medical Sciences","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Qatar National Research Fund; Qatar Foundation","keywords":"Computer science; Software; Resection; Medicine; Software engineering; Surgery; Programming language","score_opus":0.10300627137005147,"score_gpt":0.45660893891440985,"score_spread":0.3536026675443584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3142047004","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9290846,0.002525529,0.0623364,0.00056253426,0.000060203456,0.00017592982,0.0007615484,0.0005722848,0.0039209514],"genre_scores_gemma":[0.9865806,0.0002620904,0.011939155,0.00003858276,0.000015800664,0.00004885446,0.00039778912,0.00005398328,0.0006631507],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99295324,0.0034202463,0.00036348018,0.00065928884,0.0023815583,0.00022212086],"domain_scores_gemma":[0.87761384,0.09537759,0.015636103,0.0046300874,0.0061672097,0.0005750761],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072442535,0.0006930412,0.0004088487,0.0022117042,0.00025002722,0.0014990653,0.0007376918,0.00077159907,0.0025213738],"category_scores_gemma":[0.07626435,0.0003076853,0.0009207574,0.0010816591,0.00039176006,0.0007741909,0.0008547047,0.0005405253,0.00039693073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00298079,0.00033082863,0.5969811,0.00042736324,0.0008590183,0.0007103608,0.0003137457,0.19284926,0.006224058,0.0053663896,0.0018849246,0.19107218],"study_design_scores_gemma":[0.00013954658,0.0020909074,0.19719522,0.00014149655,0.00080211594,0.0027287914,0.00026173444,0.7650688,0.01831309,0.0075357454,0.005565855,0.00015660792],"about_ca_topic_score_codex":0.0019315373,"about_ca_topic_score_gemma":0.0015302795,"teacher_disagreement_score":0.0072442535,"about_ca_system_score_codex":0.0010045986,"about_ca_system_score_gemma":0.00070886366,"threshold_uncertainty_score":0.03831178},"labels":[],"label_agreement":null},{"id":"W3142317587","doi":"10.18280/ria.350105","title":"An Efficient and Scalable Heart Disease Diagnosis System with Attribute Impact Based Weights and Genetic Correlation Analysis","year":2021,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Data mining; Artificial neural network; Fuzzy logic; Machine learning; Artificial intelligence; Scalability; Rough set; Feature (linguistics); Correlation; Feature selection; Database","score_opus":0.06479023828447894,"score_gpt":0.38828172294235835,"score_spread":0.3234914846578794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3142317587","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08721487,0.0005048864,0.8996472,0.0003968469,0.00019071373,0.0002986209,0.0005383141,0.007870277,0.003338306],"genre_scores_gemma":[0.6917398,0.00037636375,0.3012789,0.00031654284,0.0001164487,0.00031585648,0.0011481091,0.000066221204,0.004641827],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99970144,0.000023554765,0.00002341934,0.00010198444,0.000117586285,0.000031937318],"domain_scores_gemma":[0.9997763,0.000042088028,0.000019342693,0.000027343987,0.00011141466,0.000023491155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041719107,0.00048158292,0.0006949003,0.0007790735,0.00051161426,0.00062596356,0.00077253825,0.00056324195,0.0013511846],"category_scores_gemma":[0.0008619045,0.00020927003,0.00043710208,0.00067542464,0.00014852572,0.00074110006,0.00059698906,0.00045860614,0.00047882413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060555973,0.000492618,0.011286355,0.00019207565,0.00019503584,0.00057031563,0.00015022927,0.08062063,0.06185349,0.0026748606,0.009462065,0.8318967],"study_design_scores_gemma":[0.000078158264,0.00018406023,0.0055769393,0.00001481903,0.00011088546,0.00039168977,0.00002854283,0.9682863,0.01946968,0.0019828274,0.0038305905,0.00004539014],"about_ca_topic_score_codex":0.006913633,"about_ca_topic_score_gemma":0.0062650735,"teacher_disagreement_score":0.006913633,"about_ca_system_score_codex":0.0005376383,"about_ca_system_score_gemma":0.00096218,"threshold_uncertainty_score":0.013746798},"labels":[],"label_agreement":null},{"id":"W3146759418","doi":"10.3389/fpubh.2021.561873","title":"Convergence of Precision Medicine and Public Health Into Precision Public Health: Toward a Big Data Perspective","year":2021,"lang":"en","type":"review","venue":"Frontiers in Public Health","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":83,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Public Health Ontario; University of Toronto; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Precision medicine; Public health; Data science; Big data; Public health surveillance; Field (mathematics); Perspective (graphical); Population health; Convergence (economics); Population; Computer science; Data mining; Medicine; Environmental health; Artificial intelligence; Pathology; Mathematics","score_opus":0.6563282597205701,"score_gpt":0.5660616168884935,"score_spread":0.09026664283207653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3146759418","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014572366,0.9647008,0.005222436,0.026621956,0.0009918787,0.000030355359,0.000061475854,0.000029648194,0.0021957238],"genre_scores_gemma":[0.0052854326,0.97004795,0.007896303,0.013289756,0.0029576563,0.0001427682,0.000091877664,0.000020472115,0.00026772078],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97234446,0.016824612,0.002357487,0.0017470304,0.0059562656,0.0007701077],"domain_scores_gemma":[0.7939992,0.1861721,0.004102909,0.004990355,0.0090508675,0.0016846046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.054442022,0.0016030059,0.0050757946,0.012033286,0.0012064432,0.008859402,0.0038101387,0.008512248,0.0028118533],"category_scores_gemma":[0.059390716,0.0011599268,0.0028046307,0.013785442,0.012266779,0.017945122,0.007572435,0.015242637,0.0010518093],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000102005724,0.00008447019,0.0010317992,0.034529515,0.00074306945,0.00025154828,0.0012250595,0.001260978,0.00030254267,0.3631521,0.025902292,0.57141453],"study_design_scores_gemma":[0.000056094952,0.00015842654,0.0016977539,0.058774386,0.00041746884,0.00069219846,0.0013000284,0.0010492974,0.00046709678,0.3613726,0.57388484,0.00012984547],"about_ca_topic_score_codex":0.004083312,"about_ca_topic_score_gemma":0.0038224768,"teacher_disagreement_score":0.054442022,"about_ca_system_score_codex":0.0072314525,"about_ca_system_score_gemma":0.015124086,"threshold_uncertainty_score":0.28792036},"labels":[],"label_agreement":null},{"id":"W3150815347","doi":"10.2174/1573411016999201015142327","title":"Open Access Journals: A Boon or Bane for Early Career Researchers in India","year":2020,"lang":"en","type":"article","venue":"Current Analytical Chemistry","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scopus; Publication; Library science; Political science; China; Medicine; MEDLINE; Computer science; Law","score_opus":0.8431618365658586,"score_gpt":0.6789766696002197,"score_spread":0.1641851669656389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3150815347","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11978772,0.23493508,0.0036876958,0.40030673,0.055584673,0.00052541966,0.0041571357,0.001975613,0.17903993],"genre_scores_gemma":[0.5199579,0.24888344,0.009809064,0.078245625,0.022530962,0.0003119357,0.0032983932,0.00075058336,0.11621205],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9926292,0.0011578262,0.0009619179,0.000554747,0.0030275816,0.0016687172],"domain_scores_gemma":[0.9537087,0.009991935,0.006522756,0.0022814907,0.008345689,0.01914941],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0062020267,0.0006260987,0.0007278582,0.0058444696,0.0049539357,0.017176,0.0019766337,0.0030394602,0.023766013],"category_scores_gemma":[0.015105069,0.0005278008,0.00076099613,0.011056982,0.0045008515,0.007755111,0.0065364125,0.004606132,0.006965408],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062221155,0.00047152993,0.048988488,0.0121157365,0.00013075059,0.00814474,0.008999646,0.00015071951,0.008050645,0.04814072,0.46990475,0.39428008],"study_design_scores_gemma":[0.00002531652,0.00013642522,0.047519997,0.002796601,0.000056116936,0.0075505497,0.011837388,0.0000921342,0.0011786994,0.0040860567,0.924614,0.00010665894],"about_ca_topic_score_codex":0.002976852,"about_ca_topic_score_gemma":0.0036021615,"teacher_disagreement_score":0.9980234,"about_ca_system_score_codex":0.0030135836,"about_ca_system_score_gemma":0.019339316,"threshold_uncertainty_score":0.079505205},"labels":[],"label_agreement":null},{"id":"W3152925331","doi":"10.36227/techrxiv.12053985.v1","title":"Development of On-Device Machine Learning Tools for Medication Warning Label Recognition","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Pill; Warning system; Computer science; Internet privacy; Medicine; Psychology; Nursing; Telecommunications","score_opus":0.5000611816440992,"score_gpt":0.5302722402444039,"score_spread":0.030211058600304708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3152925331","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019844675,0.00065154175,0.920417,0.00059415645,0.00084156863,0.0009326125,0.0015888187,0.044815045,0.010314577],"genre_scores_gemma":[0.16070655,0.0008511067,0.7962578,0.0008653514,0.00019494616,0.0011647758,0.0056164605,0.001594377,0.032748505],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99893767,0.00015089735,0.00008159647,0.00021902128,0.00048536767,0.00012544189],"domain_scores_gemma":[0.99742234,0.0008989796,0.00010479375,0.00032881973,0.0011224799,0.00012264245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012120601,0.0011665968,0.00079425494,0.0012818787,0.00043540803,0.0016321229,0.0025251315,0.0013709611,0.01373911],"category_scores_gemma":[0.0052032974,0.00058789167,0.0009254805,0.00069061556,0.00029459628,0.0017550447,0.0012333767,0.0015303865,0.009189329],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043316177,0.00079993065,0.0025173505,0.00044215226,0.00019004839,0.0007231508,0.00023285461,0.015150275,0.035259593,0.0051423563,0.05200501,0.887104],"study_design_scores_gemma":[0.00021185025,0.0005992811,0.004646584,0.00026287083,0.00012954396,0.0007766983,0.0002737101,0.7683414,0.118331596,0.0112171685,0.095081724,0.00012749007],"about_ca_topic_score_codex":0.004348309,"about_ca_topic_score_gemma":0.0047912775,"teacher_disagreement_score":0.01373911,"about_ca_system_score_codex":0.0005981255,"about_ca_system_score_gemma":0.0009959267,"threshold_uncertainty_score":0.045961916},"labels":[],"label_agreement":null},{"id":"W3154957374","doi":"10.24908/iqurcp.11549","title":"A Medical Decision Support Tool Using Text-mining Techniques with Electronic Medical Records","year":2018,"lang":"en","type":"article","venue":"Inquiry Queen s Undergraduate Research Conference Proceedings","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Medical record; Text messaging; Artificial intelligence; Data mining; Machine learning; Electronic medical record; Text mining; Information retrieval; Clinical decision support system; Information extraction; Decision support system; Medicine; World Wide Web","score_opus":0.24873762334864213,"score_gpt":0.5377392199443134,"score_spread":0.28900159659567126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154957374","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041435473,0.0010277916,0.82137096,0.0042267204,0.0003634469,0.0020441422,0.020800311,0.100822344,0.007908845],"genre_scores_gemma":[0.097513884,0.00040558778,0.88706505,0.0008905826,0.00016618831,0.0005871584,0.010027396,0.00048145265,0.0028626],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976713,0.00057597476,0.0005052297,0.00052159344,0.0006603023,0.000065548535],"domain_scores_gemma":[0.9853226,0.0114151575,0.0008850467,0.0009793025,0.0011105639,0.00028729934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036225992,0.0012522367,0.00092547614,0.005855898,0.0008429234,0.0027571465,0.0017812736,0.0014557373,0.008865697],"category_scores_gemma":[0.017385796,0.00057760044,0.0011719576,0.0036324556,0.00030206805,0.0031748281,0.0016341219,0.0011123524,0.004749672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007594293,0.00081788725,0.009750716,0.0013035935,0.00046070287,0.0025861047,0.000644346,0.015957125,0.01003653,0.0074574947,0.053439315,0.89678675],"study_design_scores_gemma":[0.00071172713,0.0007125958,0.010453862,0.001199825,0.0005480392,0.0044509685,0.0010626601,0.72019553,0.04917127,0.05766373,0.15356559,0.00026428603],"about_ca_topic_score_codex":0.0021520744,"about_ca_topic_score_gemma":0.002628902,"teacher_disagreement_score":0.008865697,"about_ca_system_score_codex":0.0006211237,"about_ca_system_score_gemma":0.0011734577,"threshold_uncertainty_score":0.029658675},"labels":[],"label_agreement":null},{"id":"W3155501624","doi":"10.1007/978-1-0716-1138-8_34","title":"Changing Health-Related Behaviors 6: Analysis, Interpretation, and Application of Big Data","year":2021,"lang":"en","type":"review","venue":"Methods in molecular biology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; IBM (Canada)","funders":"","keywords":"Big data; Perspective (graphical); Data science; Interpretation (philosophy); Health care; Value (mathematics); Computer science; Data mining; Artificial intelligence; Political science","score_opus":0.3247739357124168,"score_gpt":0.6435753683036743,"score_spread":0.31880143259125754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3155501624","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000085482396,0.9980439,0.00052989804,0.0008678923,0.00014121851,0.000011805736,0.00007557822,0.000010904546,0.00023336214],"genre_scores_gemma":[0.00074551883,0.9969398,0.0014397289,0.00042368032,0.0002448705,0.000026385249,0.00008882537,0.000004025847,0.00008717032],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99792176,0.00075176044,0.00029963482,0.00028571975,0.0006685575,0.000072550916],"domain_scores_gemma":[0.9844096,0.012912649,0.0009717292,0.00028923718,0.0012139955,0.00020272566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069303433,0.0016272693,0.0036733588,0.005685694,0.00035968624,0.0025099828,0.0018579094,0.0021409865,0.0022854568],"category_scores_gemma":[0.010188693,0.0006483547,0.0021942172,0.0059349276,0.0012714172,0.002561598,0.0013773666,0.0030052657,0.00089566724],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049743136,0.000083070365,0.00087229814,0.02780256,0.00065082,0.000034392637,0.000098221644,0.00041169664,0.00020843057,0.0055706697,0.012798332,0.9514198],"study_design_scores_gemma":[0.00010347018,0.0002228915,0.014038414,0.07915431,0.0023576063,0.00091516686,0.00037361158,0.001764943,0.001002625,0.0328065,0.8670376,0.000222839],"about_ca_topic_score_codex":0.0054473034,"about_ca_topic_score_gemma":0.009734312,"teacher_disagreement_score":0.0069303433,"about_ca_system_score_codex":0.001630319,"about_ca_system_score_gemma":0.0042400607,"threshold_uncertainty_score":0.03665155},"labels":[],"label_agreement":null},{"id":"W3155879942","doi":"10.1088/1757-899x/1131/1/012007","title":"Impact of Hidden Dense Layers in Convolutional Neural Network to enhance Performance of Classification Model","year":2021,"lang":"en","type":"article","venue":"IOP Conference Series Materials Science and Engineering","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Convolutional neural network; Computer science; Deep learning; Artificial intelligence; Convolution (computer science); Artificial neural network; Machine learning; Layer (electronics); Pattern recognition (psychology); Materials science","score_opus":0.10020503732356968,"score_gpt":0.4028112147850816,"score_spread":0.3026061774615119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3155879942","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8446853,0.0041661956,0.14052092,0.0016330288,0.00053346856,0.00012564377,0.0003805924,0.002178349,0.005776503],"genre_scores_gemma":[0.9753807,0.00046258233,0.022647332,0.000119528115,0.00003498768,0.000032520045,0.0002658598,0.000050787436,0.0010056435],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930775,0.00015399148,0.00007851258,0.000114949085,0.00016612351,0.00017860853],"domain_scores_gemma":[0.99668247,0.001753624,0.00021484404,0.00025419347,0.00096214225,0.00013269816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019214529,0.001469867,0.00065883744,0.0006468216,0.0004752059,0.0011332262,0.000997801,0.0010499211,0.002076394],"category_scores_gemma":[0.006991579,0.0004263328,0.0006988262,0.00045215397,0.00047884652,0.002162506,0.00083997723,0.0013971698,0.00038373726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016098673,0.00094470236,0.024574874,0.00043499697,0.000501295,0.00045558822,0.00015155177,0.7132577,0.038265124,0.0022373016,0.004140106,0.2134269],"study_design_scores_gemma":[0.000026522965,0.00027402802,0.002752551,0.00005104728,0.000110248766,0.000050084574,0.000043588665,0.97741735,0.018070685,0.00077681156,0.00040964867,0.00001736094],"about_ca_topic_score_codex":0.010741408,"about_ca_topic_score_gemma":0.009304472,"teacher_disagreement_score":0.010741408,"about_ca_system_score_codex":0.0009343152,"about_ca_system_score_gemma":0.001208578,"threshold_uncertainty_score":0.021357775},"labels":[],"label_agreement":null},{"id":"W3157262084","doi":"10.1164/ajrccm-conference.2021.203.1_meetingabstracts.a2307","title":"A Machine Learning Classifier to Predict Prognosis in Acute Exacerbations of Chronic Obstructive Pulmonary Disease","year":2021,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Health Sciences Centre; University Health Network; University of Toronto","funders":"","keywords":"Pulmonary disease; Classifier (UML); Computer science; Artificial intelligence; Machine learning; Disease; Intensive care medicine; Medicine; Internal medicine","score_opus":0.09259910578247131,"score_gpt":0.42511498535645365,"score_spread":0.3325158795739823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157262084","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8927519,0.003905574,0.083606474,0.002955294,0.0023337668,0.00048709198,0.0047742645,0.0010274568,0.00815826],"genre_scores_gemma":[0.9665173,0.00073706516,0.024943125,0.00028197875,0.00070146564,0.00015350422,0.004093319,0.000024159748,0.002548157],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992454,0.00014987035,0.00014317007,0.00013905545,0.00022946711,0.000093076844],"domain_scores_gemma":[0.99663395,0.0018902058,0.00017807697,0.0001272347,0.0009979643,0.00017260469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018153086,0.00047875155,0.0010434367,0.0020877975,0.00055560516,0.0012365297,0.0007039862,0.0011701749,0.0016783639],"category_scores_gemma":[0.0075520175,0.0001466076,0.0007618258,0.000791899,0.0001535176,0.00084693125,0.00044975893,0.0010680188,0.000940545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015501194,0.0018358937,0.33107704,0.00020554505,0.00047437495,0.00070359814,0.0001175201,0.021987965,0.0036150992,0.00095561036,0.02570339,0.61177385],"study_design_scores_gemma":[0.0001955787,0.0009249363,0.0782425,0.00013344802,0.00047958002,0.0008729716,0.00017656498,0.9094666,0.0028585952,0.0025260297,0.0040748673,0.000048295227],"about_ca_topic_score_codex":0.0035784657,"about_ca_topic_score_gemma":0.003931848,"teacher_disagreement_score":0.0035784657,"about_ca_system_score_codex":0.00044905127,"about_ca_system_score_gemma":0.00095096184,"threshold_uncertainty_score":0.009600341},"labels":[],"label_agreement":null},{"id":"W3157601164","doi":"10.1016/s0735-1097(21)02885-0","title":"PREDICTING MORTALITY IN PATIENTS WITH CORONARY ARTERY DISEASE REFERRED TO CARDIAC REHABILITATION: A MACHINE LEARNING APPROACH","year":2021,"lang":"en","type":"article","venue":"Journal of the American College of Cardiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Medicine; Rehabilitation; Coronary artery disease; Cardiology; Internal medicine; Disease; Physical therapy","score_opus":0.04861260297661527,"score_gpt":0.3761614927551679,"score_spread":0.3275488897785526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157601164","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98851997,0.00049302314,0.008200438,0.00096795114,0.000076027434,0.000049215338,0.000518953,0.00006075157,0.0011137676],"genre_scores_gemma":[0.99603647,0.00017652917,0.0025982244,0.000076563316,0.00009777479,0.000021536482,0.0006800813,0.0000043913788,0.00030844274],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994843,0.00021436955,0.00006390393,0.000110092136,0.00005500632,0.000072352035],"domain_scores_gemma":[0.9974825,0.0017954365,0.00020100754,0.00007438563,0.00026944766,0.00017728163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014988682,0.0006918738,0.0010220907,0.0022085654,0.000557363,0.0015088028,0.0008968649,0.0014216,0.0011109821],"category_scores_gemma":[0.004740617,0.0002479886,0.0010743411,0.0007588331,0.00027332996,0.0007351002,0.0005153946,0.0014149689,0.0003110485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009223572,0.0012880214,0.93654245,0.000039873863,0.0004005912,0.00016443069,0.000074786454,0.015605563,0.0005121456,0.00027435724,0.0011391905,0.043036196],"study_design_scores_gemma":[0.00011529898,0.00066474883,0.35777503,0.000046828383,0.00040772074,0.00027201456,0.00045333273,0.63722515,0.00051219296,0.0021322921,0.00035448163,0.000040926247],"about_ca_topic_score_codex":0.0053222883,"about_ca_topic_score_gemma":0.005811873,"teacher_disagreement_score":0.0053222883,"about_ca_system_score_codex":0.00055310567,"about_ca_system_score_gemma":0.00069679687,"threshold_uncertainty_score":0.010582626},"labels":[],"label_agreement":null},{"id":"W3160936361","doi":"10.2196/27304","title":"Using Machine Learning Techniques to Predict Factors Contributing to the Incidence of Metabolic Syndrome in Tehran: Cohort Study","year":2021,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Research Institute for Endocrine Sciences, Shahid Beheshti University of Medical Sciences; Hamedan University of Medical Sciences; Hamadan University of Medical Sciences","keywords":"Incidence (geometry); Cohort; Medicine; Environmental health; Cohort study; Metabolic syndrome; Computer science; Obesity; Internal medicine; Mathematics","score_opus":0.12237918434766913,"score_gpt":0.4590940387093069,"score_spread":0.3367148543616377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160936361","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99882585,0.00010917477,0.00040325217,0.000052545944,0.000017775477,0.00002508693,0.00044215322,0.0000072941502,0.0001168766],"genre_scores_gemma":[0.99708563,0.00013595451,0.0013822542,0.000023075696,0.000024788738,0.00005785279,0.0010684824,0.0000036167926,0.00021835351],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994241,0.00019963684,0.00006818683,0.00012138172,0.00011054219,0.000076250006],"domain_scores_gemma":[0.99864167,0.00034749354,0.00037428224,0.00022357215,0.00024585339,0.0001670916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027939794,0.0005104355,0.00040587605,0.0012167413,0.00041774323,0.0006384684,0.0005469261,0.00042281448,0.00073546596],"category_scores_gemma":[0.003299313,0.00032885408,0.0012863593,0.0009579782,0.00016469772,0.0003078663,0.00032954486,0.0009511604,0.00021749568],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015891592,0.00010942964,0.9972268,0.0000065106206,0.00014283044,0.000033722146,0.00004549719,0.0001682644,0.000109912326,0.000010180211,0.00012275552,0.001865085],"study_design_scores_gemma":[0.000055298377,0.00035188813,0.9942259,0.000010761493,0.00017819187,0.00016369016,0.0001646631,0.004478951,0.00012204601,0.000056761484,0.00018252809,0.000009387156],"about_ca_topic_score_codex":0.008175547,"about_ca_topic_score_gemma":0.009343709,"teacher_disagreement_score":0.008175547,"about_ca_system_score_codex":0.0003720715,"about_ca_system_score_gemma":0.00066740444,"threshold_uncertainty_score":0.016255915},"labels":[],"label_agreement":null},{"id":"W3162357606","doi":"10.33844/cjm.2021.60503","title":"Pharmacology, Toxicology, and Pharmaceutics Research Output in One Hundred and Fifty Countries for the Year 2019-2020","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pharmaceutics; Scopus; Toxicology; Pharmacology; Traditional medicine; Medicine; Biology; MEDLINE","score_opus":0.43149524943583567,"score_gpt":0.5724868859732081,"score_spread":0.1409916365373724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162357606","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09644198,0.20753695,0.001590535,0.003878535,0.0014961322,0.00013981893,0.63975215,0.00091330917,0.04825054],"genre_scores_gemma":[0.3166085,0.22572978,0.007748163,0.0013691596,0.0009138521,0.0004898804,0.43026763,0.00035410668,0.016518904],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9956012,0.00052595686,0.0013990203,0.0005109123,0.001585334,0.0003774771],"domain_scores_gemma":[0.9861622,0.0050022965,0.0035801218,0.00058327644,0.004083277,0.0005888078],"candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.0037176143,0.00073307595,0.000751591,0.028150039,0.00053555385,0.0031998907,0.00045630353,0.00043851061,0.010884145],"category_scores_gemma":[0.013521306,0.00030858626,0.0016362462,0.06628679,0.00035739763,0.0026613378,0.0013756355,0.00069354963,0.0068952944],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009982814,0.00009886823,0.20065361,0.05609181,0.002569224,0.0013570647,0.0014933257,0.001648707,0.003815356,0.0074572572,0.2910268,0.4327897],"study_design_scores_gemma":[0.000071376,0.00024293135,0.3246812,0.011634901,0.0017630192,0.0024446666,0.0023116749,0.000570248,0.0040017655,0.001290534,0.6508883,0.000099387835],"about_ca_topic_score_codex":0.00466439,"about_ca_topic_score_gemma":0.0053035724,"teacher_disagreement_score":0.97185,"about_ca_system_score_codex":0.001391908,"about_ca_system_score_gemma":0.003939808,"threshold_uncertainty_score":0.036411047},"labels":[],"label_agreement":null},{"id":"W3162838148","doi":"10.1016/j.compeleceng.2021.107187","title":"Prognosis analysis of thick data: Clustering heart diseases risk groups case study","year":2021,"lang":"en","type":"article","venue":"Computers & Electrical Engineering","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Medicine; Internal medicine; Cardiology; Computer science; Data mining; Artificial intelligence","score_opus":0.11169323263869077,"score_gpt":0.4295254555644752,"score_spread":0.3178322229257844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162838148","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.976999,0.00018972752,0.020525806,0.00039523875,0.00003985098,0.00010153697,0.0008031206,0.00008100052,0.0008647153],"genre_scores_gemma":[0.9896101,0.000078401885,0.008641069,0.000028144685,0.000031736974,0.000028048036,0.00084901374,0.000009044814,0.0007244592],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992399,0.00015259112,0.00009040853,0.00017996077,0.00019576518,0.00014143481],"domain_scores_gemma":[0.9975834,0.0011026976,0.00022907669,0.0003300448,0.000490192,0.00026464614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013839429,0.00051189814,0.000520963,0.0022865366,0.0008988317,0.00084016577,0.0007470463,0.0012053871,0.001581594],"category_scores_gemma":[0.0038330262,0.0002337292,0.00095094915,0.0010918742,0.00047997982,0.0006183297,0.00072732917,0.0005888801,0.00026057893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002420615,0.0021099686,0.7696006,0.00026813755,0.0004414092,0.014232467,0.001683536,0.071238756,0.017249608,0.0038591137,0.006742826,0.11015306],"study_design_scores_gemma":[0.0001378531,0.0015097624,0.29309756,0.00012592456,0.0005644204,0.008852469,0.0058646877,0.65520054,0.021221774,0.008296123,0.0049842666,0.00014465452],"about_ca_topic_score_codex":0.006523967,"about_ca_topic_score_gemma":0.00412704,"teacher_disagreement_score":0.006523967,"about_ca_system_score_codex":0.0004901005,"about_ca_system_score_gemma":0.0005972403,"threshold_uncertainty_score":0.012971997},"labels":[],"label_agreement":null},{"id":"W3162841855","doi":"10.18280/isi.260210","title":"A Diabetic Prediction System Based on Mean Shift Clustering","year":2021,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Bayes' theorem; Naive Bayes classifier; Diabetes mellitus; Body mass index; Artificial intelligence; Mean-shift; Medicine; Computer science; Machine learning; Internal medicine; Pattern recognition (psychology); Endocrinology; Bayesian probability","score_opus":0.05846500220636072,"score_gpt":0.34791396893025606,"score_spread":0.2894489667238953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162841855","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19489819,0.0012569501,0.7641758,0.00097423565,0.00057753816,0.00041135566,0.002126771,0.028714083,0.0068651172],"genre_scores_gemma":[0.7243282,0.00046822923,0.2658314,0.0002962537,0.00015248991,0.00018606108,0.0025225251,0.00015811533,0.0060566706],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994444,0.00005234614,0.00005259744,0.00021672984,0.00017085427,0.00006308298],"domain_scores_gemma":[0.9993529,0.00010982663,0.000049860504,0.00006288249,0.00038414248,0.00004035867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007654837,0.0007049597,0.000987774,0.0015725543,0.0009396909,0.0010344845,0.0013453542,0.0009705446,0.001778969],"category_scores_gemma":[0.0015042932,0.0003221913,0.0007238235,0.0011442091,0.00017569833,0.0006975181,0.0005393172,0.0006230417,0.0014247157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012321947,0.0006804981,0.020630833,0.00019210023,0.00029888868,0.0006916608,0.00019022396,0.12677379,0.01738659,0.0019254712,0.019666197,0.8103315],"study_design_scores_gemma":[0.000026307735,0.00008808379,0.0031200137,0.000012728799,0.000055365465,0.0001591937,0.000031788313,0.98774207,0.0059236907,0.0012229009,0.0015834925,0.000034337743],"about_ca_topic_score_codex":0.028653996,"about_ca_topic_score_gemma":0.018587084,"teacher_disagreement_score":0.028653996,"about_ca_system_score_codex":0.0009480823,"about_ca_system_score_gemma":0.0009459723,"threshold_uncertainty_score":0.05697447},"labels":[],"label_agreement":null},{"id":"W3162922322","doi":"10.33844/cjm.2021.60500","title":"Analysis and Prediction of Heart Disease Using Machine Learning and Data Mining Techniques","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"C4.5 algorithm; Decision tree; Random forest; Machine learning; Naive Bayes classifier; Computer science; Artificial intelligence; Logistic regression; Coronary heart disease; Software; Ensemble learning; Data mining; Medicine; Support vector machine; Internal medicine","score_opus":0.2375841033714225,"score_gpt":0.4963301962771604,"score_spread":0.2587460929057379,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162922322","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46788466,0.008530625,0.5047967,0.0036252874,0.00057043263,0.0005527395,0.0046796934,0.0026748483,0.0066850837],"genre_scores_gemma":[0.84115833,0.00284247,0.14864653,0.00030707766,0.00028380388,0.00019278408,0.003981714,0.000049116752,0.0025380908],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888843,0.00030714975,0.00015905204,0.00020458711,0.00032674882,0.00011406247],"domain_scores_gemma":[0.9971565,0.0018000711,0.0003253363,0.00020332639,0.0004296406,0.000085189684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001942927,0.001018597,0.0007950849,0.0042631566,0.00044003144,0.0014683343,0.0008850929,0.0009157952,0.0016987644],"category_scores_gemma":[0.005909357,0.0002756873,0.0011613104,0.0020324613,0.00025636939,0.0011798419,0.0005405654,0.0011345715,0.0007989629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031751939,0.0011242104,0.2750979,0.00045766716,0.00044363638,0.0004638552,0.00018879313,0.13152821,0.004125952,0.002335904,0.006857048,0.5770592],"study_design_scores_gemma":[0.000029887115,0.00030376462,0.04231129,0.00016456014,0.00014205831,0.00037468452,0.00029407922,0.93985677,0.005871018,0.0056939796,0.0048995516,0.000058324917],"about_ca_topic_score_codex":0.0068499907,"about_ca_topic_score_gemma":0.0077851797,"teacher_disagreement_score":0.0068499907,"about_ca_system_score_codex":0.00057765166,"about_ca_system_score_gemma":0.00095384294,"threshold_uncertainty_score":0.013620257},"labels":[],"label_agreement":null},{"id":"W3164811543","doi":"10.3233/shti210215","title":"Towards a Knowledge Graph-Based Explainable Decision Support System in Healthcare","year":2021,"lang":"en","type":"book-chapter","venue":"Studies in health technology and informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cape Breton University","funders":"","keywords":"Knowledge graph; Computer science; Decision support system; Health professionals; Clinical decision support system; Health care; Healthcare system; Graph; Knowledge management; Artificial intelligence; Data science; Theoretical computer science","score_opus":0.17256783104422305,"score_gpt":0.4782929733626078,"score_spread":0.30572514231838477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164811543","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035239998,0.00068664586,0.9842519,0.001887259,0.0000950952,0.00013855734,0.00041036704,0.0025414284,0.006464799],"genre_scores_gemma":[0.03162291,0.0010318519,0.95764893,0.0005195483,0.000057786747,0.00014552075,0.0012915307,0.00025422726,0.007427757],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939203,0.00021432317,0.000054724773,0.000119889504,0.00018450686,0.000034500463],"domain_scores_gemma":[0.9990331,0.00060993055,0.000054883938,0.000111795714,0.0001459638,0.00004431119],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014035365,0.0006767952,0.00037996258,0.0012289586,0.0005718196,0.0027754467,0.001678952,0.0015026904,0.008239705],"category_scores_gemma":[0.00320021,0.00046560835,0.0011052692,0.0012200628,0.0009249225,0.0036419167,0.0023520095,0.0024576774,0.0022192132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009477511,0.00011429619,0.0010259307,0.00073790905,0.0001429647,0.00079657976,0.0017357965,0.072977535,0.00889038,0.5144713,0.025894737,0.37311783],"study_design_scores_gemma":[0.000037099515,0.000055825803,0.000578988,0.00033792818,0.00011894068,0.00040972925,0.00028938727,0.47279996,0.0069150226,0.33528456,0.18311688,0.000055687393],"about_ca_topic_score_codex":0.005462504,"about_ca_topic_score_gemma":0.0061389883,"teacher_disagreement_score":0.008239705,"about_ca_system_score_codex":0.0011878528,"about_ca_system_score_gemma":0.0013895651,"threshold_uncertainty_score":0.027564585},"labels":[],"label_agreement":null},{"id":"W3165826902","doi":"10.1109/urtc45901.2018.9437568","title":"Artificial Intelligence-Based Cardiac Rehabilitation Therapy Exercise Recommendation System","year":2018,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Rehabilitation; Computer science; Physical medicine and rehabilitation; Physical therapy; Medicine","score_opus":0.1864626409149261,"score_gpt":0.47722516604896253,"score_spread":0.29076252513403644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165826902","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16442311,0.0016912331,0.7772429,0.00518633,0.00048663688,0.0014708102,0.009445801,0.020856781,0.01919637],"genre_scores_gemma":[0.75405467,0.0006918185,0.23039882,0.0009572253,0.00011577247,0.000774582,0.0062872134,0.00008752192,0.006632311],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99955827,0.000088083754,0.00007572698,0.0001415051,0.00009557335,0.000040735555],"domain_scores_gemma":[0.99921966,0.00036423528,0.00006863508,0.00006212026,0.00024124322,0.000044098873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006536682,0.0006541537,0.00092671363,0.00093119673,0.00054174586,0.0010373925,0.0015883498,0.0014256911,0.0048540463],"category_scores_gemma":[0.0025902058,0.00029142064,0.0007354775,0.0009683837,0.00017388072,0.00079111935,0.0004268202,0.0008510043,0.0014379306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006403441,0.00112965,0.015727343,0.0004364513,0.0002866382,0.00081515074,0.00014826214,0.53271866,0.005290525,0.0041625923,0.024463836,0.41418058],"study_design_scores_gemma":[0.000025753681,0.00003893425,0.0009976791,0.000011925309,0.000028144535,0.000046320656,0.000012468438,0.99620664,0.0004751307,0.00081046915,0.001336462,0.000010222763],"about_ca_topic_score_codex":0.032814223,"about_ca_topic_score_gemma":0.030557863,"teacher_disagreement_score":0.032814223,"about_ca_system_score_codex":0.00095907773,"about_ca_system_score_gemma":0.0012233478,"threshold_uncertainty_score":0.06524646},"labels":[],"label_agreement":null},{"id":"W3166672888","doi":"10.29252/koomesh.23.3.402","title":"Predictive factors of glycosylated hemoglobin using additive regression model","year":2021,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Waist; Medicine; Diabetes mellitus; Linear regression; Regression analysis; Internal medicine; Stepwise regression; Regression; Obesity; Statistics; Mathematics; Endocrinology","score_opus":0.23903584470061184,"score_gpt":0.4962615517358617,"score_spread":0.25722570703524983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3166672888","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7662661,0.0058761234,0.21053573,0.0038563835,0.00079143286,0.00048946356,0.0041022794,0.0015260098,0.006556471],"genre_scores_gemma":[0.97412926,0.0012888097,0.01708052,0.0001360823,0.00027165175,0.0002222119,0.0019276954,0.00007655256,0.0048672976],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99749786,0.0013249988,0.00011625484,0.00048889185,0.00027811303,0.00029386554],"domain_scores_gemma":[0.9926523,0.0055091833,0.00058424607,0.00020326934,0.00075658783,0.0002943696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041532037,0.0020169003,0.0017337335,0.0029867725,0.00058422517,0.0023665202,0.002063965,0.0010427719,0.007974901],"category_scores_gemma":[0.011465451,0.000733912,0.002918449,0.0018376845,0.00034313786,0.0008242127,0.0008465298,0.0020057352,0.0015063767],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013690667,0.0013167523,0.664654,0.00044503057,0.0035850448,0.0014698303,0.0005050365,0.22046906,0.000861421,0.005524181,0.010830468,0.08897009],"study_design_scores_gemma":[0.000061928,0.00029296282,0.036884047,0.00011747634,0.0006868115,0.00028540668,0.0001720905,0.9560658,0.00018334352,0.0037486602,0.0014506774,0.0000509163],"about_ca_topic_score_codex":0.020462058,"about_ca_topic_score_gemma":0.0076530366,"teacher_disagreement_score":0.020462058,"about_ca_system_score_codex":0.00070486596,"about_ca_system_score_gemma":0.0016538736,"threshold_uncertainty_score":0.04068595},"labels":[],"label_agreement":null},{"id":"W3166779014","doi":"","title":"Effectiveness of Service Quality of Hospitals and Integrated Delivery Networks Based on Early Readmission Rate","year":2018,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Hospital readmission; Service delivery framework; Service (business); Business; Medicine; Emergency medicine; Marketing","score_opus":0.06291787123474896,"score_gpt":0.3808491271133099,"score_spread":0.31793125587856097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3166779014","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98495436,0.0012357209,0.0007441091,0.001292807,0.000037095906,0.000029041257,0.010047999,0.000033336477,0.0016254472],"genre_scores_gemma":[0.9924184,0.00026080044,0.0003303505,0.00010583759,0.000040564053,0.000022055767,0.006502491,0.000008145776,0.00031140138],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.994024,0.0022457568,0.00073696335,0.00088295253,0.0011735971,0.00093685533],"domain_scores_gemma":[0.96510416,0.012965151,0.015301555,0.000990814,0.0031582976,0.0024799765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004481242,0.00039124824,0.000874989,0.002560356,0.00025814964,0.0017530592,0.0006749504,0.0005205086,0.0029508027],"category_scores_gemma":[0.033533286,0.00021168565,0.0010865917,0.0048169293,0.00037586133,0.0015401571,0.0012847382,0.0013910857,0.00040581182],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014056514,0.00009009914,0.9906675,0.00005348971,0.00026007852,0.000032120726,0.00006716942,0.0019618564,0.000036546484,0.00018271885,0.0012515059,0.005256304],"study_design_scores_gemma":[0.000020305824,0.00011921007,0.9934402,0.000038048303,0.00009531368,0.000049657578,0.00036996303,0.005100115,0.00009940693,0.00018230923,0.00047578372,0.000009570447],"about_ca_topic_score_codex":0.032318156,"about_ca_topic_score_gemma":0.031761143,"teacher_disagreement_score":0.032318156,"about_ca_system_score_codex":0.0024148813,"about_ca_system_score_gemma":0.0016651644,"threshold_uncertainty_score":0.064260066},"labels":[],"label_agreement":null},{"id":"W3168884196","doi":"10.1007/s00521-021-06143-y","title":"Improvement of grey wolf optimizer with adaptive middle filter to adjust support vector machine parameters to predict diabetes complications","year":2021,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Support vector machine; Artificial intelligence; Particle swarm optimization; Machine learning; Filter (signal processing)","score_opus":0.10687351179884803,"score_gpt":0.3860019175852083,"score_spread":0.2791284057863603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168884196","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.178349,0.0011812467,0.81728965,0.00024627012,0.00016617209,0.00006532544,0.00004805706,0.0009364262,0.0017178453],"genre_scores_gemma":[0.8903559,0.0002800281,0.10761284,0.00009576832,0.00003393092,0.000076079064,0.000102148726,0.000042313615,0.0014010695],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996302,0.00008471558,0.00003453308,0.00008504666,0.000114906485,0.00005053299],"domain_scores_gemma":[0.9994742,0.0002191939,0.00005875526,0.000034741955,0.0001918109,0.00002127078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010500151,0.00067614793,0.0009005814,0.00067509094,0.00025145302,0.0005974922,0.0006585791,0.00094541686,0.00083987566],"category_scores_gemma":[0.0020278648,0.00023298718,0.0007901091,0.0004759972,0.00026014404,0.000599992,0.0002486842,0.00054279796,0.0001991195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005145686,0.0003478617,0.006931846,0.00014998954,0.00023209464,0.00022618087,0.00011901278,0.6778701,0.025675645,0.0012933619,0.0016456147,0.2849937],"study_design_scores_gemma":[0.000008750529,0.000049918126,0.000762968,0.000003773446,0.0000123120935,0.0000103428465,0.000004735156,0.99740016,0.001537693,0.00008858242,0.0001156756,0.000004976362],"about_ca_topic_score_codex":0.0063307066,"about_ca_topic_score_gemma":0.002731798,"teacher_disagreement_score":0.0063307066,"about_ca_system_score_codex":0.00033077778,"about_ca_system_score_gemma":0.00048890343,"threshold_uncertainty_score":0.012587726},"labels":[],"label_agreement":null},{"id":"W3169054238","doi":"10.1007/978-3-030-77977-1_17","title":"Addressing Missing Data in a Healthcare Dataset Using an Improved kNN Algorithm","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cape Breton University","funders":"","keywords":"Computer science; Missing data; Health care; Data mining; Algorithm; Machine learning; Political science","score_opus":0.396577230241086,"score_gpt":0.5102513893714219,"score_spread":0.1136741591303359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169054238","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034119554,0.0015503528,0.95727825,0.000623351,0.00046255704,0.00014788978,0.0024695531,0.0021139341,0.0012346171],"genre_scores_gemma":[0.20695218,0.0006172618,0.777242,0.00036972895,0.00035332647,0.00016391218,0.009785622,0.00020578926,0.004310255],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974337,0.00044376883,0.00027980865,0.0009316323,0.0006474526,0.00026369098],"domain_scores_gemma":[0.9946702,0.0026721838,0.00027568897,0.0008496091,0.0014096171,0.00012275475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042333137,0.000989914,0.0019622534,0.0024170326,0.0010966031,0.0018039235,0.002465994,0.0024989862,0.0022251871],"category_scores_gemma":[0.01037123,0.00057915004,0.001755241,0.0037618736,0.0004975271,0.0024524552,0.0016817077,0.0024653913,0.0015926008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005325016,0.00045903985,0.009459688,0.0003725256,0.00030301572,0.0003600457,0.00016173365,0.25109905,0.0048928075,0.0035227723,0.016705234,0.7121316],"study_design_scores_gemma":[0.000016616325,0.00004528465,0.0012596765,0.000027799097,0.00005106029,0.00013766807,0.00006423449,0.9892966,0.0013551519,0.004917094,0.0028096572,0.000019122463],"about_ca_topic_score_codex":0.018300021,"about_ca_topic_score_gemma":0.01734699,"teacher_disagreement_score":0.018300021,"about_ca_system_score_codex":0.00078733877,"about_ca_system_score_gemma":0.002257425,"threshold_uncertainty_score":0.036387026},"labels":[],"label_agreement":null},{"id":"W3170429894","doi":"10.21428/594757db.31ebdee8","title":"HEAL: Heterogeneous Ensemble and Active Learning Framework","year":2021,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Ensemble learning; Intrusion detection system; Artificial intelligence; Machine learning; Set (abstract data type); Ensemble forecasting; Active learning (machine learning); Domain (mathematical analysis); Data mining","score_opus":0.14207591980093492,"score_gpt":0.4900659873466095,"score_spread":0.3479900675456746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170429894","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006509116,0.00038918428,0.9910529,0.00016932671,0.000048394206,0.000040785166,0.00006841098,0.00072718,0.0009946973],"genre_scores_gemma":[0.49383205,0.00087544764,0.49734643,0.00047948185,0.00039269731,0.0003485889,0.00067296124,0.0002374847,0.005814884],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894243,0.00037392214,0.000043780616,0.00021994143,0.00031121186,0.000108700246],"domain_scores_gemma":[0.9989127,0.00055916555,0.00008295361,0.000116382886,0.00023980885,0.00008889792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002541683,0.00076771184,0.0011782303,0.001050596,0.00056382956,0.00135694,0.00283847,0.0014893932,0.0017137253],"category_scores_gemma":[0.0030475655,0.00043313843,0.0010416033,0.0007927192,0.00049981364,0.0016754343,0.0018338425,0.0017494672,0.0005349442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016377537,0.00025829521,0.0026043986,0.00007735101,0.00027556877,0.00013723438,0.00015457527,0.6972127,0.0029652622,0.017092722,0.0040795538,0.27497858],"study_design_scores_gemma":[0.0000051350644,0.000025766178,0.000087950604,0.000004062852,0.000012875665,0.000014425039,0.0000070179444,0.995308,0.0004496351,0.003264287,0.0008159367,0.000004804397],"about_ca_topic_score_codex":0.0043416955,"about_ca_topic_score_gemma":0.003991061,"teacher_disagreement_score":0.0043416955,"about_ca_system_score_codex":0.0005756236,"about_ca_system_score_gemma":0.0008852687,"threshold_uncertainty_score":0.013441801},"labels":[],"label_agreement":null},{"id":"W3173478665","doi":"","title":"Cardio Vascular Ailments Prediction and Analysis Based On Deep Learning Techniques","year":2021,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity College","funders":"","keywords":"Computer science; Artificial intelligence; Random forest; Machine learning; Measure (data warehouse); Classifier (UML); Data mining","score_opus":0.07552928889282962,"score_gpt":0.43901966024357886,"score_spread":0.36349037135074924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173478665","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25269964,0.0020365894,0.7355657,0.0008499387,0.00013468783,0.00012163715,0.001222248,0.0018749338,0.0054946053],"genre_scores_gemma":[0.92061967,0.00092149124,0.07233793,0.00012912236,0.00005638109,0.0000978782,0.00096354634,0.000041601445,0.004832378],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998197,0.000025277659,0.000016222228,0.000039083585,0.00006161536,0.00003817268],"domain_scores_gemma":[0.9996482,0.00013583741,0.00004761798,0.000022288024,0.00012601474,0.000020022571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040442054,0.00047712514,0.00044602974,0.0011498512,0.00019432744,0.0005887662,0.000455819,0.0005057636,0.0015899129],"category_scores_gemma":[0.00091870327,0.00022564062,0.0006629391,0.00062194443,0.00014040312,0.00048574535,0.00033702076,0.00076326466,0.00036467123],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028816017,0.0005722808,0.043375358,0.0002314052,0.00024168218,0.00051209907,0.00012528876,0.38328308,0.020049967,0.0031449026,0.0060303835,0.5421454],"study_design_scores_gemma":[0.0000054228567,0.000061679675,0.0054968726,0.000016714761,0.000019966581,0.000080885715,0.000015895295,0.9897709,0.002637177,0.0013270502,0.0005582323,0.0000092848095],"about_ca_topic_score_codex":0.006887475,"about_ca_topic_score_gemma":0.007827105,"teacher_disagreement_score":0.006887475,"about_ca_system_score_codex":0.00043113678,"about_ca_system_score_gemma":0.0005965002,"threshold_uncertainty_score":0.013694763},"labels":[],"label_agreement":null},{"id":"W3175384364","doi":"10.1016/b978-0-12-821777-1.00020-3","title":"Machine learning for optimizing healthcare resources","year":2021,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thompson Rivers University","funders":"","keywords":"Pandemic; Health care; Computer science; Artificial intelligence; Machine learning; Key (lock); Quality (philosophy); Feature engineering; Coronavirus disease 2019 (COVID-19); Feature (linguistics); Data science; Medicine; Computer security; Deep learning; Political science","score_opus":0.13233003260478526,"score_gpt":0.41932513025931223,"score_spread":0.28699509765452696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175384364","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074276584,0.021723118,0.8273503,0.0054508494,0.0010413943,0.00008147229,0.0010364186,0.0035271668,0.13236162],"genre_scores_gemma":[0.15932547,0.018924098,0.59073275,0.0012097193,0.0010845686,0.00026697217,0.0018504162,0.0010138936,0.22559205],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997551,0.000062834646,0.000011551016,0.000045815785,0.0001047829,0.00001988854],"domain_scores_gemma":[0.9996296,0.00026315663,0.000016582657,0.00003937463,0.000042557524,0.0000087150775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045215333,0.00090142613,0.00065255654,0.0006101793,0.00020372705,0.0013551111,0.00076710084,0.00086943456,0.020117655],"category_scores_gemma":[0.0014576925,0.00036362838,0.00044759354,0.0014162671,0.00032993438,0.0016292451,0.0006600671,0.001416572,0.005045156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030760497,0.000051280727,0.00035691293,0.00026562146,0.000054003867,0.000057445275,0.00004108934,0.16072838,0.0012299478,0.05999976,0.06465304,0.71253175],"study_design_scores_gemma":[0.000013653413,0.000029214438,0.00048453215,0.00018144753,0.000032178847,0.00009056008,0.000044179764,0.76596576,0.002059898,0.13770421,0.093371294,0.000022954982],"about_ca_topic_score_codex":0.0034280627,"about_ca_topic_score_gemma":0.00474386,"teacher_disagreement_score":0.020117655,"about_ca_system_score_codex":0.0008103889,"about_ca_system_score_gemma":0.0006156417,"threshold_uncertainty_score":0.06730032},"labels":[],"label_agreement":null},{"id":"W3176579585","doi":"10.2337/db21-872-p","title":"872-P: Impact of Telemedicine Consultations during the COVID-19 Pandemic on Glycemic Control of Diabetes Patients","year":2021,"lang":"en","type":"article","venue":"Diabetes","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Telemedicine; Medicine; Glycemic; Pandemic; Diabetes mellitus; Context (archaeology); Coronavirus disease 2019 (COVID-19); Psychosocial; Diabetes management; Emergency medicine; Internal medicine; Type 2 diabetes; Disease; Health care; Endocrinology","score_opus":0.08098178588542398,"score_gpt":0.4430801413015201,"score_spread":0.36209835541609614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176579585","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9974987,0.00022918006,0.000017325661,0.00025420205,0.000011592496,0.000012735219,0.00024583092,0.0000025048903,0.001727997],"genre_scores_gemma":[0.99937147,0.00014365879,0.000048211077,0.00010535592,0.000018047183,0.000014403873,0.00012766753,0.0000014545993,0.00016993102],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990941,0.00043923612,0.00006619648,0.00006825338,0.00013955474,0.00019264358],"domain_scores_gemma":[0.9945874,0.0021735562,0.0017195517,0.000099779354,0.00039446514,0.001025186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008056317,0.00006969888,0.00014597944,0.000350226,0.0005136898,0.00063411583,0.00016898903,0.0002518878,0.0040732627],"category_scores_gemma":[0.0064654285,0.0000687592,0.00032962844,0.0006334272,0.00018910535,0.00029770803,0.00050073495,0.00045890134,0.00022410248],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005874662,0.0003488619,0.9747103,0.000059352693,0.00003106715,0.0003895659,0.0004210892,0.00012526417,0.00029413466,0.00003573591,0.0009922284,0.022005033],"study_design_scores_gemma":[0.00001675779,0.00041740696,0.9977685,0.000027763179,0.000016284876,0.00018919134,0.000986837,0.0001045081,0.000095493335,0.00000973395,0.00036300896,0.000004418996],"about_ca_topic_score_codex":0.012130644,"about_ca_topic_score_gemma":0.014462573,"teacher_disagreement_score":0.012130644,"about_ca_system_score_codex":0.0009708632,"about_ca_system_score_gemma":0.00096669904,"threshold_uncertainty_score":0.024120092},"labels":[],"label_agreement":null},{"id":"W3181767717","doi":"10.3390/diabetology2030011","title":"An Online Risk Tool for Predicting Type 2 Diabetes Mellitus","year":2021,"lang":"en","type":"article","venue":"Diabetology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University; Sinai Health System; University of Toronto; York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Logistic regression; Calculator; Body mass index; Diabetes mellitus; Type 2 Diabetes Mellitus; Medicine; Medical record; Risk assessment; Type 2 diabetes; Internal medicine; Computer science; Gerontology; Endocrinology","score_opus":0.14547705577653997,"score_gpt":0.47402806338451775,"score_spread":0.3285510076079778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3181767717","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48288596,0.0043689557,0.21273279,0.00499335,0.00084052264,0.003251924,0.114777096,0.110987574,0.06516188],"genre_scores_gemma":[0.70530856,0.0017854116,0.22756511,0.0010895382,0.00033747943,0.001299914,0.042144287,0.00073245063,0.019737205],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999132,0.00017607432,0.00012326952,0.00012261038,0.00037660298,0.00006945513],"domain_scores_gemma":[0.99322426,0.004230072,0.0006057201,0.0002837241,0.001185321,0.00047090463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010759158,0.00082237617,0.0005813828,0.004020221,0.0004248344,0.0010364688,0.00080176606,0.0006702959,0.0120168235],"category_scores_gemma":[0.011274112,0.00028546076,0.00050544884,0.0018918081,0.000083577695,0.00085427595,0.00087619835,0.0005982775,0.0043659084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012805861,0.0010707828,0.24419366,0.0003187445,0.00020697,0.00085992325,0.00029331096,0.0054752384,0.0018531583,0.0015984154,0.10130049,0.64154863],"study_design_scores_gemma":[0.001013487,0.0011370201,0.5187896,0.0008253452,0.0008534998,0.0050644325,0.00073648023,0.27813572,0.014487996,0.01252518,0.16593759,0.00049361645],"about_ca_topic_score_codex":0.019042734,"about_ca_topic_score_gemma":0.022625936,"teacher_disagreement_score":0.019042734,"about_ca_system_score_codex":0.0006552054,"about_ca_system_score_gemma":0.0012941875,"threshold_uncertainty_score":0.040200293},"labels":[],"label_agreement":null},{"id":"W3181956947","doi":"10.18280/ria.350304","title":"A Novel Design of Classification of Coronary Artery Disease Using Deep Learning and Data Mining Algorithms","year":2021,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cart; Artificial intelligence; Support vector machine; Computer science; Artificial neural network; Principal component analysis; Ensemble learning; Pattern recognition (psychology); Deep learning; Machine learning; Decision tree; Kernel (algebra); Data mining; Mathematics; Engineering","score_opus":0.4125166050998428,"score_gpt":0.4744332678970537,"score_spread":0.06191666279721092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3181956947","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012868535,0.00028456596,0.9842764,0.0003006375,0.00007870973,0.000104133534,0.00013439906,0.0007814538,0.0011711884],"genre_scores_gemma":[0.49050397,0.00056232954,0.50044286,0.0005448666,0.00018966381,0.00060490926,0.0007341507,0.00007950028,0.0063377717],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999428,0.00009536279,0.00005102689,0.00019690029,0.00015036951,0.00007835118],"domain_scores_gemma":[0.99938476,0.00013810655,0.00005654525,0.00004542178,0.00032813306,0.000046968682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011711931,0.0007123445,0.0009945153,0.00096878415,0.0004877676,0.0010813628,0.001399487,0.0011702006,0.0024144838],"category_scores_gemma":[0.0018055919,0.00053385994,0.0007817362,0.00073007605,0.00030854275,0.0010179447,0.000857517,0.00094493735,0.0007822381],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003375527,0.00053192157,0.010727868,0.00020275639,0.0002755775,0.00024774257,0.00012262393,0.19845301,0.02135471,0.010890709,0.007272462,0.74958307],"study_design_scores_gemma":[0.000015587575,0.00008347077,0.0010188207,0.0000123007185,0.00002971908,0.00008798749,0.000010286587,0.99226063,0.002840729,0.0024085017,0.0012210455,0.000010849851],"about_ca_topic_score_codex":0.0049281497,"about_ca_topic_score_gemma":0.0062646074,"teacher_disagreement_score":0.0049281497,"about_ca_system_score_codex":0.00088262785,"about_ca_system_score_gemma":0.001571065,"threshold_uncertainty_score":0.009798884},"labels":[],"label_agreement":null},{"id":"W3183005013","doi":"10.1109/access.2021.3096139","title":"An Optimised Multivariable Regression Model for Predictive Analysis of Diabetic Disease Progression","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Multivariable calculus; Computer science; Regression analysis; Mean squared error; Field (mathematics); Health care; Data mining; Regression; Predictive modelling; Linear regression; Time series; Artificial intelligence; Machine learning; Statistics; Engineering; Mathematics","score_opus":0.22059400201878082,"score_gpt":0.5561678301823652,"score_spread":0.33557382816358433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183005013","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1327859,0.0010510216,0.8617208,0.000520428,0.00010538175,0.00007806743,0.00046462874,0.0012680185,0.0020057762],"genre_scores_gemma":[0.9408995,0.00040094322,0.054829728,0.000084285144,0.000045192657,0.00014615411,0.0005290119,0.000054628697,0.003010566],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993723,0.00025448165,0.000037050577,0.00016749474,0.0001001664,0.00006851606],"domain_scores_gemma":[0.9993315,0.00039068933,0.00008200512,0.000025480187,0.00015694243,0.000013540094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012837608,0.00062641205,0.0009347916,0.0005910934,0.00022379265,0.000931316,0.00095442747,0.0007737314,0.0015438771],"category_scores_gemma":[0.0026285658,0.0003834186,0.0010815735,0.0007287626,0.00025850133,0.00041406837,0.00046577837,0.0011445731,0.0004004809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022967694,0.00008769627,0.004085658,0.00008850665,0.00012935256,0.00013345382,0.000077265286,0.9584548,0.0027907388,0.00080620777,0.000593134,0.032523394],"study_design_scores_gemma":[0.000008404764,0.000044214856,0.0009805285,0.000005437335,0.000018040331,0.000019779935,0.000006055191,0.9981445,0.00032770494,0.00023819767,0.00019950011,0.000007649663],"about_ca_topic_score_codex":0.009505056,"about_ca_topic_score_gemma":0.005670107,"teacher_disagreement_score":0.009505056,"about_ca_system_score_codex":0.000483219,"about_ca_system_score_gemma":0.000722469,"threshold_uncertainty_score":0.0188995},"labels":[],"label_agreement":null},{"id":"W3185213748","doi":"10.18280/rces.080206","title":"Research on the Construction of Precision Medical System Under the Background of Big Data-The Roles and Responsibilities of Government, Hospitals and Medical Workers","year":2021,"lang":"en","type":"article","venue":"Review of Computer Engineering Studies","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Big data; Government (linguistics); Obligation; Work (physics); Business; Field (mathematics); Big government; Public relations; Data science; Computer science; Political science; Engineering; Data mining; Law; Politics","score_opus":0.300986690180273,"score_gpt":0.5078818390217361,"score_spread":0.2068951488414631,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185213748","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2088699,0.051052682,0.35294056,0.10109496,0.0028961068,0.0008943499,0.0005378419,0.0008197269,0.28089395],"genre_scores_gemma":[0.90367925,0.021097181,0.057191774,0.002995825,0.0008206361,0.0002727342,0.00035636252,0.000092606075,0.0134935165],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9925943,0.0028588483,0.00047191264,0.0010280944,0.002251075,0.00079581706],"domain_scores_gemma":[0.9904295,0.003990768,0.0011556308,0.0011316092,0.0024578425,0.00083460956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007746882,0.0004360689,0.0004411831,0.002775403,0.0034523914,0.008327249,0.0014728556,0.0018396659,0.0034380876],"category_scores_gemma":[0.012033853,0.00047081363,0.00063494855,0.0036150154,0.0042656087,0.012036269,0.0041247364,0.002073949,0.00075792614],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008630916,0.0001412841,0.027710024,0.0016965185,0.00009061483,0.00052715477,0.01216631,0.0040056077,0.0022063833,0.6628905,0.012294195,0.27618513],"study_design_scores_gemma":[0.00005579149,0.00029023978,0.040331885,0.0028944963,0.00021249588,0.0013971383,0.038069103,0.02091227,0.007088274,0.3358743,0.5526955,0.00017855762],"about_ca_topic_score_codex":0.005565835,"about_ca_topic_score_gemma":0.0028990253,"teacher_disagreement_score":0.008327249,"about_ca_system_score_codex":0.004374886,"about_ca_system_score_gemma":0.015094892,"threshold_uncertainty_score":0.04096991},"labels":[],"label_agreement":null},{"id":"W3185516026","doi":"10.1016/j.compbiomed.2021.104672","title":"Heart disease prediction using supervised machine learning algorithms: Performance analysis and comparison","year":2021,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":482,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; University of Saskatchewan","keywords":"Machine learning; Random forest; Artificial intelligence; Decision tree; Computer science; Feature (linguistics); Heart disease; k-nearest neighbors algorithm; Statistical classification; Algorithm; Medicine","score_opus":0.13424266952788694,"score_gpt":0.47830489260383396,"score_spread":0.344062223075947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185516026","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9073557,0.0048609367,0.078605406,0.00051878963,0.00038340956,0.0001886041,0.0020162794,0.0021701339,0.003900607],"genre_scores_gemma":[0.95871603,0.0007941965,0.034835007,0.00006945448,0.00014768833,0.00010636374,0.0040749367,0.00008012128,0.001176111],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975568,0.0010499861,0.0002851841,0.0003646889,0.0006036657,0.00013965623],"domain_scores_gemma":[0.983223,0.011643125,0.0005538279,0.0011484164,0.0031024092,0.0003291643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054527954,0.0008011402,0.0015399709,0.0019731713,0.00041797227,0.0009243076,0.00094223215,0.0011269609,0.0011659185],"category_scores_gemma":[0.012170898,0.00018250282,0.0009497146,0.0011517621,0.0003006255,0.0010991959,0.0006470565,0.0007446702,0.00064940227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0057526873,0.0027002713,0.12838356,0.0005511958,0.00176062,0.00012901153,0.00013553909,0.24776326,0.003548978,0.0011757005,0.008705983,0.59939325],"study_design_scores_gemma":[0.00013122344,0.0011935605,0.020896096,0.000030275596,0.00020603002,0.00014439301,0.00006706188,0.971951,0.0036668957,0.0010120838,0.0006740283,0.000027470956],"about_ca_topic_score_codex":0.0033053146,"about_ca_topic_score_gemma":0.0021009094,"teacher_disagreement_score":0.0054527954,"about_ca_system_score_codex":0.00060678576,"about_ca_system_score_gemma":0.0011354489,"threshold_uncertainty_score":0.028837502},"labels":[],"label_agreement":null},{"id":"W3185940995","doi":"10.2147/imcrj.s322827","title":"Machine Learning in an Elderly Man with Heart Failure","year":2021,"lang":"en","type":"article","venue":"International Medical Case Reports Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; Health Sciences Centre","funders":"","keywords":"Heart failure; Medicine; Cardiology","score_opus":0.08601214956269013,"score_gpt":0.4753442980839074,"score_spread":0.3893321485212172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185940995","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84495497,0.009669521,0.008018226,0.096147485,0.0016659391,0.00021925029,0.00033476442,0.0002410305,0.03874885],"genre_scores_gemma":[0.97767967,0.0028572637,0.0035307338,0.009653229,0.0013264227,0.000035058674,0.0000792264,0.00002532518,0.0048130206],"study_design_codex":"case_report","study_design_gemma":"case_report","domain_scores_codex":[0.9996153,0.000079359605,0.00003508022,0.000047454305,0.00009295728,0.00012988357],"domain_scores_gemma":[0.99899524,0.00034130926,0.00020754828,0.000035003337,0.000078590725,0.00034229108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052841794,0.0005152345,0.00059602194,0.001320213,0.0019508083,0.000874994,0.00057926297,0.0034441934,0.001580292],"category_scores_gemma":[0.0032681809,0.00026217083,0.00053811254,0.0008578067,0.0010184583,0.0010827029,0.00096440245,0.003060219,0.0004939987],"study_design_candidate":"case_report","study_design_consensus":"case_report","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000635711,0.00014948465,0.017534325,0.00005261867,0.0000111206755,0.9649837,0.0015509451,0.00046389273,0.00035934788,0.0021712503,0.0043269284,0.008332943],"study_design_scores_gemma":[0.000011695554,0.0001711996,0.014065464,0.00014019008,0.000016501586,0.97201073,0.0012894461,0.00287819,0.00033980253,0.0025467407,0.006501364,0.000028703382],"about_ca_topic_score_codex":0.003634082,"about_ca_topic_score_gemma":0.0061231526,"teacher_disagreement_score":0.003634082,"about_ca_system_score_codex":0.0012801461,"about_ca_system_score_gemma":0.00082170375,"threshold_uncertainty_score":0.009288132},"labels":[],"label_agreement":null},{"id":"W3186575844","doi":"10.5430/jnep.v11n11p22","title":"Expanding the faculty capacity to help meet the increased national demand resulting from the addition of nursing informatics in the baccalaureate program: A Philippines experience","year":2021,"lang":"en","type":"article","venue":"Journal of Nursing Education and Practice","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"University of the Philippines; Adelphi University","keywords":"Health informatics; Informatics; Competence (human resources); Medical education; Nursing; Health care; Engineering informatics; Nurse education; Medicine; Computer science; Psychology; Engineering; Political science","score_opus":0.41611841926506843,"score_gpt":0.5905696211659163,"score_spread":0.17445120190084784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186575844","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9364492,0.0009828229,0.005678619,0.021408685,0.00021115023,0.00041193503,0.00007868226,0.00049123587,0.034287795],"genre_scores_gemma":[0.95812196,0.0014618164,0.0132749695,0.0031454412,0.00016403987,0.00021746926,0.00009401601,0.00015069892,0.023369567],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9974632,0.0013427594,0.000067743465,0.00013028218,0.00043726445,0.00055867265],"domain_scores_gemma":[0.9899974,0.001696115,0.00046077577,0.00039781406,0.0019950347,0.0054529044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067815217,0.00041533954,0.00016471076,0.0005400484,0.0046270094,0.0029888945,0.0016123886,0.000992789,0.008306307],"category_scores_gemma":[0.0058812303,0.00032005133,0.000239704,0.0006805748,0.0016363809,0.0022904715,0.0068764435,0.0020059797,0.0012322224],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003734016,0.0031205316,0.062071767,0.0011685543,0.000033304063,0.0050310926,0.25548342,0.003422066,0.023330443,0.0047807666,0.03325682,0.6079278],"study_design_scores_gemma":[0.00014563455,0.00423751,0.10788878,0.0006031608,0.00005003706,0.0021319073,0.2651931,0.0057028728,0.015563025,0.0019601663,0.59628993,0.00023383794],"about_ca_topic_score_codex":0.010583154,"about_ca_topic_score_gemma":0.02875989,"teacher_disagreement_score":0.010583154,"about_ca_system_score_codex":0.003612464,"about_ca_system_score_gemma":0.013868591,"threshold_uncertainty_score":0.035864532},"labels":[],"label_agreement":null},{"id":"W3186791804","doi":"10.14740/jocmr4568","title":"Potential Role of Artificial Intelligence for the Previous Study Using Traditional Analysis","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Medicine Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Artificial intelligence; Computer science","score_opus":0.8145235244909845,"score_gpt":0.7188164823216835,"score_spread":0.09570704216930104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186791804","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43923616,0.028957902,0.3606998,0.036264136,0.0034416774,0.0013184983,0.0016009248,0.00046312806,0.12801765],"genre_scores_gemma":[0.882832,0.0033873077,0.09943294,0.0050006215,0.0013321803,0.0003864426,0.00046784978,0.00010585064,0.007054853],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9785478,0.012730867,0.0019511449,0.0028130775,0.0034553006,0.0005018202],"domain_scores_gemma":[0.87816316,0.09264138,0.005868669,0.013405304,0.008955088,0.0009664304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031538017,0.000873136,0.0009932545,0.005883584,0.0025387818,0.010450978,0.0036485272,0.001106125,0.011597274],"category_scores_gemma":[0.090697885,0.00034270305,0.0013450999,0.0057907403,0.0046515693,0.008303582,0.0026246333,0.0015423966,0.0013160043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008424854,0.0013405678,0.38582546,0.002748203,0.001963324,0.001232812,0.007905912,0.0026723938,0.0023593938,0.19055477,0.00757969,0.39497498],"study_design_scores_gemma":[0.00023802932,0.000987779,0.2822545,0.0033680433,0.0019332767,0.0037091752,0.017533256,0.059123237,0.008612904,0.55176395,0.07016704,0.00030881166],"about_ca_topic_score_codex":0.005094818,"about_ca_topic_score_gemma":0.00733717,"teacher_disagreement_score":0.031538017,"about_ca_system_score_codex":0.002477643,"about_ca_system_score_gemma":0.0035414046,"threshold_uncertainty_score":0.16679102},"labels":[],"label_agreement":null},{"id":"W3187014496","doi":"10.1177/2327857921101027","title":"Optimizing Public Health Data Collection From Internet of Things Sensors: An Integrated Data-Sharing Platform","year":2021,"lang":"en","type":"article","venue":"Proceedings of the International Symposium on Human Factors and Ergonomics in Health Care","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Data collection; Internet of Things; Data sharing; Computer science; The Internet; Internet privacy; World Wide Web; Public health; Data science; Sociology; Medicine","score_opus":0.2922159358691342,"score_gpt":0.4370832069141898,"score_spread":0.1448672710450556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3187014496","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24483463,0.0002831353,0.738867,0.0007348518,0.00020660427,0.00058755133,0.0005758986,0.006535163,0.0073752683],"genre_scores_gemma":[0.8431111,0.00010088753,0.15383044,0.0001281693,0.000044690252,0.0001722405,0.0006822484,0.00012051074,0.0018096205],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989489,0.00020360718,0.00007554438,0.00019851656,0.00042590665,0.00014756664],"domain_scores_gemma":[0.9991373,0.00016339243,0.000054225973,0.00024861132,0.00032329216,0.000073217314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001378461,0.0008309152,0.00071956316,0.0005934912,0.0006652412,0.0014616966,0.0015908517,0.00064595736,0.0016925097],"category_scores_gemma":[0.0019708946,0.00040384632,0.0006171641,0.0007924753,0.00030030098,0.0017549093,0.0017683172,0.0006028736,0.0004530039],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021158366,0.00283712,0.020743849,0.00030518792,0.0005664984,0.00076709053,0.00062436593,0.21594499,0.2067844,0.015844818,0.015247981,0.518218],"study_design_scores_gemma":[0.00006628529,0.00024440608,0.004199985,0.000011772982,0.000117870644,0.00010413652,0.00022524806,0.9453154,0.039809994,0.005016593,0.004846536,0.00004178393],"about_ca_topic_score_codex":0.0026140718,"about_ca_topic_score_gemma":0.003232434,"teacher_disagreement_score":0.0026140718,"about_ca_system_score_codex":0.00042166494,"about_ca_system_score_gemma":0.001299287,"threshold_uncertainty_score":0.0072900653},"labels":[],"label_agreement":null},{"id":"W3194775808","doi":"10.4018/ijhisi.20211001.oa17","title":"Artificial Intelligence for Healthcare in India","year":2021,"lang":"en","type":"article","venue":"International Journal of Healthcare Information Systems and Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Health care; Framing (construction); Government (linguistics); Healthcare policy; Healthcare system; Health sector; Healthcare industry; Business; Computer science; Knowledge management; Health policy; Medicine; Economic growth; Engineering; Health services; Health care reform; Economics","score_opus":0.12432823238684336,"score_gpt":0.4637502677376325,"score_spread":0.33942203535078913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194775808","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027351098,0.07190211,0.010343077,0.18607569,0.0040038694,0.00021827324,0.00083834986,0.00047298428,0.6987946],"genre_scores_gemma":[0.6743071,0.09937518,0.023431532,0.029282803,0.0017307112,0.00039942854,0.0011438446,0.00015487755,0.17017452],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984022,0.00055094704,0.00014811565,0.00014050148,0.00050591317,0.00025237259],"domain_scores_gemma":[0.9981799,0.0007431865,0.00015010082,0.00017047398,0.0005099898,0.00024635543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014833827,0.00032811816,0.00030496053,0.0015671939,0.0022066915,0.0065811463,0.0007112517,0.0012642732,0.010966019],"category_scores_gemma":[0.0027557765,0.00020125788,0.00035864513,0.0027805136,0.0028314472,0.0020190524,0.0035043561,0.0027872503,0.0023523655],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043837863,0.00006502474,0.0036396869,0.0008684695,0.000025718333,0.0012120974,0.003322395,0.0012964628,0.0010593003,0.6998754,0.09369843,0.19489326],"study_design_scores_gemma":[0.000012685684,0.000059599064,0.008741927,0.0009722412,0.000017934659,0.0012187198,0.0033030408,0.00089122076,0.0006724869,0.06120185,0.92286503,0.000043238255],"about_ca_topic_score_codex":0.017651267,"about_ca_topic_score_gemma":0.017997142,"teacher_disagreement_score":0.017651267,"about_ca_system_score_codex":0.0069565084,"about_ca_system_score_gemma":0.013211311,"threshold_uncertainty_score":0.050473213},"labels":[],"label_agreement":null},{"id":"W3195976034","doi":"10.1016/j.cca.2021.08.023","title":"FIUS: Fixed partitioning undersampling method","year":2021,"lang":"en","type":"article","venue":"Clinica Chimica Acta","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Undersampling; Computer science; Classifier (UML); Data mining; Artificial intelligence; Logistic regression; Machine learning; Pattern recognition (psychology)","score_opus":0.36205653401151233,"score_gpt":0.5728659147389963,"score_spread":0.21080938072748395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3195976034","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008806397,0.00058668316,0.9789578,0.00026101578,0.00039948267,0.00035889362,0.0012665336,0.007999115,0.0013641234],"genre_scores_gemma":[0.07922918,0.00020161105,0.9059634,0.00062340894,0.00028426404,0.00063843984,0.007684116,0.0009912162,0.004384225],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980261,0.00074008544,0.00012828896,0.0004864168,0.0004619237,0.00015716703],"domain_scores_gemma":[0.9976235,0.0011206504,0.000075360666,0.00047607883,0.0006088647,0.00009546198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002874605,0.0014881762,0.0016041839,0.0018819011,0.001446985,0.0011929214,0.0025792122,0.0020526054,0.008557263],"category_scores_gemma":[0.0110699935,0.0007484526,0.0015339208,0.0010595572,0.0005655931,0.0009972901,0.0015271294,0.0016340906,0.003174959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068568083,0.00031274662,0.0034686618,0.00036693888,0.0004804461,0.00024037568,0.00012882467,0.10408412,0.006680329,0.009013122,0.06920272,0.80533606],"study_design_scores_gemma":[0.00010887165,0.00009975354,0.00087544805,0.000038066733,0.00007947791,0.00016328912,0.000043065178,0.97348773,0.0038113017,0.008012007,0.0132526755,0.000028312545],"about_ca_topic_score_codex":0.014694898,"about_ca_topic_score_gemma":0.021942722,"teacher_disagreement_score":0.014694898,"about_ca_system_score_codex":0.00059267605,"about_ca_system_score_gemma":0.0022036184,"threshold_uncertainty_score":0.029218733},"labels":[],"label_agreement":null},{"id":"W3196693015","doi":"10.1109/wiecon-ece54711.2021.9829577","title":"Survival Prediction of Heart Failure Patients using Stacked Ensemble Machine Learning Algorithm","year":2021,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Ensemble learning; Algorithm; Machine learning; Artificial intelligence","score_opus":0.13920243938688032,"score_gpt":0.4309503772063769,"score_spread":0.2917479378194966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196693015","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6435024,0.0015440668,0.35113043,0.00064973213,0.00018883377,0.000069207,0.0005230534,0.0008792736,0.0015129821],"genre_scores_gemma":[0.97217035,0.0002939535,0.026043037,0.00007817106,0.00006833029,0.000038000395,0.00065846695,0.000014150354,0.0006355741],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995963,0.00011412697,0.00003957106,0.00009134888,0.00009432089,0.00006425602],"domain_scores_gemma":[0.9989754,0.00048219349,0.000106625404,0.00007071847,0.00029339932,0.000071698254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013503227,0.00071532174,0.0011691488,0.0011963716,0.00030596642,0.00058236724,0.00057663565,0.0006292729,0.00056298194],"category_scores_gemma":[0.0027056732,0.00018948076,0.0008444456,0.00052037067,0.00011584619,0.00065912755,0.00046986874,0.000652754,0.00021466677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037157163,0.00038540678,0.09578206,0.000051150895,0.00043619133,0.00024728343,0.00012035989,0.5802811,0.0030438872,0.0007000476,0.0034848747,0.31509605],"study_design_scores_gemma":[0.0000044547455,0.00005375164,0.002646831,0.0000042639026,0.00003239452,0.0000252946,0.000008918286,0.99635446,0.00040016315,0.00034332252,0.00011946574,0.000006655516],"about_ca_topic_score_codex":0.005690486,"about_ca_topic_score_gemma":0.0043633967,"teacher_disagreement_score":0.005690486,"about_ca_system_score_codex":0.00035647993,"about_ca_system_score_gemma":0.000667117,"threshold_uncertainty_score":0.01131475},"labels":[],"label_agreement":null},{"id":"W3198946153","doi":"10.1007/s11036-021-01835-0","title":"A Deep Neural Network Combined with Radial Basis Function for Abnormality Classification","year":2021,"lang":"en","type":"article","venue":"Mobile Networks and Applications","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University; University of Guelph; Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Classifier (UML); Adaptive neuro fuzzy inference system; Pattern recognition (psychology); Perceptron; Radial basis function; Artificial neural network; Inference; Machine learning; Multilayer perceptron; Radial basis function network; Principal component analysis; Fuzzy logic; Data mining; Fuzzy control system","score_opus":0.06524382574668527,"score_gpt":0.3828735454958513,"score_spread":0.317629719749166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198946153","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048571665,0.0012971763,0.94263536,0.00046172788,0.00033417295,0.0000944071,0.00061884377,0.0037499783,0.0022367619],"genre_scores_gemma":[0.5954436,0.0009957476,0.38556316,0.0004819876,0.00023207233,0.00015800713,0.0019538715,0.0002256363,0.014946004],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996124,0.000053585558,0.000024258676,0.000101755715,0.00013896068,0.000069038884],"domain_scores_gemma":[0.99953663,0.00007536296,0.00003054711,0.000048511796,0.00027552326,0.000033491135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006575897,0.0007503215,0.00093887834,0.00084836327,0.0003120807,0.00063660333,0.0012962143,0.0011096976,0.0023284713],"category_scores_gemma":[0.000928334,0.00040599678,0.00086135766,0.00086735724,0.00018596883,0.00082387036,0.0009205316,0.0011182916,0.0012961057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031957464,0.00026200947,0.0028291894,0.00009225402,0.00015505792,0.00017000506,0.00002704324,0.07695454,0.024740215,0.0016350157,0.01025455,0.8825605],"study_design_scores_gemma":[0.0000076498445,0.000050390696,0.0006132583,0.000007014765,0.000027605847,0.000052101,0.000004809623,0.9930428,0.004856121,0.00043656473,0.00089204,0.0000096024505],"about_ca_topic_score_codex":0.011876936,"about_ca_topic_score_gemma":0.011129059,"teacher_disagreement_score":0.011876936,"about_ca_system_score_codex":0.00053001824,"about_ca_system_score_gemma":0.00097232714,"threshold_uncertainty_score":0.023615599},"labels":[],"label_agreement":null},{"id":"W3200949378","doi":"10.18438/eblip29981","title":"A Landscape Study Highlights the Urgent Need for Evidence Based Strategies to Enable Electronic Health Records Integration in the National Healthcare Systems of Low- and Middle-Income Countries","year":2021,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Grey literature; Scopus; Sustainability; Health care; Developing country; Political science; MEDLINE; Library science; Medicine; Business; Computer science; Economic growth","score_opus":0.09294249616855693,"score_gpt":0.4106600323026944,"score_spread":0.31771753613413745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200949378","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.106266096,0.229771,0.023178685,0.5816661,0.0024278038,0.0008869724,0.0018994667,0.00017984518,0.05372407],"genre_scores_gemma":[0.8112511,0.08814978,0.03841374,0.0571425,0.0009359364,0.000955761,0.0009287791,0.00007876903,0.002143642],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9796448,0.013618242,0.0020744773,0.0012479549,0.0022339753,0.0011805984],"domain_scores_gemma":[0.9171718,0.06517635,0.0053506517,0.0023866668,0.007811844,0.0021028102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036907084,0.0006698648,0.0011480948,0.009649652,0.002777921,0.012904756,0.0020948867,0.0040006996,0.0070284316],"category_scores_gemma":[0.051409923,0.00044907525,0.0018935401,0.0117612155,0.004395574,0.015544079,0.0066774623,0.002833152,0.00054406724],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029770812,0.00040667315,0.04189872,0.06193405,0.0014826668,0.0065762233,0.047864903,0.001481683,0.002874482,0.13836439,0.060915932,0.6359026],"study_design_scores_gemma":[0.00010863891,0.0007209815,0.06917222,0.08058066,0.001385705,0.004490305,0.1598419,0.0011904746,0.0013011798,0.09998374,0.58099896,0.00022533035],"about_ca_topic_score_codex":0.004634148,"about_ca_topic_score_gemma":0.014154449,"teacher_disagreement_score":0.036907084,"about_ca_system_score_codex":0.007690809,"about_ca_system_score_gemma":0.015954973,"threshold_uncertainty_score":0.19518566},"labels":[],"label_agreement":null},{"id":"W3201061916","doi":"10.2196/30277","title":"Accurate Prediction of Stroke for Hypertensive Patients Based on Medical Big Data and Machine Learning Algorithms: Retrospective Study","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Chinese Academy of Sciences","keywords":"Machine learning; Artificial intelligence; Algorithm; Stroke (engine); Receiver operating characteristic; Medical record; Medicine; Big data; Boosting (machine learning); Computer science; Gradient boosting; Decision tree; Random forest; Population; Data mining; Internal medicine; Engineering","score_opus":0.1911957114018802,"score_gpt":0.4521485853851026,"score_spread":0.2609528739832224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201061916","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9966049,0.00037521866,0.001874213,0.000059074137,0.000014931409,0.000048746693,0.0007942243,0.000012073894,0.00021662253],"genre_scores_gemma":[0.9973078,0.00026532673,0.00072791486,0.000041917418,0.000039595165,0.000043451877,0.0014775886,0.0000043785467,0.00009204835],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99838316,0.0005873998,0.00028438246,0.00033581076,0.0002806255,0.00012865175],"domain_scores_gemma":[0.9940798,0.0021818858,0.001215196,0.0012365317,0.0008845078,0.00040200335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003055582,0.0004504356,0.0006292426,0.0014436838,0.00042379426,0.00068123505,0.0004976689,0.00056228664,0.0009067264],"category_scores_gemma":[0.007909603,0.00044691435,0.0011522553,0.0013039836,0.00040702586,0.0010134624,0.0005454188,0.00075538905,0.00031595095],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003583218,0.000136084,0.9952152,0.00003014536,0.0001714442,0.000098149794,0.0000624212,0.00032824263,0.00010292919,0.00005721539,0.00023015843,0.0032097038],"study_design_scores_gemma":[0.00007422537,0.0008002197,0.98450226,0.00003603658,0.0004344618,0.0006830349,0.00030140617,0.011790849,0.00038519278,0.00027493117,0.0006837716,0.00003376408],"about_ca_topic_score_codex":0.0026807128,"about_ca_topic_score_gemma":0.00211438,"teacher_disagreement_score":0.003055582,"about_ca_system_score_codex":0.00032038896,"about_ca_system_score_gemma":0.00064305065,"threshold_uncertainty_score":0.016159713},"labels":[],"label_agreement":null},{"id":"W3205747317","doi":"10.2147/rmhp.s328180","title":"Machine Learning-Based Prediction for 4-Year Risk of Metabolic Syndrome in Adults: A Retrospective Cohort Study","year":2021,"lang":"en","type":"article","venue":"Risk Management and Healthcare Policy","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nipissing University","funders":"National Office for Philosophy and Social Sciences; National Natural Science Foundation of China","keywords":"Metabolic syndrome; Retrospective cohort study; Medicine; Cohort; Artificial intelligence; Machine learning; Computer science; Internal medicine; Obesity","score_opus":0.038714985679990196,"score_gpt":0.4036399559829319,"score_spread":0.3649249703029417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205747317","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9989373,0.00017778453,0.00043166496,0.000015645255,0.0000055972346,0.000018318022,0.0002855728,0.0000036110766,0.00012453095],"genre_scores_gemma":[0.9990208,0.00009562277,0.0003110268,0.000014518173,0.0000072323965,0.00001988836,0.00045345526,0.0000022767513,0.00007520585],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994023,0.00015185152,0.00008290053,0.00015885032,0.00014923434,0.00005486517],"domain_scores_gemma":[0.9983992,0.00036388746,0.00056297303,0.0003204712,0.00023022195,0.00012324433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020787804,0.00030325545,0.00034293838,0.00061739277,0.0003479558,0.00047445772,0.00033075604,0.00041763057,0.0007455173],"category_scores_gemma":[0.002979875,0.00028791168,0.0007471403,0.0006562621,0.00019873865,0.0005394318,0.00032301556,0.0006856472,0.00018791117],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014454656,0.000028250106,0.99891305,0.000004485821,0.000051007315,0.000034191497,0.00001844477,0.000048144866,0.00009698189,0.000012356314,0.000025481084,0.0006229886],"study_design_scores_gemma":[0.000019845875,0.00033088794,0.99772364,0.000010166757,0.000089577305,0.00037768632,0.0000790949,0.0010361447,0.0001292472,0.000032583677,0.00016464636,0.000006525765],"about_ca_topic_score_codex":0.0022664797,"about_ca_topic_score_gemma":0.0020058537,"teacher_disagreement_score":0.0022664797,"about_ca_system_score_codex":0.00020533889,"about_ca_system_score_gemma":0.0003675759,"threshold_uncertainty_score":0.010993779},"labels":[],"label_agreement":null},{"id":"W3206855610","doi":"10.2196/30824","title":"Self–Training With Quantile Errors for Multivariate Missing Data Imputation for Regression Problems in Electronic Medical Records: Algorithm Development Study","year":2021,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Ministry of Trade, Industry and Energy; Ministry of Food and Drug Safety; Korea Medical Device Development Fund","keywords":"Missing data; Imputation (statistics); Wilcoxon signed-rank test; Decision tree; Computer science; Statistics; Random forest; Multivariate statistics; Test data; Mean squared error; Data mining; Artificial intelligence; Machine learning; Mathematics","score_opus":0.24612168456138858,"score_gpt":0.4960280886115006,"score_spread":0.24990640405011202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206855610","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024642387,0.00072700554,0.9733733,0.00024298186,0.000021104945,0.00012568952,0.000031053427,0.00038085555,0.00045559104],"genre_scores_gemma":[0.19933766,0.00069302425,0.7980725,0.00013349732,0.000059995586,0.0003830349,0.00023754912,0.00011574227,0.0009669808],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99632734,0.0024041284,0.00021892843,0.0004268108,0.00046894458,0.00015389384],"domain_scores_gemma":[0.9587408,0.035366867,0.0011730704,0.0016524749,0.0027961982,0.00027050322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017433416,0.0006720418,0.0012705493,0.001158659,0.00042569602,0.00083490653,0.0021094368,0.0014636493,0.0019249391],"category_scores_gemma":[0.041499685,0.00058230944,0.0010583119,0.0014939514,0.0006086401,0.0020449122,0.0015490877,0.0020564261,0.00041834358],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033504612,0.0005232815,0.018240063,0.0002619622,0.0002622009,0.00010452533,0.00037166354,0.5483502,0.0011079201,0.014338303,0.0019728297,0.41413194],"study_design_scores_gemma":[0.00001637494,0.000058849826,0.0005486606,0.000022263524,0.000013047574,0.00003869295,0.000017997016,0.997027,0.00039628058,0.0015301018,0.00032617195,0.0000045456613],"about_ca_topic_score_codex":0.0032612884,"about_ca_topic_score_gemma":0.0020264226,"teacher_disagreement_score":0.017433416,"about_ca_system_score_codex":0.0008235823,"about_ca_system_score_gemma":0.0016177285,"threshold_uncertainty_score":0.092197835},"labels":[],"label_agreement":null},{"id":"W3209399758","doi":"10.1136/oem-2021-epi.442","title":"S-464 Automated Occupational Encoding to the Canadian National Occupation Classification using an Ensemble Classifier from TF-IDF and Doc2Vec Embeddings","year":2021,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Coding (social sciences); Classifier (UML); Support vector machine; Data mining; Artificial intelligence; Machine learning","score_opus":0.34738118149560815,"score_gpt":0.5158195507423838,"score_spread":0.1684383692467757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209399758","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.526192,0.0015894152,0.2821368,0.0022111323,0.0028264893,0.0011389458,0.088764705,0.04825897,0.04688149],"genre_scores_gemma":[0.5469954,0.0006316298,0.23469175,0.00043318066,0.00023734891,0.0005666446,0.14817457,0.0010544485,0.067215085],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994066,0.000042282594,0.00002561599,0.00013971693,0.00023743609,0.000148389],"domain_scores_gemma":[0.99906904,0.00009621686,0.000023069771,0.00009352431,0.0006538418,0.00006429064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042340555,0.001103465,0.00045078006,0.0018226433,0.00096023444,0.0011603439,0.0008099315,0.00063568057,0.0134814475],"category_scores_gemma":[0.0021450755,0.00019019611,0.00080818677,0.0018074473,0.0002763349,0.0006406991,0.0006961507,0.0008626703,0.0081571555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067759544,0.00023921963,0.019096917,0.00023559561,0.00009952692,0.00043279427,0.00033897063,0.016650591,0.027561333,0.0023629416,0.14109777,0.79120684],"study_design_scores_gemma":[0.00006817006,0.00026033554,0.046959314,0.00013086449,0.000114818926,0.00032368567,0.0014320654,0.79847246,0.059864044,0.0029133142,0.08933354,0.00012734144],"about_ca_topic_score_codex":0.42498752,"about_ca_topic_score_gemma":0.5199836,"teacher_disagreement_score":0.57501245,"about_ca_system_score_codex":0.0027485788,"about_ca_system_score_gemma":0.0060771103,"threshold_uncertainty_score":0.8450276},"labels":[],"label_agreement":null},{"id":"W3210290409","doi":"10.1155/2021/2621655","title":"A Machine-Learning-Based System for Prediction of Cardiovascular and Chronic Respiratory Diseases","year":2021,"lang":"en","type":"article","venue":"Journal of Healthcare Engineering","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":17,"is_retracted":true,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Vital signs; Machine learning; Decision tree; Support vector machine; Artificial intelligence; Naive Bayes classifier; Medicine; Clinical decision support system; Computer science; Decision support system","score_opus":0.06145172069090836,"score_gpt":0.3635881226520493,"score_spread":0.30213640196114094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210290409","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32763147,0.0036359522,0.5936908,0.002870508,0.0013703819,0.0011963422,0.009920257,0.050410394,0.009273892],"genre_scores_gemma":[0.85683244,0.0005926634,0.1322468,0.0005570813,0.00019302127,0.00052001607,0.0048426124,0.000070257425,0.004145092],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993144,0.00009226505,0.00008651726,0.0002849571,0.00014918193,0.0000726722],"domain_scores_gemma":[0.9989213,0.00048733762,0.00012204351,0.0000739829,0.00032876976,0.00006653779],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011590935,0.0010219543,0.0010538442,0.0013453466,0.00056631624,0.0006901941,0.0011324179,0.0012156744,0.0029855003],"category_scores_gemma":[0.0031326744,0.00030282987,0.0006038414,0.0008666769,0.00014955606,0.0009162002,0.00045602437,0.0009596093,0.0016771627],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014251388,0.0022664205,0.0678486,0.0005098437,0.00033360624,0.0013169906,0.00019944565,0.09591893,0.017084027,0.0014192308,0.038357876,0.77331984],"study_design_scores_gemma":[0.000052749063,0.00028519408,0.009600109,0.000040179115,0.000056241493,0.00017709387,0.000028050023,0.9815702,0.0046187015,0.0009813955,0.002553191,0.000036761234],"about_ca_topic_score_codex":0.00949154,"about_ca_topic_score_gemma":0.0076348763,"teacher_disagreement_score":0.00949154,"about_ca_system_score_codex":0.0006906251,"about_ca_system_score_gemma":0.0009238867,"threshold_uncertainty_score":0.01887256},"labels":[],"label_agreement":null},{"id":"W3210344725","doi":"10.5220/0010717100003059","title":"Machine Learning Applications to Sports Injury: A Review","year":2021,"lang":"en","type":"review","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Sports injury; Artificial intelligence; Medicine; Physical therapy","score_opus":0.34935729914767244,"score_gpt":0.6102759827916103,"score_spread":0.2609186836439379,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210344725","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000057378562,0.99931157,0.0000750617,0.00015870115,0.000091583366,0.000008107312,0.000023801913,0.00000353326,0.00027020084],"genre_scores_gemma":[0.0003152939,0.9991447,0.0001370245,0.00016399029,0.000084393876,0.000006441245,0.000023347975,9.339439e-7,0.00012383016],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996369,0.00007489654,0.00008345231,0.00005531812,0.00012524283,0.000024230922],"domain_scores_gemma":[0.99846005,0.00093926373,0.00019658712,0.000026520564,0.0003110515,0.00006652127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012785688,0.00085570785,0.00246558,0.0034483727,0.00025774137,0.0012288223,0.0010593544,0.0013844142,0.004141769],"category_scores_gemma":[0.0026316592,0.00034874986,0.0013352036,0.0037654438,0.00039790172,0.0011851692,0.00084305473,0.001386594,0.0014826265],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101392114,0.00009274391,0.00034219335,0.07658636,0.00053551025,0.00013472684,0.00005354594,0.0003579776,0.00049460446,0.0011959941,0.029004643,0.8911003],"study_design_scores_gemma":[0.0001804817,0.00032225114,0.004014158,0.08955499,0.0035847588,0.0012421331,0.0001478721,0.00039723492,0.00046956833,0.0021939103,0.89781916,0.00007344996],"about_ca_topic_score_codex":0.002411677,"about_ca_topic_score_gemma":0.0061070914,"teacher_disagreement_score":0.004141769,"about_ca_system_score_codex":0.0006264374,"about_ca_system_score_gemma":0.0021564888,"threshold_uncertainty_score":0.013855636},"labels":[],"label_agreement":null},{"id":"W3210358020","doi":"10.3390/app10186553","title":"Healthcare Applications of Artificial Intelligence and Analytics: A Review and Proposed Framework","year":2020,"lang":"en","type":"review","venue":"Applied Sciences","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; Carleton University; University of Ottawa; Université du Québec en Outaouais","funders":"","keywords":"Health care; Analytics; Data science; Applications of artificial intelligence; Field (mathematics); Computer science; Big data; Knowledge management; Artificial intelligence; Political science","score_opus":0.34516631197836184,"score_gpt":0.5427890556584459,"score_spread":0.1976227436800841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210358020","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009996078,0.99763,0.00039534087,0.0006875651,0.00014815107,0.000015808839,0.00002331418,0.000007803198,0.0009920624],"genre_scores_gemma":[0.00083094614,0.99790704,0.000572652,0.0003166331,0.00017686778,0.000020593561,0.000024571133,0.0000017999807,0.0001489389],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989784,0.00025761762,0.00023497861,0.00013745896,0.00032637303,0.00006520617],"domain_scores_gemma":[0.99612975,0.0027406332,0.0003346203,0.00006300709,0.0006388113,0.00009310218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023141394,0.0012387937,0.0016585073,0.009152993,0.00061089505,0.0025358433,0.0011598814,0.0017336162,0.0031701413],"category_scores_gemma":[0.003964936,0.0004905213,0.0013807662,0.00910972,0.00092893385,0.002845309,0.0012457228,0.0019795708,0.0011287879],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005595233,0.000101585254,0.000721013,0.07593606,0.00028510185,0.00026993774,0.00038309148,0.00063424185,0.0006269397,0.016773725,0.022715079,0.88149714],"study_design_scores_gemma":[0.000018962031,0.0001341545,0.0023513658,0.059966933,0.000814399,0.0016432746,0.00038674945,0.00052568584,0.00039167106,0.010210094,0.9234914,0.00006528405],"about_ca_topic_score_codex":0.0024419576,"about_ca_topic_score_gemma":0.003593922,"teacher_disagreement_score":0.009152993,"about_ca_system_score_codex":0.0014672442,"about_ca_system_score_gemma":0.0050706873,"threshold_uncertainty_score":0.012238443},"labels":[],"label_agreement":null},{"id":"W3210824720","doi":"10.21203/rs.3.rs-958135/v1","title":"Comparison of State-Of-The-Art Neural Network Survival Models With The Pooled Cohort Equations for Cardiovascular Disease Risk Prediction","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"U.S. National Library of Medicine; National Institutes of Health","keywords":"Proportional hazards model; Pooling; Cohort; Survival analysis; Artificial neural network; Medicine; Computer science; Statistics; Artificial intelligence; Internal medicine; Mathematics","score_opus":0.310725653595216,"score_gpt":0.5205198769652457,"score_spread":0.20979422337002973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210824720","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8331518,0.018968713,0.12962568,0.002884264,0.001256086,0.00020224927,0.008677348,0.0013693245,0.003864522],"genre_scores_gemma":[0.9574215,0.0030778623,0.027007975,0.0003748002,0.0003350704,0.0001690364,0.008534059,0.00018603334,0.0028937317],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970624,0.0018233571,0.00022775275,0.00051455415,0.00024312621,0.0001288719],"domain_scores_gemma":[0.97848105,0.017537644,0.00051808025,0.0014806831,0.001698,0.00028449914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020193977,0.0014575294,0.0024352146,0.0011252551,0.00047815003,0.0017051803,0.0023820116,0.0017523709,0.0027870806],"category_scores_gemma":[0.02555481,0.0005700899,0.0027563889,0.0010412887,0.00038381192,0.0017690709,0.0012053393,0.0027580368,0.0008102479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012453369,0.0010074801,0.082827225,0.00095385744,0.009647023,0.0001736691,0.00032103673,0.6551152,0.000803804,0.0038750204,0.011464043,0.22135833],"study_design_scores_gemma":[0.00025326625,0.00043592288,0.0152004175,0.00012175349,0.0010452316,0.00004534258,0.000070697264,0.979229,0.00036707756,0.0022577455,0.0009175076,0.00005604884],"about_ca_topic_score_codex":0.034221537,"about_ca_topic_score_gemma":0.023358224,"teacher_disagreement_score":0.034221537,"about_ca_system_score_codex":0.0011521154,"about_ca_system_score_gemma":0.0021177933,"threshold_uncertainty_score":0.10679722},"labels":[],"label_agreement":null},{"id":"W3211063541","doi":"10.11648/j.ijiis.20211005.11","title":"Designing Adaptive Mechanism for COVID-19 and Exacerbation in Cases of COPD Patients Using Machine Learning Approaches","year":2021,"lang":"en","type":"article","venue":"International Journal of Intelligent Information Systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"COPD; Exacerbation; Context (archaeology); Medicine; Artificial intelligence; Machine learning; Dashboard; Coronavirus disease 2019 (COVID-19); Copd exacerbation; Intensive care medicine; Computer science; Disease; Internal medicine; Data science; Infectious disease (medical specialty)","score_opus":0.32190834867781515,"score_gpt":0.44500441010973724,"score_spread":0.12309606143192209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211063541","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18901366,0.00064216676,0.7999876,0.0012953064,0.00022306613,0.00039665354,0.00014951164,0.0017656558,0.006526288],"genre_scores_gemma":[0.9651811,0.00012541097,0.032632917,0.00018577222,0.000055972905,0.00020222909,0.00008636764,0.000025732817,0.0015045363],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991424,0.0001490725,0.000082174185,0.0002917771,0.0001792222,0.00015527452],"domain_scores_gemma":[0.99874496,0.0005148968,0.00023329924,0.000096048345,0.0002728957,0.00013777093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093663565,0.00054724293,0.00063297607,0.0008733518,0.0005774351,0.000938555,0.0014248189,0.0011294392,0.0029118904],"category_scores_gemma":[0.0050873063,0.00034359386,0.0006502117,0.00028152848,0.00043993705,0.001012247,0.0008729363,0.00084618066,0.00047689732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008338502,0.0011159952,0.12376675,0.00034884232,0.0002528161,0.0032756971,0.0012634033,0.378597,0.03354048,0.014657597,0.007266391,0.43508118],"study_design_scores_gemma":[0.000027921762,0.00012527684,0.0073573873,0.000024155677,0.0000443112,0.00046253853,0.00012535702,0.9841697,0.0029038333,0.0033918216,0.0013424661,0.000025091642],"about_ca_topic_score_codex":0.0031489294,"about_ca_topic_score_gemma":0.0025243473,"teacher_disagreement_score":0.0031489294,"about_ca_system_score_codex":0.0006375834,"about_ca_system_score_gemma":0.00095437065,"threshold_uncertainty_score":0.009741247},"labels":[],"label_agreement":null},{"id":"W3212465484","doi":"10.1155/2021/8336887","title":"[Retracted] Obesity Mass Monitoring in Medical Big Data Based on High‐Order Simulated Annealing Neural Network Algorithm","year":2021,"lang":"en","type":"article","venue":"Computational Intelligence and Neuroscience","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":true,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Tianjin University; University of Toronto","keywords":"Simulated annealing; Big data; Computer science; Artificial neural network; Order (exchange); Data mining; Artificial intelligence; Algorithm; Business; Finance","score_opus":0.29846633397246514,"score_gpt":0.4775499181994073,"score_spread":0.17908358422694215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212465484","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010013603,0.000846121,0.97708195,0.002530912,0.0018462818,0.00015177407,0.00024148021,0.0011144846,0.00617346],"genre_scores_gemma":[0.31616753,0.0024820825,0.6471563,0.0020046856,0.0011043503,0.00061619503,0.0013044209,0.0005232391,0.02864126],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946374,0.00018656043,0.000054788805,0.000111458874,0.00014961959,0.00003377968],"domain_scores_gemma":[0.99883765,0.00031299354,0.000061434446,0.00011073112,0.0006335337,0.000043588938],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0011834562,0.0006876601,0.0006652143,0.00052827114,0.0005528521,0.00084213424,0.0014918695,0.001278939,0.004523484],"category_scores_gemma":[0.004223225,0.0003948311,0.0014658993,0.0009358677,0.0004910998,0.0011436995,0.000765063,0.0018629016,0.0012672759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025931277,0.00009493022,0.0053690877,0.00051030604,0.0003936426,0.00040783503,0.00028816445,0.6904366,0.0039430503,0.027437562,0.04198534,0.22887412],"study_design_scores_gemma":[0.000023765204,0.00002555623,0.0005403048,0.000025067424,0.000027303622,0.000047906236,0.000017321985,0.98482645,0.0009700893,0.0058374964,0.0076395757,0.000019041014],"about_ca_topic_score_codex":0.015916666,"about_ca_topic_score_gemma":0.0102213295,"teacher_disagreement_score":0.99872106,"about_ca_system_score_codex":0.00049683446,"about_ca_system_score_gemma":0.0011865095,"threshold_uncertainty_score":0.03164804},"labels":[],"label_agreement":null},{"id":"W3214120707","doi":"10.1075/cilt.356.09emb","title":"The perils of big data","year":2021,"lang":"en","type":"book-chapter","venue":"Amsterdam studies in the theory and history of linguistic science. Series 4, Current issues in linguistic theory","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Big data; Data science; Process (computing); Computer science; History; Data mining","score_opus":0.3078001384030181,"score_gpt":0.4859037882114023,"score_spread":0.17810364980838417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214120707","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024921,0.09199673,0.018185232,0.82693344,0.015327566,0.000060601364,0.0005602628,0.0003346408,0.044109408],"genre_scores_gemma":[0.20735249,0.20134233,0.049913846,0.421206,0.07751328,0.0008828514,0.001735383,0.0018851665,0.03816871],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95188195,0.025856268,0.0013806213,0.002117112,0.017615905,0.0011481015],"domain_scores_gemma":[0.7397544,0.2207584,0.0032317303,0.018540885,0.012906473,0.0048081647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06599303,0.00075646414,0.0013003876,0.004879614,0.004359715,0.022365209,0.0040096724,0.0076927347,0.01020442],"category_scores_gemma":[0.1163038,0.0007247287,0.0010839336,0.008765613,0.019418925,0.046505626,0.009382768,0.0206008,0.0034801152],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006658587,0.000029296536,0.00074833207,0.0006833906,0.000056012555,0.00015249304,0.0020308045,0.0006335622,0.00013057361,0.7059878,0.22348544,0.06599571],"study_design_scores_gemma":[0.000013737097,0.000021322909,0.000469104,0.0014591957,0.000012661207,0.00019422182,0.0019629654,0.0011185076,0.0001490813,0.50263274,0.49193108,0.000035406807],"about_ca_topic_score_codex":0.0022124555,"about_ca_topic_score_gemma":0.0024179698,"teacher_disagreement_score":0.06599303,"about_ca_system_score_codex":0.0042208554,"about_ca_system_score_gemma":0.006974851,"threshold_uncertainty_score":0.34900868},"labels":[],"label_agreement":null},{"id":"W3214205714","doi":"10.1016/j.cmpb.2021.106479","title":"Corrigendum to Longitudinal machine learning modeling of MS patient trajectories improves predictions of disability progression: [Computer Methods and Programs in Biomedicine, Volume 208, (September 2021) 106180]","year":2021,"lang":"en","type":"erratum","venue":"Computer Methods and Programs in Biomedicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; Centre intégré de santé et de services sociaux de Chaudière-Appalaches","funders":"","keywords":"Biomedicine; Volume (thermodynamics); Computer science; Machine learning; Artificial intelligence; Data science; Bioinformatics","score_opus":0.19168419341457277,"score_gpt":0.4925775119264919,"score_spread":0.30089331851191914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214205714","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001565707,0.0011404936,0.00067545305,0.0420606,0.9479665,0.0000471088,0.0011596006,0.00055719324,0.006236592],"genre_scores_gemma":[0.008192588,0.0076421085,0.0045405664,0.104867406,0.34788916,0.00035420255,0.0049928543,0.0016873291,0.5198337],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99479336,0.00083196355,0.00086428673,0.0007285628,0.0022798062,0.0005020378],"domain_scores_gemma":[0.9663326,0.0050622327,0.0009719092,0.0017809732,0.024516318,0.0013358719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038424542,0.0027087335,0.003149922,0.00402974,0.0037797615,0.00515757,0.0038913721,0.009381168,0.117402256],"category_scores_gemma":[0.048922464,0.0012592503,0.0024047124,0.0028170014,0.0013777707,0.001802178,0.001859271,0.007578794,0.0671007],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018824408,0.000010129123,0.000047702142,0.00004481992,0.0000063486073,0.00007301585,0.0000044088647,0.000034319757,0.00001769955,0.00016383192,0.9956025,0.0039764075],"study_design_scores_gemma":[0.00008704494,0.000090125235,0.0025210741,0.00048876635,0.00008840398,0.00039446072,0.000063411746,0.0013542102,0.00055759674,0.0019380674,0.99234456,0.000072354844],"about_ca_topic_score_codex":0.05569914,"about_ca_topic_score_gemma":0.071031794,"teacher_disagreement_score":0.117402256,"about_ca_system_score_codex":0.005351666,"about_ca_system_score_gemma":0.0065070065,"threshold_uncertainty_score":0.39274967},"labels":[],"label_agreement":null},{"id":"W3216116934","doi":"","title":"Promoting Positive Change with Blood Glucose Entry Error and Documentation in Acute Care","year":2021,"lang":"en","type":"article","venue":"Student Research Proceedings","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Documentation; Patient safety; Nursing; Health care; Intervention (counseling); Medicine; Presentation (obstetrics); Acute care; Medical education; Psychology; Political science; Computer science; Surgery","score_opus":0.2289002505483496,"score_gpt":0.5663892927363576,"score_spread":0.337489042188008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216116934","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9526328,0.00071731803,0.011054916,0.011112456,0.00044809532,0.003280803,0.000047025438,0.00051550963,0.020191053],"genre_scores_gemma":[0.9279996,0.0013463628,0.05943324,0.0022126373,0.00014205764,0.0022864037,0.0000709996,0.00005584575,0.0064528077],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98392075,0.0108535,0.00060874777,0.0005831432,0.0026160388,0.0014178255],"domain_scores_gemma":[0.98222315,0.0070797084,0.002310865,0.00091055315,0.0023208742,0.005154873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016374068,0.0005580093,0.00044035856,0.00075621373,0.0040927394,0.0031715864,0.0017325175,0.00155801,0.0039200746],"category_scores_gemma":[0.03234932,0.00048518216,0.0006022743,0.0004846816,0.001712834,0.002006014,0.005967568,0.002554822,0.000861712],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046842656,0.026143026,0.027410908,0.0024003265,0.000057990626,0.0008681207,0.07317605,0.00051022676,0.0065425285,0.0017211699,0.012037501,0.8486638],"study_design_scores_gemma":[0.0017402816,0.059484556,0.4518261,0.006875101,0.0003491502,0.002679756,0.28633937,0.0057909866,0.04412918,0.008000766,0.13227785,0.00050680566],"about_ca_topic_score_codex":0.0020034781,"about_ca_topic_score_gemma":0.0044799363,"teacher_disagreement_score":0.016374068,"about_ca_system_score_codex":0.0022468593,"about_ca_system_score_gemma":0.013868799,"threshold_uncertainty_score":0.08659536},"labels":[],"label_agreement":null},{"id":"W38781171","doi":"10.3233/978-1-61499-488-6-308","title":"Mining Association Rules in the BCCA Liver Cancer Data Set","year":2015,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"BC Cancer Agency; University of Victoria","funders":"","keywords":"Association rule learning; Computer science; Set (abstract data type); Association (psychology); Liver cancer; Data mining; Cancer; Medicine; Internal medicine; Programming language; Psychology","score_opus":0.5360176541878315,"score_gpt":0.5770954342712672,"score_spread":0.041077780083435655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W38781171","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9606207,0.0011697608,0.009652411,0.00079790544,0.000061969404,0.0002731875,0.025585718,0.00035160463,0.0014867871],"genre_scores_gemma":[0.8804198,0.00078567915,0.049842913,0.00021283867,0.000061300576,0.00033538984,0.06754076,0.00002251909,0.00077889767],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99681866,0.0006781863,0.00047693166,0.0005610905,0.0011766441,0.0002884175],"domain_scores_gemma":[0.9916276,0.0048890393,0.001055214,0.0007830602,0.0013669543,0.00027811778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021666691,0.00054662046,0.0009975301,0.0051991697,0.0010442969,0.0017060976,0.00074204133,0.0007781234,0.00041358356],"category_scores_gemma":[0.010435622,0.00025137677,0.00079401047,0.005354195,0.00043611237,0.0005764227,0.00065090926,0.00081924634,0.0002930167],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00090849353,0.0014608843,0.7505928,0.0006414018,0.0007018757,0.005285178,0.0010291381,0.04428755,0.005468062,0.001319568,0.0124949915,0.17581001],"study_design_scores_gemma":[0.00020379797,0.0005178459,0.6813299,0.00032463874,0.0005026343,0.0043575964,0.0042253565,0.26630595,0.008552076,0.0049769063,0.028579062,0.0001241771],"about_ca_topic_score_codex":0.064437225,"about_ca_topic_score_gemma":0.07441983,"teacher_disagreement_score":0.064437225,"about_ca_system_score_codex":0.0011815452,"about_ca_system_score_gemma":0.0030125782,"threshold_uncertainty_score":0.1281243},"labels":[],"label_agreement":null},{"id":"W4200042763","doi":"10.1109/ictc52510.2021.9620780","title":"An Evaluation of Machine Learning Classifiers for Prediction of Alzheimer's Disease, Mild Cognitive Impairment and Normal Cognition","year":2021,"lang":"en","type":"article","venue":"2021 International Conference on Information and Communication Technology Convergence (ICTC)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Ministry of Science and ICT, South Korea; National Research Foundation","keywords":"Dementia; Machine learning; Naive Bayes classifier; Artificial intelligence; Support vector machine; Random forest; Decision tree; Computer science; Disease; Cognition; Alzheimer's disease; Statistical classification; Logistic regression; Supervised learning; Medicine; Artificial neural network; Psychiatry; Pathology","score_opus":0.16491398997414525,"score_gpt":0.4376043587043143,"score_spread":0.27269036873016905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200042763","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9655667,0.006476495,0.018227564,0.0007704241,0.00066636474,0.00045599107,0.0026789836,0.0006929533,0.0044645555],"genre_scores_gemma":[0.9766591,0.00090480904,0.016844412,0.00013477019,0.00011351548,0.0001675891,0.0041383854,0.000018801184,0.0010185788],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974402,0.0009492598,0.0003097193,0.0004316556,0.00066757697,0.00020154858],"domain_scores_gemma":[0.9915828,0.005605681,0.00035090544,0.00037321984,0.0017915961,0.000295739],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008179414,0.0013120283,0.0011695632,0.0024193653,0.00059711334,0.0011526467,0.0009567632,0.0013936331,0.0008781056],"category_scores_gemma":[0.012815819,0.0002200826,0.00089942245,0.0011360797,0.00029734636,0.0011482768,0.00058823416,0.00087416236,0.00041626132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008165525,0.0048448555,0.25582525,0.0007972086,0.0015397418,0.00028154653,0.00020581379,0.19653027,0.0036200036,0.0012322904,0.015752496,0.51120496],"study_design_scores_gemma":[0.00017079565,0.0022646685,0.040157106,0.00010551486,0.0002510943,0.000113733426,0.00020936142,0.952714,0.0022225662,0.00050251937,0.0012582121,0.000030412952],"about_ca_topic_score_codex":0.011746787,"about_ca_topic_score_gemma":0.006529023,"teacher_disagreement_score":0.011746787,"about_ca_system_score_codex":0.0010763033,"about_ca_system_score_gemma":0.0014667273,"threshold_uncertainty_score":0.043257356},"labels":[],"label_agreement":null},{"id":"W4200296940","doi":"10.1016/j.compbiomed.2021.105102","title":"A machine learning framework for risk prediction of multi-label cardiovascular events based on focused carotid plaque B-Mode ultrasound: A Canadian study","year":2021,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Medicine; Demographics; Ultrasound; Artificial intelligence; Area under the curve; Coronary artery disease; Internal medicine; Machine learning; Cardiology; Radiology; Computer science","score_opus":0.10877528221570278,"score_gpt":0.4465551529747957,"score_spread":0.33777987075909294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200296940","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41120732,0.0048395786,0.5677725,0.005042298,0.000252884,0.00043042828,0.002523943,0.0012123069,0.006718734],"genre_scores_gemma":[0.81008464,0.0015478142,0.17833044,0.00038028357,0.0001367999,0.00018448509,0.0021192892,0.00011555148,0.00710064],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918777,0.00033005895,0.00003881677,0.00016418922,0.00016491047,0.000114311],"domain_scores_gemma":[0.9968098,0.0016593763,0.00012186732,0.00012527117,0.0011545492,0.00012907672],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004802345,0.0008748952,0.0010739783,0.0020433257,0.0011344829,0.0017265165,0.0018471393,0.0010752073,0.0018855294],"category_scores_gemma":[0.00798962,0.00038410473,0.0011907371,0.0014894528,0.00055840437,0.0007436792,0.0006834095,0.0016999634,0.00044670608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010643251,0.0012908473,0.07779447,0.00017938654,0.0009597429,0.0005583578,0.00050088065,0.45851496,0.0028270301,0.022626292,0.016428182,0.4172556],"study_design_scores_gemma":[0.00004684969,0.000059367638,0.009755216,0.000021328595,0.00009514592,0.000054934426,0.000052728246,0.98533314,0.00020468919,0.003133229,0.0012159037,0.000027440261],"about_ca_topic_score_codex":0.7484131,"about_ca_topic_score_gemma":0.6063646,"teacher_disagreement_score":0.2515869,"about_ca_system_score_codex":0.00579378,"about_ca_system_score_gemma":0.008563972,"threshold_uncertainty_score":0.50613713},"labels":[],"label_agreement":null},{"id":"W4200356965","doi":"10.1109/smartgencon51891.2021.9645906","title":"Deep Learning based System Design for Diabetes Prediction","year":2021,"lang":"en","type":"article","venue":"2021 International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Diabetes mellitus; Type 2 diabetes; Computer science; Artificial neural network; MNIST database; Artificial intelligence; Backpropagation; Medicine; Deep learning; Machine learning; Dropout (neural networks)","score_opus":0.2064133697448031,"score_gpt":0.41009902180507296,"score_spread":0.20368565206026987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200356965","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03761084,0.00149241,0.9451232,0.0009166874,0.0003408807,0.00025333068,0.00054392114,0.00587703,0.007841785],"genre_scores_gemma":[0.85773677,0.00079957506,0.13120963,0.0005853555,0.00011455946,0.0004325876,0.0008817578,0.00006898709,0.008170824],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997212,0.00004098201,0.000026471434,0.000087960936,0.00006497384,0.000058343136],"domain_scores_gemma":[0.999634,0.00008067221,0.000034411343,0.000025877529,0.00019700776,0.000027952809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064915605,0.0005234852,0.00049304496,0.00037044255,0.00045060416,0.0008325911,0.0011810052,0.00080654956,0.0054720608],"category_scores_gemma":[0.0010902274,0.00030528023,0.00041172912,0.00030476376,0.00022627573,0.0007227403,0.00073205744,0.0011973525,0.001285993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064656144,0.00044333324,0.00472265,0.00033845392,0.00013713785,0.00036932246,0.0001256385,0.45125172,0.020238949,0.005801214,0.012631574,0.50329345],"study_design_scores_gemma":[0.0000151697,0.00008812713,0.00043223874,0.000015146845,0.000021793223,0.000043637083,0.000008798954,0.9931003,0.003306396,0.0013098393,0.0016489483,0.000009610225],"about_ca_topic_score_codex":0.008797464,"about_ca_topic_score_gemma":0.008737856,"teacher_disagreement_score":0.008797464,"about_ca_system_score_codex":0.00090076076,"about_ca_system_score_gemma":0.0011292713,"threshold_uncertainty_score":0.018305898},"labels":[],"label_agreement":null},{"id":"W4200369656","doi":"10.2196/33105","title":"Correction: Evaluation of Three Feasibility Tools for Identifying Patient Data and Biospecimen Availability: Comparative Usability Study","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Bundesministerium für Bildung und Forschung; Friedrich-Alexander-Universität Erlangen-Nürnberg","keywords":"Usability; Computer science; Data science; Information retrieval; Software engineering; Human–computer interaction","score_opus":0.638175536280701,"score_gpt":0.5905782631291309,"score_spread":0.04759727315157014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200369656","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009412581,0.000822656,0.0034819462,0.13995008,0.8478878,0.00024457282,0.0030578382,0.0011595745,0.002454193],"genre_scores_gemma":[0.07674346,0.0074339034,0.03906948,0.31749094,0.29418272,0.003504715,0.007160247,0.0076794527,0.24673513],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.98005277,0.005144988,0.004553132,0.0019136771,0.0073263375,0.0010089679],"domain_scores_gemma":[0.64101803,0.082844116,0.011384023,0.016854454,0.24199778,0.005901573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018000416,0.0019877534,0.002331647,0.0048800814,0.0044061034,0.0051776273,0.0047250846,0.009763658,0.047333542],"category_scores_gemma":[0.3477156,0.0016488087,0.0017683712,0.0029832006,0.003921961,0.0031010539,0.0034859793,0.0118315155,0.023917845],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007645116,0.000011955688,0.00019914462,0.00041194347,0.000028134062,0.00025263516,0.00024765098,0.000051054416,0.00015090541,0.0005066259,0.9914135,0.0066501144],"study_design_scores_gemma":[0.00021224596,0.00007227396,0.0033759037,0.0020278646,0.00016737632,0.0010542962,0.00088711444,0.0009343321,0.0011704832,0.0015434899,0.98838633,0.00016821401],"about_ca_topic_score_codex":0.032200914,"about_ca_topic_score_gemma":0.031231292,"teacher_disagreement_score":0.047333542,"about_ca_system_score_codex":0.007986173,"about_ca_system_score_gemma":0.014511686,"threshold_uncertainty_score":0.15834647},"labels":[],"label_agreement":null},{"id":"W4200513061","doi":"10.18280/isi.260604","title":"Framework Two-Tier Feature Selection on the Intelligence System Model for Detecting Coronary Heart Disease","year":2021,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Badan Riset dan Inovasi Nasional","keywords":"Feature selection; Computer science; Normalization (sociology); Artificial intelligence; Context (archaeology); Feature (linguistics); Selection (genetic algorithm); Machine learning; Predictive modelling; Data mining; Pattern recognition (psychology)","score_opus":0.09604406356798188,"score_gpt":0.39403385238368005,"score_spread":0.29798978881569815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200513061","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07840289,0.0007231324,0.9142817,0.0006533951,0.00009140129,0.0003394952,0.00036010303,0.002470786,0.002677105],"genre_scores_gemma":[0.884152,0.00033019632,0.10969768,0.00017778481,0.0000771669,0.00038618088,0.00071371975,0.00003616343,0.0044291047],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999134,0.00021415486,0.0000538346,0.0002318178,0.00023401507,0.00013219014],"domain_scores_gemma":[0.99945813,0.00014399497,0.000045068005,0.000036062625,0.00028916358,0.00002759056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011832995,0.00092209014,0.0008126457,0.0009795704,0.00044528255,0.0010592903,0.0008957436,0.0006546617,0.001618384],"category_scores_gemma":[0.0014228203,0.00023863679,0.00090659293,0.00066944904,0.00030281054,0.00066305563,0.00053372106,0.000538248,0.00058247324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007425722,0.00062779424,0.01984899,0.00022734045,0.00049787184,0.00050240563,0.0002691612,0.4951141,0.019691862,0.0069720433,0.00638562,0.44912037],"study_design_scores_gemma":[0.000011334478,0.0001498488,0.0032323399,0.000007752475,0.000049061724,0.00007740902,0.000014713409,0.9928329,0.0017199365,0.0011680091,0.00072000065,0.00001667238],"about_ca_topic_score_codex":0.011421208,"about_ca_topic_score_gemma":0.0065635964,"teacher_disagreement_score":0.011421208,"about_ca_system_score_codex":0.000810339,"about_ca_system_score_gemma":0.0011121904,"threshold_uncertainty_score":0.02270943},"labels":[],"label_agreement":null},{"id":"W4200515998","doi":"10.3390/ijerph19010226","title":"Clinical Decision Support System Based on Hybrid Knowledge Modeling: A Case Study of Chronic Kidney Disease-Mineral and Bone Disorder Treatment","year":2021,"lang":"en","type":"article","venue":"International Journal of Environmental Research and Public Health","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"","keywords":"Clinical decision support system; Concordance; Medicine; Medical prescription; Cronbach's alpha; Usability; Kidney disease; Hemodialysis; Decision support system; Intensive care medicine; Medical physics; Internal medicine; Data mining; Computer science; Nursing; Psychometrics; Clinical psychology","score_opus":0.2972481111212916,"score_gpt":0.5594149110202615,"score_spread":0.2621667998989699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200515998","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9487211,0.0011202954,0.03443717,0.0046172854,0.00010177406,0.00057422963,0.0037888936,0.00086951785,0.005769675],"genre_scores_gemma":[0.9328335,0.0005739491,0.060545303,0.00047752837,0.000049869814,0.00021700631,0.0033035593,0.00005611941,0.0019431849],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981402,0.000788391,0.00027765406,0.00029502728,0.0003653479,0.00013345055],"domain_scores_gemma":[0.9946162,0.0038711573,0.0002585202,0.00039494803,0.00047579122,0.00038335682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00272204,0.0005506308,0.0006504516,0.0014492694,0.0011237871,0.0015665792,0.0013778048,0.0019201457,0.00226429],"category_scores_gemma":[0.0069199153,0.0002774751,0.0009196075,0.0016106172,0.00050418667,0.0014229884,0.0012284385,0.00097429164,0.00040198793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032364314,0.008345547,0.27039972,0.0024552804,0.0006976436,0.06796601,0.008932525,0.2131803,0.012835033,0.011261454,0.03843081,0.3622593],"study_design_scores_gemma":[0.0005601573,0.0009234244,0.052264165,0.00028401552,0.0003486488,0.007704408,0.0063678618,0.8658831,0.0123984935,0.006927801,0.046151917,0.0001859909],"about_ca_topic_score_codex":0.01398032,"about_ca_topic_score_gemma":0.019317921,"teacher_disagreement_score":0.01398032,"about_ca_system_score_codex":0.0017119542,"about_ca_system_score_gemma":0.0017062877,"threshold_uncertainty_score":0.027797937},"labels":[],"label_agreement":null},{"id":"W4200580008","doi":"10.3390/electronics10233026","title":"Effective Voting Ensemble of Homogenous Ensembling with Multiple Attribute-Selection Approaches for Improved Identification of Thyroid Disorder","year":2021,"lang":"en","type":"article","venue":"Electronics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Feature selection; Artificial intelligence; Computer science; Random forest; Thyroid; Pattern recognition (psychology); Boosting (machine learning); Machine learning; Decision tree; Ensemble learning; Voting; Internal medicine; Medicine","score_opus":0.07031332372671006,"score_gpt":0.3722459394283462,"score_spread":0.30193261570163615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200580008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21182,0.0011788185,0.78405,0.00015825077,0.00010405424,0.00008565515,0.00007678312,0.00082547823,0.0017008985],"genre_scores_gemma":[0.90735817,0.00017584043,0.090759955,0.00010240651,0.00004628236,0.000061767605,0.00023518964,0.000036477486,0.0012239409],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991999,0.00029849776,0.000049035716,0.00017802113,0.00016738234,0.00010718192],"domain_scores_gemma":[0.9990971,0.0003557133,0.000069403104,0.00012092082,0.00028847723,0.00006842055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022766003,0.00088529487,0.0015727713,0.00081266434,0.00049640913,0.0007158052,0.0009775334,0.00055779476,0.0005927212],"category_scores_gemma":[0.0024870336,0.00032967338,0.0009986917,0.00061389036,0.00026283882,0.0007259875,0.00075298356,0.0005645219,0.00026076334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044357547,0.00029695724,0.011829639,0.000094740455,0.00037975758,0.00025540483,0.00026944553,0.4852225,0.02306383,0.0016920919,0.002125539,0.47432652],"study_design_scores_gemma":[0.000005848856,0.000095526404,0.0011197513,0.0000055560467,0.000042762244,0.000038458114,0.000024288838,0.9956773,0.0021249175,0.00058174785,0.00027531458,0.000008612959],"about_ca_topic_score_codex":0.0027261362,"about_ca_topic_score_gemma":0.0028772056,"teacher_disagreement_score":0.0027261362,"about_ca_system_score_codex":0.00033060124,"about_ca_system_score_gemma":0.00063726446,"threshold_uncertainty_score":0.012039959},"labels":[],"label_agreement":null},{"id":"W4200607868","doi":"10.1038/s41598-021-02282-3","title":"Systems biology and machine learning approaches identify drug targets in diabetic nephropathy","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Institute for Medical Research Development; Isfahan University of Medical Sciences","keywords":"Machine learning; Computational biology; Renal cortex; Computer science; Diabetic nephropathy; Artificial intelligence; Bioinformatics; Medulla; Drug discovery; Proteome; Biology; Medicine; Kidney; Internal medicine; Genetics","score_opus":0.14564373557017418,"score_gpt":0.41713699276147753,"score_spread":0.27149325719130335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200607868","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22369133,0.026990194,0.7322061,0.002372715,0.00026927245,0.00044836197,0.0016865141,0.0033991104,0.008936388],"genre_scores_gemma":[0.8096972,0.006550726,0.17999674,0.000578268,0.00013295673,0.00028764733,0.0011645685,0.000055441164,0.0015364763],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996431,0.00011445113,0.000029515591,0.00009881946,0.000081376646,0.000032719796],"domain_scores_gemma":[0.9995646,0.00022986921,0.00009003294,0.00003018744,0.000065046865,0.000020164402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011589504,0.0009137034,0.00093093945,0.0022146746,0.0003375151,0.0010565424,0.00050591474,0.0006659654,0.0011572691],"category_scores_gemma":[0.001481896,0.0003064338,0.00083339115,0.0010188668,0.00034337153,0.0006038524,0.00053423975,0.00065739616,0.00034595863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005033447,0.00046413622,0.030020135,0.0018016564,0.0008005625,0.0005018935,0.00012949115,0.3388979,0.080222555,0.015408922,0.0033500772,0.5278994],"study_design_scores_gemma":[0.000025296873,0.000272334,0.0062959986,0.000059447062,0.00014591943,0.00013741525,0.000037597383,0.9587453,0.015822817,0.014686291,0.0037438343,0.000027708085],"about_ca_topic_score_codex":0.0013104541,"about_ca_topic_score_gemma":0.0013282476,"teacher_disagreement_score":0.0022146746,"about_ca_system_score_codex":0.0008654094,"about_ca_system_score_gemma":0.00080753246,"threshold_uncertainty_score":0.0062790513},"labels":[],"label_agreement":null},{"id":"W4205712074","doi":"10.5539/jmr.v14n1p46","title":"Relationship between Event Prevalence Rate and Gini Coefficient of Predictive Model","year":2022,"lang":"en","type":"article","venue":"Journal of Mathematics Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Statistic; Mathematics; Gini coefficient; Statistics; Event (particle physics); Econometrics; Measure (data warehouse); Inequality; Data mining; Computer science; Economic inequality","score_opus":0.5758864769581103,"score_gpt":0.6063297702660546,"score_spread":0.030443293307944264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205712074","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44310033,0.011797964,0.51849943,0.006193637,0.0007003287,0.0002967265,0.0036305161,0.0009839408,0.01479715],"genre_scores_gemma":[0.9752618,0.0015313067,0.020457068,0.00014422851,0.00017436546,0.00012458331,0.0012602949,0.000095496194,0.00095073506],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99373287,0.002483459,0.00039156532,0.0012065507,0.0016650137,0.00052063],"domain_scores_gemma":[0.92962605,0.05771895,0.0048772735,0.0026369358,0.0042993417,0.0008413457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009213631,0.00070980197,0.001290045,0.0033463864,0.00046914554,0.0018886063,0.0011817344,0.0013144372,0.001763871],"category_scores_gemma":[0.08889299,0.00030157887,0.00095694285,0.0027131075,0.0012684102,0.0022769882,0.001586431,0.0021921154,0.00034876497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003897443,0.00013709028,0.5535205,0.0005743729,0.0013102934,0.0009792735,0.0007733068,0.24400735,0.0015566471,0.09591407,0.008887755,0.09194963],"study_design_scores_gemma":[0.000037633705,0.00024091279,0.14927678,0.00021727016,0.0004407068,0.002423543,0.00044918942,0.63983166,0.0013878972,0.19851743,0.006984702,0.00019227366],"about_ca_topic_score_codex":0.0031256226,"about_ca_topic_score_gemma":0.001405112,"teacher_disagreement_score":0.009213631,"about_ca_system_score_codex":0.0014954909,"about_ca_system_score_gemma":0.0013456476,"threshold_uncertainty_score":0.048726916},"labels":[],"label_agreement":null},{"id":"W4205826720","doi":"10.17265/2159-5275/2021.06.004","title":"Stroke Prediction","year":2021,"lang":"en","type":"article","venue":"Journal of Mechanics Engineering and Automation","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Stroke (engine); Medicine; Engineering; Mechanical engineering","score_opus":0.04934288101487166,"score_gpt":0.3679345819532275,"score_spread":0.3185917009383558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205826720","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1982785,0.010173701,0.35882443,0.016344879,0.0060932953,0.0040710415,0.21014267,0.014000346,0.18207115],"genre_scores_gemma":[0.6814578,0.0063525266,0.08102331,0.0019761987,0.0014193379,0.0010770229,0.14646079,0.00047859235,0.079754405],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991522,0.0000990134,0.000090830436,0.00026707293,0.00025106463,0.00013982382],"domain_scores_gemma":[0.99777466,0.000506283,0.00014538814,0.00022541724,0.0012181515,0.00013019887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013832861,0.0013631391,0.0010029896,0.0023152716,0.0005233303,0.0018032084,0.0013957389,0.0010151037,0.021822777],"category_scores_gemma":[0.0077158175,0.0003651743,0.0014345701,0.001530721,0.00017775549,0.0012296911,0.0008043928,0.0017104457,0.014041389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073753827,0.00064701564,0.16457051,0.0004314793,0.00030842482,0.0006135538,0.000107778564,0.023325652,0.00075567357,0.0058349175,0.24332651,0.559341],"study_design_scores_gemma":[0.00031588264,0.00077829766,0.1650022,0.000945766,0.000880289,0.002116742,0.0005287386,0.50215876,0.006843081,0.044817258,0.27539054,0.00022243186],"about_ca_topic_score_codex":0.017266905,"about_ca_topic_score_gemma":0.015910177,"teacher_disagreement_score":0.021822777,"about_ca_system_score_codex":0.0007576156,"about_ca_system_score_gemma":0.001625305,"threshold_uncertainty_score":0.073004484},"labels":[],"label_agreement":null},{"id":"W4205916580","doi":"10.1109/bigdata52589.2021.9671738","title":"Predicting family physicians based on their practice using machine learning","year":2021,"lang":"en","type":"article","venue":"2021 IEEE International Conference on Big Data (Big Data)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"NOSM University; Lakehead University","funders":"","keywords":"Machine learning; Rurality; Artificial intelligence; Computer science; Health care; Binary classification; Field (mathematics); Class (philosophy); Medicine; Rural area; Support vector machine; Mathematics","score_opus":0.6762616049797713,"score_gpt":0.5199363785259139,"score_spread":0.15632522645385738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205916580","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9802316,0.0006313676,0.01454895,0.00078662275,0.000031660835,0.00007535316,0.0013713432,0.00016903444,0.00215418],"genre_scores_gemma":[0.99176824,0.00022822185,0.0065064603,0.000049643077,0.00002818028,0.000029684992,0.0010176956,0.0000038522667,0.00036805033],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990729,0.00031316912,0.000101621205,0.0001665503,0.0002360649,0.00010975891],"domain_scores_gemma":[0.9940724,0.0039179716,0.0010037539,0.0001385262,0.0006340768,0.0002332943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012828514,0.00037009575,0.00042739793,0.0030705477,0.00030645222,0.0006948589,0.00039677997,0.00075426983,0.0012362236],"category_scores_gemma":[0.00918502,0.00017044952,0.00048128556,0.002033933,0.0001995209,0.0007011142,0.0002988167,0.0004842212,0.0004990358],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008840846,0.00021620831,0.94186026,0.00003623701,0.00005890986,0.00013572306,0.00010961179,0.023658823,0.00020815327,0.00018772003,0.0010445275,0.032395422],"study_design_scores_gemma":[0.000028113716,0.0002460155,0.4215892,0.000054458193,0.000054026976,0.00032346378,0.00048235003,0.5741881,0.0007274528,0.0011772851,0.0010987415,0.000030760693],"about_ca_topic_score_codex":0.015527144,"about_ca_topic_score_gemma":0.016533185,"teacher_disagreement_score":0.015527144,"about_ca_system_score_codex":0.0006950145,"about_ca_system_score_gemma":0.00083404966,"threshold_uncertainty_score":0.030873477},"labels":[],"label_agreement":null},{"id":"W4206214705","doi":"10.1109/conecct52877.2021.9622600","title":"Ensemble learning as a prerogative method of predicting mortality of patients with cardiovascular diseases","year":2021,"lang":"en","type":"article","venue":"2021 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Toronto","keywords":"Computer science; Logistic regression; Machine learning; Predictive modelling; Mortality rate; Artificial neural network; Artificial intelligence; Ensemble learning; Data mining; Medicine; Internal medicine","score_opus":0.08695466419065778,"score_gpt":0.4259541591739206,"score_spread":0.3389994949832628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206214705","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.077621564,0.0025186578,0.9109518,0.0007847155,0.00035046556,0.00009041876,0.00055326225,0.0014785619,0.0056505096],"genre_scores_gemma":[0.7918552,0.0020283798,0.19960108,0.00018430172,0.00033103896,0.00012991506,0.0009876864,0.00008122701,0.0048010647],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991835,0.00026997202,0.0000580088,0.00013906963,0.00028780938,0.0000617106],"domain_scores_gemma":[0.9989856,0.00044631673,0.00009175111,0.00013624437,0.0002972515,0.00004294571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001767141,0.0005944213,0.0007648012,0.0017485581,0.0003626122,0.00077275024,0.00064361875,0.00044546594,0.00101159],"category_scores_gemma":[0.0027708905,0.00016007593,0.00068759423,0.0011450344,0.00015955036,0.00077538873,0.0004657966,0.0008577928,0.00032981925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013938674,0.00020376907,0.034220666,0.000118377924,0.0004632204,0.00023364602,0.00022773094,0.20748758,0.0034034627,0.0055274614,0.008707466,0.7392673],"study_design_scores_gemma":[0.000008527367,0.00019551204,0.0071187657,0.00004788556,0.0001305125,0.00023545454,0.000067938876,0.97815585,0.0031812885,0.0059426106,0.004884153,0.000031487125],"about_ca_topic_score_codex":0.0031597398,"about_ca_topic_score_gemma":0.0037558775,"teacher_disagreement_score":0.0031597398,"about_ca_system_score_codex":0.00031052463,"about_ca_system_score_gemma":0.000521511,"threshold_uncertainty_score":0.009345651},"labels":[],"label_agreement":null},{"id":"W4206316315","doi":"10.1145/3487664.3487728","title":"A Generic Knowledge Based Medical Diagnosis Expert System","year":2021,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Nvidia","keywords":"Inference engine; Expert system; Computer science; Inference; Knowledge representation and reasoning; Legal expert system; Knowledge base; Knowledge-based systems; Graphical user interface; Medical knowledge; User interface; Knowledge acquisition; Representation (politics); Machine learning; Artificial intelligence; Software engineering; Programming language; Medicine","score_opus":0.26194181049591253,"score_gpt":0.5210059147572734,"score_spread":0.2590641042613609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206316315","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0104242945,0.00079016894,0.9509649,0.00062488014,0.00014002506,0.00048145757,0.0017834016,0.025394468,0.009396374],"genre_scores_gemma":[0.14720245,0.0008368877,0.8365141,0.0016206065,0.00015709351,0.00024678506,0.005832701,0.00037538863,0.0072139627],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892586,0.00016358407,0.00015954203,0.00033449338,0.0003399474,0.00007650137],"domain_scores_gemma":[0.9990526,0.00023387061,0.00008807177,0.0002379637,0.00029334534,0.0000941096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013782386,0.0004960683,0.0008162016,0.0015969268,0.000398534,0.0012548544,0.0018365872,0.0016145248,0.00731138],"category_scores_gemma":[0.002643274,0.0002872509,0.00078216876,0.0009632426,0.00047214708,0.0011369311,0.0014010352,0.00075649266,0.0040902756],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006198421,0.0004172367,0.004887717,0.0014645485,0.00025834207,0.0020377706,0.0003209626,0.033547685,0.048814014,0.026278593,0.048237197,0.83311623],"study_design_scores_gemma":[0.00055315567,0.0005438503,0.011137477,0.00044328245,0.0006741373,0.00971111,0.00017695797,0.59525025,0.054786075,0.04634447,0.2801071,0.00027205003],"about_ca_topic_score_codex":0.0017284869,"about_ca_topic_score_gemma":0.0015071629,"teacher_disagreement_score":0.00731138,"about_ca_system_score_codex":0.00055134605,"about_ca_system_score_gemma":0.0011810834,"threshold_uncertainty_score":0.024459004},"labels":[],"label_agreement":null},{"id":"W4206829205","doi":"10.1109/access.2021.3133700","title":"A Machine Learning Analysis of Health Records of Patients With Chronic Kidney Disease at Risk of Cardiovascular Disease","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Kidney disease; Medicine; Context (archaeology); Disease; Diabetes mellitus; Medical record; Renal function; Ranking (information retrieval); Feature (linguistics); Term (time); Artificial intelligence; Intensive care medicine; Computer science; Machine learning; Internal medicine","score_opus":0.07544052414019527,"score_gpt":0.4171521250970025,"score_spread":0.34171160095680725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206829205","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9664533,0.0010178252,0.010354137,0.0012381428,0.00008752702,0.00018539687,0.018432118,0.00040844944,0.0018229791],"genre_scores_gemma":[0.971001,0.00023079563,0.013053206,0.00012787519,0.000094112904,0.00007129336,0.015006118,0.00000837259,0.00040716157],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973574,0.000827918,0.0004782555,0.0005935757,0.0005602684,0.00018254714],"domain_scores_gemma":[0.98951554,0.0056472453,0.001793901,0.0010439093,0.001697527,0.00030178932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024078533,0.000435434,0.00064555387,0.004793142,0.00051092566,0.0010440333,0.00049098255,0.00085705705,0.0009298698],"category_scores_gemma":[0.016482238,0.00011746726,0.00075404986,0.0038538016,0.00021692284,0.00063489226,0.00046578594,0.0006448793,0.0004930489],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058712304,0.00072991336,0.88935745,0.00022187385,0.00046987136,0.00064692926,0.00028937723,0.0090105925,0.00186386,0.00038124897,0.004483065,0.091958724],"study_design_scores_gemma":[0.000043115597,0.00064773485,0.8191922,0.00009798939,0.00026105074,0.0010380944,0.0006371121,0.16922635,0.0029023066,0.001109485,0.0047898754,0.000054667456],"about_ca_topic_score_codex":0.0116066625,"about_ca_topic_score_gemma":0.013047377,"teacher_disagreement_score":0.0116066625,"about_ca_system_score_codex":0.0006129465,"about_ca_system_score_gemma":0.001177168,"threshold_uncertainty_score":0.023078203},"labels":[],"label_agreement":null},{"id":"W4210519831","doi":"10.2196/preprints.25138","title":"Mobile and Wearable Technology for the Monitoring of Diabetes-Related Parameters: Systematic Review (Preprint)","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scopus; Wearable computer; Preprint; Wearable technology; Systematic review; Medicine; Web of science; Diabetes mellitus; MEDLINE; Computer science; Data science; Meta-analysis; World Wide Web; Internal medicine; Embedded system; Political science","score_opus":0.15694727650401863,"score_gpt":0.4582108657597475,"score_spread":0.3012635892557289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210519831","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016236462,0.99191815,0.0003551243,0.00086035166,0.0007129944,0.0021149758,0.0018425117,0.00003116919,0.00054107915],"genre_scores_gemma":[0.017363269,0.97239166,0.0014267258,0.0018323489,0.00052563625,0.004871149,0.0010052578,0.000019855455,0.0005640243],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.99004436,0.0030240375,0.0042515737,0.00053293176,0.0018198007,0.0003274206],"domain_scores_gemma":[0.9567485,0.026559476,0.011253915,0.0005905555,0.0045054164,0.00034212318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010814117,0.0015579024,0.0075754947,0.008586598,0.0006049051,0.0029241461,0.0017222482,0.0019803303,0.01552864],"category_scores_gemma":[0.06282542,0.0010108867,0.007864661,0.0126525415,0.00067205174,0.0032025962,0.0016783071,0.0011388259,0.0011186961],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014736124,0.000007992656,0.00041586364,0.9807731,0.004887922,0.00005199669,0.00008310544,0.00003099994,0.00010058109,0.00006264914,0.0026563008,0.0107821515],"study_design_scores_gemma":[0.00032857558,0.00017770304,0.0042434107,0.93125427,0.048379753,0.0002279225,0.00019720572,0.000071592716,0.00021495119,0.00014480758,0.014730984,0.00002890376],"about_ca_topic_score_codex":0.0051991525,"about_ca_topic_score_gemma":0.015998567,"teacher_disagreement_score":0.01552864,"about_ca_system_score_codex":0.004397371,"about_ca_system_score_gemma":0.011282977,"threshold_uncertainty_score":0.057191193},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4210820680","doi":"10.2196/preprints.20123","title":"Risk Stratification for Early Detection of Diabetes and Hypertension in Resource-Limited Settings: Machine Learning Analysis (Preprint)","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Diabetes mellitus; Medicine; Receiver operating characteristic; Risk stratification; Preprint; Population; Random forest; Machine learning; Risk assessment; Artificial intelligence; Environmental health; Gerontology; Computer science; Internal medicine; Endocrinology; Computer security","score_opus":0.09543935315670549,"score_gpt":0.38991577825323054,"score_spread":0.29447642509652505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210820680","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8610361,0.0056915726,0.09509303,0.019031651,0.0015169799,0.00033764393,0.009322272,0.0009774423,0.006993343],"genre_scores_gemma":[0.9670656,0.0012957467,0.024580635,0.00061897875,0.0005198458,0.00013808413,0.003621085,0.000056468976,0.0021037168],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993087,0.00041721924,0.00004683075,0.00008992237,0.000080314305,0.00005700223],"domain_scores_gemma":[0.9932214,0.0052484632,0.0005224107,0.00035756303,0.00051602704,0.00013412803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028785493,0.0003491171,0.0003574188,0.0008616868,0.0002058311,0.0011123716,0.00035575422,0.0004529199,0.0032000502],"category_scores_gemma":[0.015685616,0.0001463929,0.00060615945,0.00071724906,0.00017848851,0.0006379222,0.00035664116,0.00081235886,0.00083862885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004935989,0.0005127499,0.6318175,0.00030256342,0.00052926474,0.00032836056,0.00020416682,0.09622971,0.0008210491,0.0022276866,0.061633706,0.20489949],"study_design_scores_gemma":[0.000060416976,0.00026082728,0.29659235,0.00024544998,0.0001389754,0.00019320656,0.000340161,0.68974155,0.0010324914,0.00678459,0.0045603085,0.000049544513],"about_ca_topic_score_codex":0.007750086,"about_ca_topic_score_gemma":0.0077179237,"teacher_disagreement_score":0.007750086,"about_ca_system_score_codex":0.0006479955,"about_ca_system_score_gemma":0.00070581376,"threshold_uncertainty_score":0.015409946},"labels":[],"label_agreement":null},{"id":"W4211033497","doi":"10.24124/2020/59109","title":"Data visualization and predictive modeling for identifying comorbidities in diabetic patients","year":2020,"lang":"en","type":"dissertation","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"University of British Columbia; University of Northern British Columbia","keywords":"Dashboard; CHAID; Diabetes mellitus; Bayesian network; Medicine; Computer science; Logistic regression; Comorbidity; Data mining; Health informatics; Predictive analytics; Random forest; Artificial intelligence; Machine learning; Decision tree; Data science; Internal medicine; Public health","score_opus":0.41071571025654574,"score_gpt":0.553492475945105,"score_spread":0.14277676568855924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211033497","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26180527,0.012058486,0.51489824,0.017753456,0.0012128587,0.001049957,0.105938144,0.028749768,0.05653373],"genre_scores_gemma":[0.55245394,0.0062981416,0.37374476,0.00044033342,0.00034616396,0.0006573375,0.053927764,0.00054036354,0.011591189],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994529,0.00020273565,0.00004390742,0.00009185963,0.0001767956,0.000031682568],"domain_scores_gemma":[0.9968953,0.0021226245,0.0001945344,0.00021825146,0.00045378192,0.000115575705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019605397,0.00082216697,0.0003949813,0.0023132127,0.00040766541,0.0016039326,0.00053253426,0.0004853182,0.0075045764],"category_scores_gemma":[0.00840346,0.00022695721,0.0008222308,0.00237357,0.00015448501,0.0008824928,0.0008684405,0.0010546503,0.0016639299],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000897792,0.00077473227,0.052596193,0.0010481373,0.00017882048,0.00046865654,0.001307597,0.13298099,0.0040650424,0.015984258,0.16228989,0.6274079],"study_design_scores_gemma":[0.00011466241,0.00017579766,0.022977546,0.00042755736,0.00009805875,0.00024044483,0.00092811434,0.84793866,0.0053689377,0.03066024,0.09098515,0.00008479336],"about_ca_topic_score_codex":0.008039076,"about_ca_topic_score_gemma":0.010203626,"teacher_disagreement_score":0.008039076,"about_ca_system_score_codex":0.0005775198,"about_ca_system_score_gemma":0.0010658106,"threshold_uncertainty_score":0.025105357},"labels":[],"label_agreement":null},{"id":"W4211237409","doi":"10.1016/j.cjca.2022.02.008","title":"Deep Phenotyping and Prediction of Long-term Cardiovascular Disease: Optimized by Machine Learning","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Cardiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Medicine; Interpretability; Brier score; Cohort; Disease; Internal medicine; Random forest; Quartile; Concordance; Framingham Risk Score; Machine learning; Confidence interval","score_opus":0.058948743994401205,"score_gpt":0.3406960712179757,"score_spread":0.2817473272235745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211237409","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63500154,0.0022200397,0.35449567,0.003057167,0.0002032582,0.00006360293,0.0017941631,0.0013828902,0.0017816648],"genre_scores_gemma":[0.9752974,0.000314671,0.021288173,0.00025377894,0.00009456673,0.00003934721,0.0012429573,0.000033048153,0.0014361537],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997445,0.0000788174,0.000013492661,0.00007635334,0.000025351683,0.00006152682],"domain_scores_gemma":[0.99877924,0.00077805127,0.00009493949,0.00009092998,0.00015178508,0.00010505616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001073518,0.00072156865,0.001036377,0.00053636153,0.00030700958,0.00076075067,0.00094402034,0.0013013924,0.0011023028],"category_scores_gemma":[0.0031422712,0.00046843945,0.0006517814,0.00040842642,0.00036599155,0.0006835558,0.0007854114,0.0014780598,0.00040661302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00095392676,0.0006957052,0.049344555,0.000078696634,0.0002568304,0.00039494075,0.000084867665,0.749457,0.004704845,0.002956809,0.00692123,0.18415055],"study_design_scores_gemma":[0.000010678987,0.000021300073,0.0019549807,0.000004320931,0.000008832025,0.000022331442,0.000004883712,0.99604416,0.00021177423,0.0016167213,0.0000958662,0.000004239135],"about_ca_topic_score_codex":0.010661983,"about_ca_topic_score_gemma":0.0124242585,"teacher_disagreement_score":0.010661983,"about_ca_system_score_codex":0.0005465702,"about_ca_system_score_gemma":0.0011953595,"threshold_uncertainty_score":0.021199882},"labels":[],"label_agreement":null},{"id":"W4212970471","doi":"10.1145/3511430.3511464","title":"A Report on Tutorials and Tech-Briefings co-located with ISEC 2022","year":2022,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Session (web analytics); Presentation (obstetrics); Software; Engineering; Computer science; Engineering management; Software engineering; World Wide Web; Operating system","score_opus":0.13045379495593498,"score_gpt":0.4784342038097695,"score_spread":0.3479804088538345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4212970471","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008923232,0.07044654,0.04816797,0.029323725,0.38127106,0.004424,0.021768931,0.015065149,0.4206094],"genre_scores_gemma":[0.0072725844,0.034127846,0.018163124,0.0062934747,0.042096645,0.0025925413,0.03280412,0.004989397,0.85166025],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99291515,0.0009925741,0.0004154772,0.0005525411,0.0043210234,0.00080322055],"domain_scores_gemma":[0.9683533,0.002781409,0.0011302538,0.0008266455,0.019331725,0.007576693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061158556,0.0023527392,0.0014242275,0.005859078,0.0018447399,0.01002859,0.0018978557,0.0019976108,0.23734495],"category_scores_gemma":[0.021252796,0.0007778099,0.001139516,0.006859956,0.00032400838,0.0049249614,0.0044318903,0.0033575932,0.27248064],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008039697,0.00018226552,0.00011189616,0.0003975642,0.00000824654,0.000087122804,0.00006252669,0.00017323215,0.0011789317,0.00060107396,0.8948972,0.10221959],"study_design_scores_gemma":[0.000013291496,0.000107294334,0.00043695356,0.00023288725,0.000007534969,0.0001045528,0.0000953636,0.00015019879,0.00054642436,0.00037404982,0.9979097,0.000021773214],"about_ca_topic_score_codex":0.0024583065,"about_ca_topic_score_gemma":0.004015544,"teacher_disagreement_score":0.23734495,"about_ca_system_score_codex":0.0021853237,"about_ca_system_score_gemma":0.004999667,"threshold_uncertainty_score":0.79399794},"labels":[],"label_agreement":null},{"id":"W4213295491","doi":"10.1101/2022.02.21.481356","title":"Supervised Rank aggregation (SRA): A novel rank aggregation approach for ensemble-based feature selection","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Princess Margaret Cancer Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Prostate Cancer Canada","keywords":"Feature selection; Categorical variable; Computer science; Feature (linguistics); Rank (graph theory); Artificial intelligence; Machine learning; Data mining; Ensemble learning; Pattern recognition (psychology); Mathematics","score_opus":0.07560128630664867,"score_gpt":0.34638227044809244,"score_spread":0.2707809841414438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213295491","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011814048,0.00037625866,0.9863753,0.000120816905,0.000049804712,0.000060117098,0.000121956815,0.0005891024,0.0004925577],"genre_scores_gemma":[0.3940671,0.00043361523,0.6013961,0.0002135412,0.0003427538,0.00034579344,0.0011172881,0.00018093098,0.0019028818],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967656,0.0012840864,0.000248901,0.0005199442,0.0009886487,0.00019282874],"domain_scores_gemma":[0.99473566,0.002152631,0.0005225137,0.00079068844,0.001625178,0.0001734057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045585693,0.001396006,0.0022702776,0.0024560413,0.00079701433,0.0013536627,0.0016210666,0.0009517351,0.0016952874],"category_scores_gemma":[0.007384159,0.00044102882,0.0018713358,0.0022240311,0.00049535744,0.0011519854,0.0013708854,0.0013615257,0.00076242175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026497734,0.0003153801,0.0065651513,0.00020170394,0.0006597604,0.00019697942,0.00018764744,0.30421087,0.007715142,0.0065529286,0.008503375,0.664626],"study_design_scores_gemma":[0.000015410571,0.00010052932,0.0008988641,0.000012135712,0.000054013843,0.00006540352,0.000015193111,0.9926334,0.0013778365,0.0036847328,0.0011252111,0.000017298255],"about_ca_topic_score_codex":0.0030672317,"about_ca_topic_score_gemma":0.003549052,"teacher_disagreement_score":0.0045585693,"about_ca_system_score_codex":0.00044416712,"about_ca_system_score_gemma":0.0012990277,"threshold_uncertainty_score":0.02410829},"labels":[],"label_agreement":null},{"id":"W4213324158","doi":"10.35940/ijitee.f4707.049620","title":"Cardiovascular Disease Risk Factors among White-Collar Workers towards Healthy Communities in Malaysia","year":2020,"lang":"en","type":"article","venue":"International Journal of Innovative Technology and Exploring Engineering","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Big data; Health care; Government (linguistics); Disease; Business; Social media; Analytics; Medicine; Public relations; Environmental health; Economic growth; Political science; Data science; Computer science; Data mining; Economics; Pathology","score_opus":0.12587708487039057,"score_gpt":0.3625754710356824,"score_spread":0.23669838616529182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213324158","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9984665,0.00017107707,0.000021780523,0.00026280756,0.000011496205,0.000010151571,0.00018573445,0.0000012752431,0.0008692627],"genre_scores_gemma":[0.9984397,0.00035711107,0.00006023816,0.0001717268,0.000010353795,0.000011377243,0.00014319291,0.0000014661952,0.00080482214],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.999728,0.00004887516,0.00002538535,0.00005392047,0.00006910484,0.00007469329],"domain_scores_gemma":[0.99936146,0.00006272706,0.0001896308,0.000021091275,0.00011970317,0.00024534596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043219083,0.00025575247,0.00021432912,0.0006719342,0.00089398597,0.0008907486,0.00025345583,0.00033990334,0.0022051414],"category_scores_gemma":[0.0009658686,0.00023150336,0.00028720818,0.00054051727,0.00030461737,0.00052449235,0.0007271431,0.00067640893,0.00037797124],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003568375,0.00011412704,0.9894693,0.000046299916,0.000018424844,0.00027990888,0.004463197,0.000016982474,0.000316644,0.000040378764,0.00055490877,0.0046442337],"study_design_scores_gemma":[0.0000027011922,0.00011525647,0.98448724,0.000063819585,0.000012221324,0.00021865225,0.014266826,0.00008272892,0.000064380816,0.000029343446,0.0006472227,0.00000954725],"about_ca_topic_score_codex":0.038118023,"about_ca_topic_score_gemma":0.051910378,"teacher_disagreement_score":0.038118023,"about_ca_system_score_codex":0.0004501467,"about_ca_system_score_gemma":0.00072189496,"threshold_uncertainty_score":0.07579231},"labels":[],"label_agreement":null},{"id":"W4213432609","doi":"10.1155/2022/5849995","title":"Effectiveness of Artificial Intelligence Models for Cardiovascular Disease Prediction: Network Meta-Analysis","year":2022,"lang":"en","type":"article","venue":"Computational Intelligence and Neuroscience","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"King Saud University","keywords":"Computer science; Meta-analysis; Artificial intelligence; Disease; Machine learning; Medicine; Internal medicine","score_opus":0.40466119773862286,"score_gpt":0.458609185178876,"score_spread":0.05394798744025314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213432609","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020519432,0.95933044,0.014881796,0.0013315469,0.00073305384,0.0005885721,0.0014426732,0.0001834008,0.000989076],"genre_scores_gemma":[0.6623587,0.31271765,0.0166925,0.001489588,0.0012040546,0.0022228677,0.0022735076,0.00017163895,0.000869535],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9656529,0.027262434,0.0029457712,0.0023629055,0.0014020241,0.00037400593],"domain_scores_gemma":[0.9184974,0.0739661,0.0033655644,0.002049505,0.0017532234,0.0003681984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04318116,0.0042523635,0.016467217,0.0053172163,0.00062295794,0.0040251785,0.0028007245,0.002483967,0.0033323416],"category_scores_gemma":[0.08002229,0.0013174358,0.054542843,0.0050187134,0.00077144906,0.0028200478,0.0018447796,0.003551674,0.0003349811],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0042456803,0.00004185729,0.007255765,0.046121784,0.9215401,0.000088460234,0.0000421272,0.0060970513,0.00010171675,0.0003843593,0.00056777813,0.01351331],"study_design_scores_gemma":[0.00080340076,0.00028344386,0.0022792008,0.0036114287,0.9862488,0.000047333542,0.00001746351,0.004463438,0.00009674006,0.0012565146,0.0008675798,0.000024683035],"about_ca_topic_score_codex":0.004871396,"about_ca_topic_score_gemma":0.0043182927,"teacher_disagreement_score":0.04318116,"about_ca_system_score_codex":0.0020269146,"about_ca_system_score_gemma":0.0018682478,"threshold_uncertainty_score":0.22836655},"labels":[],"label_agreement":null},{"id":"W4214595570","doi":"10.3390/s22051843","title":"Machine Learning and Smart Devices for Diabetes Management: Systematic Review","year":2022,"lang":"en","type":"review","venue":"Sensors","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":141,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cegep de Sept Iles; Université du Québec à Chicoutimi; Université du Québec à Rimouski","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Diabetes mellitus; Scopus; Diabetes management; Wearable technology; Wearable computer; Medicine; Blood sugar; Computer science; Intensive care medicine; Artificial intelligence; MEDLINE; Risk analysis (engineering); Type 2 diabetes; Embedded system","score_opus":0.20599350209804215,"score_gpt":0.4991403695490511,"score_spread":0.29314686745100893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214595570","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038477048,0.9988249,0.000075777796,0.00019753771,0.000062098625,0.00011244266,0.00015117817,0.000004131695,0.00018710754],"genre_scores_gemma":[0.0069156643,0.9917454,0.0003689663,0.0003786092,0.00007115207,0.0002819217,0.0001339121,0.000002407587,0.000101896716],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.996228,0.0013586064,0.001200066,0.0002563792,0.00080945145,0.00014749769],"domain_scores_gemma":[0.97817093,0.017416641,0.002870055,0.00018753539,0.0011730343,0.00018183714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050563198,0.0010512918,0.005314012,0.0058015916,0.00043858978,0.0017963108,0.0015916267,0.0018202697,0.0064987903],"category_scores_gemma":[0.025876561,0.0005751292,0.004879727,0.0076900376,0.0005594368,0.0018693784,0.0009635349,0.0010803331,0.00039776746],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013572928,0.000023976567,0.0006493837,0.94518226,0.00427777,0.00007163059,0.00009202191,0.00012935737,0.00005108385,0.00022740653,0.0026929262,0.04646639],"study_design_scores_gemma":[0.00020163211,0.00015577192,0.0034819955,0.9463594,0.028344875,0.00030640786,0.00013694407,0.00016734455,0.00008965163,0.00032153097,0.020407736,0.000026792955],"about_ca_topic_score_codex":0.0064465385,"about_ca_topic_score_gemma":0.017099729,"teacher_disagreement_score":0.0064987903,"about_ca_system_score_codex":0.0026579988,"about_ca_system_score_gemma":0.007877045,"threshold_uncertainty_score":0.02674073},"labels":[],"label_agreement":null},{"id":"W4214817333","doi":"10.1109/icaiic54071.2022.9722652","title":"Heart Disease Prediction Using Adaptive Infinite Feature Selection and Deep Neural Networks","year":2022,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Feature selection; Artificial intelligence; Artificial neural network; Machine learning; Multilayer perceptron; Heart disease; Feature (linguistics); Test data; Deep learning; Selection (genetic algorithm); Blood pressure; Pattern recognition (psychology); Data mining; Internal medicine; Medicine","score_opus":0.12008459776233381,"score_gpt":0.4227805782276293,"score_spread":0.3026959804652955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214817333","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54372394,0.002737826,0.44709408,0.0011516035,0.00021227237,0.00008674028,0.0014332889,0.0020339151,0.0015262868],"genre_scores_gemma":[0.961935,0.00024785555,0.035380032,0.00016582302,0.0000824167,0.00004644556,0.0013687857,0.000018405934,0.00075517927],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937445,0.00021265501,0.0000567715,0.00013813333,0.00011811317,0.0000998613],"domain_scores_gemma":[0.99894387,0.00055262743,0.000112234586,0.00009273357,0.00023479307,0.000063829495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015174405,0.00065053307,0.0009435491,0.0012901452,0.00024164739,0.00048415727,0.00079422205,0.00057500944,0.00063530175],"category_scores_gemma":[0.0023940348,0.00023472545,0.00071973394,0.0008719346,0.00022938858,0.0006353499,0.00064538134,0.0006696826,0.00018328476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011470852,0.0009350499,0.059390884,0.000100649784,0.0003868927,0.000536925,0.00007130553,0.48016763,0.006473128,0.0011771091,0.007803621,0.44180977],"study_design_scores_gemma":[0.000015614429,0.00004666215,0.0031453727,0.0000056765252,0.000013033658,0.000029702445,0.0000054899,0.9953312,0.00056158524,0.00069548585,0.0001434376,0.0000066964826],"about_ca_topic_score_codex":0.007633193,"about_ca_topic_score_gemma":0.008555107,"teacher_disagreement_score":0.007633193,"about_ca_system_score_codex":0.00053566997,"about_ca_system_score_gemma":0.0005789999,"threshold_uncertainty_score":0.015177488},"labels":[],"label_agreement":null},{"id":"W4220684949","doi":"10.18280/ria.360118","title":"Risk Assessment of Cardiovascular Diseases Using kNN and Decision Tree Classifier","year":2022,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Decision tree; Disease; Classifier (UML); Artificial intelligence; Machine learning; Computer science; Decision tree learning; Diabetes mellitus; Cardiovascular event; Medicine; Intensive care medicine; Internal medicine","score_opus":0.15787161351156714,"score_gpt":0.44899169331928057,"score_spread":0.2911200798077134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220684949","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12907043,0.004768984,0.8402066,0.0017118574,0.0010376744,0.0006652753,0.0020683354,0.0035385636,0.016932236],"genre_scores_gemma":[0.7681986,0.0027259751,0.21683803,0.0003823592,0.00037719886,0.00028623184,0.0025889291,0.000085300824,0.008517312],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986854,0.000215701,0.00016958099,0.00025800103,0.00052498735,0.00014628921],"domain_scores_gemma":[0.9989618,0.00032040724,0.00011159239,0.00005407259,0.00048450462,0.00006760034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011073912,0.0007873095,0.001014628,0.0026961777,0.0004858143,0.0013549667,0.0011230776,0.0010168706,0.0023122116],"category_scores_gemma":[0.0030297586,0.00021945355,0.00096838275,0.0013069758,0.000207493,0.0009842935,0.00047052672,0.00078598235,0.0012407493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005857142,0.00053822226,0.04338677,0.00045904017,0.00038713086,0.0009213533,0.00019498808,0.15430537,0.005643281,0.0056738276,0.0154795945,0.77242476],"study_design_scores_gemma":[0.000038454422,0.00029002252,0.0110495435,0.000171464,0.00014284975,0.00071441225,0.00013082991,0.9668493,0.004968879,0.007975263,0.007595931,0.0000729546],"about_ca_topic_score_codex":0.00787617,"about_ca_topic_score_gemma":0.006537558,"teacher_disagreement_score":0.00787617,"about_ca_system_score_codex":0.00076130265,"about_ca_system_score_gemma":0.0009891368,"threshold_uncertainty_score":0.015660644},"labels":[],"label_agreement":null},{"id":"W4220888071","doi":"10.18280/ts.390104","title":"Heart Disease Detection Based on Feature Fusion Technique with Augmented Classification Using Deep Learning Technology","year":2022,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Deep learning; Convolutional neural network; Machine learning; Random forest; Pattern recognition (psychology); Particle swarm optimization; Cluster analysis","score_opus":0.07784970748837595,"score_gpt":0.39199196008891307,"score_spread":0.31414225260053713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220888071","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14969888,0.001469739,0.82811403,0.0006015898,0.00033581562,0.00015010027,0.0034063002,0.009863532,0.00636003],"genre_scores_gemma":[0.742519,0.0009291481,0.24179001,0.00032154855,0.000177443,0.00017431473,0.0064133145,0.00020001756,0.0074750725],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997278,0.000016557578,0.000022114693,0.00008095623,0.00010256827,0.00004991447],"domain_scores_gemma":[0.99977785,0.000036463414,0.000027369882,0.00004135686,0.00009815142,0.000018734669],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030615958,0.0006204394,0.0006551582,0.0017194598,0.00023861541,0.0006665921,0.0006157799,0.000545878,0.0026829767],"category_scores_gemma":[0.0007204706,0.00023960049,0.00084526674,0.0009808027,0.00014450189,0.00082089135,0.00087462686,0.00055509224,0.0010368342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043077077,0.00026943092,0.012094902,0.00018008165,0.00014537161,0.00051623076,0.000115904004,0.030143179,0.061572302,0.001575984,0.013823334,0.87913245],"study_design_scores_gemma":[0.000035080644,0.0002471196,0.018403266,0.00005051372,0.0001377838,0.00083958067,0.000083151936,0.90622854,0.06007842,0.004068862,0.0097469855,0.000080686215],"about_ca_topic_score_codex":0.0033688373,"about_ca_topic_score_gemma":0.003423457,"teacher_disagreement_score":0.0033688373,"about_ca_system_score_codex":0.00038413072,"about_ca_system_score_gemma":0.00042575024,"threshold_uncertainty_score":0.008975446},"labels":[],"label_agreement":null},{"id":"W4221003624","doi":"10.51731/cjht.2022.285","title":"2022 Health Technology Trends to Watch: Top 10 List","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Health Technologies","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; Ministry of Health; Alberta Health Services","funders":"","keywords":"Health care; Government (linguistics); Equity (law); Emerging technologies; Health technology; Business; Public relations; Knowledge management; Internet privacy; Computer science; Political science","score_opus":0.1581079539453819,"score_gpt":0.4694129010248179,"score_spread":0.311304947079436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221003624","genre_codex":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004474732,0.040306546,0.003939201,0.13148093,0.037506808,0.0016112099,0.19151469,0.0071517574,0.58201414],"genre_scores_gemma":[0.037230536,0.07284293,0.016018478,0.10678591,0.008841225,0.0013893092,0.28238112,0.0021804697,0.47233003],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9934755,0.00015556901,0.00027456222,0.00022610735,0.0043593585,0.0015089667],"domain_scores_gemma":[0.9669319,0.000861636,0.0009297357,0.00033464024,0.023269547,0.007672496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029660452,0.0015570363,0.0009971543,0.008381277,0.0033938258,0.0094812075,0.0021784368,0.0046024383,0.08852213],"category_scores_gemma":[0.011690162,0.0006521946,0.0013686625,0.009540452,0.0010228783,0.0036956682,0.0028902967,0.0040611364,0.051853225],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021175827,0.00001637693,0.0006169785,0.0002881768,0.0000067192395,0.000024538493,0.00001596633,0.000045497934,0.0001121824,0.0012376035,0.96997327,0.027641576],"study_design_scores_gemma":[0.000020437774,0.000020516434,0.0046988325,0.0003923987,0.000016757775,0.0000399738,0.00008137826,0.00013278767,0.00016112912,0.00042716353,0.993982,0.000026623567],"about_ca_topic_score_codex":0.57872355,"about_ca_topic_score_gemma":0.74175084,"teacher_disagreement_score":0.57872355,"about_ca_system_score_codex":0.01539972,"about_ca_system_score_gemma":0.081085026,"threshold_uncertainty_score":0.84751487},"labels":[],"label_agreement":null},{"id":"W4221015832","doi":"10.1093/ije/dyac064","title":"Commentary: Deep learning approaches applied to routinely collected health data: future directions","year":2022,"lang":"en","type":"letter","venue":"International Journal of Epidemiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Public Health Ontario; Trillium Health Centre; University of Toronto","funders":"","keywords":"Deep learning; Artificial intelligence; Machine learning; Cornerstone; Computer science; Data science; Predictive modelling; Epidemiology; Medicine; Pathology","score_opus":0.39798237019283744,"score_gpt":0.5116118690724216,"score_spread":0.11362949887958418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221015832","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000050926075,0.000497851,0.00008537822,0.9815015,0.017425282,0.000006657597,0.000069108566,0.000028724487,0.00033453826],"genre_scores_gemma":[0.0006726507,0.0005866675,0.00021095533,0.96004146,0.037228182,0.00003248947,0.000027659577,0.000018471874,0.0011815417],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99088293,0.0028921727,0.0012077877,0.0012253373,0.0032270746,0.00056457747],"domain_scores_gemma":[0.9286345,0.049713936,0.002348755,0.0016508739,0.014361397,0.0032905731],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012810903,0.0015623978,0.0025645837,0.0016808378,0.0042071054,0.004383075,0.005962352,0.07191144,0.010620456],"category_scores_gemma":[0.08839036,0.0011927213,0.0024744668,0.0019191235,0.0064272652,0.0077426787,0.0023351926,0.07690989,0.015904056],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025367353,0.000011940961,0.00012732275,0.000051736668,0.000009123629,0.00018562011,0.00004805071,0.000044442062,0.000039869345,0.00095980347,0.9942327,0.0042641256],"study_design_scores_gemma":[0.00020926443,0.00006980416,0.0008815892,0.0011794481,0.000055031633,0.001328946,0.000404711,0.0011855412,0.00032177658,0.022250941,0.97197276,0.00014007621],"about_ca_topic_score_codex":0.011304951,"about_ca_topic_score_gemma":0.011568684,"teacher_disagreement_score":0.07191144,"about_ca_system_score_codex":0.005778739,"about_ca_system_score_gemma":0.008824049,"threshold_uncertainty_score":0.06775135},"labels":[],"label_agreement":null},{"id":"W4223442957","doi":"10.1038/s41746-022-00577-x","title":"A high-generalizability machine learning framework for predicting the progression of Alzheimer’s disease using limited data","year":2022,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Program on Open Innovation Platform with Enterprises, Research Institute and Academia; National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Eisai; Japan Science and Technology Agency; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Fujifilm Corporation; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Generalizability theory; Artificial intelligence; Machine learning; Computer science; Disease; Alzheimer's disease; Psychology; Medicine; Developmental psychology; Internal medicine","score_opus":0.36847750045530964,"score_gpt":0.5231412404781808,"score_spread":0.15466374002287114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223442957","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05039307,0.001687768,0.94212496,0.0011901824,0.000102257705,0.00026301618,0.00073675904,0.0021717777,0.0013302806],"genre_scores_gemma":[0.781185,0.0012466706,0.20864059,0.0009924171,0.00047903231,0.00064567226,0.0029486963,0.00016368441,0.003698224],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830997,0.0006337911,0.00010573082,0.0005214348,0.0003135262,0.00011555013],"domain_scores_gemma":[0.9967512,0.0018976505,0.00028819838,0.00032264873,0.0006165383,0.00012385783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050893747,0.0015152834,0.0013179327,0.002149213,0.0005111246,0.0011343186,0.002323543,0.0017665387,0.0012103134],"category_scores_gemma":[0.008362229,0.00047611928,0.0014763345,0.001332815,0.0007203834,0.0015448624,0.0016051022,0.0025583045,0.00080766715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004317668,0.0006751322,0.014562958,0.00020082334,0.00050576276,0.0004809979,0.00021200452,0.59982264,0.0039282925,0.005315035,0.006488189,0.3673764],"study_design_scores_gemma":[0.000016281962,0.000071343165,0.0010057009,0.000015978207,0.000030408502,0.00003799182,0.000010389012,0.9939957,0.0002944117,0.003984335,0.0005269508,0.000010484292],"about_ca_topic_score_codex":0.012218694,"about_ca_topic_score_gemma":0.0119076865,"teacher_disagreement_score":0.012218694,"about_ca_system_score_codex":0.00082238286,"about_ca_system_score_gemma":0.0012284232,"threshold_uncertainty_score":0.02691549},"labels":[],"label_agreement":null},{"id":"W4223489644","doi":"10.2196/36481","title":"Big Data Health Care Platform With Multisource Heterogeneous Data Integration and Massive High-Dimensional Data Governance for Large Hospitals: Design, Development, and Application","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"West China Hospital, Sichuan University; National Health Commission of the People's Republic of China; Sichuan University","keywords":"Big data; Data governance; Data science; Computer science; Data integration; Health care; Corporate governance; Data mining; Process management; Database; Business; Operations management; Engineering; Data quality","score_opus":0.17240508261820836,"score_gpt":0.43898978512715636,"score_spread":0.266584702508948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223489644","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18511823,0.0014754157,0.77628374,0.0040140487,0.0004856506,0.00738016,0.00082948455,0.0065490194,0.01786428],"genre_scores_gemma":[0.45843598,0.0011856525,0.5274356,0.0009469235,0.0001585012,0.003284621,0.0024904525,0.00045585725,0.0056063915],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99631727,0.0010704857,0.00030718825,0.0004777777,0.0013866457,0.00044067338],"domain_scores_gemma":[0.99708265,0.00030322434,0.0002011977,0.00048905413,0.001143701,0.00078018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059765186,0.00068173226,0.00040983874,0.0012189768,0.0009179155,0.002727009,0.0027242168,0.00092611875,0.0017869694],"category_scores_gemma":[0.003919004,0.00043757627,0.0009671228,0.0012526452,0.0010188591,0.0035954777,0.0042178663,0.0013829357,0.0006040297],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015104321,0.002696236,0.05985996,0.0021154687,0.00047173366,0.003404288,0.0068237777,0.049101934,0.07573271,0.14708464,0.05808251,0.59311634],"study_design_scores_gemma":[0.0008839821,0.0039006819,0.033505894,0.00078408694,0.000532635,0.0017247553,0.0046320884,0.5809775,0.09114836,0.04651548,0.23484527,0.0005493064],"about_ca_topic_score_codex":0.003142921,"about_ca_topic_score_gemma":0.0017915554,"teacher_disagreement_score":0.0059765186,"about_ca_system_score_codex":0.001327196,"about_ca_system_score_gemma":0.00426959,"threshold_uncertainty_score":0.03160721},"labels":[],"label_agreement":null},{"id":"W4224293487","doi":"10.2196/38010","title":"Authors' Response to Peer Reviews of “Using Structural Equation Modelling in Routine Clinical Data on Diabetes and Depression: Observational Cohort Study”","year":2022,"lang":"en","type":"article","venue":"JMIRx Med","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Observational study; Depression (economics); Structural equation modeling; Cohort; Diabetes mellitus; Cohort study; Medicine; Clinical psychology; Psychology; Statistics; Internal medicine; Mathematics; Endocrinology; Economics","score_opus":0.7218011166436507,"score_gpt":0.6118050576427819,"score_spread":0.10999605900086873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224293487","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003100752,0.0017573073,0.0005544483,0.5913763,0.4028398,0.00015776469,0.0012617396,0.00019463066,0.0015479346],"genre_scores_gemma":[0.009349951,0.0036613722,0.0027504365,0.6860258,0.26531368,0.0014860171,0.0016205941,0.0005722906,0.029219879],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9272272,0.02187801,0.016758462,0.004866254,0.025950085,0.0033199594],"domain_scores_gemma":[0.54857236,0.11214886,0.028725382,0.016832769,0.28398493,0.009735771],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.046268057,0.0013999349,0.004341609,0.0033805575,0.0059584784,0.008508358,0.003985144,0.021442393,0.038068842],"category_scores_gemma":[0.45891324,0.0018213555,0.0035740342,0.0027254517,0.003721426,0.0030024326,0.0053575705,0.018781109,0.030812312],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000062850115,0.000009008158,0.0003712807,0.0003456912,0.0000467566,0.00009596257,0.00009528073,0.000025894664,0.000050366285,0.00021629294,0.9960247,0.00265595],"study_design_scores_gemma":[0.00020241665,0.000033512122,0.0032651261,0.0023599165,0.00014682108,0.00036967496,0.00067116006,0.0006242181,0.0003201608,0.0013395285,0.99054354,0.00012397874],"about_ca_topic_score_codex":0.009527969,"about_ca_topic_score_gemma":0.014373942,"teacher_disagreement_score":0.95373195,"about_ca_system_score_codex":0.005964251,"about_ca_system_score_gemma":0.014440114,"threshold_uncertainty_score":0.24469179},"labels":[],"label_agreement":null},{"id":"W4229789498","doi":"10.24251/hicss.2018.351","title":"Introduction to the Minitrack on Big Data on Healthcare Application","year":2018,"lang":"en","type":"article","venue":"Proceedings of the ... Annual Hawaii International Conference on System Sciences/Proceedings of the Annual Hawaii International Conference on System Sciences","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Big data; Health care; Data science; Data mining; Political science","score_opus":0.2147990094879426,"score_gpt":0.43561528755304263,"score_spread":0.22081627806510004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229789498","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036300847,0.14334136,0.5020906,0.12314958,0.07746418,0.0020048304,0.013953644,0.036943216,0.097422555],"genre_scores_gemma":[0.022790829,0.14575699,0.35708362,0.075683676,0.08957163,0.001983196,0.036250297,0.016561791,0.254318],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968823,0.0006555453,0.00028845575,0.00052766554,0.0014245883,0.00022144656],"domain_scores_gemma":[0.9801052,0.0076723816,0.00047191934,0.0026210928,0.0068249987,0.002304383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006773266,0.0016417453,0.0014182215,0.005552839,0.001570709,0.008482448,0.0033263776,0.0032198401,0.05079914],"category_scores_gemma":[0.017266477,0.0017704774,0.0015817959,0.006236118,0.0015978462,0.013673636,0.006088515,0.008833475,0.03006493],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008849107,0.00007673009,0.0006080235,0.0006780644,0.000043872606,0.0000846916,0.00014034909,0.0004260058,0.0025175042,0.013482266,0.77286637,0.20898773],"study_design_scores_gemma":[0.000017741004,0.000044890156,0.0005878738,0.0003321601,0.000014236468,0.00017529575,0.00006013254,0.0013837069,0.00076378573,0.008310008,0.9882691,0.00004108622],"about_ca_topic_score_codex":0.0031962257,"about_ca_topic_score_gemma":0.006068683,"teacher_disagreement_score":0.05079914,"about_ca_system_score_codex":0.0014561331,"about_ca_system_score_gemma":0.0027596466,"threshold_uncertainty_score":0.16994},"labels":[],"label_agreement":null},{"id":"W4229930240","doi":"10.18653/v1/d19-62","title":"Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"U.S. National Library of Medicine","keywords":"Computer science; Data science; Information retrieval; Library science","score_opus":0.11482474901560408,"score_gpt":0.46077759682747815,"score_spread":0.3459528478118741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229930240","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02115691,0.10695873,0.69169676,0.06111996,0.03594248,0.0017104422,0.015832344,0.014263897,0.05131848],"genre_scores_gemma":[0.073073015,0.040915787,0.5700428,0.012675888,0.011449318,0.0019708811,0.079781994,0.006262808,0.20382743],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99110985,0.0044856085,0.0007119125,0.0016151001,0.0015849575,0.00049252773],"domain_scores_gemma":[0.9827739,0.008186053,0.0004446842,0.003772536,0.0029373672,0.001885499],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01879458,0.0015698479,0.0025000623,0.0046192813,0.0014346896,0.0074174637,0.0029707304,0.0027889118,0.044613436],"category_scores_gemma":[0.020367097,0.00079715945,0.0021254434,0.0029923862,0.0019844405,0.007558836,0.0074780467,0.0045352313,0.023964778],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049496035,0.00042129803,0.0011578535,0.00088654243,0.00020870299,0.0003393411,0.0009132,0.0010801163,0.0064127045,0.010751832,0.4033979,0.57393557],"study_design_scores_gemma":[0.000073162446,0.00018405406,0.0037075675,0.00084374094,0.00013584518,0.00057313347,0.00083461363,0.012406993,0.005317281,0.03437493,0.9414659,0.000082769846],"about_ca_topic_score_codex":0.0030710483,"about_ca_topic_score_gemma":0.004867521,"teacher_disagreement_score":0.044613436,"about_ca_system_score_codex":0.0022488195,"about_ca_system_score_gemma":0.0038008995,"threshold_uncertainty_score":0.14924687},"labels":[],"label_agreement":null},{"id":"W4230121020","doi":"10.1007/978-3-319-77911-9","title":"Advanced Data Analytics in Health","year":2018,"lang":"en","type":"book","venue":"Smart innovation, systems and technologies","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Analytics; Data science; Data analysis; Computer science; Data mining","score_opus":0.2900005977995761,"score_gpt":0.47857767033959575,"score_spread":0.18857707254001965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230121020","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013795539,0.40966234,0.12037092,0.030098531,0.021359595,0.00022803759,0.0017493832,0.0024321622,0.4127195],"genre_scores_gemma":[0.019338267,0.25801924,0.06394143,0.017421212,0.020966485,0.0003101919,0.0027432046,0.00084243075,0.6164176],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99909127,0.00016388709,0.000056076544,0.00011277693,0.00053288357,0.000043163654],"domain_scores_gemma":[0.99847907,0.00092149957,0.00006351234,0.00015973095,0.00029091068,0.00008523884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009789929,0.001243988,0.0010955104,0.0027606217,0.00060194405,0.0046794144,0.00079361413,0.001287148,0.021358209],"category_scores_gemma":[0.0029912286,0.00050713116,0.00056641176,0.0042738253,0.0016369849,0.0058081793,0.0025324707,0.0035562958,0.01439241],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019366913,0.00003414366,0.00014130725,0.0005873479,0.000029323317,0.000058500696,0.0002382563,0.000834972,0.00059465633,0.088889815,0.6023375,0.30623484],"study_design_scores_gemma":[0.000004753459,0.000010801529,0.0003019331,0.00038596828,0.000009796953,0.00016291998,0.00007672024,0.0014209938,0.00022040613,0.08204904,0.9153447,0.000012007829],"about_ca_topic_score_codex":0.0013683635,"about_ca_topic_score_gemma":0.0018510716,"teacher_disagreement_score":0.021358209,"about_ca_system_score_codex":0.0011689728,"about_ca_system_score_gemma":0.0014175059,"threshold_uncertainty_score":0.07145035},"labels":[],"label_agreement":null},{"id":"W4230275497","doi":"10.1007/978-3-030-67303-1","title":"Multiple Perspectives on Artificial Intelligence in Healthcare","year":2021,"lang":"en","type":"book","venue":"Lecture notes in bioengineering","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Health care; Artificial intelligence; Computer science; Political science","score_opus":0.08963825646908932,"score_gpt":0.40493645039975246,"score_spread":0.31529819393066316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230275497","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017607795,0.30216122,0.0505846,0.086000666,0.007420154,0.000030200446,0.0001051247,0.000085424464,0.5518518],"genre_scores_gemma":[0.22935656,0.39787376,0.0679134,0.029917791,0.03470384,0.00033226903,0.00039614437,0.00024191076,0.23926435],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997603,0.001183212,0.000104162034,0.00020058657,0.00077884377,0.00013018244],"domain_scores_gemma":[0.9955486,0.0036150785,0.00009885266,0.00018191083,0.00030799312,0.0002475292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003214343,0.0012541123,0.0012755588,0.0033571303,0.0014175936,0.010096756,0.0013961629,0.0034088518,0.0141526265],"category_scores_gemma":[0.0029377718,0.0005751753,0.0008501099,0.0037792912,0.009249621,0.011402402,0.002993384,0.0075840144,0.002515812],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010843871,0.000017859673,0.000056868666,0.00019897046,0.000017593886,0.000049865583,0.0003951144,0.00036598765,0.0001102019,0.95324713,0.019587135,0.02594249],"study_design_scores_gemma":[0.000013720151,0.000019060883,0.00017613318,0.00052404986,0.000016811578,0.00015829032,0.00050516427,0.0012221456,0.00010145982,0.7911737,0.20607638,0.0000131409315],"about_ca_topic_score_codex":0.0012781444,"about_ca_topic_score_gemma":0.002030247,"teacher_disagreement_score":0.0141526265,"about_ca_system_score_codex":0.003329109,"about_ca_system_score_gemma":0.0018028275,"threshold_uncertainty_score":0.04734522},"labels":[],"label_agreement":null},{"id":"W4231590464","doi":"10.1186/isrctn41238563","title":"Effects of remote patient monitoring on chronic disease management","year":2016,"lang":"en","type":"dataset","venue":"http://isrctn.com/","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Disease management; Computer science; Disease monitoring; Medicine; Disease; Intensive care medicine; Medical emergency; Internal medicine","score_opus":0.07078984182660018,"score_gpt":0.43577747516598997,"score_spread":0.36498763333938977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231590464","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021723244,0.00074282155,0.00024265076,0.001190163,0.00028189752,0.000047237794,0.9735238,0.00042577152,0.0018223929],"genre_scores_gemma":[0.023028854,0.00027324562,0.0005651916,0.0001872037,0.000056024004,0.000072214345,0.9743507,0.000026178284,0.0014404753],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99915504,0.00022351797,0.000098772536,0.00022490034,0.0001841873,0.000113689624],"domain_scores_gemma":[0.9983505,0.0005390392,0.0002198241,0.00034991573,0.0003159004,0.00022489762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014302363,0.0013390528,0.0009631311,0.0011091569,0.00035740345,0.0007837464,0.0015148513,0.0014741401,0.0068699177],"category_scores_gemma":[0.005840816,0.00026574844,0.0014571436,0.0015165516,0.00025230023,0.0006979067,0.0009882997,0.0011109699,0.0051845135],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014259245,0.00042585,0.044790063,0.0008453364,0.000361614,0.00011295406,0.00006210575,0.0058798804,0.00039762977,0.0004248965,0.92440116,0.020872425],"study_design_scores_gemma":[0.0031334034,0.001002179,0.3888747,0.0013067924,0.0011858288,0.0010251103,0.0006895762,0.044054642,0.0036616693,0.003031976,0.55172026,0.00031381298],"about_ca_topic_score_codex":0.050509907,"about_ca_topic_score_gemma":0.10427012,"teacher_disagreement_score":0.050509907,"about_ca_system_score_codex":0.001321919,"about_ca_system_score_gemma":0.0011542158,"threshold_uncertainty_score":0.1004318},"labels":[],"label_agreement":null},{"id":"W4231903900","doi":"10.32370/ia_2019_01_si_7","title":"Innovative Health Technologies Based on Big Data","year":2019,"lang":"en","type":"article","venue":"Intellectual Archive","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Big data; Data science; Computer science; Business; Data mining","score_opus":0.33739885318588136,"score_gpt":0.48316595147220326,"score_spread":0.1457670982863219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231903900","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012543251,0.07775291,0.59456426,0.11724432,0.008728292,0.0006609249,0.004135353,0.004061607,0.18030909],"genre_scores_gemma":[0.3234897,0.11926596,0.46345496,0.0322029,0.018696185,0.0013466555,0.0058651064,0.0005981649,0.03508038],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964222,0.0012143189,0.0002228218,0.00045312147,0.0015130064,0.00017454993],"domain_scores_gemma":[0.99235415,0.0040601995,0.00048389952,0.0017228713,0.0010528659,0.00032595117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004350382,0.0008655818,0.0008885772,0.0038569719,0.00085312576,0.0060528466,0.0021687339,0.0025361883,0.0070975577],"category_scores_gemma":[0.01012977,0.00054744456,0.0010944381,0.0038696905,0.0026797683,0.010473592,0.0048966175,0.0032747702,0.0027357382],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012248407,0.00013013877,0.003184401,0.0016737564,0.00021641816,0.00044418577,0.0009108005,0.006113974,0.0025270332,0.564231,0.075052425,0.34539336],"study_design_scores_gemma":[0.000040554543,0.00008149518,0.0015814367,0.0007874355,0.00006661771,0.0005803254,0.00068666926,0.01617508,0.0018040767,0.63541985,0.3427113,0.00006520267],"about_ca_topic_score_codex":0.0007004965,"about_ca_topic_score_gemma":0.0005805466,"teacher_disagreement_score":0.0070975577,"about_ca_system_score_codex":0.001359371,"about_ca_system_score_gemma":0.0014107588,"threshold_uncertainty_score":0.023743749},"labels":[],"label_agreement":null},{"id":"W4232594183","doi":"10.32920/ryerson.14661300.v1","title":"A Comparative Study of the Impact of Data Augmentation in Machine Learning Based Classification Accuracy","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Gramian matrix; Computer science; Pattern recognition (psychology); Discriminant; Artificial intelligence; SIGNAL (programming language); Series (stratigraphy); Linear discriminant analysis; Machine learning; Data mining; Eigenvalues and eigenvectors","score_opus":0.6646261969874546,"score_gpt":0.6398211815144802,"score_spread":0.024805015472974423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232594183","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9253223,0.01096082,0.047152292,0.0013219211,0.0011507274,0.00019641053,0.0027432097,0.0031538021,0.007998603],"genre_scores_gemma":[0.9622878,0.0010016405,0.030022405,0.000118184274,0.00016860414,0.00007576384,0.0045374217,0.00013031352,0.0016579297],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9932827,0.0023350734,0.0008867166,0.0011449179,0.001970551,0.00038003162],"domain_scores_gemma":[0.9641106,0.025666954,0.0012318278,0.004009474,0.0045549995,0.000426135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010580093,0.0013430472,0.0014705788,0.0020756589,0.00062725594,0.002366652,0.0009229058,0.0012780221,0.0013214767],"category_scores_gemma":[0.031560812,0.00026428397,0.0011074439,0.0020462575,0.0006872343,0.0025381094,0.001008639,0.0013297107,0.00089456193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005033228,0.0011850675,0.0833716,0.0008470968,0.0007890089,0.0002465366,0.00043931673,0.08995053,0.009495973,0.00093540567,0.008535424,0.7991708],"study_design_scores_gemma":[0.00015407633,0.0044600694,0.09710402,0.00032478033,0.00065693515,0.00062662776,0.0008323781,0.84700596,0.037031867,0.002618346,0.009013184,0.00017174742],"about_ca_topic_score_codex":0.0032948472,"about_ca_topic_score_gemma":0.0021659764,"teacher_disagreement_score":0.010580093,"about_ca_system_score_codex":0.00076447485,"about_ca_system_score_gemma":0.0007743266,"threshold_uncertainty_score":0.055953562},"labels":[],"label_agreement":null},{"id":"W4235500727","doi":"10.1109/bigdia51454.2020.00005","title":"The 6th International Conference on Big Data and Information Analytics (BigDIA 2020)","year":2020,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Big data; Pleasure; Data science; Computer science; Analytics; Data analysis; Data mining; Psychology","score_opus":0.5174191743337576,"score_gpt":0.5134582743012287,"score_spread":0.003960900032528913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235500727","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042602313,0.063842066,0.06224561,0.12748466,0.45335877,0.0010993144,0.02061896,0.009230841,0.2578595],"genre_scores_gemma":[0.020614346,0.059491344,0.03363905,0.041298427,0.08580816,0.0011649451,0.07909439,0.0038707308,0.6750186],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99570364,0.00069624087,0.00026446558,0.00064290175,0.002004149,0.00068851776],"domain_scores_gemma":[0.98821837,0.0011440846,0.000390361,0.0006847074,0.0045608045,0.0050016744],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006988852,0.0014777418,0.0018786535,0.0025470257,0.0010559321,0.009119366,0.0023125724,0.0034392315,0.19072227],"category_scores_gemma":[0.008004474,0.0004623682,0.0013504288,0.0018437015,0.0010648222,0.0073811538,0.005742188,0.0051897326,0.16964304],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006481559,0.000030210487,0.00022717411,0.0001740358,0.000014984797,0.000035121764,0.00002205675,0.00010857769,0.00060133036,0.0018745885,0.9425356,0.054311622],"study_design_scores_gemma":[0.000009251669,0.000033282435,0.00049109693,0.00010885512,0.0000088388715,0.000050149025,0.000046996764,0.0004323516,0.0002463483,0.0014020094,0.9971558,0.000015039886],"about_ca_topic_score_codex":0.0020336378,"about_ca_topic_score_gemma":0.002961405,"teacher_disagreement_score":0.8092777,"about_ca_system_score_codex":0.0010687241,"about_ca_system_score_gemma":0.0038030215,"threshold_uncertainty_score":0.6380296},"labels":[],"label_agreement":null},{"id":"W4235907943","doi":"10.1007/978-3-030-04506-7","title":"Analytics in Healthcare","year":2019,"lang":"en","type":"book","venue":"SpringerBriefs in health care management and economics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Data science; Analytics; Computer science; Data analysis; Health care; Field (mathematics); Software analytics; Big data; Data mining; Mathematics; Political science; Software","score_opus":0.07095995132039865,"score_gpt":0.39093705306270843,"score_spread":0.31997710174230976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235907943","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001126755,0.2124424,0.13799207,0.031000184,0.012437703,0.00018932496,0.0018192285,0.0033703765,0.599622],"genre_scores_gemma":[0.020947082,0.14095989,0.054100454,0.009098264,0.011613015,0.0002921528,0.004584394,0.0014853493,0.75691944],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981647,0.0003635783,0.00011657956,0.00024408422,0.0010178618,0.00009323777],"domain_scores_gemma":[0.9982578,0.0008989598,0.000079708654,0.000281108,0.00034861692,0.0001336971],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016043558,0.001796864,0.0015462001,0.0045271916,0.0008413073,0.008101406,0.00090593885,0.0015739085,0.048524216],"category_scores_gemma":[0.0038337598,0.00071490806,0.0007417539,0.006320558,0.0017162978,0.008658569,0.004017173,0.003139839,0.031225406],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000102613585,0.000021937041,0.00011663443,0.00040517788,0.000020972537,0.000031998272,0.00019930114,0.00066848815,0.00030525879,0.14208843,0.5264502,0.3296814],"study_design_scores_gemma":[0.0000041081103,0.000009313896,0.0002552587,0.00040916866,0.0000076578435,0.000105505904,0.000111011526,0.0019439348,0.00014806738,0.11503458,0.8819605,0.000010817031],"about_ca_topic_score_codex":0.0018660022,"about_ca_topic_score_gemma":0.0024540783,"teacher_disagreement_score":0.048524216,"about_ca_system_score_codex":0.0016317912,"about_ca_system_score_gemma":0.0017679654,"threshold_uncertainty_score":0.16232973},"labels":[],"label_agreement":null},{"id":"W4235952699","doi":"10.1007/978-0-387-39940-9_3217","title":"ORA-SS Data Model","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.23557350751899572,"score_gpt":0.44694667181444847,"score_spread":0.21137316429545275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235952699","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051218243,0.0011579838,0.7915505,0.0027772335,0.0015205283,0.0013993897,0.08390767,0.037687115,0.07487764],"genre_scores_gemma":[0.097239666,0.002595275,0.6105593,0.0025089174,0.0005738882,0.0022150686,0.18716949,0.005915486,0.09122294],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99743026,0.0003769122,0.00046329567,0.0005179754,0.0010185116,0.00019308194],"domain_scores_gemma":[0.9965642,0.00038700653,0.000116099516,0.0015299167,0.0012935303,0.00010931012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022288044,0.0011807942,0.001078153,0.0024418507,0.0008574623,0.005764987,0.0035283992,0.0012126588,0.0346662],"category_scores_gemma":[0.007990201,0.0005226646,0.0024233356,0.0032457213,0.0006573977,0.0058592027,0.002978351,0.0017532719,0.036606908],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072767,0.00026603992,0.0034960236,0.0012729985,0.00016381415,0.00044497126,0.00031145784,0.023867039,0.0067138276,0.248212,0.33987096,0.37465322],"study_design_scores_gemma":[0.0000702369,0.0000830333,0.00042371804,0.00022561495,0.00009460624,0.00035466667,0.00014498633,0.09449559,0.0067621125,0.088579185,0.8086995,0.00006678826],"about_ca_topic_score_codex":0.008463267,"about_ca_topic_score_gemma":0.0061720535,"teacher_disagreement_score":0.0346662,"about_ca_system_score_codex":0.0012320236,"about_ca_system_score_gemma":0.0041314936,"threshold_uncertainty_score":0.115970016},"labels":[],"label_agreement":null},{"id":"W4237246986","doi":"10.2139/ssrn.3487748","title":"Establishment of Acute Stroke Care Pathway and Stroke Surveillance System in Rural Northwest India Using Community Health Workers","year":2019,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Stroke (engine); Medicine; Acute stroke; Environmental health; Rural community; Community health workers; Medical emergency; Business; Socioeconomics; Nursing; Health services; Population; Emergency department","score_opus":0.03394070061724685,"score_gpt":0.372942633324112,"score_spread":0.33900193270686513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237246986","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9956528,0.000029757495,0.00061662204,0.0001980288,0.000012282427,0.0005779495,0.0012561604,0.00006677365,0.0015896143],"genre_scores_gemma":[0.9897983,0.00012358761,0.0046148347,0.00021435373,0.00001674166,0.000526156,0.0018953147,0.000010019446,0.002800705],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993605,0.00014076315,0.000096673066,0.00012284279,0.00010733316,0.000171906],"domain_scores_gemma":[0.9978077,0.00024561552,0.0002828363,0.0001657519,0.0008701907,0.0006278415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066264917,0.00023173039,0.00019531755,0.0011088686,0.0013553777,0.00091090146,0.0008298948,0.0003781738,0.0016909144],"category_scores_gemma":[0.0015819503,0.00037197876,0.00024817378,0.0012163913,0.00035548132,0.0004384665,0.0009884269,0.00055434834,0.00060766167],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013379217,0.0008118366,0.97342867,0.00011006662,0.000021825525,0.0008079889,0.003839606,0.00043741707,0.0029809119,0.00014292242,0.001232227,0.016052783],"study_design_scores_gemma":[0.000034566354,0.0006394941,0.9777009,0.000044604476,0.000047163678,0.00032483434,0.01567366,0.002180998,0.0010411764,0.000058427962,0.0022257566,0.000028472146],"about_ca_topic_score_codex":0.17571776,"about_ca_topic_score_gemma":0.1597169,"teacher_disagreement_score":0.17571776,"about_ca_system_score_codex":0.0015314259,"about_ca_system_score_gemma":0.008137584,"threshold_uncertainty_score":0.34938997},"labels":[],"label_agreement":null},{"id":"W4237553166","doi":"10.1109/isspit.2018.8642752","title":"A Comparative Analysis of Unsupervised Machine Techniques for Liver Disease Prediction","year":2018,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Unsupervised learning; Field (mathematics); Silhouette; Computational complexity theory; Data set; Set (abstract data type); Pattern recognition (psychology); Data mining; Algorithm; Mathematics","score_opus":0.23549331482326918,"score_gpt":0.5256213340002522,"score_spread":0.29012801917698305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237553166","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5056045,0.011368565,0.46920803,0.0008017635,0.00020165107,0.0002221901,0.0008982631,0.0014754299,0.010219533],"genre_scores_gemma":[0.7798864,0.0035507793,0.21287246,0.00008653507,0.00014351665,0.00013235427,0.0013530772,0.00009239817,0.001882441],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976568,0.00083290384,0.00016258248,0.0002385356,0.0010174128,0.0000917326],"domain_scores_gemma":[0.984294,0.010968216,0.0006257886,0.00080098293,0.0031882226,0.0001228441],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025280397,0.00051333394,0.0006286219,0.0033218046,0.00038021768,0.000617048,0.0005032557,0.0005768709,0.00072504993],"category_scores_gemma":[0.010880285,0.00012961018,0.0007722144,0.002532418,0.00021562682,0.00087757537,0.00040992527,0.00045937244,0.00024119252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077291206,0.00040343887,0.040594827,0.00057942676,0.00048021783,0.0001519051,0.00029099267,0.13078411,0.007328327,0.0052566035,0.0032769458,0.81008035],"study_design_scores_gemma":[0.000026347612,0.0007598971,0.049809504,0.00008109802,0.00015818793,0.00032138117,0.00023277478,0.93314254,0.008243982,0.00375028,0.0034213574,0.000052654257],"about_ca_topic_score_codex":0.00401092,"about_ca_topic_score_gemma":0.0047754194,"teacher_disagreement_score":0.00401092,"about_ca_system_score_codex":0.00051259494,"about_ca_system_score_gemma":0.0007773075,"threshold_uncertainty_score":0.013369739},"labels":[],"label_agreement":null},{"id":"W4239854611","doi":"10.21203/rs.2.19115/v1","title":"Identifying cases of chronic pain using health administrative data: A validation study","year":2019,"lang":"en","type":"preprint","venue":"Research Square","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Chronic pain; Medicine; Data mining; Physical therapy; Computer science","score_opus":0.8512663934924372,"score_gpt":0.7169636063803724,"score_spread":0.13430278711206478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239854611","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9956311,0.00006532814,0.0016177862,0.00013823902,0.00002326141,0.0005993139,0.0010402324,0.000014337816,0.0008704523],"genre_scores_gemma":[0.9895,0.0000952824,0.0029093237,0.00027122625,0.000031272644,0.00077988184,0.005714126,0.00003114098,0.00066781015],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97284025,0.019083017,0.0019230673,0.00205051,0.00306812,0.001034992],"domain_scores_gemma":[0.873175,0.07913979,0.00725931,0.022841975,0.015779927,0.0018040114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02842088,0.00097048585,0.0007170454,0.0020655813,0.0020476426,0.0019307248,0.0025565554,0.0019735065,0.0019012468],"category_scores_gemma":[0.084888674,0.00095024,0.0017799353,0.0013978513,0.002994628,0.001711648,0.0023315072,0.0019659933,0.0013193036],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022291904,0.0060236286,0.9719319,0.0001276159,0.0003791031,0.0003158524,0.003672638,0.0006207932,0.0012379371,0.00037935012,0.00142293,0.011659094],"study_design_scores_gemma":[0.0010517201,0.0037054438,0.98039013,0.00013242706,0.00040369743,0.00084193714,0.0036405642,0.0036801985,0.002062622,0.00039180086,0.0036400105,0.000059536855],"about_ca_topic_score_codex":0.013412914,"about_ca_topic_score_gemma":0.009004518,"teacher_disagreement_score":0.02842088,"about_ca_system_score_codex":0.0017211132,"about_ca_system_score_gemma":0.0033481203,"threshold_uncertainty_score":0.15030581},"labels":[],"label_agreement":null},{"id":"W4240748437","doi":"10.5206/uwomj.v87i2.1149","title":"Big Data Analytics","year":2019,"lang":"en","type":"article","venue":"University of Western Ontario Medical Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Government of Ontario; Western University","funders":"","keywords":"Big data; Analytics; Population; Population health; Environmental health; Environmental data; Public health; Data science; Data quality; Computer science; Business; Medicine; Data mining; Marketing; Nursing; Political science","score_opus":0.2927267958743495,"score_gpt":0.42331170573899524,"score_spread":0.13058490986464572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240748437","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009813544,0.020568687,0.4480173,0.042272262,0.006262978,0.0058163065,0.29998553,0.081844054,0.085419334],"genre_scores_gemma":[0.11666806,0.02107287,0.40135375,0.008833806,0.0033275157,0.004835308,0.42242137,0.005249208,0.016238177],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98181206,0.0047422885,0.0030441086,0.0027084674,0.006862494,0.00083057885],"domain_scores_gemma":[0.9494087,0.018354835,0.0029423102,0.0167265,0.009892069,0.0026756194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015895616,0.0033776718,0.0027725855,0.010606106,0.001958448,0.013931067,0.0049680024,0.0025407774,0.0171648],"category_scores_gemma":[0.05785942,0.0013963139,0.0034019982,0.014999812,0.001642908,0.013094895,0.008473565,0.004580421,0.01644718],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057860784,0.00024949445,0.012084045,0.0042640357,0.0012620097,0.00061742106,0.0009247856,0.0124806985,0.0031240939,0.08130218,0.5724233,0.31068933],"study_design_scores_gemma":[0.00011301208,0.00013234027,0.0063991463,0.0015990458,0.00015929977,0.0004347704,0.0012542559,0.05555245,0.0034976904,0.16818899,0.76249856,0.0001704109],"about_ca_topic_score_codex":0.005012017,"about_ca_topic_score_gemma":0.003558899,"teacher_disagreement_score":0.0171648,"about_ca_system_score_codex":0.0025190867,"about_ca_system_score_gemma":0.0059748758,"threshold_uncertainty_score":0.08406508},"labels":[],"label_agreement":null},{"id":"W4241105396","doi":"10.1109/asonam49781.2020.9381462","title":"International Symposium on Network Enabled Health Informatics, Biomedicine and Bioinformatics (HI-BI-BI 2020) HI-BI-BI 2020 Organizing Committee","year":2020,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Biomedicine; Informatics; Health informatics; Translational bioinformatics; Computer science; Translational research informatics; Data science; Library science; Bioinformatics; Medicine; Engineering; Health Administration Informatics; Biology; Genomics; Genome; Public health; Gene","score_opus":0.07397778458553507,"score_gpt":0.39240574575604786,"score_spread":0.3184279611705128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241105396","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017600423,0.05543615,0.25027236,0.119072184,0.205559,0.0026569648,0.017261988,0.008019206,0.3241217],"genre_scores_gemma":[0.06118387,0.044846717,0.17660566,0.018953536,0.023414392,0.002073254,0.05223277,0.002563028,0.6181268],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967842,0.0008106062,0.00012883483,0.00034112562,0.0013993435,0.00053599867],"domain_scores_gemma":[0.9879048,0.0011874186,0.0002365687,0.0006494039,0.006161146,0.003860591],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014793002,0.0017100329,0.0013360655,0.0024147963,0.0015779487,0.005250158,0.0021723825,0.0027945705,0.034887172],"category_scores_gemma":[0.0063198484,0.00050980825,0.0011485361,0.002548623,0.0007313549,0.0031224582,0.004320206,0.00362507,0.025710704],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023471592,0.00019403336,0.00082581956,0.0002743555,0.000046158177,0.00005746302,0.000039644627,0.0012524218,0.0022460544,0.010601781,0.86192256,0.12230506],"study_design_scores_gemma":[0.000024299117,0.00012196309,0.0016299225,0.00020066436,0.000040608265,0.000080466816,0.00008328256,0.00871185,0.0017188115,0.0053213197,0.9820388,0.000027984146],"about_ca_topic_score_codex":0.010104442,"about_ca_topic_score_gemma":0.015010722,"teacher_disagreement_score":0.9651128,"about_ca_system_score_codex":0.0019915823,"about_ca_system_score_gemma":0.00970442,"threshold_uncertainty_score":0.11670917},"labels":[],"label_agreement":null},{"id":"W4241596122","doi":"10.1007/978-94-007-0753-5_1190","title":"GPIAtlantic","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science","score_opus":0.2344611729338651,"score_gpt":0.4855992604766926,"score_spread":0.2511380875428275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241596122","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023517516,0.0016417621,0.0010837906,0.0013348439,0.0007864729,0.000010292778,0.00016982462,0.00014586143,0.994592],"genre_scores_gemma":[0.0014736883,0.00078379334,0.00044137516,0.00033849865,0.00007069651,0.000009641863,0.00013638822,0.00008558023,0.99666035],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9997205,0.000029494744,0.0000073087513,0.00007324637,0.00012416307,0.000045308614],"domain_scores_gemma":[0.9998487,0.000020441179,0.000006141168,0.000023182381,0.000065849534,0.000035695055],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00031744584,0.0008136321,0.0003068267,0.0012255488,0.0018712056,0.0049981875,0.0007428186,0.0017870035,0.3006985],"category_scores_gemma":[0.00077838264,0.0002772797,0.0002578928,0.0016297245,0.0008313876,0.0035454943,0.0021287855,0.0024961508,0.1643072],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018094786,0.000017502729,0.000104090665,0.0000715819,0.0000021685482,0.000056511246,0.00029493595,0.00012946586,0.00031024474,0.18349047,0.60998905,0.20551594],"study_design_scores_gemma":[9.5092173e-7,0.0000019070277,0.000050010036,0.000033793367,6.5993606e-7,0.000024856741,0.000054207987,0.000033484208,0.000054892032,0.00456147,0.99518245,0.0000013248895],"about_ca_topic_score_codex":0.009726418,"about_ca_topic_score_gemma":0.026200686,"teacher_disagreement_score":0.6993015,"about_ca_system_score_codex":0.0023252235,"about_ca_system_score_gemma":0.002169383,"threshold_uncertainty_score":0.9974687},"labels":[],"label_agreement":null},{"id":"W4241962903","doi":"10.1007/0-387-32189-6_5","title":"Enterprise Health Information Systems","year":2006,"lang":"en","type":"book-chapter","venue":"Health Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University; University of Calgary","funders":"","keywords":"Information system; Computer science; Hiss; Hospital information system; Receipt; Service (business); Health care; Communications system; Sorting; Key (lock); Telecommunications; Computer security; Engineering; Business; World Wide Web","score_opus":0.12853496812814888,"score_gpt":0.4391397485251022,"score_spread":0.3106047803969533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241962903","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012839217,0.011853307,0.059501223,0.009102136,0.0013340604,0.00016054646,0.0008278916,0.0012577394,0.9146791],"genre_scores_gemma":[0.025059938,0.016933909,0.041855656,0.004050322,0.0012694779,0.000156143,0.0025335837,0.00034274938,0.9077982],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99941695,0.00015241437,0.000034955716,0.000078482604,0.00027234407,0.00004488506],"domain_scores_gemma":[0.999488,0.0002313274,0.000017259053,0.00011180951,0.00011058353,0.000040968695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010380163,0.0005955356,0.0004464111,0.0014444175,0.0007656716,0.0050207376,0.00078278914,0.0012284542,0.045633208],"category_scores_gemma":[0.001697332,0.00043365962,0.00037736387,0.002611085,0.0009830358,0.0041400306,0.0018048339,0.0011758651,0.023102626],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011754427,0.00004603545,0.00020622139,0.00023639432,0.000020262218,0.00008045166,0.0005398234,0.0007001834,0.0006177613,0.29548657,0.37301567,0.32903874],"study_design_scores_gemma":[0.000002988039,0.00000590452,0.00017729127,0.00009596471,0.000006510395,0.00009155393,0.00008493233,0.0007662394,0.00022818727,0.038627494,0.9599091,0.0000038973863],"about_ca_topic_score_codex":0.0030590685,"about_ca_topic_score_gemma":0.0038353282,"teacher_disagreement_score":0.045633208,"about_ca_system_score_codex":0.0014351439,"about_ca_system_score_gemma":0.0018450095,"threshold_uncertainty_score":0.15265822},"labels":[],"label_agreement":null},{"id":"W4243324895","doi":"10.1088/1742-6596/1767/1/011001","title":"Preface","year":2021,"lang":"en","type":"article","venue":"Journal of Physics Conference Series","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Presentation (obstetrics); Theme (computing); Analytics; Panel discussion; Track (disk drive); Computer science; Library science; Medical education; Medicine; World Wide Web; Data science; Business","score_opus":0.2135920012866684,"score_gpt":0.4723467402622782,"score_spread":0.2587547389756098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243324895","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002204856,0.009315457,0.007126399,0.03089651,0.122409,0.00079832366,0.01563821,0.0023234105,0.8092878],"genre_scores_gemma":[0.008919459,0.0060762116,0.003684379,0.0070415945,0.016139181,0.00043062097,0.014764525,0.0010966873,0.9418474],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99856335,0.00021079108,0.0001132156,0.00030270484,0.0006459452,0.00016402997],"domain_scores_gemma":[0.9947083,0.00073152623,0.00019996772,0.00049597386,0.0029492993,0.0009150114],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018254624,0.0011703232,0.00093601475,0.002756264,0.0034095822,0.0054961666,0.001817944,0.0018259169,0.529191],"category_scores_gemma":[0.0107737575,0.00041804003,0.00076359784,0.0022902992,0.00083883427,0.0040545478,0.00292501,0.003521221,0.38296214],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037552898,0.00002266273,0.00013958543,0.00011844835,0.000002343951,0.000060524962,0.00014199197,0.00006238219,0.00012809384,0.0049357316,0.9557087,0.038641937],"study_design_scores_gemma":[0.0000033241083,0.0000162409,0.0002245475,0.000096667805,0.0000012385256,0.000065644934,0.00013909084,0.00002542573,0.000053545347,0.0014635972,0.9979063,0.000004419042],"about_ca_topic_score_codex":0.0038282368,"about_ca_topic_score_gemma":0.0041999337,"teacher_disagreement_score":0.47080898,"about_ca_system_score_codex":0.0023876545,"about_ca_system_score_gemma":0.0032982107,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4244952229","doi":"10.28924/2291-8639-17-2019-838","title":"Anemia Modelling Using the Multiple Regression Analysis","year":2019,"lang":"en","type":"article","venue":"International Journal of Analysis and Applications","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Anemia; Regression analysis; Linear regression; Regression; Linear model; Statistics; Population; Computer science; Medicine; Variables; Machine learning; Mathematics; Internal medicine; Environmental health","score_opus":0.12685472058113398,"score_gpt":0.48805882490544283,"score_spread":0.36120410432430883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244952229","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.081416965,0.0036729337,0.90690124,0.0013929204,0.00022688221,0.000109429464,0.0016797532,0.00139531,0.0032046714],"genre_scores_gemma":[0.87911487,0.003188245,0.10619895,0.0002363657,0.0002640796,0.00028735443,0.0015802047,0.00013433615,0.00899565],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991443,0.00033472548,0.00006033669,0.00024010867,0.00013554799,0.00008486057],"domain_scores_gemma":[0.99879396,0.0007051221,0.00019988805,0.000053012358,0.00021098035,0.00003702296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016172688,0.00095123734,0.0010085794,0.0012592437,0.00024880873,0.0012584853,0.0012643497,0.0010231488,0.0022209857],"category_scores_gemma":[0.004325645,0.00037782083,0.0019485293,0.0011679677,0.00025984828,0.0007624715,0.00069405505,0.0014356299,0.000871756],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000246767,0.00015432642,0.021720447,0.00024784743,0.00040283243,0.00048553906,0.00010856439,0.86438453,0.0025147465,0.007621051,0.0032466592,0.098866776],"study_design_scores_gemma":[0.0000059621707,0.000041696578,0.0018427114,0.000018151948,0.000037049293,0.00006832414,0.000011217154,0.99468625,0.00034015905,0.0019966422,0.0009403449,0.000011484716],"about_ca_topic_score_codex":0.011720285,"about_ca_topic_score_gemma":0.0051551145,"teacher_disagreement_score":0.011720285,"about_ca_system_score_codex":0.00060107774,"about_ca_system_score_gemma":0.00078586244,"threshold_uncertainty_score":0.023304164},"labels":[],"label_agreement":null},{"id":"W4245682817","doi":"10.1109/isspit.2018.8642735","title":"A Comparative Analysis of Unsupervised Machine Techniques for Liver Disease Prediction","year":2018,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Unsupervised learning; Field (mathematics); Silhouette; Computational complexity theory; Computational intelligence; Set (abstract data type); Data set; Data mining; Pattern recognition (psychology); Algorithm; Mathematics","score_opus":0.23549331482326918,"score_gpt":0.5256213340002522,"score_spread":0.29012801917698305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245682817","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5056045,0.011368565,0.46920803,0.0008017635,0.00020165107,0.0002221901,0.0008982631,0.0014754299,0.010219533],"genre_scores_gemma":[0.7798864,0.0035507793,0.21287246,0.00008653507,0.00014351665,0.00013235427,0.0013530772,0.00009239817,0.001882441],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976568,0.00083290384,0.00016258248,0.0002385356,0.0010174128,0.0000917326],"domain_scores_gemma":[0.984294,0.010968216,0.0006257886,0.00080098293,0.0031882226,0.0001228441],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025280397,0.00051333394,0.0006286219,0.0033218046,0.00038021768,0.000617048,0.0005032557,0.0005768709,0.00072504993],"category_scores_gemma":[0.010880285,0.00012961018,0.0007722144,0.002532418,0.00021562682,0.00087757537,0.00040992527,0.00045937244,0.00024119252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077291206,0.00040343887,0.040594827,0.00057942676,0.00048021783,0.0001519051,0.00029099267,0.13078411,0.007328327,0.0052566035,0.0032769458,0.81008035],"study_design_scores_gemma":[0.000026347612,0.0007598971,0.049809504,0.00008109802,0.00015818793,0.00032138117,0.00023277478,0.93314254,0.008243982,0.00375028,0.0034213574,0.000052654257],"about_ca_topic_score_codex":0.00401092,"about_ca_topic_score_gemma":0.0047754194,"teacher_disagreement_score":0.00401092,"about_ca_system_score_codex":0.00051259494,"about_ca_system_score_gemma":0.0007773075,"threshold_uncertainty_score":0.013369739},"labels":[],"label_agreement":null},{"id":"W4248000657","doi":"10.22374/cjgim.v7i4.129","title":"Patient Profiling","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of General Internal Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Profiling (computer programming); Intensive care medicine; Computer science","score_opus":0.16102067954810545,"score_gpt":0.46248028273628056,"score_spread":0.3014596031881751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248000657","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030797424,0.011060589,0.06823821,0.15194775,0.009349894,0.0064485264,0.04517596,0.006844813,0.67013675],"genre_scores_gemma":[0.32633492,0.021757508,0.10725377,0.12933177,0.0068592275,0.010402032,0.038208198,0.0027067238,0.35714588],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9927099,0.0033696229,0.001162587,0.0009773457,0.0012112609,0.0005692994],"domain_scores_gemma":[0.97772425,0.0068594264,0.001960169,0.0031399443,0.007191548,0.0031246364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068602585,0.0005475523,0.0006094609,0.0022815533,0.0018705176,0.003186404,0.0013414545,0.0018152611,0.11717512],"category_scores_gemma":[0.046909414,0.00033508425,0.0005865848,0.0021948437,0.00047696824,0.002517962,0.0042269467,0.0022322924,0.04933135],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000207504,0.00008487075,0.014324282,0.00034276413,0.000022966044,0.0004406441,0.0016981873,0.00014938015,0.0002753578,0.00947819,0.69799274,0.27498317],"study_design_scores_gemma":[0.000038760878,0.000076299635,0.00599984,0.0006341096,0.000019079856,0.0016345645,0.001170887,0.00031582158,0.00033245742,0.004805522,0.9849333,0.00003940365],"about_ca_topic_score_codex":0.0027822237,"about_ca_topic_score_gemma":0.0026238968,"teacher_disagreement_score":0.11717512,"about_ca_system_score_codex":0.00226168,"about_ca_system_score_gemma":0.0054234057,"threshold_uncertainty_score":0.39198983},"labels":[],"label_agreement":null},{"id":"W4251080734","doi":"10.32920/ryerson.14661300","title":"A Comparative Study of the Impact of Data Augmentation in Machine Learning Based Classification Accuracy","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Gramian matrix; Computer science; Pattern recognition (psychology); Artificial intelligence; Discriminant; SIGNAL (programming language); Linear discriminant analysis; Machine learning; Field (mathematics); Series (stratigraphy); Data mining; Mathematics; Eigenvalues and eigenvectors","score_opus":0.6646261969874546,"score_gpt":0.6398211815144802,"score_spread":0.024805015472974423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251080734","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9253223,0.01096082,0.047152292,0.0013219211,0.0011507274,0.00019641053,0.0027432097,0.0031538021,0.007998603],"genre_scores_gemma":[0.9622878,0.0010016405,0.030022405,0.000118184274,0.00016860414,0.00007576384,0.0045374217,0.00013031352,0.0016579297],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9932827,0.0023350734,0.0008867166,0.0011449179,0.001970551,0.00038003162],"domain_scores_gemma":[0.9641106,0.025666954,0.0012318278,0.004009474,0.0045549995,0.000426135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010580093,0.0013430472,0.0014705788,0.0020756589,0.00062725594,0.002366652,0.0009229058,0.0012780221,0.0013214767],"category_scores_gemma":[0.031560812,0.00026428397,0.0011074439,0.0020462575,0.0006872343,0.0025381094,0.001008639,0.0013297107,0.00089456193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005033228,0.0011850675,0.0833716,0.0008470968,0.0007890089,0.0002465366,0.00043931673,0.08995053,0.009495973,0.00093540567,0.008535424,0.7991708],"study_design_scores_gemma":[0.00015407633,0.0044600694,0.09710402,0.00032478033,0.00065693515,0.00062662776,0.0008323781,0.84700596,0.037031867,0.002618346,0.009013184,0.00017174742],"about_ca_topic_score_codex":0.0032948472,"about_ca_topic_score_gemma":0.0021659764,"teacher_disagreement_score":0.010580093,"about_ca_system_score_codex":0.00076447485,"about_ca_system_score_gemma":0.0007743266,"threshold_uncertainty_score":0.055953562},"labels":[],"label_agreement":null},{"id":"W4251250329","doi":"10.4018/978-1-5225-6915-2.ch032","title":"Leveraging Applications of Data Mining in Healthcare Using Big Data Analytics","year":2018,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Big data; Data science; Leverage (statistics); Computer science; Analytics; Data analysis; Scalability; Health care; Data mining; Data quality; Data set; Set (abstract data type); Database; Artificial intelligence; Engineering","score_opus":0.5641746199340043,"score_gpt":0.5114758419184683,"score_spread":0.05269877801553602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251250329","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010039268,0.1975901,0.37724397,0.035482574,0.0046933475,0.00038514525,0.00080804585,0.0018836355,0.371874],"genre_scores_gemma":[0.11854846,0.27962002,0.44758794,0.011854239,0.0074146213,0.00039137626,0.0017418504,0.00070105784,0.13214049],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99938273,0.00016798408,0.000035784742,0.000102898455,0.00027426818,0.00003637469],"domain_scores_gemma":[0.9989079,0.0007900749,0.000032851134,0.00011398554,0.000098657736,0.000056394972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011838485,0.00077066984,0.0004653408,0.0019467477,0.00052841794,0.0040374734,0.0011091972,0.0012139601,0.007034618],"category_scores_gemma":[0.0019546833,0.0004215912,0.00075554854,0.0031857498,0.0010642492,0.0044395677,0.00224965,0.0019599444,0.004983695],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029298204,0.00009573212,0.001155936,0.0017031166,0.00007300711,0.0004233564,0.0011827254,0.0035850557,0.0039453614,0.18940449,0.08848356,0.7099183],"study_design_scores_gemma":[0.000009634487,0.0000455584,0.001098499,0.0015696244,0.00003594863,0.0010002668,0.0005606591,0.009206523,0.0021935774,0.1869834,0.7972588,0.00003755478],"about_ca_topic_score_codex":0.0005264653,"about_ca_topic_score_gemma":0.0010383569,"teacher_disagreement_score":0.007034618,"about_ca_system_score_codex":0.00071201427,"about_ca_system_score_gemma":0.0010613943,"threshold_uncertainty_score":0.023533165},"labels":[],"label_agreement":null},{"id":"W4252801458","doi":"10.36227/techrxiv.12053985","title":"Development of On-Device Machine Learning Tools for Medication Warning Label Recognition","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Pill; Warning system; Internet privacy; Computer science; Medicine; Computer security; Psychology; Nursing; Telecommunications","score_opus":0.5000611816440992,"score_gpt":0.5302722402444039,"score_spread":0.030211058600304708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252801458","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019844675,0.00065154175,0.920417,0.00059415645,0.00084156863,0.0009326125,0.0015888187,0.044815045,0.010314577],"genre_scores_gemma":[0.16070655,0.0008511067,0.7962578,0.0008653514,0.00019494616,0.0011647758,0.0056164605,0.001594377,0.032748505],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99893767,0.00015089735,0.00008159647,0.00021902128,0.00048536767,0.00012544189],"domain_scores_gemma":[0.99742234,0.0008989796,0.00010479375,0.00032881973,0.0011224799,0.00012264245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012120601,0.0011665968,0.00079425494,0.0012818787,0.00043540803,0.0016321229,0.0025251315,0.0013709611,0.01373911],"category_scores_gemma":[0.0052032974,0.00058789167,0.0009254805,0.00069061556,0.00029459628,0.0017550447,0.0012333767,0.0015303865,0.009189329],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043316177,0.00079993065,0.0025173505,0.00044215226,0.00019004839,0.0007231508,0.00023285461,0.015150275,0.035259593,0.0051423563,0.05200501,0.887104],"study_design_scores_gemma":[0.00021185025,0.0005992811,0.004646584,0.00026287083,0.00012954396,0.0007766983,0.0002737101,0.7683414,0.118331596,0.0112171685,0.095081724,0.00012749007],"about_ca_topic_score_codex":0.004348309,"about_ca_topic_score_gemma":0.0047912775,"teacher_disagreement_score":0.01373911,"about_ca_system_score_codex":0.0005981255,"about_ca_system_score_gemma":0.0009959267,"threshold_uncertainty_score":0.045961916},"labels":[],"label_agreement":null},{"id":"W4254474425","doi":"10.1088/1757-899x/1099/1/011001","title":"Preface","year":2021,"lang":"en","type":"article","venue":"IOP Conference Series Materials Science and Engineering","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Excellence; Big data; Computer science; Field (mathematics); Data science; Engineering management; Engineering ethics; Engineering; Political science; Mathematics; Data mining","score_opus":0.10425912659202377,"score_gpt":0.3887383340814476,"score_spread":0.2844792074894238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254474425","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013707352,0.008372319,0.0055770604,0.029140208,0.12290422,0.0006491638,0.010061376,0.0019443543,0.81998056],"genre_scores_gemma":[0.0061488003,0.0047473684,0.0023821918,0.0067821504,0.013706815,0.00031464084,0.010198433,0.0009052108,0.95481443],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984054,0.00021747754,0.000105852814,0.0003416614,0.00074099185,0.0001886703],"domain_scores_gemma":[0.995669,0.0004588444,0.00014158353,0.00041919603,0.0024599375,0.000851408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018146547,0.0012137752,0.0010141355,0.0022407754,0.0033473042,0.0062334826,0.0021166198,0.0023153145,0.601637],"category_scores_gemma":[0.008705317,0.00040327772,0.0008774152,0.0019498708,0.00089970016,0.0046588057,0.0034387705,0.003785278,0.43359625],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026163123,0.000018246523,0.000089904664,0.000101660255,0.0000023103248,0.000045647317,0.00009042817,0.000046676276,0.00012731514,0.005220015,0.95871484,0.035516847],"study_design_scores_gemma":[0.0000028211614,0.000010515227,0.00014991952,0.00007334062,0.0000011383488,0.000045468278,0.00009177577,0.000024673589,0.000049520408,0.0011343267,0.99841285,0.0000036316924],"about_ca_topic_score_codex":0.0037776164,"about_ca_topic_score_gemma":0.0043808017,"teacher_disagreement_score":0.601637,"about_ca_system_score_codex":0.0024206673,"about_ca_system_score_gemma":0.0038569665,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4280538237","doi":"10.5281/zenodo.6564283","title":"D6.11 SSHOC Trainer Toolkit (final)","year":2022,"lang":"en","type":"report","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canarie","funders":"Rural Development Administration; European Commission","keywords":"Trainer; Computer science; Operating system","score_opus":0.37285267863505134,"score_gpt":0.4568115386404643,"score_spread":0.08395886000541297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280538237","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023448654,0.00069878146,0.15516226,0.0032314518,0.0025266418,0.0021662707,0.21829802,0.2744435,0.3411281],"genre_scores_gemma":[0.009273463,0.00094700034,0.10963234,0.0018698841,0.00032542043,0.0045662355,0.32337502,0.09521708,0.45479354],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960063,0.0009740835,0.00025621266,0.0003917523,0.0018968093,0.0004748726],"domain_scores_gemma":[0.9936512,0.0014297151,0.00021687774,0.0012580245,0.0028496503,0.0005946019],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0063789594,0.0013917225,0.00086339883,0.0020084707,0.0013409678,0.005313422,0.0036855778,0.0019452141,0.39116552],"category_scores_gemma":[0.017050711,0.0014602176,0.0013063673,0.0017766182,0.0006865793,0.004612709,0.0065520997,0.0028913154,0.37815386],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015634517,0.000051225554,0.00018497149,0.0006953135,0.000010884097,0.00007818328,0.00048108582,0.0006768406,0.0014663001,0.005184192,0.9239087,0.067105904],"study_design_scores_gemma":[0.00002440497,0.00002245266,0.0002270566,0.00015359142,0.000004527806,0.00003313178,0.00012903669,0.0003593429,0.00092469173,0.0019470296,0.9961414,0.00003327811],"about_ca_topic_score_codex":0.0152385365,"about_ca_topic_score_gemma":0.01911564,"teacher_disagreement_score":0.39116552,"about_ca_system_score_codex":0.002469882,"about_ca_system_score_gemma":0.0056608906,"threshold_uncertainty_score":0.86842847},"labels":[],"label_agreement":null},{"id":"W4280594276","doi":"10.18280/isi.270213","title":"Impact of Vaccination on COVID-19 Spread in Real Time: Visualization and Analysis Tool","year":2022,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Data science; Vaccination; Big data; Variety (cybernetics); Computer science; Pandemic; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Disease; Visualization; Infectious disease (medical specialty); Virology; Data mining; Medicine; Artificial intelligence","score_opus":0.06871721484604115,"score_gpt":0.4430142869905085,"score_spread":0.37429707214446734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280594276","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8321649,0.0013705358,0.053812362,0.0036546437,0.0006650591,0.0004410688,0.042470485,0.04343568,0.021985251],"genre_scores_gemma":[0.9120214,0.0005128708,0.057680838,0.00020895993,0.00007858898,0.00012607119,0.02436894,0.0008118066,0.004190474],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946934,0.000104131424,0.0000517584,0.00011142985,0.00019518852,0.00006825005],"domain_scores_gemma":[0.9977501,0.0011240948,0.00017308416,0.0002077618,0.0005541668,0.000190876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00143344,0.00074884243,0.0004198402,0.0033652035,0.00047486447,0.0020251232,0.00049923256,0.00064648915,0.004883343],"category_scores_gemma":[0.0043115877,0.0002028459,0.0007232505,0.0014345387,0.00020263327,0.0012809345,0.000840492,0.0007094523,0.0008598574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027903102,0.0023152027,0.35566115,0.0011596285,0.00052400783,0.0022099512,0.0041778325,0.10359301,0.033622008,0.00854705,0.13488388,0.3505161],"study_design_scores_gemma":[0.00013935777,0.0005410929,0.1761311,0.00021468902,0.00020207578,0.00067865493,0.0025344072,0.7495811,0.024487618,0.0051597403,0.040168546,0.00016170317],"about_ca_topic_score_codex":0.01256928,"about_ca_topic_score_gemma":0.009590406,"teacher_disagreement_score":0.01256928,"about_ca_system_score_codex":0.0005396136,"about_ca_system_score_gemma":0.00054430304,"threshold_uncertainty_score":0.024992228},"labels":[],"label_agreement":null},{"id":"W4281486515","doi":"10.3233/shti220404","title":"Characterization of Type 2 Diabetes Using Counterfactuals and Explainable AI","year":2022,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; York University; Public Health Ontario; University of Toronto","funders":"Compagnia di San Paolo","keywords":"Medicine; Counterfactual thinking; Body mass index; Counterfactual conditional; Type 2 diabetes; Disease; Diabetes mellitus; Type 2 Diabetes Mellitus; Blood sugar; Gerontology; Internal medicine; Endocrinology; Psychology","score_opus":0.16409022026328793,"score_gpt":0.4798552198594833,"score_spread":0.3157649995961954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281486515","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22714764,0.0011199422,0.76525885,0.0022713796,0.00009743634,0.00023439815,0.0005515846,0.00016367156,0.0031551772],"genre_scores_gemma":[0.9103198,0.0004032927,0.08822465,0.00014686091,0.00007177155,0.00019369341,0.0003513555,0.000010457465,0.00027815535],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99336797,0.0049134395,0.00031101788,0.00068744854,0.00056227634,0.00015789332],"domain_scores_gemma":[0.9136494,0.07620663,0.005293452,0.00334872,0.0011814499,0.00032045884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010727636,0.00087596424,0.00075977517,0.002052334,0.00043876423,0.002486759,0.0012566772,0.0008597936,0.0014776447],"category_scores_gemma":[0.05231353,0.00029810108,0.0018121861,0.0009795588,0.0013795766,0.0016979114,0.0011949395,0.0012971646,0.00006407846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006688521,0.00045182556,0.06880801,0.00040799245,0.001309156,0.00090097147,0.0014793322,0.54682064,0.0016843877,0.31138283,0.0007568556,0.06532908],"study_design_scores_gemma":[0.00005200679,0.00014082443,0.0061762217,0.000059207956,0.00010848888,0.00014955811,0.00017364869,0.8263245,0.0004946866,0.16551216,0.00077153015,0.000037143767],"about_ca_topic_score_codex":0.0040377686,"about_ca_topic_score_gemma":0.0018629505,"teacher_disagreement_score":0.010727636,"about_ca_system_score_codex":0.0011196758,"about_ca_system_score_gemma":0.0010968199,"threshold_uncertainty_score":0.056733787},"labels":[],"label_agreement":null},{"id":"W4281729074","doi":"10.1002/9781119665885.ch49","title":"A Primer on Biostatistics","year":2022,"lang":"es","type":"other","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Canadian Blood Services; University of Calgary; University of British Columbia","funders":"","keywords":"Biostatistics; Test (biology); Disease; Descriptive statistics; Computer science; Epidemiology; Data science; Diagnostic test; Statistical hypothesis testing; Medicine; Management science; Medical physics; Statistics; Engineering; Pathology; Mathematics; Pediatrics","score_opus":0.1874976597266077,"score_gpt":0.5053587930264333,"score_spread":0.31786113329982557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281729074","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005929191,0.24552245,0.35939056,0.2585205,0.040738866,0.0007822962,0.0013174517,0.0033790858,0.08975584],"genre_scores_gemma":[0.0140106585,0.28107977,0.4520228,0.13483821,0.07709889,0.0031130712,0.0015368824,0.0028426074,0.033457134],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9557993,0.027268099,0.00443125,0.0018012003,0.009991802,0.00070836133],"domain_scores_gemma":[0.75478125,0.21616156,0.004031214,0.006264992,0.015901726,0.002859232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04529376,0.0020016646,0.0022649977,0.010384148,0.0018316687,0.011158036,0.004419488,0.0074278032,0.017561253],"category_scores_gemma":[0.10712253,0.0020023887,0.002213436,0.011810449,0.01304939,0.010559832,0.0041564647,0.025634814,0.019153746],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006057595,0.00015085515,0.0007307464,0.0027258827,0.00010736192,0.00034939827,0.0019623623,0.0015460787,0.00050084706,0.2962865,0.47762352,0.21795595],"study_design_scores_gemma":[0.000023445727,0.000034299206,0.00031363618,0.0021821081,0.000014864373,0.0004451044,0.0003506407,0.0008361401,0.0001413295,0.2504417,0.7451777,0.00003911821],"about_ca_topic_score_codex":0.0019691086,"about_ca_topic_score_gemma":0.0022052862,"teacher_disagreement_score":0.04529376,"about_ca_system_score_codex":0.0035240396,"about_ca_system_score_gemma":0.01059273,"threshold_uncertainty_score":0.2395392},"labels":[],"label_agreement":null},{"id":"W4281994329","doi":"10.3233/shti220084","title":"A Knowledge Graph of Mechanistic Associations Between COVID-19, Diabetes Mellitus, and Chronic Kidney Disease","year":2022,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Diabetes mellitus; Coronavirus disease 2019 (COVID-19); Kidney disease; Disease; Medicine; Intensive care medicine; Bioinformatics; Infectious disease (medical specialty); Internal medicine; Biology; Endocrinology","score_opus":0.15060415448028894,"score_gpt":0.48383841473617273,"score_spread":0.33323426025588376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281994329","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08441149,0.01258255,0.73801905,0.01916011,0.0006400085,0.0015206776,0.0919839,0.005370257,0.046312008],"genre_scores_gemma":[0.32785642,0.00775526,0.6157084,0.0015052893,0.00027953996,0.0006955577,0.041926805,0.00015381488,0.0041188523],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983902,0.000372349,0.00021323882,0.00046653659,0.00046805583,0.00008952343],"domain_scores_gemma":[0.99180776,0.005667049,0.00091846124,0.00043022173,0.00095389347,0.00022267795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016988849,0.00082251406,0.00069087883,0.013318592,0.0016013591,0.002912397,0.0012541518,0.0013312186,0.006233917],"category_scores_gemma":[0.011104741,0.00044513907,0.002176754,0.007756039,0.0009116464,0.00314698,0.0018596911,0.0010512348,0.00090199534],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006423362,0.00057516457,0.06724808,0.007535174,0.001980632,0.009146942,0.0028214278,0.077426165,0.011780528,0.24575815,0.05203212,0.5230533],"study_design_scores_gemma":[0.00018931675,0.00034744877,0.02950875,0.0025233098,0.0027616585,0.005539256,0.0019842626,0.17012371,0.006839944,0.46213153,0.31783944,0.0002113117],"about_ca_topic_score_codex":0.019945223,"about_ca_topic_score_gemma":0.026970915,"teacher_disagreement_score":0.019945223,"about_ca_system_score_codex":0.0015561507,"about_ca_system_score_gemma":0.004561924,"threshold_uncertainty_score":0.039658308},"labels":[],"label_agreement":null},{"id":"W4283731435","doi":"10.1136/jech-2021-217793","title":"Prediction models of diabetes complications: a scoping review","year":2022,"lang":"en","type":"review","venue":"Journal of Epidemiology & Community Health","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Institute for Clinical Evaluative Sciences; Université Laval; University of Toronto; Diabetes Canada; Health and Social Services Centre University Institute of Geriatrics of Sherbrooke; Women's College Hospital; Université de Sherbrooke","funders":"Canadian Institutes of Health Research; Diabetes Action Canada; Canada Research Chairs; Gordon and Betty Moore Foundation","keywords":"Medicine; Diabetes mellitus; MEDLINE; Type 2 diabetes; Complication; Amputation; Intensive care medicine; Dementia; Internal medicine; Surgery; Disease; Endocrinology","score_opus":0.8104287875942119,"score_gpt":0.6485173460693789,"score_spread":0.16191144152483294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283731435","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039023816,0.99564147,0.001369842,0.0009770619,0.00018385827,0.00026914995,0.000616354,0.000035331333,0.0005166632],"genre_scores_gemma":[0.008978835,0.986748,0.0023976828,0.000448446,0.00014465945,0.0006057952,0.0005542197,0.000013876696,0.00010852207],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.982842,0.008354215,0.0051293625,0.0010527445,0.0023401,0.00028156917],"domain_scores_gemma":[0.81062895,0.17182103,0.0094894655,0.0018607443,0.0058592954,0.00034042101],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02695946,0.0028408314,0.007130625,0.01929639,0.000973322,0.005209121,0.0043055466,0.0037115964,0.005620239],"category_scores_gemma":[0.16430752,0.0019445366,0.01350257,0.01731079,0.0014004989,0.00482941,0.0025243137,0.0032845594,0.00079534104],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016599787,0.000056136407,0.0018698054,0.7944003,0.010699174,0.00016155872,0.0005203837,0.0031751227,0.000052035713,0.003843905,0.0081896195,0.17686607],"study_design_scores_gemma":[0.00006647444,0.00006931794,0.0016043168,0.9454676,0.018142067,0.0001821623,0.00024584722,0.0013371308,0.00007189685,0.0037819757,0.02897165,0.000059472626],"about_ca_topic_score_codex":0.021082623,"about_ca_topic_score_gemma":0.02046294,"teacher_disagreement_score":0.02695946,"about_ca_system_score_codex":0.0063157226,"about_ca_system_score_gemma":0.01671695,"threshold_uncertainty_score":0.14257699},"labels":[],"label_agreement":null},{"id":"W4285270242","doi":"10.1504/ijmei.2022.123921","title":"Early diagnosis of coronary artery disease by SVM, decision tree algorithms and ensemble methods","year":2022,"lang":"en","type":"article","venue":"International Journal of Medical Engineering and Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Support vector machine; Random forest; Decision tree; Computer science; Voting; Heart disease; Machine learning; Artificial intelligence; Algorithm; Coronary artery disease; Data mining; Medicine; Cardiology","score_opus":0.05049668099583381,"score_gpt":0.4366698043689227,"score_spread":0.3861731233730889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285270242","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09341185,0.0026289122,0.90077156,0.00029309138,0.0002252329,0.000077682154,0.00031269627,0.0007503526,0.0015286856],"genre_scores_gemma":[0.76177573,0.0013028511,0.23438762,0.000108506436,0.00020441033,0.000074549425,0.0006424451,0.000045956873,0.0014578799],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914587,0.00025891484,0.00009167189,0.00018913516,0.00023386344,0.000080600905],"domain_scores_gemma":[0.99860805,0.000652236,0.00013296264,0.00012341514,0.00041677087,0.00006663057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019479351,0.00078451785,0.0011114511,0.0022318573,0.0002915729,0.0008639856,0.00080761826,0.0007556976,0.00070924585],"category_scores_gemma":[0.0041862815,0.00022766506,0.00096178456,0.0013040489,0.00014116628,0.0011608065,0.0005180222,0.00072492735,0.0004411888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041072525,0.00031344238,0.02729685,0.00015345581,0.0003284279,0.00017927033,0.000074246454,0.13960677,0.0077791503,0.002414665,0.0033473414,0.81809556],"study_design_scores_gemma":[0.000011510227,0.00010196499,0.0036907024,0.000023061291,0.00008809948,0.00012876179,0.00002218976,0.9903441,0.0024531838,0.0023535353,0.0007629302,0.000019898094],"about_ca_topic_score_codex":0.0025385066,"about_ca_topic_score_gemma":0.0025921972,"teacher_disagreement_score":0.0025385066,"about_ca_system_score_codex":0.0002775521,"about_ca_system_score_gemma":0.0004480302,"threshold_uncertainty_score":0.010301828},"labels":[],"label_agreement":null},{"id":"W4285325934","doi":"10.1109/hpcc-dss-smartcity-dependsys53884.2021.00005","title":"Message from the HPCC 2021 Steering Chairs","year":2021,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Honor; Steering committee; Computer science; Pleasure; Psychology; Internet privacy; Engineering; Engineering management","score_opus":0.17882098589162296,"score_gpt":0.4763826948016215,"score_spread":0.29756170890999856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285325934","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00054150075,0.0021556611,0.0014581878,0.5879923,0.3830308,0.0004416684,0.0026856675,0.0005196424,0.021174518],"genre_scores_gemma":[0.0061479593,0.0027950092,0.0025714368,0.6122958,0.10578587,0.0014015741,0.0039005382,0.0007946917,0.26430717],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9914135,0.0016806155,0.00045510902,0.0007603862,0.004418622,0.0012718416],"domain_scores_gemma":[0.9572825,0.0024885829,0.0011505748,0.0010253538,0.02393764,0.014115384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013750099,0.0014062164,0.0012483574,0.0012733921,0.0036207943,0.0068177814,0.0022587131,0.011381834,0.074823774],"category_scores_gemma":[0.03270501,0.000774641,0.0014358645,0.0011342166,0.0011704788,0.0034520156,0.004534,0.015771987,0.07191521],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015795267,0.0000052246164,0.00003141836,0.000019022445,0.0000014765799,0.000010363394,0.000006527209,0.000008554428,0.000020899739,0.0001348863,0.9982451,0.0015006425],"study_design_scores_gemma":[0.000031231917,0.000024263689,0.00046667256,0.00009742411,0.000006081452,0.00004022925,0.00012229178,0.00006547125,0.0001307212,0.0004068846,0.99858403,0.000024777879],"about_ca_topic_score_codex":0.010120499,"about_ca_topic_score_gemma":0.012800699,"teacher_disagreement_score":0.074823774,"about_ca_system_score_codex":0.0034830405,"about_ca_system_score_gemma":0.020070795,"threshold_uncertainty_score":0.25031042},"labels":[],"label_agreement":null},{"id":"W4285326688","doi":"10.1109/hpcc-dss-smartcity-dependsys53884.2021.00253","title":"Big Data Mining on Health Informatics Data for Cities","year":2021,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Big data; Informatics; Data science; Health informatics; Analytics; Computer science; Health care; Decision support system; Knowledge management; Business; Data mining; Engineering; Political science","score_opus":0.7850332586489158,"score_gpt":0.5990209700479774,"score_spread":0.18601228860093844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285326688","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2293472,0.0030897367,0.5678127,0.026908807,0.0011093873,0.0024829363,0.12717935,0.01940997,0.02265993],"genre_scores_gemma":[0.36882818,0.0019154858,0.5431091,0.00187891,0.0003278956,0.0008132876,0.07955596,0.00042189987,0.0031491234],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962386,0.000982416,0.00070788374,0.0007063324,0.0011286157,0.00023611082],"domain_scores_gemma":[0.9906035,0.003275601,0.00096038345,0.002804946,0.0018076772,0.0005478219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033052093,0.0009321762,0.000859982,0.0057543674,0.0012976823,0.0038540382,0.0012742316,0.00099841,0.0020383815],"category_scores_gemma":[0.015817782,0.0006021131,0.0021402878,0.010296029,0.00082264893,0.0027225956,0.0033992978,0.0017388187,0.0012122303],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064972445,0.0008445187,0.13929893,0.0016997078,0.0009896313,0.0018031783,0.0025093309,0.09074002,0.0101810815,0.042179894,0.13150108,0.5776029],"study_design_scores_gemma":[0.0001908721,0.00027720552,0.07375094,0.00075910357,0.0003415753,0.001027625,0.0054073827,0.6214252,0.02153441,0.10781028,0.16730876,0.00016665603],"about_ca_topic_score_codex":0.008709046,"about_ca_topic_score_gemma":0.012615139,"teacher_disagreement_score":0.008709046,"about_ca_system_score_codex":0.0013868582,"about_ca_system_score_gemma":0.00340838,"threshold_uncertainty_score":0.017479837},"labels":[],"label_agreement":null},{"id":"W4285464673","doi":"10.32920/ryerson.14660673.v1","title":"Comparative analysis of classification models for diagnosis Type 2 Diabetes","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Hospital for Sick Children; McMaster University","keywords":"C4.5 algorithm; Machine learning; Computer science; Artificial intelligence; Decision tree; Data mining; Medical diagnosis; Expert system; Multilayer perceptron; Support vector machine; Perceptron; Naive Bayes classifier; Artificial neural network; Medicine","score_opus":0.5582518129913863,"score_gpt":0.567110148366119,"score_spread":0.008858335374732684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285464673","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67648804,0.016503956,0.28925052,0.0022900116,0.00054264284,0.00041761162,0.0022186728,0.0011661202,0.011122474],"genre_scores_gemma":[0.937105,0.0022447798,0.057487167,0.00014457329,0.00010264832,0.00016010835,0.0015654487,0.000050463805,0.0011397182],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9965659,0.0018839849,0.00025811605,0.00036397245,0.00076460984,0.0001634457],"domain_scores_gemma":[0.962208,0.03387756,0.0006479588,0.00063187256,0.002452632,0.00018202851],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009718485,0.0008629058,0.0014579652,0.0038610243,0.00047055137,0.0017295575,0.00093281997,0.0011082714,0.0015940312],"category_scores_gemma":[0.02815826,0.00019586715,0.0016409563,0.0020468263,0.00023337225,0.0011808127,0.00047487102,0.00082320994,0.00031883863],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029562511,0.0007054198,0.0842296,0.0008138302,0.0017496294,0.00025857537,0.00038979796,0.49050394,0.0013086022,0.008773057,0.0050768526,0.40323448],"study_design_scores_gemma":[0.000031768734,0.00029917926,0.0127859805,0.000082248735,0.0002321965,0.000081657476,0.00014959456,0.9821699,0.00072662794,0.002649107,0.0007682885,0.000023530969],"about_ca_topic_score_codex":0.008840141,"about_ca_topic_score_gemma":0.0046548606,"teacher_disagreement_score":0.009718485,"about_ca_system_score_codex":0.0018174682,"about_ca_system_score_gemma":0.0010837694,"threshold_uncertainty_score":0.051396906},"labels":[],"label_agreement":null},{"id":"W4285727974","doi":"10.3389/fphar.2022.944516","title":"Major areas of interest of artificial intelligence research applied to health care administrative data: a scoping review","year":2022,"lang":"en","type":"review","venue":"Frontiers in Pharmacology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de Santé Publique du Québec; Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"CINAHL; MEDLINE; Medicine; Polypharmacy; Health care; Pharmacovigilance; Data science; Artificial intelligence; Computer science; Adverse effect; Intensive care medicine; Pharmacology; Psychiatry","score_opus":0.7733749619417007,"score_gpt":0.681508232675056,"score_spread":0.09186672926664474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285727974","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003867552,0.9956819,0.00048655935,0.0016531504,0.00038262008,0.00039040478,0.00028715626,0.00001287026,0.0007186202],"genre_scores_gemma":[0.0037086213,0.9922288,0.0016480394,0.0008909446,0.00020373776,0.0008544222,0.00030062284,0.000008749763,0.00015607625],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.966901,0.011195086,0.013391579,0.001870035,0.0060248114,0.0006174527],"domain_scores_gemma":[0.74825263,0.20906037,0.020141562,0.0022030787,0.019323912,0.0010183902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0371591,0.0023157815,0.0064034695,0.054833725,0.0019118076,0.007976406,0.0030190442,0.005264649,0.0056138416],"category_scores_gemma":[0.16909268,0.0019078492,0.0066675288,0.05040663,0.002781987,0.007019635,0.0033923602,0.0026939437,0.0011694629],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009344019,0.00002997905,0.0009982297,0.82333785,0.00147961,0.00021304024,0.0008055924,0.0002621767,0.00023724869,0.0019201656,0.0073167807,0.16330592],"study_design_scores_gemma":[0.000024006342,0.000042895714,0.0012075743,0.9636253,0.0034363011,0.00019136925,0.00050310174,0.000106193846,0.00012636173,0.00092547416,0.02978761,0.000023727249],"about_ca_topic_score_codex":0.009558424,"about_ca_topic_score_gemma":0.018094404,"teacher_disagreement_score":0.054833725,"about_ca_system_score_codex":0.009479264,"about_ca_system_score_gemma":0.031242142,"threshold_uncertainty_score":0.19651848},"labels":[],"label_agreement":null},{"id":"W4286517661","doi":"10.18280/ria.360301","title":"Diagnostic Analysis of Diabetes Mellitus Using Machine Learning Approach","year":2022,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Machine learning; Artificial intelligence; Decision tree; Naive Bayes classifier; Random forest; Logistic regression; Diabetes mellitus; Boosting (machine learning); Computer science; Feature selection; Gradient boosting; Statistical classification; Medicine; Algorithm; Support vector machine","score_opus":0.15304806143388613,"score_gpt":0.41361289815739133,"score_spread":0.26056483672350517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286517661","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28001276,0.005640539,0.6940907,0.0016864792,0.0005070161,0.0007260932,0.00328112,0.003519933,0.010535351],"genre_scores_gemma":[0.81996477,0.0012221102,0.17437701,0.00024214093,0.00015847583,0.00017415974,0.0023215674,0.000025338268,0.0015144333],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990627,0.00021977919,0.0001335484,0.00015586759,0.0003158621,0.00011228317],"domain_scores_gemma":[0.9988341,0.00052061264,0.00014250971,0.00005580627,0.0003860395,0.00006094835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011603859,0.00058685767,0.0008601312,0.0039224993,0.0003835027,0.0011510849,0.00066531287,0.00067997933,0.0011591343],"category_scores_gemma":[0.0035131304,0.00014059845,0.000828946,0.0016857346,0.00016442343,0.0006054934,0.0004318383,0.00068708265,0.0005544889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069042214,0.0010055747,0.1310795,0.0007236262,0.00037470984,0.0011783524,0.00020129415,0.08809789,0.014880351,0.0040824236,0.009750493,0.7479354],"study_design_scores_gemma":[0.000043683012,0.0003423565,0.0312106,0.00016352278,0.00016108113,0.0009817114,0.00035860948,0.9368009,0.016515959,0.007590271,0.005761497,0.00006975801],"about_ca_topic_score_codex":0.0025590858,"about_ca_topic_score_gemma":0.0016416962,"teacher_disagreement_score":0.0039224993,"about_ca_system_score_codex":0.0005153809,"about_ca_system_score_gemma":0.0008276764,"threshold_uncertainty_score":0.006136775},"labels":[],"label_agreement":null},{"id":"W4288442515","doi":"10.1371/journal.pone.0271723","title":"An evolutionary machine learning algorithm for cardiovascular disease risk prediction","year":2022,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Framingham Risk Score; Receiver operating characteristic; Artificial intelligence; Machine learning; Cohort; Artificial neural network; F1 score; Population; Random forest; Framingham Heart Study; Medicine; Percentile; Convolutional neural network; Algorithm; Computer science; Disease; Statistics; Internal medicine; Mathematics","score_opus":0.14574175479207566,"score_gpt":0.3784191505267768,"score_spread":0.23267739573470117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288442515","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042331334,0.00072351063,0.952735,0.00043835497,0.00010474927,0.00009292643,0.000104721,0.0004949015,0.002974453],"genre_scores_gemma":[0.5284988,0.00051742594,0.46600726,0.00032165291,0.00011118742,0.00047681242,0.0003290329,0.00008389978,0.0036539012],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951327,0.0001997373,0.000036425547,0.00011170191,0.00009589726,0.00004291659],"domain_scores_gemma":[0.99882466,0.0008003939,0.00007484318,0.000047129277,0.00022752561,0.000025331086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014091427,0.0007861688,0.00088779186,0.001122839,0.0004383307,0.0006199107,0.0009105174,0.0010339096,0.0016189304],"category_scores_gemma":[0.0036671911,0.00033837423,0.00076775794,0.0008790285,0.0004597906,0.0005541811,0.0006512512,0.00096883584,0.00037964684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038698807,0.00006605502,0.004323971,0.00005027464,0.00010799186,0.00007532923,0.000055909615,0.84158874,0.0007052555,0.004733223,0.0011105035,0.14714408],"study_design_scores_gemma":[0.0000069620833,0.00001916523,0.00021821052,0.000007117607,0.000008250123,0.000016188626,0.00000392418,0.99755657,0.00011741471,0.0016918567,0.0003513569,0.0000029606915],"about_ca_topic_score_codex":0.0066208914,"about_ca_topic_score_gemma":0.0034061135,"teacher_disagreement_score":0.0066208914,"about_ca_system_score_codex":0.0007702697,"about_ca_system_score_gemma":0.0010707858,"threshold_uncertainty_score":0.013164699},"labels":[],"label_agreement":null},{"id":"W4289520941","doi":"10.1002/cpe.7219","title":"Machine learning and IoT‐based model for patient monitoring and early prediction of diabetes","year":2022,"lang":"en","type":"article","venue":"Concurrency and Computation Practice and Experience","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pan Am Clinic","funders":"","keywords":"Machine learning; Computer science; Naive Bayes classifier; Artificial intelligence; Random forest; Support vector machine; Decision tree; Receiver operating characteristic; Logistic regression; Python (programming language)","score_opus":0.1283474163911486,"score_gpt":0.45726478509937785,"score_spread":0.32891736870822924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289520941","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36182866,0.0014703408,0.6175343,0.0018763102,0.0004122821,0.00019075017,0.0014493569,0.0021071946,0.013130924],"genre_scores_gemma":[0.98306054,0.0002629399,0.012425958,0.00007488399,0.000040496285,0.00014106071,0.0003696124,0.000014025524,0.0036103432],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997627,0.000051565352,0.000016362534,0.000064278174,0.000056376473,0.000048744703],"domain_scores_gemma":[0.99959177,0.00019046827,0.00004450614,0.000017211074,0.00013895422,0.000017142307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000562053,0.00045656197,0.00058890565,0.0005174204,0.00029319947,0.0006662034,0.0006719973,0.0006795287,0.0021409602],"category_scores_gemma":[0.001325439,0.00019091126,0.0006266622,0.00037476863,0.0001989857,0.00038357746,0.00034513357,0.000664981,0.00045097736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012448682,0.00013402247,0.00885196,0.00004030283,0.00005157692,0.00012215017,0.00003286342,0.963674,0.0008411892,0.0014689473,0.0011369259,0.023521531],"study_design_scores_gemma":[0.0000024745877,0.000016856555,0.00059854425,0.0000031104541,0.0000060794237,0.000011914075,0.000002484704,0.9988986,0.00009617248,0.00023832559,0.00012279561,0.0000026304695],"about_ca_topic_score_codex":0.012911074,"about_ca_topic_score_gemma":0.0056068427,"teacher_disagreement_score":0.012911074,"about_ca_system_score_codex":0.00068210333,"about_ca_system_score_gemma":0.0008250433,"threshold_uncertainty_score":0.02567184},"labels":[],"label_agreement":null},{"id":"W4292894023","doi":"10.22360/springsim.2016.msm.016","title":"Comparative analysis of classification models in diagnosis of type 2 diabetes","year":2016,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Data mining; Cluster analysis; Machine learning; Artificial intelligence; Support vector machine; Inference; Process (computing); MATLAB; Logistic regression; Fuzzy logic; Data classification","score_opus":0.42728633883247563,"score_gpt":0.5323262584512951,"score_spread":0.10503991961881948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292894023","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8610036,0.005022268,0.12072688,0.0019141001,0.00048921345,0.0002756136,0.0017913622,0.0011467915,0.007630207],"genre_scores_gemma":[0.974115,0.00066891697,0.022880916,0.000095213945,0.00006285071,0.000094359,0.0011718114,0.00003756801,0.0008734428],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99710447,0.0015992108,0.00023806683,0.0003730354,0.00045883947,0.0002264326],"domain_scores_gemma":[0.96994406,0.026222711,0.0006074557,0.0006047927,0.0023380977,0.00028286385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009004505,0.00088059955,0.0011005485,0.0035543072,0.00052760035,0.0016101396,0.00094345654,0.0011614796,0.002115503],"category_scores_gemma":[0.023753364,0.00021173307,0.0015623382,0.0016036121,0.0002687556,0.0011378619,0.00048409382,0.0008328759,0.0003797926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004397129,0.0010032302,0.15051375,0.000608534,0.0012739487,0.0004620718,0.0004523071,0.5865891,0.0013135406,0.0037028142,0.0064064437,0.2432771],"study_design_scores_gemma":[0.000032581276,0.00026658754,0.015049692,0.00004607975,0.00016219175,0.00008113861,0.00016343499,0.98188895,0.0007061069,0.0010983768,0.00048027904,0.00002446577],"about_ca_topic_score_codex":0.017381592,"about_ca_topic_score_gemma":0.007274059,"teacher_disagreement_score":0.017381592,"about_ca_system_score_codex":0.0017069725,"about_ca_system_score_gemma":0.0011337942,"threshold_uncertainty_score":0.047620952},"labels":[],"label_agreement":null},{"id":"W4293420779","doi":"10.3390/a15090308","title":"Early Prediction of Chronic Kidney Disease: A Comprehensive Performance Analysis of Deep Learning Models","year":2022,"lang":"en","type":"article","venue":"Algorithms","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; Lakehead University","funders":"","keywords":"Kidney disease; Computer science; Survivability; Artificial intelligence; Artificial neural network; Predictive modelling; Machine learning; Binary classification; Deep learning; F1 score; Medicine; Internal medicine; Support vector machine","score_opus":0.10569034216189938,"score_gpt":0.38954651189370393,"score_spread":0.28385616973180455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293420779","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88748306,0.010901589,0.089326456,0.0016605279,0.0002952535,0.000107069965,0.003008356,0.0015789507,0.005638697],"genre_scores_gemma":[0.9820238,0.0011535209,0.012118477,0.0001224972,0.00004495534,0.000038491085,0.0031715455,0.000039913477,0.0012867594],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992995,0.00017948986,0.00007557147,0.0001385853,0.00018986368,0.000116938274],"domain_scores_gemma":[0.99842995,0.00078903435,0.00012387418,0.00014048677,0.00044203358,0.00007453998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032019522,0.0012372761,0.0008162537,0.0011636108,0.0003007981,0.0008891574,0.00058257754,0.0008213718,0.000742453],"category_scores_gemma":[0.004572401,0.00021133413,0.0007105918,0.0007263515,0.00019468632,0.0010603676,0.00068430504,0.0008646832,0.00025087228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010376632,0.0006059555,0.10365316,0.000322869,0.00084095297,0.00024692173,0.000087729975,0.62286407,0.0029695604,0.0012052726,0.007766459,0.25839934],"study_design_scores_gemma":[0.000011994385,0.00028755906,0.012745275,0.000057681646,0.00010183159,0.00005949161,0.000039113605,0.9835355,0.0016270422,0.0007703035,0.00074563705,0.000018490482],"about_ca_topic_score_codex":0.015415069,"about_ca_topic_score_gemma":0.014022892,"teacher_disagreement_score":0.015415069,"about_ca_system_score_codex":0.00079756934,"about_ca_system_score_gemma":0.0010729787,"threshold_uncertainty_score":0.030650675},"labels":[],"label_agreement":null},{"id":"W4293758537","doi":"10.5539/ijsp.v11n5p1","title":"Application of Logistic Regression on Heart Disease Data and a ]Review of Some Standardization Methods","year":2022,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Logistic regression; Standardization; Statistics; Regression analysis; Regression; Predictive modelling; Computer science; Mathematics","score_opus":0.2516473758484932,"score_gpt":0.5754958815245017,"score_spread":0.3238485056760085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293758537","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046473052,0.85931104,0.12176317,0.00844784,0.0012840673,0.00017394367,0.0005315189,0.00027139435,0.0035697168],"genre_scores_gemma":[0.047453213,0.857619,0.08741447,0.0023111242,0.002307651,0.00041866576,0.0008346332,0.00015030106,0.0014909209],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9747184,0.01570789,0.0030645435,0.0022749256,0.004003697,0.00023051049],"domain_scores_gemma":[0.95404863,0.032823116,0.0033522795,0.0017334371,0.0078532845,0.00018933769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031521186,0.0011766505,0.0015722121,0.009024116,0.0005299175,0.0023537423,0.0019490126,0.000986944,0.0012267967],"category_scores_gemma":[0.071816996,0.0008479009,0.0025573655,0.0110342875,0.001435159,0.0025321036,0.0014291635,0.0025556632,0.0008106329],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011253516,0.00007933892,0.008544172,0.018083746,0.0011604282,0.0003105252,0.0004947874,0.0034288587,0.00073850347,0.01852962,0.018103905,0.9304136],"study_design_scores_gemma":[0.00010533168,0.00080682355,0.0445429,0.037514128,0.0023349018,0.0041510654,0.0013556979,0.025511611,0.0086657535,0.038099356,0.8363632,0.0005492727],"about_ca_topic_score_codex":0.005623987,"about_ca_topic_score_gemma":0.0037110394,"teacher_disagreement_score":0.031521186,"about_ca_system_score_codex":0.0018726635,"about_ca_system_score_gemma":0.0039379033,"threshold_uncertainty_score":0.16670197},"labels":[],"label_agreement":null},{"id":"W4294276952","doi":"10.18178/ijmlc.2022.12.5.1107","title":"Lifespan Prediction for Lung and Bronchus Cancer Patients via Machine Learning Techniques","year":2022,"lang":"en","type":"article","venue":"International Journal of Machine Learning and Computing","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Saskatchewan","keywords":"Computer science; Lung cancer; Bronchus; Artificial intelligence; Machine learning; Lung; Medicine; Oncology; Internal medicine; Respiratory disease","score_opus":0.032666097733884805,"score_gpt":0.4235129509432974,"score_spread":0.3908468532094126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294276952","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93477625,0.0014736437,0.056050792,0.0007311911,0.000057374997,0.000059575606,0.0043285647,0.00040528877,0.0021173016],"genre_scores_gemma":[0.9843864,0.00033909976,0.012439762,0.00003262243,0.000025444251,0.000037741698,0.0021957818,0.000008982016,0.00053415186],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999877,0.00004039224,0.000014239828,0.000029893581,0.000023298957,0.000015302054],"domain_scores_gemma":[0.9992322,0.00038642398,0.00017175611,0.00003441398,0.00012250438,0.000052740656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051136833,0.0003262886,0.0002638162,0.0010669475,0.00013124337,0.00028826657,0.0002413812,0.00032680418,0.00082355604],"category_scores_gemma":[0.0024841134,0.00009092925,0.00041058447,0.00053474563,0.00006393886,0.0003314151,0.00024069657,0.00040877916,0.0003006496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003921545,0.00025307917,0.52902156,0.00013376083,0.00010857745,0.0002670762,0.000120052784,0.27229553,0.0016229646,0.0009231002,0.0040569534,0.19080518],"study_design_scores_gemma":[0.000008397133,0.00016101383,0.08279313,0.00003336085,0.000032209704,0.00015403189,0.00009172078,0.9128901,0.0011636089,0.0013296012,0.0013262294,0.000016630733],"about_ca_topic_score_codex":0.005057126,"about_ca_topic_score_gemma":0.0062569,"teacher_disagreement_score":0.005057126,"about_ca_system_score_codex":0.0003663373,"about_ca_system_score_gemma":0.0004011635,"threshold_uncertainty_score":0.010055363},"labels":[],"label_agreement":null},{"id":"W4294975841","doi":"10.1109/iri54793.2022.00069","title":"Adding Explainability to Machine Learning Models to Detect Chronic Kidney Disease","year":2022,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Kidney disease; Interpretability; Renal function; Medicine; Intensive care medicine; Disease; Machine learning; Random forest; Renal replacement therapy; Stage (stratigraphy); Computer science; Internal medicine; Artificial intelligence","score_opus":0.19028713375368,"score_gpt":0.4549462510061526,"score_spread":0.2646591172524726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294975841","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21537025,0.0005165618,0.7812221,0.0005698134,0.000040219533,0.00009162741,0.0003547597,0.00077708054,0.0010576401],"genre_scores_gemma":[0.91672456,0.00019515665,0.081884414,0.00007832519,0.00003501583,0.000068847,0.0004560321,0.000029171182,0.00052861037],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999204,0.0003350543,0.00006273883,0.00015399957,0.00018090896,0.000063330655],"domain_scores_gemma":[0.9961112,0.002968204,0.00026651847,0.00020504663,0.0003931787,0.000055915254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020081706,0.0005857481,0.0004650634,0.0012205173,0.0002954181,0.0006889294,0.00055391074,0.00062802935,0.0007424389],"category_scores_gemma":[0.007856654,0.00017063931,0.0008728003,0.000530182,0.00031597327,0.00085008115,0.000586769,0.00085781445,0.00014572675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018688681,0.00020945266,0.058472242,0.00009159468,0.0003387189,0.00024663226,0.0002231052,0.7838022,0.0030948087,0.005408564,0.0009386005,0.14698721],"study_design_scores_gemma":[0.000004549706,0.00004592337,0.003323748,0.000008475669,0.000020696343,0.000030429459,0.000012626784,0.9926642,0.00042364126,0.003234677,0.00022216569,0.000008929018],"about_ca_topic_score_codex":0.006327441,"about_ca_topic_score_gemma":0.005054734,"teacher_disagreement_score":0.006327441,"about_ca_system_score_codex":0.0005567492,"about_ca_system_score_gemma":0.00057710573,"threshold_uncertainty_score":0.012581229},"labels":[],"label_agreement":null},{"id":"W4295978490","doi":"10.3390/jpm12091507","title":"Nomogram-Based Chronic Kidney Disease Prediction Model for Type 1 Diabetes Mellitus Patients Using Routine Pathological Data","year":2022,"lang":"en","type":"article","venue":"Journal of Personalized Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Universiti Kebangsaan Malaysia; Xiamen University Malaysia","keywords":"Medicine; Nomogram; Kidney disease; Logistic regression; Diabetes mellitus; Internal medicine; Receiver operating characteristic","score_opus":0.325855457590151,"score_gpt":0.49346483086470905,"score_spread":0.16760937327455805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295978490","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6598419,0.0014636785,0.32368505,0.0023237453,0.00027072118,0.00070430594,0.005360934,0.0023758463,0.003973877],"genre_scores_gemma":[0.9495467,0.00030573495,0.046271425,0.00012616294,0.000064499276,0.00041258027,0.0021518967,0.000028072396,0.0010928562],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993562,0.00024586957,0.00006417727,0.00015856225,0.00010298771,0.00007221806],"domain_scores_gemma":[0.99766916,0.001325206,0.0002747477,0.000081563376,0.0005399451,0.00010940501],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002798548,0.0008899355,0.0009468063,0.0022960652,0.0004761168,0.001208289,0.0009491538,0.00066048396,0.0014856785],"category_scores_gemma":[0.0050315927,0.0002670677,0.0011028522,0.00084988563,0.00021203634,0.00061321765,0.0005471506,0.00096514873,0.0006269771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00093262584,0.000678305,0.32361016,0.00018238963,0.0005061759,0.0006503449,0.00025834216,0.4858845,0.001426631,0.0013934942,0.009347808,0.17512926],"study_design_scores_gemma":[0.00002971213,0.00013624801,0.014462767,0.000022878816,0.000073126306,0.00010353545,0.000049247315,0.98363286,0.00023934744,0.000537359,0.0006924255,0.00002044768],"about_ca_topic_score_codex":0.012645763,"about_ca_topic_score_gemma":0.009219735,"teacher_disagreement_score":0.012645763,"about_ca_system_score_codex":0.0007447741,"about_ca_system_score_gemma":0.0010535201,"threshold_uncertainty_score":0.025144279},"labels":[],"label_agreement":null},{"id":"W4297847675","doi":"10.1007/978-3-031-14054-9_4","title":"Heart Attack Classification System Using Neural Network Trained with Particle Swarm Optimization","year":2022,"lang":"en","type":"book-chapter","venue":"Advances in intelligent systems and computing","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Fanshawe College","funders":"","keywords":"Particle swarm optimization; Artificial neural network; Computer science; Artificial intelligence; Machine learning; Pattern recognition (psychology)","score_opus":0.17944903669336446,"score_gpt":0.4272754230911961,"score_spread":0.24782638639783164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297847675","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38131478,0.0035072642,0.58386636,0.00073243753,0.0014131728,0.00037335823,0.0008200243,0.0067977672,0.021174802],"genre_scores_gemma":[0.8910671,0.0011665988,0.085818894,0.00025918457,0.00023505634,0.00019554542,0.0011682682,0.00008291285,0.020006415],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999031,0.0000093901135,0.000009299304,0.000034818604,0.000029661664,0.000013771346],"domain_scores_gemma":[0.99989593,0.0000290644,0.00000700746,0.000008278931,0.000053880383,0.0000057997236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021298621,0.00043487336,0.0006196629,0.0004445581,0.0003420814,0.00041536725,0.00042649053,0.00050870195,0.0016459611],"category_scores_gemma":[0.00035260548,0.0001940784,0.0003730413,0.0003052037,0.000094931456,0.0003733136,0.00022265739,0.00039396223,0.00044426348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075062166,0.0005938255,0.010898971,0.00020563936,0.00020013208,0.00046901597,0.00010027166,0.16348799,0.023371637,0.0008457337,0.015394613,0.7836816],"study_design_scores_gemma":[0.000025838921,0.00012253932,0.004878193,0.000009611586,0.00006509038,0.00007573745,0.00001818949,0.9881995,0.005446862,0.00025183056,0.0008910778,0.000015500505],"about_ca_topic_score_codex":0.0094901845,"about_ca_topic_score_gemma":0.007811223,"teacher_disagreement_score":0.0094901845,"about_ca_system_score_codex":0.00032492122,"about_ca_system_score_gemma":0.0003652338,"threshold_uncertainty_score":0.018869877},"labels":[],"label_agreement":null},{"id":"W4297905367","doi":"10.48550/arxiv.1508.02061","title":"Classification of Heart Disease Using K- Nearest Neighbor and Genetic Algorithm","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"k-nearest neighbors algorithm; Classifier (UML); Computer science; Data mining; Artificial intelligence; Genetic algorithm; Statistical classification; Machine learning; Heart disease; Algorithm; Pattern recognition (psychology)","score_opus":0.40029278989156747,"score_gpt":0.36931193132755114,"score_spread":0.030980858564016334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297905367","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1278726,0.0015702192,0.86325306,0.0005506447,0.00019395906,0.00026473164,0.0003377919,0.0009995265,0.004957523],"genre_scores_gemma":[0.47379616,0.0005351925,0.52254933,0.00014724433,0.00007291633,0.00018339705,0.00046564935,0.000038433696,0.002211598],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902093,0.00023259317,0.000107180196,0.00020616439,0.00036216193,0.00007096885],"domain_scores_gemma":[0.99926215,0.00033352626,0.00009316473,0.00005103667,0.00023268015,0.000027524555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090289046,0.0004600177,0.0011498305,0.0022499475,0.00049388455,0.0007801117,0.0010604524,0.0011796925,0.0008826211],"category_scores_gemma":[0.0034797678,0.0002096123,0.0008819095,0.0018233428,0.00039805117,0.000713846,0.00043920986,0.00053674605,0.00036397087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023308948,0.00033825234,0.01798392,0.0001876583,0.00026578893,0.0003009335,0.00018924323,0.3800335,0.004458908,0.00507375,0.0026541643,0.5882808],"study_design_scores_gemma":[0.000024365721,0.00009131105,0.0038455545,0.000029687531,0.00003711766,0.0002518197,0.00007434673,0.9871744,0.0019441319,0.00507015,0.0014271252,0.000030017147],"about_ca_topic_score_codex":0.009429807,"about_ca_topic_score_gemma":0.006436952,"teacher_disagreement_score":0.009429807,"about_ca_system_score_codex":0.00069579855,"about_ca_system_score_gemma":0.0008442807,"threshold_uncertainty_score":0.018749833},"labels":[],"label_agreement":null},{"id":"W4298136738","doi":"10.2196/38007","title":"Peer Review of “Using Structural Equation Modelling in Routine Clinical Data on Diabetes and Depression: Observational Cohort Study”","year":2022,"lang":"en","type":"article","venue":"JMIRx Med","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Observational study; Structural equation modeling; Depression (economics); Diabetes mellitus; Cohort; Cohort study; Medicine; Psychology; Clinical psychology; Econometrics; Statistics; Mathematics; Internal medicine; Endocrinology; Economics","score_opus":0.731915252390463,"score_gpt":0.6095242461772551,"score_spread":0.12239100621320786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298136738","genre_codex":"editorial","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026348464,0.0067269816,0.010982141,0.36787012,0.5752291,0.003323503,0.0042951526,0.0013500837,0.027588041],"genre_scores_gemma":[0.086183704,0.029525848,0.038279697,0.15789096,0.44290784,0.009194433,0.015477018,0.0048866994,0.2156539],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9103449,0.034861755,0.0109210955,0.0042165574,0.03774997,0.0019057174],"domain_scores_gemma":[0.34253877,0.07111387,0.014258927,0.026465256,0.5365178,0.009105327],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07437525,0.0010233715,0.0026848158,0.0056791874,0.0055252076,0.00794773,0.0040907515,0.0057133595,0.089315884],"category_scores_gemma":[0.47864628,0.00078013365,0.0022878556,0.0043226946,0.004058397,0.0050422866,0.0050304253,0.004375578,0.04477596],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006940985,0.000016427273,0.0004097908,0.0012993542,0.000057572644,0.00008678697,0.00018943222,0.000037159924,0.00016158215,0.0008379379,0.96858054,0.028254002],"study_design_scores_gemma":[0.00012840473,0.000052196232,0.0028337329,0.0038763578,0.000093581926,0.00021427697,0.000509847,0.00077567756,0.0005936625,0.0026282533,0.9882216,0.00007241506],"about_ca_topic_score_codex":0.0045732176,"about_ca_topic_score_gemma":0.0065549025,"teacher_disagreement_score":0.9256247,"about_ca_system_score_codex":0.0036430364,"about_ca_system_score_gemma":0.020126417,"threshold_uncertainty_score":0.39333862},"labels":[],"label_agreement":null},{"id":"W4300622140","doi":"10.1609/aaai.v32i1.11398","title":"Model AI Assignments 2018","year":2018,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Session (web analytics); Dissemination; Variety (cybernetics); Computer science; Artificial intelligence; Core (optical fiber); Multimedia; Psychology; World Wide Web; Telecommunications","score_opus":0.38762688905063925,"score_gpt":0.5698241171684207,"score_spread":0.1821972281177815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300622140","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045793787,0.002280388,0.067763485,0.03751396,0.04170938,0.001847656,0.013620734,0.014064365,0.7754063],"genre_scores_gemma":[0.10910636,0.001577705,0.022179773,0.0032947832,0.0052638915,0.0022110343,0.01689345,0.0027450193,0.836728],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99809617,0.00047886634,0.000070059454,0.000265122,0.00074721046,0.00034252647],"domain_scores_gemma":[0.9936606,0.0007845878,0.00021517662,0.0005776337,0.0016782435,0.0030836961],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044510984,0.0010997055,0.00076828856,0.0009803366,0.0024393802,0.0048127277,0.0017625527,0.0016512241,0.19993132],"category_scores_gemma":[0.01085525,0.00040323316,0.000825289,0.0007871752,0.0006524396,0.0027384548,0.004705397,0.0037337437,0.074568294],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027669407,0.00050723087,0.00055404427,0.00012719694,0.000008984111,0.0000713766,0.00038781096,0.00087353424,0.0012321122,0.006317514,0.93619996,0.05344362],"study_design_scores_gemma":[0.000034914745,0.0001223673,0.000906198,0.000050414932,0.000002730554,0.00003919192,0.00024001439,0.0016917288,0.00069060555,0.0049669906,0.99123865,0.000016241447],"about_ca_topic_score_codex":0.0016599827,"about_ca_topic_score_gemma":0.0069835023,"teacher_disagreement_score":0.19993132,"about_ca_system_score_codex":0.0023998318,"about_ca_system_score_gemma":0.0040891725,"threshold_uncertainty_score":0.66883695},"labels":[],"label_agreement":null},{"id":"W4300978803","doi":"10.21203/rs.3.rs-958135/v2","title":"Comparison of State-of-the-Art Neural Network Survival Models with the Pooled Cohort Equations for Cardiovascular Disease Risk Prediction","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"U.S. National Library of Medicine; National Institutes of Health","keywords":"Proportional hazards model; Cohort; Pooling; Artificial neural network; Survival analysis; Nomogram; Computer science; Statistics; Medicine; Artificial intelligence; Internal medicine; Mathematics","score_opus":0.3195555700324022,"score_gpt":0.526479896510951,"score_spread":0.20692432647854875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300978803","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8380618,0.018498184,0.12542775,0.0028144058,0.0012310722,0.00019804094,0.008562785,0.0013608098,0.0038452726],"genre_scores_gemma":[0.95855093,0.0029804287,0.026187051,0.00036380018,0.0003254904,0.00016380934,0.008392138,0.00018332133,0.0028532124],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99707484,0.0018197674,0.00022600777,0.0005091989,0.00024214003,0.0001281267],"domain_scores_gemma":[0.97870195,0.017329898,0.0005111598,0.0014780839,0.0016973665,0.000281575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020033797,0.0014517792,0.0023927472,0.0011200348,0.00047503514,0.0016934654,0.002351995,0.0017418873,0.0027715836],"category_scores_gemma":[0.025295593,0.00056312437,0.0027228117,0.0010332911,0.0003831745,0.0017529298,0.0011876617,0.002726048,0.0008083135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012709946,0.0010236433,0.08316268,0.0009479304,0.009628784,0.00017472885,0.00032068483,0.6543104,0.0008242991,0.0038471154,0.011559765,0.22149001],"study_design_scores_gemma":[0.0002550888,0.0004443383,0.015328151,0.000119447504,0.0010369063,0.00004536198,0.00007130625,0.9791399,0.00037641803,0.0022186667,0.0009085215,0.00005583707],"about_ca_topic_score_codex":0.034022447,"about_ca_topic_score_gemma":0.023308685,"teacher_disagreement_score":0.034022447,"about_ca_system_score_codex":0.0011449674,"about_ca_system_score_gemma":0.0020992104,"threshold_uncertainty_score":0.10595006},"labels":[],"label_agreement":null},{"id":"W4302083818","doi":"10.2196/38488","title":"Peer Review of “Using Structural Equation Modelling in Routine Clinical Data on Diabetes and Depression: Observational Cohort Study”","year":2022,"lang":"en","type":"article","venue":"JMIRx Med","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Structural equation modeling; Observational study; Depression (economics); Diabetes mellitus; Cohort; Medicine; Cohort study; Psychology; Clinical psychology; Econometrics; Statistics; Mathematics; Internal medicine; Endocrinology; Economics","score_opus":0.731915252390463,"score_gpt":0.6095242461772551,"score_spread":0.12239100621320786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302083818","genre_codex":"editorial","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047214916,0.0053138165,0.009662222,0.40168336,0.54153657,0.0024018714,0.007356535,0.001468467,0.025855664],"genre_scores_gemma":[0.10632471,0.021486973,0.035298374,0.18130147,0.34151518,0.0074393065,0.026057847,0.005654628,0.2749215],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.94081956,0.024199272,0.0069099567,0.0036690002,0.022569489,0.0018326876],"domain_scores_gemma":[0.4064592,0.076738946,0.014909567,0.032165263,0.45859823,0.011128812],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06434079,0.00087827677,0.0024501593,0.0040672203,0.0053914185,0.007184469,0.003922259,0.0060103494,0.119168006],"category_scores_gemma":[0.47001028,0.0007458559,0.0021012041,0.0032205733,0.0031363443,0.004736866,0.004996957,0.0046474757,0.048612796],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009295472,0.00002026591,0.0008344558,0.0008654155,0.00006536614,0.00008614428,0.00014641356,0.000031298,0.00017578545,0.0007051234,0.97342175,0.023555003],"study_design_scores_gemma":[0.00026382253,0.00008055293,0.006482592,0.0035554313,0.00015328242,0.00035155594,0.00062023994,0.0012352755,0.0009993917,0.0038454577,0.98231274,0.0000997015],"about_ca_topic_score_codex":0.004459861,"about_ca_topic_score_gemma":0.007089218,"teacher_disagreement_score":0.9356592,"about_ca_system_score_codex":0.0029107996,"about_ca_system_score_gemma":0.016388591,"threshold_uncertainty_score":0.39865673},"labels":[],"label_agreement":null},{"id":"W4303415323","doi":"10.3389/fncom.2022.964686","title":"Heart disease detection based on internet of things data using linear quadratic discriminant analysis and a deep graph convolutional neural network","year":2022,"lang":"en","type":"article","venue":"Frontiers in Computational Neuroscience","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Convolutional neural network; Deep learning; Computer science; Artificial intelligence; Linear discriminant analysis; Machine learning; Heart disease; Medical diagnosis; Artificial neural network; Graph; Pattern recognition (psychology); Medicine; Cardiology; Pathology","score_opus":0.13417359072821405,"score_gpt":0.4182797198974728,"score_spread":0.28410612916925876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4303415323","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6524668,0.0010615864,0.3299965,0.0014121385,0.00031426048,0.00023237496,0.005141652,0.0023814377,0.0069933967],"genre_scores_gemma":[0.9366974,0.0003112234,0.055473812,0.00023555508,0.00007234115,0.00008391808,0.004484724,0.00003145014,0.0026094115],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99980336,0.000028996485,0.0000122856845,0.000066129476,0.00005296815,0.0000363403],"domain_scores_gemma":[0.99977165,0.0000667902,0.00003406287,0.000022953878,0.00007757174,0.000026964484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002586194,0.00053516374,0.00038554153,0.0011170141,0.00020516058,0.0003273926,0.0004160933,0.00042022174,0.0007452914],"category_scores_gemma":[0.0008005225,0.00014675249,0.00047548706,0.00072959164,0.00014950146,0.00036943654,0.0004680295,0.00045151525,0.00037643363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011472824,0.0013244685,0.11717682,0.00030520817,0.00036514533,0.0014121933,0.00021180607,0.16358694,0.034684412,0.0033414534,0.022860836,0.6535835],"study_design_scores_gemma":[0.000015445012,0.00011747038,0.01763515,0.000017688651,0.00003481477,0.00017760637,0.000058907157,0.9743878,0.0044643404,0.0015789099,0.0014949011,0.000017058415],"about_ca_topic_score_codex":0.0074371565,"about_ca_topic_score_gemma":0.013529191,"teacher_disagreement_score":0.0074371565,"about_ca_system_score_codex":0.00041515112,"about_ca_system_score_gemma":0.00037384193,"threshold_uncertainty_score":0.014787734},"labels":[],"label_agreement":null},{"id":"W4304807063","doi":"10.1155/2022/1854718","title":"Alzheimer’s Disease Prediction Algorithm Based on Group Convolution and a Joint Loss Function","year":2022,"lang":"en","type":"article","venue":"Computational and Mathematical Methods in Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; Natural Science Foundation of Anhui Province; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; National Institutes of Health; H. Lundbeck A/S; Servier; National Natural Science Foundation of China; Eisai; Takeda Pharmaceutical Company; IXICO; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Roche; University of Southern California; F. Hoffmann-La Roche; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; AbbVie; Alzheimer's Association; Foundation for the National Institutes of Health; GE Healthcare; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics","keywords":"Convolution (computer science); Function (biology); Joint (building); Algorithm; Computer science; Group (periodic table); Artificial intelligence; Disease; Medicine; Biology; Engineering; Pathology; Artificial neural network; Structural engineering","score_opus":0.26003765347517294,"score_gpt":0.525667227474063,"score_spread":0.2656295739988901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4304807063","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.106232546,0.00047391822,0.8898617,0.00043037275,0.000068312685,0.0000872938,0.000058658286,0.0012362602,0.0015508638],"genre_scores_gemma":[0.7554227,0.00030132657,0.23913276,0.00024528475,0.00008315729,0.00016734435,0.00023864495,0.00006732048,0.0043414333],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996075,0.000073010044,0.000029512625,0.000108394226,0.00011516354,0.00006644585],"domain_scores_gemma":[0.9993907,0.00021767538,0.00006839942,0.00006882362,0.00020267529,0.000051785828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014962637,0.00076105056,0.0009788298,0.0007948993,0.00046920945,0.0005470281,0.0011106277,0.0011342339,0.0008822654],"category_scores_gemma":[0.002225314,0.0003081071,0.0007464261,0.00046834504,0.00045515274,0.0012059893,0.00092140597,0.00093944254,0.00030397795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003917307,0.00030189907,0.007450979,0.00004858354,0.00015367218,0.00024481778,0.000112439164,0.4387294,0.011041943,0.004557553,0.0032951077,0.5336719],"study_design_scores_gemma":[0.000009158545,0.000040640785,0.00042042116,0.0000023098314,0.000011727261,0.00004522109,0.0000036001843,0.9970246,0.001410069,0.0008472699,0.00018085212,0.000004100927],"about_ca_topic_score_codex":0.006968377,"about_ca_topic_score_gemma":0.0054275068,"teacher_disagreement_score":0.006968377,"about_ca_system_score_codex":0.00075414905,"about_ca_system_score_gemma":0.0012739095,"threshold_uncertainty_score":0.013855636},"labels":[],"label_agreement":null},{"id":"W4306248396","doi":"10.54691/bcpbm.v29i.2296","title":"Research on the development model of commercial health insurance based on big data","year":2022,"lang":"en","type":"article","venue":"BCP Business & Management","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Business; Big data; Health care; Product (mathematics); New product development; Marketing; Computer science; Economic growth; Economics","score_opus":0.7583965242362534,"score_gpt":0.5660187914479781,"score_spread":0.1923777327882753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306248396","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21307236,0.003968698,0.66449726,0.011634411,0.00025607436,0.00055927085,0.0013744948,0.0004928509,0.10414448],"genre_scores_gemma":[0.91101867,0.0026672324,0.071053,0.00028643064,0.00008062498,0.0003227359,0.0010930992,0.0000706754,0.013407596],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983908,0.00047106895,0.00009570228,0.00037090553,0.00043924476,0.00023225433],"domain_scores_gemma":[0.9973385,0.0014002257,0.00028799442,0.00015033773,0.00056200824,0.00026094666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021274025,0.0005603699,0.00045969483,0.0015623063,0.0011956568,0.003344253,0.001506888,0.0010710398,0.0053374004],"category_scores_gemma":[0.0058653885,0.00047814316,0.0013569697,0.0017470298,0.0011294564,0.0066039274,0.0015742367,0.0013248774,0.00049555226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001285884,0.00021120849,0.025442595,0.00044604405,0.000111082954,0.0013126441,0.0016444285,0.25336498,0.0019746413,0.64195174,0.008007704,0.06540431],"study_design_scores_gemma":[0.00001868994,0.00005545161,0.0022124122,0.000059962458,0.000053717307,0.0002274214,0.0006053338,0.8992441,0.00070816535,0.08609232,0.010693482,0.000028909692],"about_ca_topic_score_codex":0.018742181,"about_ca_topic_score_gemma":0.010656487,"teacher_disagreement_score":0.018742181,"about_ca_system_score_codex":0.003424484,"about_ca_system_score_gemma":0.0037067756,"threshold_uncertainty_score":0.037266135},"labels":[],"label_agreement":null},{"id":"W4307831606","doi":"10.1016/j.jacasi.2022.07.007","title":"Machine Learning Risk Prediction for Incident Heart Failure in Patients With Atrial Fibrillation","year":2022,"lang":"en","type":"article","venue":"JACC Asia","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital","funders":"Astellas Pharma; Bayer HealthCare; Pfizer; Japan Agency for Medical Research and Development; Boehringer Ingelheim; AstraZeneca; Bristol-Myers Squibb","keywords":"Medicine; Atrial fibrillation; Internal medicine; Framingham Risk Score; Cardiology; Ejection fraction; Heart failure; Receiver operating characteristic; Cohort; Framingham Heart Study; Prospective cohort study; Incidence (geometry); Creatinine; Mathematics; Disease","score_opus":0.04367930242130334,"score_gpt":0.3824877125436772,"score_spread":0.33880841012237384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307831606","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98150086,0.0004138965,0.01658674,0.00039751368,0.000046867823,0.000037259746,0.00042583552,0.00011859646,0.00047236154],"genre_scores_gemma":[0.99583876,0.00009216828,0.0033176693,0.000040074487,0.0000340417,0.000026216929,0.000550081,0.0000055405067,0.00009540059],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886334,0.0006345556,0.00009349043,0.00016757094,0.00014511101,0.000095895615],"domain_scores_gemma":[0.9936386,0.004518591,0.000705214,0.0003671867,0.0005665524,0.00020386968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039819675,0.0005087434,0.00062671,0.0010059639,0.00023795474,0.00070603675,0.00046844347,0.00055101194,0.000532861],"category_scores_gemma":[0.016163342,0.0001692769,0.0007543209,0.0005031305,0.00018752777,0.00049803837,0.00047135158,0.0008958892,0.00024738826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033280154,0.0001969754,0.9481336,0.000016948752,0.0002065393,0.00006975713,0.000053689982,0.029006574,0.00018756292,0.00012624795,0.0007132867,0.020956084],"study_design_scores_gemma":[0.00007847032,0.00035410892,0.2962972,0.00003849216,0.00016678791,0.00023702969,0.000085196596,0.70019364,0.00044095734,0.0016674879,0.00041035123,0.00003033268],"about_ca_topic_score_codex":0.003002687,"about_ca_topic_score_gemma":0.002256519,"teacher_disagreement_score":0.0039819675,"about_ca_system_score_codex":0.00029943787,"about_ca_system_score_gemma":0.00062074105,"threshold_uncertainty_score":0.021058857},"labels":[],"label_agreement":null},{"id":"W4307986809","doi":"10.18178/ijmlc.2022.12.6.1113","title":"A Machine Learning Ensemble Classifier for Cardiovascular Disease Taxonomy","year":2022,"lang":"en","type":"article","venue":"International Journal of Machine Learning and Computing","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Classifier (UML); Artificial intelligence; Machine learning; Ensemble learning; Taxonomy (biology)","score_opus":0.102513752845773,"score_gpt":0.4074249393713262,"score_spread":0.30491118652555316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307986809","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0887338,0.004099015,0.8937342,0.0005828725,0.00089961186,0.00041015798,0.0029241054,0.0033017618,0.0053144945],"genre_scores_gemma":[0.54474586,0.0017468,0.4362214,0.0003540446,0.0006736788,0.00061837904,0.009327797,0.00013480271,0.0061771977],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984182,0.00024933458,0.00016464866,0.00035030243,0.000644515,0.00017301747],"domain_scores_gemma":[0.9983558,0.00043968303,0.00008869987,0.00019679224,0.0008386573,0.0000803427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020899354,0.0008286625,0.0019275877,0.0031581977,0.00074913085,0.0010129373,0.001300083,0.0013400338,0.0016954425],"category_scores_gemma":[0.004387976,0.00021257438,0.0014402069,0.001973452,0.00012714362,0.0010683134,0.0008550794,0.0013497331,0.0015064878],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027255886,0.00031722846,0.01758275,0.00012693393,0.0003072843,0.0002627214,0.00008439494,0.0367063,0.0055826274,0.0016916431,0.013908815,0.92315686],"study_design_scores_gemma":[0.000041036816,0.000370927,0.012305158,0.00009695038,0.00028874673,0.0005899045,0.00009641284,0.9581176,0.0068682125,0.005053086,0.01610093,0.000070908776],"about_ca_topic_score_codex":0.0041017113,"about_ca_topic_score_gemma":0.004231272,"teacher_disagreement_score":0.0041017113,"about_ca_system_score_codex":0.0005066946,"about_ca_system_score_gemma":0.0010371716,"threshold_uncertainty_score":0.011052728},"labels":[],"label_agreement":null},{"id":"W4308013166","doi":"10.2196/43520","title":"Correction: Web-Based Software Tools for Systematic Literature Review in Medicine: Systematic Search and Feature Analysis","year":2022,"lang":"en","type":"erratum","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Systematic review; Information retrieval; Feature (linguistics); Software; Data science; World Wide Web; MEDLINE; Data mining; Programming language","score_opus":0.08541249724198514,"score_gpt":0.46976611827662307,"score_spread":0.38435362103463794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308013166","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011655516,0.0017267414,0.002064223,0.097968765,0.8895238,0.00030025648,0.0051059765,0.0015854812,0.0016082356],"genre_scores_gemma":[0.012201104,0.015431691,0.028060405,0.33697817,0.47251728,0.0051796134,0.010532702,0.0074096597,0.1116894],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.92574316,0.019158686,0.021178357,0.0055217627,0.025324801,0.003073309],"domain_scores_gemma":[0.6221346,0.13202848,0.027368035,0.018490365,0.1919911,0.007987452],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05180952,0.005901511,0.0067477217,0.017524328,0.0071801576,0.013024376,0.009089267,0.015786687,0.091018066],"category_scores_gemma":[0.46973068,0.004483968,0.0060200226,0.014968464,0.0065315594,0.006617913,0.0072674924,0.019393686,0.04298931],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063949185,0.0000073321694,0.0000660545,0.0013337632,0.000073560914,0.000178247,0.00007862546,0.000041885454,0.000041165313,0.00057422655,0.99411917,0.0034220882],"study_design_scores_gemma":[0.0005425414,0.000066897584,0.0011187933,0.009535779,0.0005990782,0.00080318726,0.00025208172,0.00073790626,0.00041182365,0.004083489,0.98161453,0.00023387415],"about_ca_topic_score_codex":0.03883807,"about_ca_topic_score_gemma":0.049981922,"teacher_disagreement_score":0.94819045,"about_ca_system_score_codex":0.013735342,"about_ca_system_score_gemma":0.03786299,"threshold_uncertainty_score":0.30448574},"labels":[],"label_agreement":null},{"id":"W4308092048","doi":"10.1109/ccece49351.2022.9918215","title":"Early Detection of Heart Disease Using Advances of Machine Learning for Large-Scale Patient Datasets","year":2022,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Machine learning; Support vector machine; Artificial intelligence; Computer science; Random forest; Naive Bayes classifier; Decision tree; Heart disease; Multilayer perceptron; Ensemble learning; Artificial neural network; Data mining; Medicine","score_opus":0.10149531284065338,"score_gpt":0.45668670821502244,"score_spread":0.35519139537436906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308092048","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7063057,0.009979493,0.24358648,0.005052417,0.0010767229,0.0006699799,0.022990756,0.005145446,0.005193132],"genre_scores_gemma":[0.8437971,0.0013278581,0.13314518,0.00035246531,0.00040766268,0.00023874732,0.019744458,0.000052504784,0.00093401986],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984534,0.00053564,0.00021063442,0.0003191134,0.0003555495,0.00012564693],"domain_scores_gemma":[0.9951362,0.0028079918,0.0004534839,0.00066306314,0.000739965,0.00019924568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027934588,0.0011523245,0.0014342341,0.003572038,0.00050971616,0.0011605881,0.001035991,0.001239414,0.0008363788],"category_scores_gemma":[0.009413052,0.0002633106,0.0011808448,0.0019437557,0.00024012534,0.0015012238,0.0009785099,0.0014429903,0.00063901907],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009234019,0.002108369,0.3225788,0.00063153065,0.001052524,0.0012782344,0.00025381157,0.10820294,0.011735255,0.0016192944,0.023939908,0.52567595],"study_design_scores_gemma":[0.00006121924,0.0003396944,0.08621381,0.00009280159,0.00014319662,0.00071496714,0.0002272877,0.89586765,0.0069451877,0.003203159,0.0061228788,0.00006816921],"about_ca_topic_score_codex":0.0045664734,"about_ca_topic_score_gemma":0.0074607106,"teacher_disagreement_score":0.0045664734,"about_ca_system_score_codex":0.00053235743,"about_ca_system_score_gemma":0.0006180563,"threshold_uncertainty_score":0.014773428},"labels":[],"label_agreement":null},{"id":"W4308473704","doi":"10.51817/bjp.v6i1.386","title":"Evaluasi Kesesuaian Penyimpanan Obat Di Salah Satu Apotek Kota Cimahi","year":2022,"lang":"id","type":"article","venue":"Borneo Journal of Pharmascientech","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Encana (Canada)","funders":"","keywords":"Traditional medicine; Physics; Food science; Chemistry; Medicine","score_opus":0.1439133610346294,"score_gpt":0.4708584499536657,"score_spread":0.3269450889190363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308473704","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6616885,0.018822184,0.048331544,0.014218296,0.0015803409,0.0145450095,0.01658936,0.0016200155,0.22260472],"genre_scores_gemma":[0.78981674,0.014775794,0.08177259,0.0034231576,0.00031678707,0.011824692,0.0069284216,0.0004123542,0.09072955],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99179244,0.0031835006,0.00096063875,0.0007193823,0.0027899586,0.0005541008],"domain_scores_gemma":[0.98233277,0.005632552,0.0026590868,0.0008604816,0.007281057,0.0012341767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010012927,0.0008604758,0.00089267385,0.0018619443,0.0016124378,0.0029394915,0.0010976306,0.00085650804,0.027745195],"category_scores_gemma":[0.0203012,0.00035955972,0.0012852155,0.0013430222,0.0010570241,0.002173937,0.002465064,0.001657134,0.0045760814],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021425479,0.0012110517,0.1778783,0.015099503,0.0005050668,0.00083092955,0.027961615,0.0009827208,0.014227037,0.0065096966,0.056838345,0.6958132],"study_design_scores_gemma":[0.00028916082,0.0037370513,0.39931598,0.008695959,0.0010019077,0.0010835591,0.05325279,0.0020628022,0.01699781,0.007910998,0.5052818,0.00037018373],"about_ca_topic_score_codex":0.0047923215,"about_ca_topic_score_gemma":0.012605972,"teacher_disagreement_score":0.027745195,"about_ca_system_score_codex":0.0023408728,"about_ca_system_score_gemma":0.006798481,"threshold_uncertainty_score":0.09281689},"labels":[],"label_agreement":null},{"id":"W4309091908","doi":"10.3390/app122111127","title":"An Interpretable Machine Learning Approach for Hepatitis B Diagnosis","year":2022,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Interpretability; Machine learning; Artificial intelligence; AdaBoost; Decision tree; Gradient boosting; Logistic regression; Random forest; Boosting (machine learning); Computer science; Support vector machine; Medicine","score_opus":0.1484017627015627,"score_gpt":0.45453613661608566,"score_spread":0.306134373914523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309091908","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02984439,0.00047559358,0.96045035,0.0028027275,0.00012692361,0.00009591851,0.00012638516,0.00036095676,0.005716724],"genre_scores_gemma":[0.7245859,0.00041271932,0.27185258,0.00040960318,0.00011529549,0.000126099,0.0001735587,0.000032162745,0.0022920065],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911314,0.00054219156,0.000037238115,0.00008595365,0.00018138156,0.000040039195],"domain_scores_gemma":[0.99834764,0.001078607,0.00017316453,0.000111835194,0.00022993995,0.00005888582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001822764,0.00061253796,0.00034500626,0.001125214,0.0003903022,0.0011495951,0.00082486286,0.00093751744,0.0022425277],"category_scores_gemma":[0.006186249,0.00017889096,0.0006364814,0.00043782537,0.0007316376,0.0011653306,0.0009666225,0.0012870046,0.0001933678],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001672263,0.00022664266,0.005846694,0.00022702827,0.00013026722,0.00076721347,0.00079351594,0.38394532,0.004368169,0.39459282,0.0042862957,0.20464891],"study_design_scores_gemma":[0.000017372675,0.00006056747,0.0006225201,0.00003146652,0.000018531286,0.000093362745,0.000090186586,0.8385882,0.0007911116,0.15655403,0.0031190666,0.000013657182],"about_ca_topic_score_codex":0.0015207372,"about_ca_topic_score_gemma":0.001474744,"teacher_disagreement_score":0.0022425277,"about_ca_system_score_codex":0.00089239574,"about_ca_system_score_gemma":0.0008889896,"threshold_uncertainty_score":0.009639859},"labels":[],"label_agreement":null},{"id":"W4310753593","doi":"10.1016/j.annonc.2022.10.442","title":"411P Cost-effective analysis of the various cancer screening methods in the community: Pooled analysis of camps of 5 years from 2017-to 2022","year":2022,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Continental (Canada)","funders":"","keywords":"Medicine; Cancer; Cost analysis; Oncology; Internal medicine; Operations research","score_opus":0.43668439189272,"score_gpt":0.6330045482453318,"score_spread":0.1963201563526118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310753593","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8802224,0.04779036,0.004845844,0.0013664837,0.0009554963,0.0008638836,0.059383225,0.00020655841,0.0043658623],"genre_scores_gemma":[0.97805446,0.003921382,0.0011717333,0.0005750296,0.00030176912,0.00048305446,0.0139312865,0.00005057595,0.0015106802],"study_design_codex":"meta_analysis","study_design_gemma":"observational","domain_scores_codex":[0.9877686,0.006282585,0.0015634379,0.0017567723,0.0015104902,0.0011181413],"domain_scores_gemma":[0.98854536,0.0050368537,0.003299712,0.0013201685,0.001326509,0.000471261],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0083485,0.001528395,0.0039514867,0.004146771,0.0005247271,0.0020238564,0.0014436857,0.0018898273,0.0039804075],"category_scores_gemma":[0.02338622,0.0012067076,0.028326586,0.0058194217,0.0005826026,0.0016901933,0.0029516628,0.0023178835,0.0004122289],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.075348176,0.00059668615,0.3923097,0.0078074,0.46963188,0.00038178865,0.00028717765,0.006445821,0.00063980295,0.0006422063,0.009710377,0.036198903],"study_design_scores_gemma":[0.007089965,0.0051650936,0.68414474,0.0016994217,0.28446802,0.0003694932,0.0009345603,0.0063056024,0.00068652135,0.0011793248,0.0077474,0.00020986216],"about_ca_topic_score_codex":0.058406845,"about_ca_topic_score_gemma":0.055931862,"teacher_disagreement_score":0.058406845,"about_ca_system_score_codex":0.00219679,"about_ca_system_score_gemma":0.002565507,"threshold_uncertainty_score":0.11613375},"labels":[],"label_agreement":null},{"id":"W4310937535","doi":"10.2196/40404","title":"Predicting Overweight and Obesity Status Among Malaysian Working Adults With Machine Learning or Logistic Regression: Retrospective Comparison Study","year":2022,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institutes of Biomedical Innovation, Health and Nutrition","keywords":"Overweight; Obesity; Logistic regression; Medicine; Demography; Receiver operating characteristic; Gerontology; Environmental health; Internal medicine","score_opus":0.21497791153791818,"score_gpt":0.5245115356019913,"score_spread":0.3095336240640731,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310937535","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99908257,0.0002091535,0.00029755128,0.000013699619,0.0000069908842,0.00003884845,0.0002224095,0.0000029233058,0.00012572035],"genre_scores_gemma":[0.99869776,0.00017376598,0.00039830545,0.000021849735,0.000015342408,0.00006466316,0.00047784485,0.0000030718575,0.00014737625],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99878126,0.00044515455,0.00018316305,0.0003130774,0.00015328033,0.00012415991],"domain_scores_gemma":[0.997398,0.00068027974,0.00087966805,0.0004003134,0.0003849048,0.00025686223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002890077,0.0006545715,0.0005677544,0.00094209344,0.00038677786,0.0006463933,0.0005370854,0.0005421671,0.0011683734],"category_scores_gemma":[0.004184421,0.00046320562,0.0010646184,0.0009024755,0.0003876108,0.000814754,0.000644914,0.0007133931,0.00040087182],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009792828,0.00024864444,0.99617696,0.000029040508,0.000236475,0.000040111692,0.00009283068,0.0000719459,0.00009563999,0.000018254079,0.000061628685,0.0019491356],"study_design_scores_gemma":[0.00014045463,0.0026082178,0.9930118,0.000037907223,0.00041854763,0.00042354775,0.00067407393,0.0019450763,0.00020729343,0.00005658522,0.00045717755,0.000019428164],"about_ca_topic_score_codex":0.0023940783,"about_ca_topic_score_gemma":0.0022352268,"teacher_disagreement_score":0.002890077,"about_ca_system_score_codex":0.00042483682,"about_ca_system_score_gemma":0.00043719416,"threshold_uncertainty_score":0.015284359},"labels":[],"label_agreement":null},{"id":"W4311435446","doi":"10.36227/techrxiv.21699764.v1","title":"Developing a Social Platform using MERN Stack","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"Ministère de l'Énergie et des Ressources Naturelles; Lakehead University","keywords":"World Wide Web; Variety (cybernetics); Social media; Computer science; Key (lock); Stack (abstract data type); The Internet; Digital content; Multimedia; Artificial intelligence","score_opus":0.6753057540520693,"score_gpt":0.6071993411615622,"score_spread":0.06810641289050712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311435446","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061286833,0.000682925,0.6516774,0.0020718726,0.00095947844,0.001696472,0.0015007487,0.17040001,0.10972428],"genre_scores_gemma":[0.2230171,0.00079064665,0.60393983,0.0016162904,0.00018480711,0.0008811948,0.0065394407,0.021671457,0.14135927],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99857223,0.000206788,0.00010949339,0.00024289577,0.0006696699,0.0001988274],"domain_scores_gemma":[0.9990243,0.00018445938,0.00005843054,0.00026168878,0.00028114518,0.00018989052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002387517,0.0006527587,0.0005076816,0.0008790285,0.0010293351,0.003137015,0.0014015684,0.0011580223,0.009290992],"category_scores_gemma":[0.0029504688,0.0006894965,0.001114949,0.0003799251,0.0005668171,0.0045836614,0.004135592,0.0015416009,0.0064121154],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012728337,0.001479645,0.009783406,0.0015044274,0.0003002079,0.002668983,0.0050505716,0.011530005,0.11176736,0.13526991,0.12666164,0.59271103],"study_design_scores_gemma":[0.00015992511,0.0002846203,0.002364043,0.00030243388,0.000116058414,0.000945784,0.00069274195,0.07344824,0.049096525,0.021128627,0.85122275,0.00023821593],"about_ca_topic_score_codex":0.0026934145,"about_ca_topic_score_gemma":0.004012391,"teacher_disagreement_score":0.009290992,"about_ca_system_score_codex":0.0008546533,"about_ca_system_score_gemma":0.001874072,"threshold_uncertainty_score":0.031081498},"labels":[],"label_agreement":null},{"id":"W4311435706","doi":"10.36227/techrxiv.21699764","title":"Developing a Social Platform using MERN Stack","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"Ministère de l'Énergie et des Ressources Naturelles; Lakehead University","keywords":"World Wide Web; Variety (cybernetics); Social media; Computer science; Stack (abstract data type); Key (lock); The Internet; Digital content; Multimedia; Artificial intelligence","score_opus":0.6753057540520693,"score_gpt":0.6071993411615622,"score_spread":0.06810641289050712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311435706","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06164284,0.0006301965,0.6581934,0.0029082047,0.0010089703,0.0017872883,0.0014272789,0.13759321,0.13480857],"genre_scores_gemma":[0.19288778,0.0006016888,0.6396219,0.0013651265,0.00015029057,0.00073387224,0.004776404,0.013457677,0.14640537],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99862635,0.00021600295,0.000092484835,0.00023874921,0.0006441337,0.00018228086],"domain_scores_gemma":[0.99907196,0.00016301942,0.000048741877,0.0002616581,0.00026020658,0.00019442108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023216167,0.00059309223,0.00047120696,0.0008990441,0.0012041877,0.0033194497,0.0013903646,0.0010911869,0.010673436],"category_scores_gemma":[0.0027380616,0.00069213,0.0010314028,0.00040819566,0.00062119623,0.0046946653,0.0041365465,0.0013602,0.0066867582],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00086523604,0.0012610505,0.007887943,0.0010048526,0.00021062697,0.0020470978,0.004235763,0.012091668,0.08681869,0.15161167,0.12578641,0.60617894],"study_design_scores_gemma":[0.00014811974,0.0002585031,0.0019224917,0.0002340326,0.00008635727,0.00070712983,0.00077720586,0.08718777,0.03820504,0.022768367,0.84750336,0.0002015566],"about_ca_topic_score_codex":0.0037472483,"about_ca_topic_score_gemma":0.0065223975,"teacher_disagreement_score":0.010673436,"about_ca_system_score_codex":0.0010349745,"about_ca_system_score_gemma":0.0019997035,"threshold_uncertainty_score":0.035706222},"labels":[],"label_agreement":null},{"id":"W4312710248","doi":"10.1007/978-3-031-21385-4_19","title":"ML_SPS: Stroke Prediction System Employing Machine Learning Approach","year":2022,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Random forest; Gradient boosting; Decision tree; Stroke (engine); Machine learning; Computer science; Artificial intelligence; Boosting (machine learning); Ensemble learning; Engineering","score_opus":0.19156478492683154,"score_gpt":0.4246137521139707,"score_spread":0.23304896718713913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312710248","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16534138,0.004455521,0.3984115,0.0019707717,0.0014834083,0.0011328702,0.08688508,0.29282412,0.04749531],"genre_scores_gemma":[0.53858525,0.0035809858,0.23401631,0.0016931543,0.00096359465,0.0010942032,0.123760246,0.00156358,0.09474275],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999249,0.000005684794,0.0000073757283,0.000023186758,0.000029926847,0.000008966913],"domain_scores_gemma":[0.9998989,0.000019766798,0.000007705274,0.000011497524,0.000048079546,0.000014051343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017396745,0.0006035857,0.00063527,0.0008976801,0.00023948128,0.00049495365,0.0007975598,0.00046082726,0.009071405],"category_scores_gemma":[0.0003201023,0.00019410373,0.00036751368,0.0005131104,0.000076057135,0.0005092572,0.00038533265,0.00038363007,0.0070197983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010786471,0.00033457356,0.015916785,0.0003091288,0.00010929211,0.00048820017,0.00004813958,0.010423556,0.011808284,0.0007438308,0.23771106,0.72102857],"study_design_scores_gemma":[0.0004846896,0.0010755073,0.058052894,0.00018077574,0.0004882789,0.003046669,0.00014589033,0.6855732,0.0977642,0.005765888,0.1471657,0.0002562646],"about_ca_topic_score_codex":0.0046935,"about_ca_topic_score_gemma":0.0047619543,"teacher_disagreement_score":0.009071405,"about_ca_system_score_codex":0.0002615489,"about_ca_system_score_gemma":0.00048174293,"threshold_uncertainty_score":0.03034687},"labels":[],"label_agreement":null},{"id":"W4315783472","doi":"10.1109/icet56601.2022.10004621","title":"DocOnTap: AI-based disease diagnostic system and recommendation system","year":2022,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Random forest; Medical diagnosis; Schedule; Computer science; Artificial intelligence; Machine learning; Decision tree; Logistic regression; Classifier (UML); Work schedule; Work (physics); Medicine; Engineering","score_opus":0.10470298475972306,"score_gpt":0.44961471673145986,"score_spread":0.3449117319717368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315783472","genre_codex":"software","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059173595,0.011066496,0.24082534,0.004700384,0.0019129645,0.0033501128,0.23559646,0.40437606,0.038998682],"genre_scores_gemma":[0.32398468,0.005439096,0.33452243,0.0044758446,0.0007052618,0.0022319192,0.2846709,0.0012039837,0.042765953],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994301,0.000056091383,0.00009786701,0.00017685347,0.00018756244,0.000051565312],"domain_scores_gemma":[0.99904543,0.00019458953,0.00006289565,0.00013523322,0.0004495603,0.0001122854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007029025,0.0011270124,0.0011392371,0.004069073,0.00073533494,0.0010468409,0.0016991744,0.0012333638,0.014063568],"category_scores_gemma":[0.001807899,0.00034673756,0.0008991671,0.0026834232,0.00014951071,0.0009157613,0.0006521039,0.0007095156,0.009757256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016069327,0.00058878714,0.016350143,0.001530932,0.00040566007,0.0010157038,0.00012049489,0.0039136303,0.01230318,0.0014429386,0.4438801,0.5168415],"study_design_scores_gemma":[0.0015317661,0.0012938934,0.056791816,0.00057065114,0.0012731698,0.0050093965,0.0003494597,0.41799772,0.074047886,0.008498727,0.4319911,0.00064438704],"about_ca_topic_score_codex":0.030002309,"about_ca_topic_score_gemma":0.029508898,"teacher_disagreement_score":0.030002309,"about_ca_system_score_codex":0.0010657198,"about_ca_system_score_gemma":0.0014064534,"threshold_uncertainty_score":0.05965531},"labels":[],"label_agreement":null},{"id":"W4316659579","doi":"10.1109/icaiss55157.2022.10010820","title":"Analysis of Artificial Intelligence in Medical Sectors","year":2022,"lang":"en","type":"article","venue":"2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Decision tree; Compiler; Data science; Data mining; Artificial intelligence","score_opus":0.12255589851978906,"score_gpt":0.43932983834462674,"score_spread":0.3167739398248377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4316659579","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15121658,0.106125586,0.3379996,0.03516064,0.001113931,0.00054554205,0.0014973836,0.0006754059,0.36566532],"genre_scores_gemma":[0.88692635,0.025899483,0.07110817,0.0014255262,0.00081538124,0.00028929714,0.00058402686,0.000059199952,0.012892541],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964903,0.0013570106,0.00022616195,0.0002856287,0.0014588396,0.00018202892],"domain_scores_gemma":[0.9947797,0.0033745966,0.00046409864,0.00030993955,0.0009452315,0.00012632045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024103904,0.00041511093,0.00043367615,0.0049374932,0.000783126,0.00487592,0.0005646338,0.0008342373,0.0037787273],"category_scores_gemma":[0.009115136,0.00018083573,0.0006249364,0.00532149,0.001622566,0.0027334797,0.001035551,0.0010942395,0.0008112925],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000815171,0.00016347924,0.019976107,0.0009894972,0.00018673512,0.0005216624,0.0011076856,0.012450369,0.0015253739,0.6738757,0.009205237,0.2799166],"study_design_scores_gemma":[0.0000161638,0.00010529553,0.0317261,0.00090699637,0.00010735212,0.0005815113,0.002402791,0.08185202,0.0024306716,0.76555717,0.11426024,0.00005364298],"about_ca_topic_score_codex":0.0019857169,"about_ca_topic_score_gemma":0.0009838743,"teacher_disagreement_score":0.0049374932,"about_ca_system_score_codex":0.0026254684,"about_ca_system_score_gemma":0.0020496412,"threshold_uncertainty_score":0.019049168},"labels":[],"label_agreement":null},{"id":"W4317039752","doi":"10.18280/ria.360617","title":"A Framework for Blended Sub Feature Engineering for Chronic Disease Prediction Using in-Memory Computing","year":2022,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Feature (linguistics); Computer science; Feature engineering; Computer architecture; Artificial intelligence; Software engineering; Data science; Deep learning","score_opus":0.13468711782860024,"score_gpt":0.4278457065300817,"score_spread":0.2931585887014815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317039752","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055386536,0.00016164845,0.9928519,0.00015835145,0.000028476077,0.000035294088,0.00010982019,0.00056957675,0.0005462729],"genre_scores_gemma":[0.3656719,0.00045353928,0.6301925,0.00019786236,0.0000907432,0.00037045512,0.00054386293,0.000092538074,0.0023865995],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996667,0.00008738426,0.000032740292,0.00007738391,0.000087532135,0.00004815418],"domain_scores_gemma":[0.99956757,0.00016453523,0.000043996548,0.000062785846,0.00012462758,0.000036513782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000803012,0.00068460446,0.00087778695,0.0008272144,0.00044631684,0.0010766895,0.0016685146,0.00069468305,0.0018835156],"category_scores_gemma":[0.0020342362,0.0002630083,0.0010460753,0.000978922,0.00044090438,0.001285008,0.0011210329,0.0010078489,0.0005258732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018889562,0.00026540112,0.004667433,0.00010838666,0.0001668754,0.00024010746,0.00016794364,0.6628895,0.0031683415,0.042080335,0.0039863,0.28207055],"study_design_scores_gemma":[0.000006056873,0.000020436179,0.00017991634,0.000005434614,0.000009791051,0.000017488444,0.000008777478,0.99001443,0.00032863324,0.008568709,0.00083567237,0.000004605423],"about_ca_topic_score_codex":0.010294061,"about_ca_topic_score_gemma":0.01056831,"teacher_disagreement_score":0.010294061,"about_ca_system_score_codex":0.0006153223,"about_ca_system_score_gemma":0.0009954371,"threshold_uncertainty_score":0.020468235},"labels":[],"label_agreement":null},{"id":"W4317039786","doi":"10.18280/ria.360602","title":"A Novel Ensemble Deep Learning Model for Coronary Heart Disease Prediction","year":2022,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Framingham Risk Score; Ensemble learning; Framingham Heart Study; Coronary heart disease; Recall; Artificial intelligence; Blood pressure; Machine learning; Deep learning; F1 score; Disease; Heart disease; Computer science; Medicine; Internal medicine; Ensemble forecasting; Cardiology; Psychology","score_opus":0.18310771816840987,"score_gpt":0.41893047306603926,"score_spread":0.23582275489762938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317039786","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24186248,0.0067775967,0.7371083,0.0016813567,0.00053109584,0.00009400974,0.0020139872,0.002748253,0.007182903],"genre_scores_gemma":[0.9389654,0.0012467754,0.050154343,0.0005556546,0.00014588943,0.000108509324,0.0019822163,0.00004492573,0.006796411],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99976283,0.000037176927,0.000014873557,0.000073520445,0.000057945206,0.000053675973],"domain_scores_gemma":[0.9996786,0.000100635705,0.00002791617,0.000022576782,0.00014592752,0.000024329976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007280011,0.000704511,0.001028667,0.00070660055,0.00027824708,0.00051715365,0.0012162953,0.0009127202,0.0012392363],"category_scores_gemma":[0.0010708424,0.0003158215,0.00069892337,0.0006880974,0.0001498447,0.0007416578,0.0006030253,0.0011196374,0.00042261867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030112074,0.000369818,0.01461359,0.00006272476,0.00027471402,0.00021894595,0.0000683256,0.65803736,0.0028415122,0.0019290621,0.011001748,0.31028113],"study_design_scores_gemma":[0.0000044495573,0.000021917052,0.0004678524,0.0000056381828,0.000016290416,0.000018396368,0.000002336553,0.99858224,0.0001689335,0.00047037203,0.00023774215,0.000003826806],"about_ca_topic_score_codex":0.01694334,"about_ca_topic_score_gemma":0.021651752,"teacher_disagreement_score":0.01694334,"about_ca_system_score_codex":0.00052158907,"about_ca_system_score_gemma":0.0008371933,"threshold_uncertainty_score":0.03368944},"labels":[],"label_agreement":null},{"id":"W4317042027","doi":"10.1177/20552076221149296","title":"Bibliometric analysis on the adoption of artificial intelligence applications in the e-health sector","year":2023,"lang":"en","type":"review","venue":"Digital Health","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Scopus; Field (mathematics); Data science; Bibliometrics; Computer science; MEDLINE; Management science; Political science; Library science; Engineering","score_opus":0.49864514667511284,"score_gpt":0.5691578924353806,"score_spread":0.07051274576026778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317042027","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043576255,0.91194904,0.003019194,0.0041280277,0.0006856031,0.00073669787,0.008979046,0.00014813604,0.026777908],"genre_scores_gemma":[0.23585793,0.74969894,0.0051432913,0.00062846625,0.0006884026,0.00066141604,0.0055310596,0.00004249709,0.0017478953],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9841137,0.00421122,0.004095338,0.00085475866,0.0063245147,0.00040048422],"domain_scores_gemma":[0.93648654,0.0408408,0.009718491,0.00097030296,0.011414997,0.0005688938],"candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.011856439,0.0007820655,0.0022116094,0.10619133,0.00087222,0.0037272929,0.0012445813,0.00079361035,0.00366777],"category_scores_gemma":[0.05229741,0.0003627451,0.0022466797,0.13027032,0.0009249517,0.0033111759,0.0017699922,0.0006353081,0.0005761456],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027020473,0.00011615698,0.05754576,0.23369876,0.004386582,0.00052426336,0.0023005789,0.0010714394,0.0008732703,0.009680447,0.022684699,0.6668479],"study_design_scores_gemma":[0.000109681045,0.0005434524,0.34650472,0.19284073,0.026052494,0.003833149,0.0076913354,0.003791983,0.0034545762,0.009325085,0.40554643,0.0003062645],"about_ca_topic_score_codex":0.0064243698,"about_ca_topic_score_gemma":0.011185102,"teacher_disagreement_score":0.89380866,"about_ca_system_score_codex":0.0032565207,"about_ca_system_score_gemma":0.008413049,"threshold_uncertainty_score":0.06270361},"labels":[],"label_agreement":null},{"id":"W4317907993","doi":"10.1186/s12874-022-01829-w","title":"Comparison of State-of-the-Art Neural Network Survival Models with the Pooled Cohort Equations for Cardiovascular Disease Risk Prediction","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"U.S. National Library of Medicine; National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Proportional hazards model; Cohort; Pooling; Survival analysis; Artificial neural network; Medicine; Nomogram; Framingham Risk Score; Disease; Statistics; Computer science; Artificial intelligence; Internal medicine; Mathematics","score_opus":0.7636271820778228,"score_gpt":0.6357989451054679,"score_spread":0.1278282369723549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317907993","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85290766,0.0034869665,0.13541326,0.0011297157,0.00026839244,0.00022891344,0.0035398148,0.00072327734,0.0023018743],"genre_scores_gemma":[0.96650195,0.00073078735,0.027105644,0.00022525866,0.00007454649,0.0002123703,0.0039582625,0.00006839512,0.0011227565],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981669,0.0010593301,0.00013053633,0.00035835768,0.00017100763,0.000113868395],"domain_scores_gemma":[0.9870784,0.009513769,0.0006831435,0.00074175675,0.0016835831,0.00029922018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014186597,0.0014144212,0.0013833249,0.0013163796,0.00035581528,0.00090250897,0.0019888529,0.0010158791,0.0016956507],"category_scores_gemma":[0.019653795,0.0005056074,0.0019540882,0.0008093597,0.0003803993,0.0011826019,0.0012909534,0.0018033878,0.00036285547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002319626,0.00030904924,0.07691109,0.0002256163,0.0016282776,0.00011465341,0.0001412105,0.85353667,0.00033346852,0.0019418723,0.0022694983,0.060268983],"study_design_scores_gemma":[0.000051041236,0.00016198115,0.0059755226,0.00003256626,0.0001388734,0.000020695301,0.00001981513,0.9922792,0.00016111102,0.0008832876,0.00025640006,0.000019427405],"about_ca_topic_score_codex":0.030396482,"about_ca_topic_score_gemma":0.019064106,"teacher_disagreement_score":0.030396482,"about_ca_system_score_codex":0.0013988694,"about_ca_system_score_gemma":0.0018274105,"threshold_uncertainty_score":0.07502675},"labels":[],"label_agreement":null},{"id":"W4318542906","doi":"10.1016/j.compeleceng.2023.108602","title":"Management for stroke intelligent early warning empowered by big data","year":2023,"lang":"en","type":"article","venue":"Computers & Electrical Engineering","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Big data; Wearable computer; Warning system; Computer science; Population; Computer security; Data science; Risk analysis (engineering); Medicine; Data mining; Environmental health; Telecommunications","score_opus":0.1608705694876696,"score_gpt":0.4163163879867445,"score_spread":0.2554458184990749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318542906","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18506087,0.011115317,0.6743096,0.040354546,0.004559512,0.001932704,0.013642969,0.015225195,0.053799286],"genre_scores_gemma":[0.90911967,0.0027897365,0.07032555,0.0020976698,0.0011174498,0.0004227107,0.0057597943,0.0001865892,0.008180792],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993204,0.00016752775,0.0000959243,0.0001302354,0.00017344604,0.000112529015],"domain_scores_gemma":[0.99747354,0.00063086726,0.00028334893,0.00036439285,0.00091013854,0.00033770065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017144196,0.00053837465,0.0006615972,0.0016731389,0.0008011513,0.002969269,0.0011982248,0.00082638283,0.004595246],"category_scores_gemma":[0.0048578414,0.000223096,0.00041313114,0.0008887948,0.00023295387,0.003027118,0.0019188,0.0009947233,0.0015035564],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011197482,0.0007598717,0.05652486,0.0008289232,0.00032420107,0.0014482068,0.00074369984,0.02618424,0.011305682,0.022582794,0.15690824,0.7212695],"study_design_scores_gemma":[0.0001768103,0.00045313322,0.02805722,0.0006205197,0.0005328623,0.0009190872,0.002588431,0.7146455,0.022311259,0.08758305,0.14192192,0.00019022638],"about_ca_topic_score_codex":0.0022184562,"about_ca_topic_score_gemma":0.0023142782,"teacher_disagreement_score":0.004595246,"about_ca_system_score_codex":0.0004988601,"about_ca_system_score_gemma":0.0016249903,"threshold_uncertainty_score":0.015372634},"labels":[],"label_agreement":null},{"id":"W4318613228","doi":"10.2139/ssrn.4323740","title":"A Multi-Class Neural Network Machine Learning Algorithm to Diagnose Graft Pathology in Liver Transplant Recipients","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network; University of British Columbia; Princess Margaret Cancer Centre; University of Ottawa","funders":"","keywords":"Class (philosophy); Computer science; Artificial intelligence; Artificial neural network; Machine learning; Algorithm; Pathology; Medicine","score_opus":0.10657157035467638,"score_gpt":0.4228125942062672,"score_spread":0.3162410238515908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318613228","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5945797,0.0017624163,0.39565384,0.0015463833,0.00051772315,0.00023464642,0.00059393526,0.0013974999,0.003713878],"genre_scores_gemma":[0.86238873,0.00026127725,0.13297077,0.00025420796,0.00016060425,0.00012485536,0.00047713,0.000045420595,0.0033169973],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997496,0.000057409576,0.000028433544,0.000082631006,0.000050767852,0.000031093547],"domain_scores_gemma":[0.99906677,0.0004809383,0.000055705576,0.000039611394,0.0003068442,0.0000501121],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011067721,0.00046886856,0.0005873912,0.0009627105,0.00043265126,0.0006536813,0.0007936705,0.0013840036,0.0015887294],"category_scores_gemma":[0.0026742546,0.00021436284,0.00048585903,0.00043212122,0.00016455424,0.0005952527,0.00045447252,0.00075123046,0.00038327806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013428786,0.000962302,0.044818554,0.00010881451,0.0002186856,0.00031307136,0.00006644888,0.12226997,0.012429864,0.0007895799,0.005785437,0.81089437],"study_design_scores_gemma":[0.000032864376,0.00011806959,0.0037012117,0.000008409402,0.00003855949,0.00010160467,0.00001543559,0.99295145,0.0024202014,0.00032880006,0.0002738415,0.000009424067],"about_ca_topic_score_codex":0.004708708,"about_ca_topic_score_gemma":0.0049910992,"teacher_disagreement_score":0.004708708,"about_ca_system_score_codex":0.00046808503,"about_ca_system_score_gemma":0.0007046044,"threshold_uncertainty_score":0.009362578},"labels":[],"label_agreement":null},{"id":"W4318908907","doi":"10.1145/3582491","title":"Data Science---A Systematic Treatment","year":2023,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data science","score_opus":0.7465776776167445,"score_gpt":0.6254157346368587,"score_spread":0.1211619429798858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318908907","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009720683,0.84121376,0.058435556,0.08074141,0.007078982,0.0011367762,0.0018617497,0.00020537149,0.008354278],"genre_scores_gemma":[0.018243844,0.8421625,0.09290225,0.034068402,0.005102491,0.0022894954,0.0016696719,0.00022479473,0.003336592],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9627629,0.019803151,0.006431837,0.0017692546,0.008704857,0.0005279793],"domain_scores_gemma":[0.8558163,0.102477394,0.0062078093,0.016135862,0.017755337,0.0016072283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.045805722,0.0017150008,0.0040463265,0.023466656,0.0028599969,0.008691432,0.0026799121,0.003909541,0.0056311837],"category_scores_gemma":[0.104135565,0.0014513037,0.0024370966,0.019099753,0.010215239,0.015087919,0.007480379,0.009830115,0.0022810325],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014878546,0.00019129446,0.0046266913,0.064092934,0.0010741485,0.0002572975,0.0018657439,0.0013051477,0.0010612414,0.29904616,0.13960935,0.48672122],"study_design_scores_gemma":[0.000062764666,0.00013039641,0.0018160457,0.09687435,0.00041725533,0.00061176385,0.001561525,0.0008974651,0.00067650416,0.14641348,0.750463,0.00007529784],"about_ca_topic_score_codex":0.0047315885,"about_ca_topic_score_gemma":0.009426618,"teacher_disagreement_score":0.045805722,"about_ca_system_score_codex":0.0075312816,"about_ca_system_score_gemma":0.0249614,"threshold_uncertainty_score":0.24224669},"labels":[],"label_agreement":null},{"id":"W4318969257","doi":"10.1109/icdsaai55433.2022.10028959","title":"Excogitation of Stacked Strategy for Coronary Artery Disease Diagnosis","year":2022,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"CAD; Computer science; Artificial intelligence; Boosting (machine learning); Classifier (UML); Machine learning; Coronary artery disease; Support vector machine; Feature extraction; Extreme learning machine; Statistical classification; Stacking; Pattern recognition (psychology); Medicine; Cardiology; Engineering; Artificial neural network","score_opus":0.3193880478090794,"score_gpt":0.5123206296233122,"score_spread":0.19293258181423273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318969257","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07568366,0.0018717555,0.9086645,0.000893387,0.00057721796,0.00019602812,0.00040205292,0.0027155404,0.008995809],"genre_scores_gemma":[0.62707704,0.0011497814,0.36171195,0.00057377527,0.00046241438,0.00016251074,0.001394248,0.00025838806,0.007209886],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925405,0.00016349774,0.00006052729,0.00017449564,0.00024173147,0.00010567266],"domain_scores_gemma":[0.9994523,0.00011638891,0.00003823894,0.00009091561,0.00023642696,0.00006579311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008977297,0.000882421,0.0008714927,0.0013624603,0.0006681787,0.0012873926,0.00087247853,0.000891435,0.004314473],"category_scores_gemma":[0.001899965,0.00026485202,0.001053192,0.0006865947,0.00036376982,0.00084954675,0.0011527323,0.0005706109,0.0018175064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005218581,0.000336049,0.012884269,0.0001678569,0.00028126777,0.0011809425,0.00022990168,0.059828013,0.01978986,0.011281385,0.011381714,0.8821169],"study_design_scores_gemma":[0.000053932705,0.0004070736,0.00562635,0.000052474963,0.00024565138,0.0014188976,0.0001714156,0.9461552,0.01864944,0.01672425,0.010435067,0.00006033752],"about_ca_topic_score_codex":0.0032412028,"about_ca_topic_score_gemma":0.0029262658,"teacher_disagreement_score":0.004314473,"about_ca_system_score_codex":0.0003234957,"about_ca_system_score_gemma":0.0010283211,"threshold_uncertainty_score":0.014433384},"labels":[],"label_agreement":null},{"id":"W4319006857","doi":"10.1161/str.54.suppl_1.tp189","title":"Abstract TP189: Identifying Stroke Patients At Risk For Cognitive Impairment And Dementia Using Electronic Health Record Data And Machine Learning","year":2023,"lang":"en","type":"article","venue":"Stroke","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Dementia; Logistic regression; Random forest; Stroke (engine); Canadian Cardiovascular Society; Diabetes mellitus; Medical record; Physical therapy; Physical medicine and rehabilitation; Internal medicine; Machine learning; Angina; Disease; Myocardial infarction","score_opus":0.21027864068934993,"score_gpt":0.47950713722065547,"score_spread":0.26922849653130554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319006857","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9460872,0.0005923485,0.04097003,0.0018771107,0.00012532325,0.00028434396,0.008310692,0.00047389106,0.0012790507],"genre_scores_gemma":[0.97579724,0.00015606105,0.017725421,0.00011971152,0.00013184163,0.00012026524,0.0053313635,0.00001410987,0.00060395733],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859697,0.00073387,0.00011304797,0.00030281724,0.00015675934,0.00009641917],"domain_scores_gemma":[0.99475104,0.0035070037,0.0005631376,0.0003671052,0.0006064867,0.00020525348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046763797,0.000678786,0.0005491773,0.0020754791,0.00037032092,0.0010850112,0.0009493383,0.00074596825,0.0020827805],"category_scores_gemma":[0.011270398,0.00025343217,0.0010644327,0.0013276272,0.00019469523,0.0008177918,0.0006556398,0.0008179893,0.00060883735],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00086196687,0.00102231,0.8451258,0.00020614543,0.00062127225,0.00046076378,0.00013180378,0.051256273,0.0010718501,0.0004355226,0.0054873456,0.093318954],"study_design_scores_gemma":[0.000087980516,0.000675384,0.20333439,0.00010987858,0.00024923688,0.00038671985,0.00016516529,0.79075664,0.0010865848,0.001460112,0.0016517554,0.00003622737],"about_ca_topic_score_codex":0.011802372,"about_ca_topic_score_gemma":0.0069800015,"teacher_disagreement_score":0.011802372,"about_ca_system_score_codex":0.000572462,"about_ca_system_score_gemma":0.0009598507,"threshold_uncertainty_score":0.024731398},"labels":[],"label_agreement":null},{"id":"W4319082079","doi":"10.26685/urncst.426","title":"Feasibility Study: Machine Learning in Neurodegenerative Disorders, Alzheimer’s Disease","year":2023,"lang":"en","type":"article","venue":"Undergraduate Research in Natural and Clinical Science and Technology (URNCST) Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Machine learning; Logistic regression; Medical diagnosis; Binary classification; Computer science; Clinical decision support system; Support vector machine; Medicine; Decision support system; Pathology","score_opus":0.336305018328938,"score_gpt":0.5862845611743495,"score_spread":0.24997954284541146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319082079","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93007463,0.0022628738,0.04271345,0.0069045913,0.00033810938,0.005963852,0.0029325825,0.00034056758,0.008469276],"genre_scores_gemma":[0.95394623,0.00060353026,0.03931497,0.0006111543,0.000103290564,0.002000645,0.0016927281,0.000020001171,0.0017075018],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948967,0.0032730233,0.00022872702,0.00038065933,0.0010508207,0.00016998847],"domain_scores_gemma":[0.97134554,0.020336997,0.0009353456,0.0016564534,0.0047843037,0.00094123534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015827548,0.0003927993,0.00038571135,0.0008249006,0.00052283594,0.001079339,0.000838626,0.00079801027,0.0070758653],"category_scores_gemma":[0.03987813,0.00019980055,0.0005367602,0.0010461849,0.00051703805,0.0016187078,0.0013675934,0.00096705597,0.0013829087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0074635195,0.0073933043,0.46861562,0.0016966653,0.00043894618,0.0008450402,0.0008572817,0.011262006,0.0051050344,0.0074042478,0.012430062,0.47648826],"study_design_scores_gemma":[0.0038623062,0.05207323,0.5796127,0.0017571438,0.00092460273,0.0042766756,0.0038032555,0.2612206,0.023780033,0.030463032,0.038005143,0.00022137201],"about_ca_topic_score_codex":0.0023531858,"about_ca_topic_score_gemma":0.0026001995,"teacher_disagreement_score":0.015827548,"about_ca_system_score_codex":0.0006875274,"about_ca_system_score_gemma":0.0035905049,"threshold_uncertainty_score":0.08370507},"labels":[],"label_agreement":null},{"id":"W4319450772","doi":"10.22214/ijraset.2023.48500","title":"Healthcare Monitoring System for Remote Areas","year":2023,"lang":"en","type":"article","venue":"International Journal for Research in Applied Science and Engineering Technology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Gadget; Remote patient monitoring; Computer science; Node (physics); Telemedicine; Medical emergency; Health care; Work (physics); Medicine; Real-time computing; Engineering; Nursing","score_opus":0.3270415460453178,"score_gpt":0.5761747520218533,"score_spread":0.2491332059765355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319450772","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24195683,0.0045187334,0.49498647,0.00588397,0.0018732112,0.002327526,0.012616352,0.15375891,0.082077995],"genre_scores_gemma":[0.8846481,0.0010288265,0.061654996,0.0013994887,0.00039037855,0.0006688492,0.006929878,0.0003988472,0.04288058],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99962354,0.00004804939,0.00004134196,0.00014627867,0.000100787474,0.0000399452],"domain_scores_gemma":[0.99964917,0.00006560679,0.00003780514,0.00006260549,0.0001412526,0.0000436768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004762021,0.0004702297,0.00048738558,0.0006708542,0.00052124733,0.0007605717,0.0007288835,0.0007916556,0.02245025],"category_scores_gemma":[0.0008454339,0.00017044011,0.00028083066,0.0004329213,0.0001479819,0.0006517271,0.00081640197,0.0006135713,0.007456916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027268738,0.0006981962,0.025585428,0.00096322317,0.00017996234,0.0019439863,0.0008416437,0.011782477,0.07464285,0.0054759104,0.15178598,0.72337335],"study_design_scores_gemma":[0.0009164067,0.0017808999,0.06658182,0.00045381126,0.00045479645,0.0042611402,0.0004886984,0.38759887,0.1775923,0.0075831045,0.35204855,0.00023959987],"about_ca_topic_score_codex":0.0018278187,"about_ca_topic_score_gemma":0.0009833631,"teacher_disagreement_score":0.02245025,"about_ca_system_score_codex":0.00046971874,"about_ca_system_score_gemma":0.00043171796,"threshold_uncertainty_score":0.07510352},"labels":[],"label_agreement":null},{"id":"W4320063308","doi":"10.4018/978-1-7998-9220-5.ch054","title":"Machine Learning Algorithms","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Canada West","funders":"","keywords":"Machine learning; Computer science; Artificial intelligence; Algorithm; Online machine learning; Quality (philosophy); Instance-based learning; Computational learning theory; Active learning (machine learning)","score_opus":0.29238714583234043,"score_gpt":0.4872512744570143,"score_spread":0.1948641286246739,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320063308","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017018721,0.023384692,0.9080406,0.003309528,0.0016133928,0.00056273345,0.0020506757,0.0053741415,0.053962406],"genre_scores_gemma":[0.051338885,0.03397205,0.860524,0.0020299891,0.0022476446,0.0014825793,0.008018372,0.0011233991,0.03926311],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947242,0.0016844188,0.00052594155,0.0009383571,0.0018905425,0.0002365611],"domain_scores_gemma":[0.99376327,0.0036952703,0.00031744604,0.0008610902,0.0012323766,0.00013046373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035863821,0.0024674854,0.002283831,0.0034413189,0.00096769835,0.005135246,0.0037104103,0.0025859529,0.022966845],"category_scores_gemma":[0.016153479,0.0006215338,0.001671355,0.0041012885,0.0013044402,0.0037812553,0.0031475003,0.0033482746,0.021792661],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007711607,0.00011438721,0.0011604575,0.0016369615,0.00022512267,0.00016260894,0.00015330307,0.041271765,0.00083384063,0.14024669,0.09689387,0.71722394],"study_design_scores_gemma":[0.000047729005,0.000094186275,0.00055215624,0.0010203213,0.000063794134,0.0004351181,0.00014224701,0.15848476,0.0018010428,0.43108553,0.4061933,0.00007975728],"about_ca_topic_score_codex":0.001531652,"about_ca_topic_score_gemma":0.0010152536,"teacher_disagreement_score":0.022966845,"about_ca_system_score_codex":0.0015213173,"about_ca_system_score_gemma":0.002458966,"threshold_uncertainty_score":0.0768317},"labels":[],"label_agreement":null},{"id":"W4322624953","doi":"10.2196/46102","title":"Correction: A Personalized Ontology-Based Decision Support System for Complex Chronic Patients: Retrospective Observational Study","year":2023,"lang":"en","type":"erratum","venue":"JMIR Formative Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Observational study; Ontology; Computer science; Decision support system; Clinical decision support system; Information retrieval; Retrospective cohort study; Data science; Medicine; Data mining; Internal medicine; Epistemology","score_opus":0.48166497371125283,"score_gpt":0.5942598874117507,"score_spread":0.1125949137004979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322624953","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000947789,0.0016780763,0.001724539,0.17805846,0.8083671,0.00009106604,0.005476869,0.00052535266,0.0031307],"genre_scores_gemma":[0.07925735,0.013468744,0.012287795,0.35475084,0.3899395,0.00085334835,0.008518693,0.0029631662,0.13796072],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99285156,0.0014854367,0.0019450944,0.0006691877,0.0025344123,0.00051431457],"domain_scores_gemma":[0.9433216,0.021373495,0.0034201937,0.0026130294,0.027646814,0.0016248329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064479616,0.0015371968,0.0017298935,0.0025000907,0.0023914194,0.002900877,0.0029424476,0.006339931,0.03642045],"category_scores_gemma":[0.1351836,0.0007483495,0.0017357186,0.0022999384,0.0020004734,0.002015348,0.0014122906,0.0077480474,0.014676144],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007347083,0.000009075497,0.00033989485,0.00029245016,0.00002802002,0.000965807,0.000080817066,0.000041514148,0.000037280108,0.0006697153,0.99215686,0.005305155],"study_design_scores_gemma":[0.00022000763,0.00006331019,0.0030126462,0.0022034014,0.00023354519,0.0057398714,0.0005690005,0.00072199316,0.0006777759,0.0033239096,0.9830957,0.00013897597],"about_ca_topic_score_codex":0.026389668,"about_ca_topic_score_gemma":0.024493687,"teacher_disagreement_score":0.03642045,"about_ca_system_score_codex":0.0033785738,"about_ca_system_score_gemma":0.006945519,"threshold_uncertainty_score":0.12183851},"labels":[],"label_agreement":null},{"id":"W4322703713","doi":"10.2196/44018","title":"Prediction of Weight Loss to Decrease the Risk for Type 2 Diabetes Using Multidimensional Data in Filipino Americans: Secondary Analysis","year":2023,"lang":"en","type":"article","venue":"JMIR Diabetes","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Diabetes and Digestive and Kidney Diseases","keywords":"Feature selection; Machine learning; Decision tree; Random forest; Artificial intelligence; Support vector machine; Computer science; Logistic regression; Data mining; Medicine","score_opus":0.22622561739087205,"score_gpt":0.47585491574311795,"score_spread":0.2496292983522459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322703713","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99456537,0.00014897862,0.002143376,0.00012265428,0.000022447728,0.00016143032,0.0023726865,0.00004646866,0.00041662517],"genre_scores_gemma":[0.99564266,0.00006424747,0.0017548945,0.00003527044,0.000024036024,0.00029232376,0.0018733445,0.000010049381,0.00030318517],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980134,0.0011098939,0.00013340941,0.00034112346,0.00023055276,0.0001716957],"domain_scores_gemma":[0.99203557,0.0046886723,0.0011016456,0.0008307957,0.0009829822,0.00036037975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055353483,0.0009006427,0.0009882569,0.0024982388,0.00062571955,0.0009199949,0.000877498,0.00070333306,0.0027981983],"category_scores_gemma":[0.0113610765,0.00023421175,0.0032250276,0.0013343075,0.0004080612,0.00039450775,0.00090028025,0.0013040241,0.00047812497],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0047599315,0.0012132229,0.9735719,0.00015160181,0.0015761097,0.00006416207,0.00013116229,0.0029057832,0.0005001732,0.00013256076,0.0011044861,0.013888924],"study_design_scores_gemma":[0.000340125,0.0022962764,0.9622816,0.00007020824,0.0012030761,0.000121762605,0.00028190494,0.031311926,0.000974481,0.0003420277,0.0007393863,0.000037208032],"about_ca_topic_score_codex":0.0042173397,"about_ca_topic_score_gemma":0.0028385092,"teacher_disagreement_score":0.0055353483,"about_ca_system_score_codex":0.0005741193,"about_ca_system_score_gemma":0.00068971503,"threshold_uncertainty_score":0.029274046},"labels":[],"label_agreement":null},{"id":"W4322768055","doi":"10.1007/s00607-023-01163-z","title":"Advances of machine learning in IoT-cloud for healthcare","year":2023,"lang":"en","type":"article","venue":"Computing","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Cloud computing; Internet of Things; Computer science; Health care; Artificial intelligence; Embedded system; Operating system","score_opus":0.2072215111091151,"score_gpt":0.5270424325630477,"score_spread":0.3198209214539326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322768055","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06558938,0.2548762,0.48319837,0.031989463,0.009659845,0.00022477205,0.0010364876,0.0012435716,0.15218185],"genre_scores_gemma":[0.6616808,0.16037841,0.14470546,0.0036713143,0.0054930425,0.000107118736,0.0012505208,0.00017453144,0.022538817],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991466,0.00019009133,0.000059198253,0.00015876713,0.00032693334,0.00011841215],"domain_scores_gemma":[0.998781,0.00045896487,0.00006168986,0.00014822697,0.00044603177,0.00010405505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013302021,0.00041131154,0.0005978084,0.0008044047,0.00038150788,0.0021426182,0.0011058283,0.00089362316,0.0043672645],"category_scores_gemma":[0.0019740222,0.00017786602,0.00065871567,0.0015269243,0.00064257585,0.004392522,0.001296331,0.0015067502,0.0010699633],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014587185,0.00025190457,0.008239572,0.0010261155,0.00010679899,0.00021915925,0.00015786773,0.012691703,0.005241845,0.2216067,0.037561443,0.7127509],"study_design_scores_gemma":[0.000033803015,0.00021160883,0.007373871,0.0006767603,0.00012447887,0.0007065268,0.00065387116,0.4171092,0.007985366,0.22532986,0.3397112,0.000083384635],"about_ca_topic_score_codex":0.0015570311,"about_ca_topic_score_gemma":0.0015547703,"teacher_disagreement_score":0.0043672645,"about_ca_system_score_codex":0.00080528134,"about_ca_system_score_gemma":0.0012448628,"threshold_uncertainty_score":0.014609933},"labels":[],"label_agreement":null},{"id":"W4323047889","doi":"10.18280/mmep.100106","title":"Influence of Class Imbalance and Resampling on Classification Accuracy of Chronic Kidney Disease Detection","year":2023,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Resampling; Kidney disease; Class (philosophy); Artificial intelligence; Disease; Computer science; Pattern recognition (psychology); Medicine; Internal medicine","score_opus":0.12122839416599544,"score_gpt":0.3827136543241812,"score_spread":0.26148526015818574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323047889","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91567856,0.0034863718,0.07555951,0.0010652818,0.0005855065,0.00018549764,0.00047469197,0.00054812484,0.0024163697],"genre_scores_gemma":[0.98666674,0.00019857408,0.012208183,0.00014468272,0.000081675615,0.000034054283,0.0004165925,0.000025016834,0.00022450976],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9870725,0.005657104,0.0011666347,0.0019631325,0.0034013505,0.00073922065],"domain_scores_gemma":[0.9480067,0.037096016,0.0034694448,0.0047652083,0.0059633167,0.0006993926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017739173,0.0007260788,0.001356232,0.0013069615,0.0010063895,0.001479761,0.000712163,0.0010059093,0.0003899853],"category_scores_gemma":[0.059770785,0.00017174816,0.00066134974,0.0008385858,0.00092285563,0.0013146306,0.00092798466,0.00093843834,0.0002442773],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0055750334,0.00082800654,0.31829846,0.0004564099,0.0007435777,0.0007328333,0.001094421,0.18039528,0.019052928,0.0025804886,0.0076589733,0.46258363],"study_design_scores_gemma":[0.0001307094,0.0014206007,0.14440891,0.00016035636,0.00038543026,0.0009626948,0.0011312146,0.8073606,0.03433115,0.0055848435,0.004002037,0.00012152032],"about_ca_topic_score_codex":0.0040549906,"about_ca_topic_score_gemma":0.0025451693,"teacher_disagreement_score":0.017739173,"about_ca_system_score_codex":0.00073226506,"about_ca_system_score_gemma":0.00078550726,"threshold_uncertainty_score":0.09381485},"labels":[],"label_agreement":null},{"id":"W4323241178","doi":"10.5220/0011628800003414","title":"Predicting Comorbidities in Diabetic Patients and Visualizing Data for Improved Healthcare","year":2023,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Health care; Computer science; Data mining; Medicine; Data science","score_opus":0.3372152808364619,"score_gpt":0.5335755142804626,"score_spread":0.19636023344400066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323241178","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8486197,0.0047752745,0.09547604,0.00694702,0.0005145049,0.00027251607,0.031792734,0.0041212244,0.007481011],"genre_scores_gemma":[0.92817056,0.0016166498,0.06057204,0.00031932446,0.0001725874,0.000047687572,0.008229316,0.00008149125,0.0007903553],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9996425,0.00011174256,0.00006876517,0.00005511858,0.000083298044,0.000038583406],"domain_scores_gemma":[0.99744296,0.0014597253,0.00038182797,0.00021381055,0.00031298638,0.00018874943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008763941,0.000637942,0.00050070515,0.0031673335,0.00026121398,0.002536555,0.00035120986,0.0006479189,0.0021720333],"category_scores_gemma":[0.005900297,0.00017207401,0.0006024928,0.0020000536,0.00014104063,0.0011072361,0.0006426472,0.0007002068,0.0003661423],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012888944,0.0006780706,0.64302397,0.00060470134,0.00035826088,0.00082571566,0.0008137282,0.01865743,0.011653323,0.003360458,0.02111355,0.29762182],"study_design_scores_gemma":[0.00017158003,0.00074342353,0.397723,0.0008465685,0.00078104285,0.0023722698,0.0052376557,0.49358726,0.025275832,0.037771266,0.0352628,0.00022730856],"about_ca_topic_score_codex":0.0055883774,"about_ca_topic_score_gemma":0.007998887,"teacher_disagreement_score":0.0055883774,"about_ca_system_score_codex":0.00041414693,"about_ca_system_score_gemma":0.0005833455,"threshold_uncertainty_score":0.011111736},"labels":[],"label_agreement":null},{"id":"W4323545656","doi":"10.6000/1929-6029.2023.12.02","title":"Comparison of Some Prediction Models and their Relevance in the Clinical Research","year":2023,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Predictive modelling; Logistic regression; Artificial intelligence; Machine learning; Feature selection; Relevance (law); Artificial neural network; Feature (linguistics); Selection (genetic algorithm); Data mining","score_opus":0.7795987724141072,"score_gpt":0.7470700299392866,"score_spread":0.03252874247482063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323545656","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12290658,0.17614517,0.6217184,0.023426725,0.0025893706,0.00058133487,0.005885076,0.002099057,0.044648293],"genre_scores_gemma":[0.7430101,0.07161794,0.17307086,0.0017539643,0.002138104,0.0006545497,0.004479482,0.00032528635,0.0029496667],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9924528,0.003559189,0.0006839282,0.0010269926,0.002024857,0.00025221595],"domain_scores_gemma":[0.97040313,0.023156611,0.00095232495,0.0008978,0.0042632404,0.000326992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014141149,0.0013180652,0.0011977833,0.0052978727,0.0005841823,0.003651803,0.0016053452,0.0014206425,0.0026209909],"category_scores_gemma":[0.045329012,0.0002981616,0.0017265149,0.004355975,0.0006182053,0.0031451418,0.00095883425,0.0019862952,0.0008730278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010980152,0.0002610105,0.045199387,0.0024598609,0.0010815376,0.00030014227,0.0004179532,0.10234368,0.00051588286,0.055724252,0.01441344,0.7761848],"study_design_scores_gemma":[0.00018878446,0.001000782,0.037009537,0.0028384074,0.0013831629,0.0008486798,0.001008622,0.79687184,0.0018584264,0.110685565,0.04608149,0.00022457633],"about_ca_topic_score_codex":0.007007175,"about_ca_topic_score_gemma":0.0034968092,"teacher_disagreement_score":0.014141149,"about_ca_system_score_codex":0.0021164264,"about_ca_system_score_gemma":0.0019300451,"threshold_uncertainty_score":0.074786425},"labels":[],"label_agreement":null},{"id":"W4324356412","doi":"10.47611/jsrhs.v11i3.3380","title":"Predicting the Chance of Heart Attack with a Machine Learning Approach – Supervised Learning","year":2022,"lang":"en","type":"article","venue":"Journal of Student Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centennial College","funders":"","keywords":"Artificial intelligence; Machine learning; Computer science; Heart rate; Blood pressure; Supervised learning; Field (mathematics); Set (abstract data type); Artificial neural network; Medicine; Internal medicine; Mathematics","score_opus":0.4881802273776676,"score_gpt":0.5819542241543257,"score_spread":0.09377399677665815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324356412","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42781115,0.0005831467,0.5645093,0.00097612187,0.000121100515,0.00022499156,0.00075731653,0.0012483158,0.0037685987],"genre_scores_gemma":[0.9048689,0.00015345492,0.09259593,0.000085614236,0.00010095907,0.00011347843,0.0008511293,0.000024725989,0.0012057485],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897027,0.00040899278,0.00008911381,0.00023967863,0.00022556064,0.00006640755],"domain_scores_gemma":[0.99520063,0.0034220591,0.0003790557,0.00034232993,0.00055298535,0.00010294898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015859628,0.00040631465,0.0007500677,0.0011408689,0.00034785978,0.0007289053,0.0006951543,0.00073963637,0.00083302427],"category_scores_gemma":[0.0055021415,0.00021781049,0.0008314331,0.0005935155,0.00029975947,0.00070368673,0.0003666925,0.000758507,0.00034038295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046891224,0.0012696299,0.09285596,0.0001526132,0.00044070146,0.00025019541,0.00018379056,0.6114437,0.0039201826,0.0033423032,0.0041350354,0.281537],"study_design_scores_gemma":[0.000011491715,0.00014708596,0.00530985,0.00000970957,0.00001959196,0.000070037364,0.00001810901,0.9905511,0.0010647394,0.0024200424,0.00036696292,0.000011328602],"about_ca_topic_score_codex":0.002441075,"about_ca_topic_score_gemma":0.0027282345,"teacher_disagreement_score":0.002441075,"about_ca_system_score_codex":0.00042944972,"about_ca_system_score_gemma":0.00076024735,"threshold_uncertainty_score":0.008387446},"labels":[],"label_agreement":null},{"id":"W4327520566","doi":"10.15173/mujph.v1i1.3073","title":"Methods Content Analysis: A Role in Applied Health Research","year":2022,"lang":"en","type":"article","venue":"McMaster University Journal of Public Health","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Content analysis; Content (measure theory); Quality (philosophy); Data science; Sketch; Multimethodology; Quantitative analysis (chemistry); Information retrieval; Data mining; Psychology; Mathematics; Mathematics education; Sociology; Epistemology","score_opus":0.6892950976294748,"score_gpt":0.5660031632577146,"score_spread":0.12329193437176023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327520566","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015823767,0.015605164,0.8447283,0.09769113,0.0062581496,0.008185802,0.0011651813,0.0012204812,0.023563407],"genre_scores_gemma":[0.020566216,0.008535274,0.9357901,0.009684132,0.0024795753,0.018700715,0.00037851237,0.00053396006,0.0033314824],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.54104275,0.3957862,0.019418038,0.010154799,0.032245096,0.0013531002],"domain_scores_gemma":[0.25291917,0.6278509,0.018357852,0.049112864,0.04778016,0.0039790054],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.37249348,0.0020821176,0.0034383424,0.017418556,0.00767542,0.02649095,0.0065544927,0.006110548,0.013473878],"category_scores_gemma":[0.5074248,0.0018220093,0.0018884768,0.025366453,0.031595927,0.02298017,0.01266706,0.013473789,0.005958687],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009842591,0.000100632475,0.0012690295,0.0076472727,0.00025459373,0.00015334482,0.034519702,0.0005273273,0.0007467485,0.56364506,0.07310961,0.31792828],"study_design_scores_gemma":[0.00008897907,0.00005851808,0.0007024303,0.011310625,0.00008452077,0.00025065397,0.013120028,0.0018758342,0.000611714,0.66114694,0.31059706,0.00015268782],"about_ca_topic_score_codex":0.0027376008,"about_ca_topic_score_gemma":0.0018623617,"teacher_disagreement_score":0.6275065,"about_ca_system_score_codex":0.010979707,"about_ca_system_score_gemma":0.02983062,"threshold_uncertainty_score":0.77382725},"labels":[],"label_agreement":null},{"id":"W4327560022","doi":"10.1016/j.dcan.2023.03.005","title":"Big data in healthcare: Conceptual network structure, key challenges and opportunities","year":2023,"lang":"en","type":"article","venue":"Digital Communications and Networks","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Lakehead University","funders":"Ministerio de Ciencia e Innovación; Consejo Nacional de Ciencia y Tecnología; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Big data; Data science; Computer science; Centrality; Health care; Thematic analysis; Knowledge management; Data mining; Qualitative research; Sociology","score_opus":0.5862401526345736,"score_gpt":0.46473671205272227,"score_spread":0.12150344058185136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327560022","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.089685,0.11890604,0.4716448,0.26113412,0.0021373874,0.0007143215,0.0035416647,0.0004698693,0.051766776],"genre_scores_gemma":[0.61793727,0.0707152,0.2981694,0.0048363185,0.0016350977,0.00082110724,0.0020070437,0.00012298232,0.0037556319],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99250823,0.004772317,0.000435861,0.00067279884,0.0014293636,0.00018141791],"domain_scores_gemma":[0.97691953,0.016040197,0.0021562707,0.0012115081,0.002846243,0.0008263091],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013437955,0.00049578917,0.0006754227,0.009460415,0.0019612107,0.010793224,0.0014564194,0.0015267731,0.0017468884],"category_scores_gemma":[0.027445294,0.0003656386,0.00062424445,0.015295894,0.0052042976,0.015772047,0.0033034899,0.0019718863,0.00035014522],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006270273,0.000048046568,0.01895512,0.0036104324,0.00016802539,0.00038996202,0.0060527204,0.0048717814,0.00080640265,0.7675119,0.012801498,0.18472148],"study_design_scores_gemma":[0.00001113331,0.000042621883,0.008174544,0.002969306,0.00008753937,0.00056377304,0.012373359,0.017746013,0.00050619425,0.81491476,0.14254066,0.00007014853],"about_ca_topic_score_codex":0.0031181863,"about_ca_topic_score_gemma":0.0038979258,"teacher_disagreement_score":0.013437955,"about_ca_system_score_codex":0.0043976656,"about_ca_system_score_gemma":0.0058171763,"threshold_uncertainty_score":0.07106757},"labels":[],"label_agreement":null},{"id":"W4353100324","doi":"10.54097/hset.v34i.5494","title":"Predicting Titanic Survivors by Using Machine Learning","year":2023,"lang":"en","type":"article","venue":"Highlights in Science Engineering and Technology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cruise; Artificial intelligence; Machine learning; Task (project management); Test (biology); Competition (biology); Hull; Point (geometry); Computer science; Test set; Oceanography; History; Engineering; Geology; Mathematics; Ecology; Paleontology","score_opus":0.05033633436373746,"score_gpt":0.3774473887674155,"score_spread":0.32711105440367805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353100324","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9788847,0.0003318539,0.015877869,0.00056901836,0.000084256135,0.00008297993,0.0013980127,0.00024743576,0.0025238735],"genre_scores_gemma":[0.99266726,0.000120586046,0.0045908825,0.000055251294,0.00003097928,0.000031868767,0.0014204775,0.000007646308,0.0010750951],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99952006,0.00014383261,0.000044440898,0.0000960996,0.000113646376,0.000081896316],"domain_scores_gemma":[0.99752146,0.0015018574,0.0003152416,0.000111090674,0.00039561902,0.00015466717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011218153,0.000570379,0.00033452566,0.0022157128,0.00028672448,0.00072154356,0.00044504783,0.00054182333,0.0012523052],"category_scores_gemma":[0.0054717157,0.000106876454,0.00042409997,0.00083214766,0.00020572101,0.00055353553,0.00043546222,0.0005380394,0.00067697064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041998035,0.00048175332,0.7275519,0.00010402156,0.00017450146,0.00028345326,0.00041836698,0.092644244,0.0013027512,0.0005036003,0.0051082373,0.17100707],"study_design_scores_gemma":[0.000026196552,0.0010299154,0.25825214,0.00008972992,0.000093609255,0.00039232284,0.0015619692,0.72827303,0.0032446773,0.0026225238,0.0043490585,0.000064811626],"about_ca_topic_score_codex":0.00666865,"about_ca_topic_score_gemma":0.0077356626,"teacher_disagreement_score":0.00666865,"about_ca_system_score_codex":0.00041065237,"about_ca_system_score_gemma":0.00044198247,"threshold_uncertainty_score":0.013259709},"labels":[],"label_agreement":null},{"id":"W4360792247","doi":"10.2196/45913","title":"Obstacles to Health Big Data Utilization Based on the Perceptions and Demands of Health Care Workers in South Korea: Web-Based Survey Study","year":2023,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Big data; Health care; Context (archaeology); Government (linguistics); Public health; Survey data collection; Psychology; Environmental health; Medicine; Business; Nursing; Political science; Computer science; Geography; Data mining; Statistics","score_opus":0.6798985156279234,"score_gpt":0.6171446683772646,"score_spread":0.0627538472506588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360792247","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99884087,0.000073108815,0.000064060856,0.00048043445,0.000004550271,0.00002791931,0.00014715017,0.0000018669966,0.00036006374],"genre_scores_gemma":[0.99909043,0.00015835765,0.00014587976,0.0003124062,0.000005546186,0.00004592829,0.000121876656,0.0000022812483,0.00011732819],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997577,0.00081767084,0.00047976477,0.00022156474,0.000450834,0.000453163],"domain_scores_gemma":[0.9891452,0.0031188685,0.004017004,0.0003405146,0.0012468331,0.002131548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040387986,0.00023499843,0.00031827405,0.0011950794,0.0012029902,0.0015827753,0.0004814546,0.00060241955,0.002111403],"category_scores_gemma":[0.008168675,0.00043987605,0.00059081655,0.0014776194,0.0007677623,0.0016567862,0.002050607,0.0012093564,0.00026309054],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004404029,0.00019864425,0.97921115,0.00014616047,0.000038406106,0.00025186103,0.014956495,0.00003919652,0.0002861061,0.00007653921,0.00061718025,0.004134235],"study_design_scores_gemma":[0.000009605426,0.0001434103,0.8890557,0.00015812925,0.000029172354,0.00023555077,0.10836829,0.0004355847,0.00013698185,0.0000626147,0.0013348832,0.000030081366],"about_ca_topic_score_codex":0.009719889,"about_ca_topic_score_gemma":0.01257163,"teacher_disagreement_score":0.009719889,"about_ca_system_score_codex":0.0011692385,"about_ca_system_score_gemma":0.0022403446,"threshold_uncertainty_score":0.021359444},"labels":[],"label_agreement":null},{"id":"W4360824212","doi":"10.1117/12.2668989","title":"Risk assessment for heart failure using multiple linear regression model","year":2023,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Heart failure; Linear regression; Medicine; Angina; Regression analysis; Population; Cardiology; Sample size determination; Heart disease; Internal medicine; Statistics; Mathematics; Environmental health","score_opus":0.35426586169933605,"score_gpt":0.576388611693895,"score_spread":0.22212274999455894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360824212","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54951775,0.004945062,0.42181188,0.0050990004,0.0008050835,0.00064304,0.00737678,0.0018576464,0.0079436535],"genre_scores_gemma":[0.9525669,0.0012456658,0.03718099,0.00016536821,0.000259078,0.00040725234,0.0023655563,0.000049088114,0.005760029],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861395,0.0006367386,0.00011637738,0.00030914627,0.00021085203,0.000112938906],"domain_scores_gemma":[0.9968046,0.0022940128,0.00036368694,0.000093708826,0.0003378661,0.00010618215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024366004,0.0010348344,0.0009424198,0.002268945,0.00034246253,0.0014347313,0.0012415644,0.00096945814,0.0062157824],"category_scores_gemma":[0.008173757,0.0002940306,0.0017478765,0.0013219349,0.00017517775,0.0008122497,0.0006618444,0.0016295159,0.0013364454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012936052,0.0011441585,0.55455077,0.0005625264,0.0019065881,0.0012679399,0.00037709082,0.22681811,0.0016597607,0.006343634,0.013076924,0.19099885],"study_design_scores_gemma":[0.000042176373,0.00040815657,0.04091385,0.00008402153,0.0003750304,0.0004056749,0.00015403483,0.95110506,0.00034601532,0.0039684833,0.002144541,0.00005293201],"about_ca_topic_score_codex":0.00805686,"about_ca_topic_score_gemma":0.0048656324,"teacher_disagreement_score":0.00805686,"about_ca_system_score_codex":0.00049099635,"about_ca_system_score_gemma":0.0008095055,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4360825297","doi":"10.1117/12.2669045","title":"Predicting mortality in patients with heart failure based on machine learning approaches","year":2023,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Random forest; Decision tree; Pruning; Machine learning; Logistic regression; Artificial intelligence; Computer science; Heart failure; Selection (genetic algorithm); Regression; Failure rate; k-nearest neighbors algorithm; Feature selection; Statistics; Mathematics; Medicine; Internal medicine","score_opus":0.21223039244775865,"score_gpt":0.4266438821643162,"score_spread":0.21441348971655755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360825297","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81136423,0.008609525,0.16769475,0.0023461506,0.00045966203,0.00034355104,0.0019469552,0.00093718205,0.006298043],"genre_scores_gemma":[0.9710343,0.0010557733,0.026115285,0.00013577263,0.0001737688,0.0000864816,0.00091913744,0.00001001145,0.00046946292],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915326,0.00029866316,0.00009925355,0.00011772496,0.00025291246,0.00007827154],"domain_scores_gemma":[0.9984964,0.000976802,0.00014175843,0.000048952148,0.00026728204,0.00006872748],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014636004,0.0006532771,0.00079341786,0.002472469,0.00030574686,0.0007296368,0.0004729392,0.0005739316,0.00072259357],"category_scores_gemma":[0.0043750834,0.000112971975,0.0007811755,0.0010393818,0.00012549417,0.0006612634,0.0004060196,0.0006146535,0.00029384423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070190727,0.000802665,0.39802942,0.00031885516,0.0005411955,0.000351294,0.0002102491,0.1636285,0.0015303361,0.0011407104,0.0046072104,0.4281377],"study_design_scores_gemma":[0.000044342232,0.00033735,0.06458438,0.00010621041,0.00016828929,0.00020955868,0.00024331501,0.9293722,0.0010986547,0.002689435,0.0010984442,0.000047830847],"about_ca_topic_score_codex":0.0030808144,"about_ca_topic_score_gemma":0.0033191799,"teacher_disagreement_score":0.0030808144,"about_ca_system_score_codex":0.00039911494,"about_ca_system_score_gemma":0.00055258634,"threshold_uncertainty_score":0.0077403784},"labels":[],"label_agreement":null},{"id":"W4360989112","doi":"10.18280/ria.370111","title":"An Improved CHI2 Feature Selection Based a Two-Stage Prediction of Comorbid Cancer Patient Survivability","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Survivability; Stage (stratigraphy); Feature selection; Selection (genetic algorithm); Cancer; Feature (linguistics); Artificial intelligence; Computer science; Pattern recognition (psychology); Medicine; Internal medicine; Biology","score_opus":0.13303607764379077,"score_gpt":0.44416414368876117,"score_spread":0.3111280660449704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360989112","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47704995,0.0013652698,0.5093251,0.002354667,0.00042647656,0.00036845554,0.004415698,0.0031752556,0.0015191538],"genre_scores_gemma":[0.932285,0.00019434543,0.061255198,0.0003263337,0.00021352101,0.00023750032,0.0034024182,0.000051789204,0.0020338895],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989448,0.0003000167,0.000099475976,0.00025397283,0.0002082305,0.00019350111],"domain_scores_gemma":[0.9961972,0.0023178705,0.00016337745,0.00019555922,0.0009360713,0.0001899877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024509518,0.00086970924,0.0014293534,0.0016366208,0.00059036317,0.00087770744,0.0013842019,0.00096820464,0.0022870144],"category_scores_gemma":[0.0054135094,0.00029950953,0.0014109375,0.0015417859,0.0003047501,0.00075557013,0.0007610491,0.0012852435,0.0005827675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036880006,0.0015900953,0.19312896,0.00031626588,0.00074030017,0.001253235,0.0003597806,0.2834935,0.011182236,0.0015907414,0.021969201,0.48068777],"study_design_scores_gemma":[0.000044625158,0.0002123768,0.0102166915,0.000011802262,0.000052475134,0.00014821626,0.000029825529,0.98713374,0.0009006658,0.0006361156,0.00058895187,0.000024553752],"about_ca_topic_score_codex":0.019768478,"about_ca_topic_score_gemma":0.014347418,"teacher_disagreement_score":0.019768478,"about_ca_system_score_codex":0.000570745,"about_ca_system_score_gemma":0.0014541841,"threshold_uncertainty_score":0.03930682},"labels":[],"label_agreement":null},{"id":"W4360989136","doi":"10.18280/ria.370115","title":"Machine Learning Algorithm and GESTOSIS Score Assisted High Risk Pregnancy Induced Hypertension Prediction","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pregnancy; Computer science; Preeclampsia; Machine learning; High risk pregnancy; Artificial intelligence","score_opus":0.18481151457111458,"score_gpt":0.38750495320617007,"score_spread":0.20269343863505548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360989136","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8192745,0.0014414196,0.17006077,0.00054839824,0.000255042,0.0003343967,0.0008814112,0.00094006484,0.0062640333],"genre_scores_gemma":[0.958775,0.00022159831,0.039479766,0.00007305544,0.000056564102,0.00009202912,0.00038707352,0.000016295822,0.0008985514],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883455,0.0007115527,0.00008138995,0.00012218849,0.00018602722,0.000064241605],"domain_scores_gemma":[0.9963735,0.0024534448,0.0002777124,0.00018405628,0.00058378605,0.00012752962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028293033,0.00049466384,0.00075432984,0.0013067337,0.00018181032,0.00064161146,0.00035962468,0.00046490628,0.0014725653],"category_scores_gemma":[0.0078093647,0.0001342421,0.0005490661,0.00057625654,0.00016031666,0.00029760017,0.0003802695,0.00062951737,0.0005805591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021383367,0.0011025766,0.4738266,0.0001405446,0.00051351334,0.00022951364,0.00013619427,0.067504175,0.0055082985,0.0009023564,0.002596417,0.4454015],"study_design_scores_gemma":[0.00012467,0.0015361172,0.1683135,0.000070825125,0.00023904919,0.0005847374,0.000082523424,0.82081383,0.004288291,0.002064105,0.001832686,0.00004958259],"about_ca_topic_score_codex":0.0012864555,"about_ca_topic_score_gemma":0.00087429903,"teacher_disagreement_score":0.0028293033,"about_ca_system_score_codex":0.00021274814,"about_ca_system_score_gemma":0.00048643711,"threshold_uncertainty_score":0.014962912},"labels":[],"label_agreement":null},{"id":"W4361009208","doi":"10.3390/electronics12071558","title":"Reviewing Multimodal Machine Learning and Its Use in Cardiovascular Diseases Detection","year":2023,"lang":"en","type":"article","venue":"Electronics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cegep de Sept Iles; Université du Québec à Chicoutimi; Université du Québec à Rimouski","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Machine learning; Computer science; Field (mathematics); Process (computing); Workflow; Key (lock); Variety (cybernetics); Obstacle; Deep learning; Multimodal therapy; Sensor fusion; Medicine","score_opus":0.10576687460377471,"score_gpt":0.4230848282736733,"score_spread":0.31731795366989857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361009208","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012126677,0.97617835,0.011379895,0.0019146601,0.0011849661,0.000024278657,0.000058213598,0.000039947357,0.008006893],"genre_scores_gemma":[0.011608272,0.97499996,0.006166956,0.0014916671,0.0025967394,0.000036645226,0.00012683391,0.0000203148,0.00295258],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99958915,0.0001228512,0.000060635648,0.000079676625,0.00012488286,0.000022749604],"domain_scores_gemma":[0.9982229,0.0012289049,0.000108300046,0.000032968976,0.00037554046,0.000031357973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010518022,0.00046089073,0.0005062623,0.0019283033,0.00024809642,0.00091114105,0.0005455363,0.0011097008,0.002485658],"category_scores_gemma":[0.0024541076,0.00023980094,0.0004424164,0.0021029096,0.0004676373,0.0012593798,0.00037663413,0.00093950116,0.0012196266],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049345967,0.00005417961,0.0010988419,0.011613203,0.00013010779,0.00034462343,0.00022955242,0.0029195421,0.0030647588,0.019243246,0.04279718,0.9184554],"study_design_scores_gemma":[0.0000049176256,0.00028536157,0.0037603357,0.007249709,0.00019096413,0.0021798764,0.00019234794,0.0038129254,0.003420465,0.009272869,0.96957,0.000060254162],"about_ca_topic_score_codex":0.0012742887,"about_ca_topic_score_gemma":0.0015036302,"teacher_disagreement_score":0.002485658,"about_ca_system_score_codex":0.00050080346,"about_ca_system_score_gemma":0.0008239606,"threshold_uncertainty_score":0.008315384},"labels":[],"label_agreement":null},{"id":"W4361019722","doi":"10.1109/hpcc-dss-smartcity-dependsys57074.2022.00026","title":"Message from Data Science and Systems 2022 General Chairs","year":2022,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Data science","score_opus":0.33167296623245934,"score_gpt":0.5108006548005469,"score_spread":0.17912768856808758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361019722","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019428077,0.0015864449,0.0004982422,0.7085947,0.2806183,0.00008352151,0.00049377355,0.00018852833,0.0077421847],"genre_scores_gemma":[0.0032154715,0.0019915977,0.0009818701,0.7323204,0.10243392,0.00028419791,0.0008045085,0.00034630072,0.1576217],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9936185,0.0011645365,0.00034189931,0.00079155556,0.0032886425,0.00079495297],"domain_scores_gemma":[0.9709908,0.003530954,0.00081223674,0.0008708607,0.014723819,0.009071367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010190174,0.0014298367,0.0014485768,0.001058506,0.003790838,0.0075245844,0.0016428643,0.01646097,0.0693051],"category_scores_gemma":[0.027709361,0.00075579295,0.0014687189,0.0010386577,0.0012128679,0.0042572985,0.003589693,0.023700016,0.06065545],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017387312,0.000005590937,0.00003064868,0.000018892117,0.0000015717125,0.000013838849,0.000010684812,0.0000065556196,0.000036861984,0.00022305502,0.99804926,0.0015856373],"study_design_scores_gemma":[0.000023927043,0.000021413278,0.00036499192,0.00007297159,0.000005677764,0.000044152883,0.00013074746,0.000049888025,0.000099193276,0.0004485756,0.9987208,0.000017586855],"about_ca_topic_score_codex":0.0070120874,"about_ca_topic_score_gemma":0.011842185,"teacher_disagreement_score":0.0693051,"about_ca_system_score_codex":0.0035357166,"about_ca_system_score_gemma":0.010927423,"threshold_uncertainty_score":0.23184866},"labels":[],"label_agreement":null},{"id":"W4361022466","doi":"10.11591/ijai.v12.i3.pp1508-1520","title":"Discrete separation of patients’ profiles for chronical obstructive pulmonary disease context-aware healthcare efficient systems","year":2023,"lang":"en","type":"article","venue":"IAES International Journal of Artificial Intelligence","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Chicoutimi","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"COPD; Context (archaeology); Health care; Pulmonary disease; Medicine; Intensive care medicine; Computer science; Healthcare system; Separation (statistics); Disease; Machine learning; Internal medicine","score_opus":0.13223860742419344,"score_gpt":0.4826349348603317,"score_spread":0.35039632743613824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361022466","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.095891505,0.0008537067,0.8972233,0.0014719524,0.00012338595,0.0004164558,0.00086384156,0.00120073,0.0019549981],"genre_scores_gemma":[0.8318385,0.00029655712,0.16577835,0.00019077522,0.00006301331,0.00018847513,0.00081579614,0.000026651072,0.0008019338],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977191,0.00064072903,0.00027224544,0.0006208232,0.0005401364,0.00020694619],"domain_scores_gemma":[0.99755895,0.0010489488,0.00035184325,0.00032908405,0.000517372,0.00019366178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002345944,0.0007086192,0.0009277452,0.0013331884,0.00076959137,0.0018888788,0.0010056506,0.0009793255,0.0012475615],"category_scores_gemma":[0.007805616,0.00033715152,0.00097205763,0.00094551855,0.00045250647,0.0019899323,0.0015775693,0.0013528257,0.00046482435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008937347,0.0008883371,0.058340635,0.00043759603,0.00037602597,0.0006425522,0.0009851424,0.47097483,0.009365719,0.032879908,0.005275412,0.4189401],"study_design_scores_gemma":[0.000012725305,0.00008108844,0.0034852664,0.000020639654,0.00003099482,0.0001044769,0.00007935724,0.98406225,0.001082295,0.009593564,0.0014312039,0.000016223426],"about_ca_topic_score_codex":0.007154943,"about_ca_topic_score_gemma":0.006320204,"teacher_disagreement_score":0.007154943,"about_ca_system_score_codex":0.0012362071,"about_ca_system_score_gemma":0.0014381455,"threshold_uncertainty_score":0.014226615},"labels":[],"label_agreement":null},{"id":"W4361799752","doi":"10.59284/jgpeman42","title":"Preliminary considerations for electronic medical record (EMR) in the public hospitals of Gandaki province in Nepal","year":2022,"lang":"en","type":"article","venue":"Journal of General Practice and Emergency Medicine of Nepal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Health care; Medical record; Transparency (behavior); Electronic medical record; Medicine; Government (linguistics); Medical emergency; Business; Computer security; Economic growth; Surgery; Computer science","score_opus":0.13617140596046534,"score_gpt":0.48744059853690824,"score_spread":0.3512691925764429,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361799752","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41244766,0.0038723205,0.001466149,0.53762907,0.00083697616,0.0011986399,0.0013318359,0.00011126903,0.041106127],"genre_scores_gemma":[0.8793917,0.0041060396,0.007936409,0.09247389,0.00054195384,0.00094261434,0.000856735,0.000043752585,0.013706831],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98149604,0.008716678,0.0018668722,0.000792115,0.0038844782,0.0032437728],"domain_scores_gemma":[0.929382,0.036365956,0.00627617,0.0014249048,0.017053837,0.00949701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01389274,0.00023400638,0.00024467238,0.0013951442,0.0032691502,0.008535433,0.0028241351,0.0040830094,0.012282215],"category_scores_gemma":[0.05866101,0.00042549745,0.0006620311,0.0016113874,0.0014549805,0.0045736926,0.0028265198,0.0031117762,0.001037638],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082095456,0.00089780206,0.5661242,0.005799071,0.00015271828,0.028128102,0.05862375,0.0011266874,0.0057982965,0.037641544,0.10550407,0.18938282],"study_design_scores_gemma":[0.00012356455,0.0015582745,0.46955228,0.008193112,0.00014850275,0.0102778785,0.23249637,0.0015621773,0.002479867,0.0033005679,0.27005902,0.00024836324],"about_ca_topic_score_codex":0.06916967,"about_ca_topic_score_gemma":0.14107755,"teacher_disagreement_score":0.06916967,"about_ca_system_score_codex":0.0066986457,"about_ca_system_score_gemma":0.032430846,"threshold_uncertainty_score":0.13753414},"labels":[],"label_agreement":null},{"id":"W4362512781","doi":"10.26443/mjm.v21i1.1033","title":"Artificial Intelligence and Data Mining in Health Research (AI/MDRS)","year":2022,"lang":"en","type":"article","venue":"McGill Journal of Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Artificial intelligence; Computer science","score_opus":0.7761908423092294,"score_gpt":0.6435537886136481,"score_spread":0.13263705369558132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362512781","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045666494,0.52766687,0.14574826,0.22216746,0.02386883,0.00021961535,0.0006699998,0.0008174136,0.07427489],"genre_scores_gemma":[0.1377944,0.5351167,0.18514106,0.039483298,0.053378925,0.00052337383,0.0008410845,0.00027311305,0.04744812],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99553394,0.0017207375,0.0007462008,0.0004491476,0.0014278414,0.00012213319],"domain_scores_gemma":[0.9638696,0.027330032,0.0018232937,0.0019402308,0.0036758801,0.0013610624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010046458,0.00045284542,0.00093773584,0.0052042976,0.0007903437,0.00558701,0.0007378261,0.002258637,0.0054783495],"category_scores_gemma":[0.021677913,0.00036889408,0.0006288943,0.00424388,0.0045666904,0.00457103,0.0030027393,0.0037934212,0.001576359],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036295067,0.00009036077,0.0022766362,0.0014063097,0.00010169189,0.00014951632,0.0003537902,0.0010943324,0.00055062317,0.2447796,0.14097676,0.6081841],"study_design_scores_gemma":[0.000026156791,0.000093651775,0.0041850326,0.0023671247,0.000087748274,0.0011174596,0.0003289381,0.009714302,0.00082335284,0.4844157,0.49677604,0.000064437234],"about_ca_topic_score_codex":0.0029643562,"about_ca_topic_score_gemma":0.002914676,"teacher_disagreement_score":0.010046458,"about_ca_system_score_codex":0.0020006676,"about_ca_system_score_gemma":0.0040872972,"threshold_uncertainty_score":0.053131342},"labels":[],"label_agreement":null},{"id":"W4362632104","doi":"10.17615/s2x3-5k76","title":"Development and external validation of machine learning algorithms for postnatal gestational age estimation using clinical data and metabolomic markers","year":2023,"lang":"en","type":"article","venue":"UNC Libraries","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Institutes of Health; Bill and Melinda Gates Foundation","keywords":"Computer science; Metabolomics; Algorithm; Estimation; Gestational age; Machine learning; Artificial intelligence; Bioinformatics; Pregnancy; Biology; Engineering","score_opus":0.41149148827890275,"score_gpt":0.515654931258923,"score_spread":0.10416344298002028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362632104","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35731906,0.0013590737,0.6326733,0.0010818964,0.0001454085,0.00063886883,0.0015980063,0.0027317696,0.0024525356],"genre_scores_gemma":[0.78614026,0.0003115106,0.20867948,0.00037620997,0.00003540344,0.0005909367,0.0028135972,0.00014955497,0.00090302975],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941612,0.0032668693,0.00052712124,0.0011153342,0.0006603157,0.00026914274],"domain_scores_gemma":[0.9682962,0.021492537,0.0017016561,0.001901247,0.0062606554,0.0003477128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023716385,0.0016442515,0.000952645,0.0015399774,0.0006986717,0.0018461777,0.0020416686,0.0013883078,0.0010943621],"category_scores_gemma":[0.061638564,0.00046958443,0.0012158053,0.00093954674,0.0008263423,0.0009927872,0.0018034916,0.002061159,0.00057321903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007562322,0.00033136923,0.15063372,0.0002208372,0.0007767733,0.0001935534,0.00027481825,0.6636012,0.0028605012,0.002413752,0.0029326247,0.17500465],"study_design_scores_gemma":[0.00005577335,0.00010739456,0.009836708,0.00006389161,0.0000558598,0.00006747617,0.00005998399,0.9852807,0.002184515,0.0014374092,0.0008279907,0.000022324015],"about_ca_topic_score_codex":0.045522492,"about_ca_topic_score_gemma":0.022122463,"teacher_disagreement_score":0.045522492,"about_ca_system_score_codex":0.0024368055,"about_ca_system_score_gemma":0.0058097797,"threshold_uncertainty_score":0.12542576},"labels":[],"label_agreement":null},{"id":"W4362672441","doi":"10.1016/j.suscom.2023.100868","title":"Multivariate time-series sensor vital sign forecasting of cardiovascular and chronic respiratory diseases","year":2023,"lang":"en","type":"article","venue":"Sustainable Computing Informatics and Systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"Høgskulen på Vestlandet","keywords":"Computer science; Machine learning; Artificial intelligence; Feature (linguistics); Random forest; Vital signs; Support vector machine; Naive Bayes classifier; Feature engineering; Medicine; Deep learning","score_opus":0.07856979135498487,"score_gpt":0.36249202610573084,"score_spread":0.28392223475074596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362672441","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9606038,0.00043028363,0.035388764,0.00031024666,0.00011963984,0.000018707768,0.001954233,0.00022912813,0.0009451681],"genre_scores_gemma":[0.99672663,0.0001184804,0.0020201332,0.000012553691,0.000027317858,0.0000048222882,0.00076264626,0.000005233696,0.0003222576],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99985147,0.000028983171,0.000014218227,0.000043100164,0.000036068246,0.000026187336],"domain_scores_gemma":[0.99952316,0.00021391531,0.000078482786,0.000044247183,0.000105958694,0.000034278713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005074208,0.00041349384,0.00036841698,0.0007703196,0.00010913861,0.00038855936,0.00024613217,0.00032748125,0.00088461774],"category_scores_gemma":[0.001982699,0.000099420104,0.0004119877,0.00077147153,0.000072690425,0.00043901853,0.00020177051,0.00044351598,0.0002763383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011853159,0.00065019453,0.49242282,0.00013345413,0.00040441033,0.00034549442,0.00013451661,0.23063587,0.017829489,0.001173286,0.0044783102,0.2506068],"study_design_scores_gemma":[0.000007417152,0.000106747866,0.16741726,0.000010122461,0.000051876617,0.000090686684,0.000042814358,0.8298025,0.0015147362,0.0005220592,0.00041847306,0.000015432395],"about_ca_topic_score_codex":0.006950352,"about_ca_topic_score_gemma":0.0068947393,"teacher_disagreement_score":0.006950352,"about_ca_system_score_codex":0.00021312416,"about_ca_system_score_gemma":0.00032822046,"threshold_uncertainty_score":0.013819814},"labels":[],"label_agreement":null},{"id":"W4366439428","doi":"10.1186/s12911-023-02169-5","title":"Cardiovascular disease incidence prediction by machine learning and statistical techniques: a 16-year cohort study from eastern Mediterranean region","year":2023,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Isfahan University of Medical Sciences","keywords":"Incidence (geometry); Health informatics; Cohort; Disease; Mediterranean climate; Medicine; Computer science; Artificial intelligence; Geography; Public health; Internal medicine; Pathology","score_opus":0.10956120472515134,"score_gpt":0.444043470851605,"score_spread":0.33448226612645365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366439428","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99947804,0.00007347875,0.00010418061,0.000030232908,0.000004539651,0.000012073314,0.00022108968,0.0000022081404,0.0000742513],"genre_scores_gemma":[0.9985751,0.00011027904,0.00043735292,0.000032527863,0.000014600455,0.000025266521,0.00059527374,0.000002663138,0.0002069253],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99940133,0.00020052756,0.00005365058,0.00014784171,0.00010522441,0.00009153649],"domain_scores_gemma":[0.9989618,0.00020850469,0.0002416269,0.000214815,0.00020212533,0.0001711998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025327504,0.000410588,0.00042990214,0.0010211295,0.0005154538,0.0005704617,0.000571545,0.00058334385,0.00088974426],"category_scores_gemma":[0.0022834386,0.00044251196,0.0011440564,0.001070923,0.00023865544,0.000503492,0.00054007594,0.00074112613,0.0002595972],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112838796,0.000084752144,0.99801046,0.000004457089,0.00010027308,0.00006335009,0.00014608525,0.00006694116,0.00006624739,0.0000128206275,0.00010991312,0.0012219292],"study_design_scores_gemma":[0.00001853177,0.00013020185,0.9982486,0.000008125114,0.00007121176,0.00009063534,0.0003527969,0.00086262275,0.00003511836,0.000022714785,0.00015476781,0.000004616774],"about_ca_topic_score_codex":0.020900598,"about_ca_topic_score_gemma":0.022105252,"teacher_disagreement_score":0.020900598,"about_ca_system_score_codex":0.00052979327,"about_ca_system_score_gemma":0.000601454,"threshold_uncertainty_score":0.041557908},"labels":[],"label_agreement":null},{"id":"W4366967359","doi":"10.1109/wi-iat55865.2022.00086","title":"MediBox: An Integrated Web Service System for Personalized Medical Assistance","year":2022,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"Lakehead University","keywords":"Upload; Medical prescription; Soundness; Service (business); Medical history; Internet privacy; Work (physics); Bridge (graph theory); Medicine; Computer science; Medical record; Medical emergency; World Wide Web; Business; Nursing; Engineering; Surgery","score_opus":0.1899992785962264,"score_gpt":0.4951490043823202,"score_spread":0.3051497257860938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366967359","genre_codex":"software","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032970484,0.0019329295,0.257155,0.0026928748,0.0007928056,0.0011521928,0.015461607,0.6563261,0.03151604],"genre_scores_gemma":[0.5157677,0.0040091635,0.2636948,0.0077746864,0.0017094152,0.0016425016,0.061687432,0.02012799,0.12358639],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995443,0.00008604226,0.000051503175,0.00009160723,0.0001751214,0.000051383766],"domain_scores_gemma":[0.9989209,0.00027395485,0.00008457582,0.0002517778,0.00015187843,0.00031698198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010141274,0.0007328937,0.00073165674,0.0012309279,0.0004800702,0.0016518019,0.0015744983,0.001407004,0.040282566],"category_scores_gemma":[0.00232629,0.00041426596,0.0005377418,0.00072323397,0.0003248354,0.0027572708,0.0026579152,0.0009376776,0.01918654],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0046709124,0.0010004399,0.007220086,0.0012616065,0.00034942303,0.0013504555,0.000666274,0.0028281359,0.03519577,0.008268028,0.43366924,0.50351965],"study_design_scores_gemma":[0.0011816979,0.0009846168,0.013288329,0.0004169365,0.0003155006,0.0029193745,0.00050195586,0.15614055,0.043695133,0.020686911,0.7593355,0.00053351757],"about_ca_topic_score_codex":0.0014303657,"about_ca_topic_score_gemma":0.0012863948,"teacher_disagreement_score":0.040282566,"about_ca_system_score_codex":0.0006043985,"about_ca_system_score_gemma":0.00074067817,"threshold_uncertainty_score":0.13475865},"labels":[],"label_agreement":null},{"id":"W4367601161","doi":"10.1164/ajrccm-conference.2023.207.1_meetingabstracts.a1650","title":"Machine Learning Based Model to Predict COVID-19 Mortality Using Clinical Data and Serum Cytokine Levels","year":2023,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Computer science; Data modeling; Cytokine; Artificial intelligence; Machine learning; Medicine; Immunology; Internal medicine; Infectious disease (medical specialty)","score_opus":0.817430937144851,"score_gpt":0.6556430566611307,"score_spread":0.1617878804837204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367601161","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75618804,0.0024488084,0.22505206,0.0026779713,0.0006692426,0.00025658763,0.004397856,0.0016858758,0.006623588],"genre_scores_gemma":[0.98154587,0.00036250564,0.010856559,0.0001735651,0.000091493086,0.00015587146,0.0014954315,0.0000145344075,0.0053041927],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997714,0.000052337502,0.000023525856,0.000066785986,0.00003776969,0.000048182286],"domain_scores_gemma":[0.99926394,0.00043613467,0.000059768197,0.000026206439,0.00018140738,0.000032475884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092487584,0.0006528125,0.00076350727,0.0010174521,0.00034571812,0.0008192866,0.00077113777,0.00087529165,0.0028352407],"category_scores_gemma":[0.0016060118,0.00024594847,0.00093525526,0.00053358194,0.00018593231,0.00038294282,0.00033308056,0.0009918044,0.0008871243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015168575,0.0015056935,0.08368657,0.00018166624,0.0006490929,0.00048546126,0.000103251994,0.7514954,0.0035702032,0.0013141285,0.006271533,0.14922018],"study_design_scores_gemma":[0.00001542548,0.0000943659,0.0032399856,0.000008886351,0.00003758717,0.000033792516,0.00000977303,0.9957451,0.0002908599,0.0003107037,0.00020749622,0.0000060118086],"about_ca_topic_score_codex":0.011850335,"about_ca_topic_score_gemma":0.008176417,"teacher_disagreement_score":0.011850335,"about_ca_system_score_codex":0.0006854502,"about_ca_system_score_gemma":0.0011222652,"threshold_uncertainty_score":0.02356273},"labels":[],"label_agreement":null},{"id":"W4367601292","doi":"10.1164/ajrccm-conference.2023.207.1_meetingabstracts.a4281","title":"Unsupervised Clustering of Plasma Protein Biomarkers, Clinical Features, and Whole Blood Gene Expression Captures Prognostic and Predictive Heterogeneity in Critically Ill Patients With Sepsis","year":2023,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Sepsis; Critically ill; Biomarker; Cluster analysis; Severe sepsis; Medicine; Intensive care medicine; Bioinformatics; Computer science; Computational biology; Internal medicine; Machine learning; Biology; Septic shock","score_opus":0.07171695921255984,"score_gpt":0.40214796180059925,"score_spread":0.3304310025880394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367601292","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.996494,0.00026046374,0.002466394,0.00011139912,0.000017796054,0.000017787806,0.00029398027,0.00002822785,0.00030995088],"genre_scores_gemma":[0.99797136,0.0000663269,0.0011129027,0.000043332097,0.000019194751,0.000014173827,0.0006478798,0.000009566932,0.00011526378],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994198,0.00019990727,0.000055108303,0.00013896982,0.00007083398,0.00011526244],"domain_scores_gemma":[0.99859375,0.0005858633,0.0002883624,0.00017599558,0.00024240947,0.00011372214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076630694,0.00029902134,0.0008272774,0.0011052939,0.00039736443,0.0009478954,0.00045012933,0.00059909513,0.0005411181],"category_scores_gemma":[0.0034131971,0.00014535787,0.0005037961,0.0008670978,0.00035922977,0.00039098665,0.000501564,0.0005189889,0.00026072605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035486785,0.00044411942,0.9102244,0.00009864516,0.00061827165,0.0003051477,0.0006048104,0.0077907187,0.018186051,0.0003826616,0.002310482,0.055486046],"study_design_scores_gemma":[0.00006911444,0.00038046655,0.9340597,0.000039701576,0.00021662055,0.0005125133,0.0009703289,0.057950042,0.0020669953,0.0028406768,0.0008417751,0.000052154744],"about_ca_topic_score_codex":0.0023714686,"about_ca_topic_score_gemma":0.0027388379,"teacher_disagreement_score":0.0023714686,"about_ca_system_score_codex":0.000344429,"about_ca_system_score_gemma":0.00044736578,"threshold_uncertainty_score":0.004715383},"labels":[],"label_agreement":null},{"id":"W4367692322","doi":"10.1155/2023/6864343","title":"Machine Learning‐Based Model to Predict Heart Disease in Early Stage Employing Different Feature Selection Techniques","year":2023,"lang":"en","type":"article","venue":"BioMed Research International","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Education – Kingdom of Saudi Arabi","keywords":"Feature selection; Computer science; Artificial intelligence; Selection (genetic algorithm); Machine learning; Model selection; Feature (linguistics); Stage (stratigraphy); Heart disease; Pattern recognition (psychology); Medicine; Biology; Internal medicine","score_opus":0.31588708047710323,"score_gpt":0.5661686835794968,"score_spread":0.25028160310239356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367692322","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32165626,0.0034365123,0.66630614,0.0013898701,0.00030082313,0.00035035412,0.0014123581,0.0014600819,0.003687587],"genre_scores_gemma":[0.94988316,0.0008162108,0.044512462,0.00016652327,0.00010476791,0.00031975223,0.0011615872,0.00002416628,0.0030113466],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996145,0.00009769761,0.000037484715,0.00008937126,0.00009723277,0.00006364487],"domain_scores_gemma":[0.9995289,0.0002539159,0.00004287676,0.000017578572,0.00014029819,0.000016546914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011746712,0.00079790683,0.000857832,0.0010058115,0.0002934889,0.00072008045,0.0008123937,0.00064257893,0.0011589895],"category_scores_gemma":[0.0015570378,0.0002008214,0.0012279517,0.000633583,0.00016813654,0.00047183796,0.0002942967,0.0006833017,0.00043626621],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060515763,0.00055539224,0.043714263,0.00024707202,0.00040435191,0.0005430691,0.00011763614,0.70479226,0.007869366,0.0015737335,0.004635312,0.23494244],"study_design_scores_gemma":[0.00001444619,0.00010605331,0.0030311416,0.000015905911,0.000051938754,0.000066000386,0.000011010213,0.9950635,0.00066584424,0.00051865005,0.00044336816,0.000012139925],"about_ca_topic_score_codex":0.006807177,"about_ca_topic_score_gemma":0.0041760146,"teacher_disagreement_score":0.006807177,"about_ca_system_score_codex":0.00043849615,"about_ca_system_score_gemma":0.0009114471,"threshold_uncertainty_score":0.013535142},"labels":[],"label_agreement":null},{"id":"W4368341782","doi":"10.1016/j.cosrev.2023.100558","title":"Leveraging 6G, extended reality, and IoT big data analytics for healthcare: A review","year":2023,"lang":"en","type":"review","venue":"Computer Science Review","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":84,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Ministry of Education – Kingdom of Saudi Arabi","keywords":"Computer science; Big data; Data science; Analytics; Internet of Things; Health care; World Wide Web; Data mining","score_opus":0.8586978192979458,"score_gpt":0.6437188803933398,"score_spread":0.21497893890460595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4368341782","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013068561,0.9979448,0.00028862662,0.00056540477,0.0002583938,0.000010229998,0.000041852487,0.000007740382,0.000752307],"genre_scores_gemma":[0.000712047,0.9981838,0.00031276152,0.00034985834,0.00021595131,0.000007663809,0.00004098315,0.0000015464607,0.00017548213],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99961346,0.00007825527,0.00006555404,0.00006571223,0.00014305832,0.000033962966],"domain_scores_gemma":[0.9981592,0.001154666,0.00016714615,0.000032973032,0.0004114743,0.00007443937],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014386374,0.00091220596,0.0014316154,0.0025769803,0.00026748815,0.0012653478,0.0010144395,0.001142413,0.0044235415],"category_scores_gemma":[0.002630364,0.00032766644,0.00096908695,0.0032166752,0.000404814,0.0022832006,0.001011588,0.0013445677,0.0013858639],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077835655,0.00008275865,0.0003881997,0.028240902,0.00017541504,0.00013296638,0.000054267974,0.00047484107,0.001010954,0.004057694,0.03062829,0.9346758],"study_design_scores_gemma":[0.000031872172,0.00022683963,0.0012992168,0.015549374,0.00058650103,0.00077960995,0.00016292077,0.00043499598,0.0005981802,0.0032795647,0.9769931,0.000057812977],"about_ca_topic_score_codex":0.00199252,"about_ca_topic_score_gemma":0.0035186936,"teacher_disagreement_score":0.0044235415,"about_ca_system_score_codex":0.00048472593,"about_ca_system_score_gemma":0.0018135847,"threshold_uncertainty_score":0.014798164},"labels":[],"label_agreement":null},{"id":"W4372311241","doi":"10.1016/j.dajour.2023.100242","title":"A novel machine learning model with Stacking Ensemble Learner for predicting emergency readmission of heart-disease patients","year":2023,"lang":"en","type":"article","venue":"Decision Analytics Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":104,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Ryerson University","keywords":"Machine learning; Artificial intelligence; Ensemble learning; Heart disease; Computer science; Emergency department; Disease; Ensemble forecasting; Robustness (evolution); Overcrowding; Novelty; Medical emergency; Medicine; Cardiology; Internal medicine; Psychology","score_opus":0.21207801563382717,"score_gpt":0.4805615421646227,"score_spread":0.26848352653079555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4372311241","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20889299,0.001932817,0.78233355,0.0014540545,0.00024095496,0.00014879445,0.00064449693,0.0012150314,0.0031372448],"genre_scores_gemma":[0.91641176,0.00068212074,0.076357365,0.0005268143,0.00016966862,0.0002284426,0.001076467,0.000047717233,0.004499692],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951506,0.00015574778,0.000030790736,0.00014007966,0.00008469088,0.0000736611],"domain_scores_gemma":[0.998809,0.0005535003,0.00011086171,0.000057573896,0.00040025974,0.00006877746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019036843,0.0010129557,0.0012289047,0.00090322475,0.00045127966,0.00093315734,0.0015468319,0.0011576418,0.0011381849],"category_scores_gemma":[0.0032099627,0.00029572047,0.0009896825,0.00058343,0.00027617265,0.0010357986,0.00077125576,0.0015336148,0.00053356134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020420944,0.00030962285,0.02230803,0.00005213589,0.0002743356,0.00018235328,0.00009212441,0.8366741,0.0012887381,0.0015851924,0.004468657,0.13256058],"study_design_scores_gemma":[0.0000039246543,0.000035693734,0.00048787898,0.000004721768,0.000016112548,0.000014399582,0.000007176378,0.9986557,0.00020544497,0.0004040366,0.00015942343,0.0000054385687],"about_ca_topic_score_codex":0.008090763,"about_ca_topic_score_gemma":0.0070684557,"teacher_disagreement_score":0.008090763,"about_ca_system_score_codex":0.00052146777,"about_ca_system_score_gemma":0.0011347157,"threshold_uncertainty_score":0.016087353},"labels":[],"label_agreement":null},{"id":"W4372324595","doi":"10.54691/bcpbm.v44i.4860","title":"Titanic Disaster Prediction Based on Machine Learning Algorithms","year":2023,"lang":"en","type":"article","venue":"BCP Business & Management","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Ticket; Random forest; Machine learning; Class (philosophy); Decision tree; Artificial intelligence; Feature (linguistics); Algorithm; Computer science; Space (punctuation); Tree (set theory); Mathematics; Computer security","score_opus":0.12022757046303462,"score_gpt":0.42298964518927396,"score_spread":0.30276207472623934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4372324595","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52637976,0.0027087089,0.45530993,0.0017046628,0.00038082045,0.00029310267,0.002227845,0.0029759263,0.008019274],"genre_scores_gemma":[0.9245894,0.00051813904,0.070320226,0.000113894646,0.00009023765,0.000110647125,0.0022689712,0.000039624956,0.0019488387],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930704,0.00019056624,0.00006848363,0.00017983474,0.00014204829,0.00011210036],"domain_scores_gemma":[0.998185,0.0011619661,0.00015065515,0.00007236113,0.0003643806,0.00006571376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011486225,0.0009049541,0.0008000817,0.002333116,0.000515907,0.0009938191,0.0007569996,0.00080236414,0.0016815437],"category_scores_gemma":[0.0038205544,0.00021082377,0.0009803333,0.0015353025,0.00023612817,0.0009031662,0.0003942861,0.0009228262,0.00048380316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021293132,0.00028759782,0.032025233,0.00012521048,0.00015692502,0.00020346668,0.00007233129,0.7616894,0.00078431994,0.00143118,0.004940364,0.19807102],"study_design_scores_gemma":[0.0000039426827,0.000021990056,0.0016176774,0.000009385287,0.000009995084,0.000018142186,0.000029566623,0.99690646,0.00025350007,0.00083571096,0.00028792705,0.0000057041043],"about_ca_topic_score_codex":0.01490908,"about_ca_topic_score_gemma":0.007693,"teacher_disagreement_score":0.01490908,"about_ca_system_score_codex":0.00068185764,"about_ca_system_score_gemma":0.00105113,"threshold_uncertainty_score":0.029644608},"labels":[],"label_agreement":null},{"id":"W4376477583","doi":"10.2139/ssrn.4414662","title":"Integrating Unsupervised and Supervised Learning Techniques to Predict Traumatic Brain Injury: A Population-Based Study","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"","keywords":"Traumatic brain injury; Unsupervised learning; Supervised learning; Population; Psychology; Artificial intelligence; Machine learning; Computer science; Medicine; Psychiatry; Artificial neural network","score_opus":0.12604016354915953,"score_gpt":0.4638827457262444,"score_spread":0.33784258217708485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376477583","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9994456,0.00004052588,0.0002735999,0.000020548781,0.0000053401313,0.0000111954505,0.0000816688,0.0000033881392,0.00011812766],"genre_scores_gemma":[0.9989838,0.000075788186,0.00024716218,0.0000304976,0.00001808395,0.000021800288,0.00030682073,0.000007414967,0.00030857348],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983333,0.00073544256,0.00012092533,0.0004325143,0.00024410844,0.00013379521],"domain_scores_gemma":[0.99609816,0.001581621,0.00057997106,0.00056969695,0.0008740253,0.00029646247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033157635,0.00071010744,0.0007299759,0.0012376833,0.0009789477,0.0011267569,0.00077034824,0.0013742566,0.0016394422],"category_scores_gemma":[0.009065946,0.000603699,0.0013586651,0.0011310417,0.0008953618,0.0014320728,0.0008177669,0.0015382707,0.0006785622],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006783958,0.0017188311,0.98974717,0.000016723243,0.00042974835,0.00013326226,0.0007639832,0.00016998158,0.00035256255,0.0000334538,0.00030571307,0.0056502833],"study_design_scores_gemma":[0.000082941624,0.0025588297,0.9918819,0.000012705217,0.00036705122,0.0005251434,0.0017667648,0.002197957,0.00013181982,0.00013393805,0.00031161678,0.000029315997],"about_ca_topic_score_codex":0.0066918368,"about_ca_topic_score_gemma":0.006851931,"teacher_disagreement_score":0.0066918368,"about_ca_system_score_codex":0.00039815917,"about_ca_system_score_gemma":0.00045580245,"threshold_uncertainty_score":0.017535627},"labels":[],"label_agreement":null},{"id":"W4376638873","doi":"10.18280/isi.280225","title":"A Hybrid Resampling Method with K-Nearest Neighbour (FHR-KNN) for Imbalanced Preeclampsia Dataset","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Universitas Diponegoro","keywords":"Resampling; k-nearest neighbors algorithm; Pattern recognition (psychology); Artificial intelligence; Nearest neighbour; Preeclampsia; Computer science; Biology; Pregnancy; Genetics","score_opus":0.10693515518083856,"score_gpt":0.43150770948141504,"score_spread":0.32457255430057647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376638873","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36906657,0.0022216868,0.6187937,0.00058976957,0.0005260355,0.00057978666,0.0016716823,0.003586563,0.0029641974],"genre_scores_gemma":[0.72635484,0.0005490989,0.26739466,0.00016213696,0.0001049713,0.0003200746,0.0029349986,0.00007938451,0.0020998276],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852306,0.0003519634,0.00013805777,0.0004114088,0.00045256526,0.00012294673],"domain_scores_gemma":[0.99899775,0.000315632,0.00011503261,0.0001737774,0.0003570819,0.000040720824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002220315,0.00078117626,0.0008935746,0.0014775919,0.0005484609,0.00070106547,0.0009153786,0.00071592565,0.00047998028],"category_scores_gemma":[0.0037966154,0.00017659589,0.00086174393,0.0008968376,0.00024353847,0.00077408575,0.0005197701,0.0006176061,0.00032117587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001087164,0.0006220332,0.030546213,0.00039957403,0.00031570945,0.00063412177,0.00039622822,0.18824163,0.02156413,0.0021480122,0.010350416,0.7436948],"study_design_scores_gemma":[0.000035039087,0.0003346787,0.010775265,0.00003487437,0.00006381393,0.0002801266,0.00015864872,0.96588314,0.014867667,0.0017413637,0.0057710777,0.00005431097],"about_ca_topic_score_codex":0.008106971,"about_ca_topic_score_gemma":0.00982858,"teacher_disagreement_score":0.008106971,"about_ca_system_score_codex":0.0005659396,"about_ca_system_score_gemma":0.0008577078,"threshold_uncertainty_score":0.0161196},"labels":[],"label_agreement":null},{"id":"W4376638890","doi":"10.18280/isi.280205","title":"Selection of Features Using Adaptive Tunicate Swarm Algorithm with Optimized Deep Learning Model for Thyroid Disease Classification","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Tunicate; Artificial intelligence; Selection (genetic algorithm); Computer science; Swarm behaviour; Deep learning; Algorithm; Machine learning; Feature selection; Pattern recognition (psychology); Biology","score_opus":0.12249767950229538,"score_gpt":0.39169461625248464,"score_spread":0.26919693675018924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376638890","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19122738,0.0017682115,0.80113685,0.00096095155,0.00023355344,0.00014064544,0.00022535044,0.0012468798,0.0030601614],"genre_scores_gemma":[0.89334804,0.00042074654,0.10143661,0.0003827621,0.00008084345,0.00023690188,0.0006715612,0.0000635139,0.0033589804],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99970466,0.0000693766,0.0000288,0.00007732871,0.00005748819,0.00006236904],"domain_scores_gemma":[0.9996183,0.00018988423,0.00003359252,0.000018736826,0.00011388811,0.000025513642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007181273,0.00094100076,0.0011644879,0.00073803565,0.0003682635,0.0008188336,0.0011280591,0.0012045875,0.0011219942],"category_scores_gemma":[0.0017025596,0.00042108432,0.0011904837,0.000512603,0.00044185272,0.0004904458,0.00068858213,0.001192007,0.00022775712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016005867,0.00011936412,0.004184903,0.00007107594,0.00010702609,0.00018720108,0.00008308066,0.8855041,0.0023363507,0.0010797357,0.0022171068,0.10394993],"study_design_scores_gemma":[0.0000051153747,0.000014017137,0.00016173086,0.0000028152963,0.0000047296494,0.0000058698033,0.000004658615,0.9993767,0.00015106937,0.00019194004,0.000079422556,0.0000019679069],"about_ca_topic_score_codex":0.018606162,"about_ca_topic_score_gemma":0.011663609,"teacher_disagreement_score":0.018606162,"about_ca_system_score_codex":0.0007862584,"about_ca_system_score_gemma":0.0012307713,"threshold_uncertainty_score":0.03699571},"labels":[],"label_agreement":null},{"id":"W4376638934","doi":"10.18280/isi.280203","title":"An Overview on Related Searches Recommendation","year":2023,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Information retrieval; Computer science; Data science","score_opus":0.23909513328206752,"score_gpt":0.4577942841479612,"score_spread":0.21869915086589367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376638934","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007296605,0.7181147,0.20146157,0.0034090814,0.0018920429,0.0006990439,0.0024258138,0.0015332954,0.063167796],"genre_scores_gemma":[0.04333738,0.7367548,0.17144036,0.0025438855,0.004417184,0.0006301391,0.008388368,0.00028532906,0.03220258],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980046,0.00047406473,0.00021647026,0.00040624812,0.0007863459,0.00011211003],"domain_scores_gemma":[0.99739397,0.0011860282,0.00013680424,0.0003340266,0.0008430512,0.000106011146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018813736,0.0014580633,0.0016723466,0.008790831,0.00093550165,0.0025204709,0.0021442103,0.0022656906,0.013679644],"category_scores_gemma":[0.0057003614,0.0009290808,0.0016957838,0.01703503,0.00042113246,0.0044727456,0.0011596223,0.0015531295,0.013749517],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012619603,0.0003277149,0.0023811965,0.004743044,0.00021361146,0.00021750489,0.00019897947,0.0053616664,0.0021629515,0.022754464,0.06634054,0.8951721],"study_design_scores_gemma":[0.00005548184,0.00036585573,0.0037785657,0.0026449903,0.00040897648,0.0016043619,0.00024071865,0.036329344,0.0026844954,0.02814944,0.92357165,0.00016621638],"about_ca_topic_score_codex":0.008883178,"about_ca_topic_score_gemma":0.0068118502,"teacher_disagreement_score":0.013679644,"about_ca_system_score_codex":0.0012688417,"about_ca_system_score_gemma":0.0014730527,"threshold_uncertainty_score":0.045763016},"labels":[],"label_agreement":null},{"id":"W4376853397","doi":"10.23977/jaip.2023.060304","title":"Design of an intelligent prevention and control platform for major public health emergencies based on a new generation of information technology","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Practice","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pandemic; Social media; Public health; Business; Health care; Computer security; Civilization; Internet privacy; Computer science; Engineering; Medicine; Coronavirus disease 2019 (COVID-19); Political science; Economic growth; Nursing; World Wide Web; Economics","score_opus":0.37948871531401235,"score_gpt":0.5027440124431911,"score_spread":0.12325529712917876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376853397","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07935265,0.00050732365,0.89079326,0.0005873204,0.00037767706,0.0016957137,0.00020836909,0.007525492,0.018952318],"genre_scores_gemma":[0.60840416,0.0005367199,0.37487632,0.00058166956,0.00007751948,0.0012506759,0.00049956876,0.00024250649,0.013530945],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995828,0.000052518655,0.000041638294,0.00010593965,0.00014225833,0.00007481902],"domain_scores_gemma":[0.9997253,0.00003966269,0.000040827617,0.00003279331,0.000108182685,0.00005319581],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004828907,0.00056045695,0.00042230813,0.00045944232,0.00046969767,0.0011821594,0.001390066,0.00075064506,0.002482423],"category_scores_gemma":[0.00060690433,0.00035733174,0.00060594344,0.00019088287,0.00031181422,0.0008899443,0.00083006243,0.0006213875,0.00077844085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013699154,0.0014040917,0.01818296,0.0016624994,0.0004915393,0.004422749,0.0015810862,0.12106651,0.38144264,0.044596486,0.021175751,0.40260375],"study_design_scores_gemma":[0.00028569697,0.0016010153,0.010316394,0.00015978594,0.0004974806,0.0011835318,0.0004216497,0.79104996,0.09570106,0.0071868272,0.09140985,0.00018675275],"about_ca_topic_score_codex":0.0016793356,"about_ca_topic_score_gemma":0.001525248,"teacher_disagreement_score":0.002482423,"about_ca_system_score_codex":0.000349992,"about_ca_system_score_gemma":0.0010963446,"threshold_uncertainty_score":0.008304477},"labels":[],"label_agreement":null},{"id":"W4377027740","doi":"10.1177/22925503231176010","title":"An Approach to “Big Data”","year":2023,"lang":"en","type":"article","venue":"Plastic Surgery","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; McMaster University","funders":"","keywords":"Big data; Computer science; Data science; Data mining","score_opus":0.6083145185833758,"score_gpt":0.510966684242691,"score_spread":0.09734783434068484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377027740","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026990364,0.0018930295,0.955004,0.026217256,0.0023646515,0.00024076959,0.0010930102,0.00072715484,0.009760971],"genre_scores_gemma":[0.15291668,0.0034553006,0.81687087,0.012271275,0.004734467,0.000804074,0.0023576466,0.00037976625,0.006210002],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98525256,0.007901071,0.0010362789,0.0014972914,0.0038778584,0.0004349468],"domain_scores_gemma":[0.9422621,0.031225555,0.0020526664,0.015229552,0.0073828544,0.0018472722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0160195,0.0011407156,0.001633421,0.0045470246,0.0027580264,0.008616293,0.004646492,0.003100861,0.00552733],"category_scores_gemma":[0.052752633,0.00090713566,0.0027084772,0.0066707768,0.006396392,0.016965466,0.011034876,0.0060712434,0.0013933437],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012274232,0.0000940427,0.0023653212,0.00056417973,0.0002276581,0.00021630508,0.00057452347,0.008440721,0.0005051365,0.8696119,0.036022533,0.08125491],"study_design_scores_gemma":[0.000019846242,0.00002371432,0.00030592838,0.000141775,0.000043200682,0.0001166986,0.00047061883,0.039842267,0.0004415863,0.9095295,0.049035057,0.000029800409],"about_ca_topic_score_codex":0.0024927265,"about_ca_topic_score_gemma":0.0025454392,"teacher_disagreement_score":0.0160195,"about_ca_system_score_codex":0.0019243393,"about_ca_system_score_gemma":0.004003859,"threshold_uncertainty_score":0.084720254},"labels":[],"label_agreement":null},{"id":"W4377232862","doi":"10.1117/12.2673747","title":"The classification of patient blood samples with machine learning techniques","year":2023,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Payment; Health care; Artificial intelligence; Healthcare system; Machine learning; Variety (cybernetics)","score_opus":0.18778777981299005,"score_gpt":0.46393405443808977,"score_spread":0.2761462746250997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377232862","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43513727,0.0034916983,0.55105495,0.0011606622,0.0005660992,0.00036238818,0.0010659025,0.001789858,0.005371243],"genre_scores_gemma":[0.76159436,0.0011225484,0.23312037,0.00024059326,0.0001591945,0.00016415925,0.001214332,0.000030735435,0.0023536906],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853635,0.0004531811,0.00021107303,0.00024390883,0.00043365374,0.00012183997],"domain_scores_gemma":[0.99808145,0.0010183167,0.00020933023,0.00014492638,0.0005097771,0.000036187426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015959432,0.00062779867,0.00066725694,0.0026764737,0.00034947475,0.0011568355,0.0005577413,0.00082472176,0.0005691558],"category_scores_gemma":[0.004838558,0.00019313139,0.00069710705,0.0017364994,0.0002769101,0.0007841629,0.0003321844,0.00079745374,0.0006236432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000574346,0.00065511133,0.070268795,0.0003059468,0.00020853573,0.0003247806,0.0002418102,0.036404613,0.019676058,0.0018809292,0.0039561335,0.8655029],"study_design_scores_gemma":[0.000035353904,0.0006082955,0.043865323,0.00010767888,0.00010812136,0.0006756219,0.0003925096,0.906042,0.036932696,0.005163916,0.005994153,0.00007426262],"about_ca_topic_score_codex":0.0017811923,"about_ca_topic_score_gemma":0.0011509351,"teacher_disagreement_score":0.0026764737,"about_ca_system_score_codex":0.00036756764,"about_ca_system_score_gemma":0.00055770646,"threshold_uncertainty_score":0.008440256},"labels":[],"label_agreement":null},{"id":"W4378187052","doi":"10.18280/ria.370226","title":"Prediction of Chronic Kidney Disease with Machine Learning Models and Feature Analysis Using SHAP","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Feature (linguistics); Kidney disease; Artificial intelligence; Computer science; Medicine; Internal medicine","score_opus":0.19613651305828764,"score_gpt":0.4097559467544276,"score_spread":0.21361943369613998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378187052","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39686587,0.004980585,0.5858845,0.0015554898,0.000513271,0.00029931442,0.0032585629,0.0030976604,0.003544726],"genre_scores_gemma":[0.93935704,0.00083604275,0.05597423,0.00012930737,0.00017613816,0.00013201174,0.0022943234,0.000031516225,0.0010694262],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999158,0.00023288655,0.00009491437,0.00020450265,0.00020319682,0.00010649997],"domain_scores_gemma":[0.99853015,0.00088510383,0.00016669686,0.000088040826,0.00028653428,0.000043581542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001613337,0.0008476207,0.0010643698,0.0019251866,0.00031644112,0.001171051,0.0006021802,0.0007758407,0.0010646305],"category_scores_gemma":[0.004990413,0.00021875415,0.0014422656,0.0013171679,0.00017176126,0.00084468187,0.0004892456,0.0010843736,0.0006057096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074431335,0.0008662219,0.14379987,0.00031264868,0.0006266375,0.00048459822,0.00012024116,0.33391535,0.004457387,0.0017959408,0.0104568135,0.50242],"study_design_scores_gemma":[0.000009506126,0.00011802442,0.007947397,0.00003357382,0.00004845736,0.000095733165,0.00003324425,0.98914427,0.0008112036,0.0012069282,0.0005332362,0.00001836964],"about_ca_topic_score_codex":0.008024457,"about_ca_topic_score_gemma":0.003999359,"teacher_disagreement_score":0.008024457,"about_ca_system_score_codex":0.00046926088,"about_ca_system_score_gemma":0.0007336945,"threshold_uncertainty_score":0.015955508},"labels":[],"label_agreement":null},{"id":"W4378418319","doi":"10.18280/ria.370220","title":"An Intelligent Evolutionary Schema on Precision Medicine for Diabetes Using Big Data Analytics","year":2023,"lang":"fr","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Schema (genetic algorithms); Big data; Computer science; Analytics; Data science; Data analysis; Precision medicine; Diabetes mellitus; Data mining; Machine learning; Medicine; Endocrinology","score_opus":0.5535323450164978,"score_gpt":0.5117232649872918,"score_spread":0.041809080029206025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378418319","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026848732,0.0008230717,0.93543917,0.005329928,0.0002828169,0.00030754754,0.00028855348,0.00092560786,0.029754525],"genre_scores_gemma":[0.23444088,0.0008375328,0.75030905,0.00087696867,0.00010599483,0.00020144442,0.000562634,0.00008874335,0.0125768],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991246,0.00020100098,0.00007393714,0.00023625187,0.00028847248,0.000075706324],"domain_scores_gemma":[0.999213,0.00018199958,0.00007366918,0.0001480387,0.00028655198,0.00009672112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012827158,0.00037272065,0.0003521461,0.0012776161,0.0013780015,0.0021274388,0.0014822868,0.0011356382,0.003675478],"category_scores_gemma":[0.0027395152,0.00023458854,0.0008898701,0.0013195574,0.00096263795,0.0024019834,0.002013538,0.00099141,0.00066265796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012565304,0.00029898557,0.010972135,0.0002766816,0.00011212248,0.0008383515,0.0013852655,0.054055437,0.006909643,0.44554472,0.018442227,0.4610389],"study_design_scores_gemma":[0.000055127075,0.00016854718,0.0051404717,0.00021269146,0.0001389876,0.0011279322,0.00089430896,0.6341659,0.009828172,0.22310512,0.1250852,0.00007763458],"about_ca_topic_score_codex":0.006636629,"about_ca_topic_score_gemma":0.007018558,"teacher_disagreement_score":0.006636629,"about_ca_system_score_codex":0.001318298,"about_ca_system_score_gemma":0.0025252744,"threshold_uncertainty_score":0.0131959915},"labels":[],"label_agreement":null},{"id":"W4378418351","doi":"10.18280/ria.370222","title":"Smart Health Monitoring Using Deep Learning and Artificial Intelligence","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Deep learning; Artificial intelligence; Computer science; Psychology","score_opus":0.2813323118952614,"score_gpt":0.4868245829503897,"score_spread":0.2054922710551283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378418351","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020057853,0.0063227494,0.96182215,0.002287485,0.00026310515,0.000087410925,0.0004927537,0.0020641487,0.006602265],"genre_scores_gemma":[0.7024857,0.0066846604,0.27890825,0.0013096444,0.00044229784,0.00026037305,0.00198345,0.00016466172,0.007760974],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994999,0.000121572244,0.000044791712,0.00012816681,0.00014069246,0.00006480441],"domain_scores_gemma":[0.99932516,0.00033339593,0.00007940113,0.00006518278,0.00015976036,0.00003710463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010606105,0.0008833042,0.00086671027,0.0011328371,0.00030269913,0.0015394797,0.001290281,0.0011437192,0.0018809582],"category_scores_gemma":[0.0027564506,0.0004827929,0.0008131019,0.0011706755,0.0005755731,0.0014468059,0.0013452985,0.0018578547,0.0006541621],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014208216,0.00023117109,0.0050770994,0.00033791838,0.00025577255,0.00018903943,0.0000920079,0.461908,0.0032810587,0.011893301,0.009684597,0.5069079],"study_design_scores_gemma":[0.000004869446,0.000020875697,0.000420153,0.000030798044,0.000012779217,0.000022379638,0.000011445803,0.98815584,0.00060940976,0.009067177,0.001635374,0.000008891823],"about_ca_topic_score_codex":0.007942475,"about_ca_topic_score_gemma":0.0069539957,"teacher_disagreement_score":0.007942475,"about_ca_system_score_codex":0.0010725412,"about_ca_system_score_gemma":0.00090307806,"threshold_uncertainty_score":0.015792489},"labels":[],"label_agreement":null},{"id":"W4379197097","doi":"10.1177/14604582231180581","title":"Breaking the 80:20 rule in health research using large administrative data sets","year":2023,"lang":"en","type":"article","venue":"Health Informatics Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Alberta Bone and Joint Health Institute; University of Calgary","funders":"Canadian Institutes of Health Research; Canada Foundation for Innovation","keywords":"Online analytical processing; Data warehouse; Computer science; Data cube; Data mining; Leverage (statistics); Data science; Analytics; Health care; Population; Database; Medicine","score_opus":0.8455603265902553,"score_gpt":0.6929477354375245,"score_spread":0.15261259115273074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379197097","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18255718,0.011394105,0.6743054,0.081566125,0.003324884,0.002664454,0.005220222,0.0030090294,0.03595864],"genre_scores_gemma":[0.35251787,0.0035259945,0.61987156,0.013810844,0.0022454797,0.002338709,0.0029983427,0.00052919006,0.0021620037],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.72136974,0.1670274,0.031352162,0.025640106,0.05175264,0.0028579247],"domain_scores_gemma":[0.36931926,0.52565587,0.032999475,0.046947084,0.021096097,0.0039821533],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.28752556,0.0012179479,0.0034932785,0.0073732347,0.0043862164,0.020381993,0.0051878076,0.003816865,0.0020807497],"category_scores_gemma":[0.48529834,0.0017595397,0.0032685304,0.018645292,0.010326886,0.01646243,0.011865565,0.00925553,0.0021092952],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001529397,0.000889397,0.2119352,0.0035648048,0.0015085656,0.0023443028,0.0075353864,0.031897753,0.0021136366,0.17984536,0.04118149,0.51565474],"study_design_scores_gemma":[0.00044247793,0.0005465749,0.0429194,0.0027755816,0.00043250748,0.0016265245,0.0043492327,0.08899788,0.003723734,0.77073294,0.08318154,0.00027166193],"about_ca_topic_score_codex":0.009246422,"about_ca_topic_score_gemma":0.0063566365,"teacher_disagreement_score":0.28752556,"about_ca_system_score_codex":0.005331894,"about_ca_system_score_gemma":0.013730364,"threshold_uncertainty_score":0.8786078},"labels":[],"label_agreement":null},{"id":"W4379522898","doi":"10.21428/594757db.0041f830","title":"Meta-GCN: A Dynamically Weighted Loss Minimization Method for Dealing with the Data Imbalance in Graph Neural Networks","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Outlier; Computer science; Skewness; Graph; Artificial neural network; Minification; Artificial intelligence; Set (abstract data type); Data set; Pattern recognition (psychology); Machine learning; Data mining; Algorithm; Mathematics; Statistics; Theoretical computer science","score_opus":0.39606920742956825,"score_gpt":0.520168301933918,"score_spread":0.1240990945043498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379522898","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023560135,0.0009551428,0.97217226,0.00044103814,0.00010008039,0.000115974886,0.00015168547,0.0014871779,0.0010165429],"genre_scores_gemma":[0.458217,0.0005793528,0.53500426,0.0009726115,0.00020444422,0.00047016115,0.0010172239,0.00070890493,0.0028260362],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987804,0.00044844561,0.000050889474,0.00031775574,0.00029898912,0.00010351616],"domain_scores_gemma":[0.9980204,0.0009363077,0.00022152501,0.00030156516,0.0004172305,0.00010301329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035017892,0.0020583312,0.0018065537,0.0019651272,0.0008387651,0.0011568161,0.0039377464,0.002431365,0.001183981],"category_scores_gemma":[0.007603095,0.0008137686,0.0010683632,0.0019831085,0.001177962,0.0025346603,0.0021471821,0.0026529534,0.00044748967],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014614729,0.0001469788,0.0024639014,0.000109838336,0.00018160124,0.000099006065,0.00013994647,0.7750457,0.0028439146,0.005793789,0.0044200034,0.2086091],"study_design_scores_gemma":[0.000008336047,0.000023732315,0.0001023316,0.000008386042,0.00001156013,0.000016652779,0.000007908459,0.9951957,0.0003574429,0.0039022628,0.00036098287,0.0000046641226],"about_ca_topic_score_codex":0.00691528,"about_ca_topic_score_gemma":0.011543161,"teacher_disagreement_score":0.00691528,"about_ca_system_score_codex":0.0019381727,"about_ca_system_score_gemma":0.0016545863,"threshold_uncertainty_score":0.018519461},"labels":[],"label_agreement":null},{"id":"W4380077406","doi":"10.3389/fpubh.2023.1116682","title":"Enabling data sharing and utilization for African population health data using OHDSI tools with an OMOP-common data model","year":2023,"lang":"en","type":"article","venue":"Frontiers in Public Health","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"International Development Research Centre; Wellcome Trust; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Data sharing; Metadata; Computer science; Cloud computing; Reuse; Big data; Gateway (web page); Data science; Data access; World Wide Web; Database; Data mining; Engineering","score_opus":0.8149729577987126,"score_gpt":0.5759426356508224,"score_spread":0.23903032214789022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380077406","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016418273,0.0009228718,0.86276597,0.01624875,0.0010127339,0.0031795201,0.027423758,0.04223719,0.029790916],"genre_scores_gemma":[0.21225189,0.0014131727,0.70842785,0.003987744,0.00052322116,0.0033282961,0.05667633,0.0052918075,0.008099685],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.95652896,0.016675623,0.009221597,0.0062811538,0.008672718,0.002620009],"domain_scores_gemma":[0.9095613,0.02525907,0.005366068,0.04500673,0.010097665,0.004709134],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.06748233,0.00133582,0.0014931906,0.0075534936,0.002778818,0.013014799,0.006668619,0.0025063357,0.00916934],"category_scores_gemma":[0.12628043,0.0017077699,0.004523383,0.009209157,0.0026536235,0.019940574,0.03424326,0.00434478,0.0052446644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015149551,0.000736331,0.049339265,0.0018520362,0.0009281503,0.0018827613,0.012543504,0.023334462,0.0059258635,0.42439738,0.16765217,0.30989313],"study_design_scores_gemma":[0.00041650323,0.0002468446,0.011944614,0.002097392,0.00022946719,0.00082702935,0.004714195,0.1139208,0.008250701,0.27888715,0.57800204,0.0004633111],"about_ca_topic_score_codex":0.015907198,"about_ca_topic_score_gemma":0.011917065,"teacher_disagreement_score":0.9933314,"about_ca_system_score_codex":0.004891469,"about_ca_system_score_gemma":0.014586218,"threshold_uncertainty_score":0.35688496},"labels":[],"label_agreement":null},{"id":"W4380190507","doi":"10.1007/978-3-031-34619-4_10","title":"PreCKD_ML: Machine Learning Based Development of Prediction Model for Chronic Kidney Disease and Identify Significant Risk Factors","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Kidney disease; Medicine; Disease; Machine learning; Artificial intelligence; Intensive care medicine; Internal medicine; Computer science","score_opus":0.092521679932356,"score_gpt":0.35433873859050063,"score_spread":0.26181705865814464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380190507","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031684123,0.0019481285,0.89757186,0.0014834352,0.00065777404,0.00024289433,0.018045118,0.040831696,0.007534921],"genre_scores_gemma":[0.24780329,0.0016439124,0.6800481,0.00070116913,0.0004901807,0.0006088439,0.03989439,0.0017347293,0.027075384],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997634,0.00004489985,0.000018529985,0.000074437936,0.00007671952,0.000022059576],"domain_scores_gemma":[0.99947745,0.00030813325,0.000020202157,0.000048262977,0.00012630768,0.000019631985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007722603,0.0007101403,0.0006515566,0.0007280917,0.00029918534,0.000877891,0.0011014002,0.0006403963,0.012113246],"category_scores_gemma":[0.002282067,0.00041329328,0.0009111714,0.00053488323,0.000099304314,0.0007625994,0.00071604433,0.0011164789,0.0057029943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037023713,0.00031431104,0.011258547,0.00030803893,0.00026596233,0.0003027818,0.000062407365,0.1018301,0.0041456628,0.003832521,0.11762229,0.7596872],"study_design_scores_gemma":[0.000054506385,0.00009315046,0.0032531163,0.00004188542,0.000078752826,0.00025354992,0.00002207535,0.96361804,0.006170999,0.005627572,0.020755567,0.00003080125],"about_ca_topic_score_codex":0.0056211744,"about_ca_topic_score_gemma":0.006301267,"teacher_disagreement_score":0.012113246,"about_ca_system_score_codex":0.00030431576,"about_ca_system_score_gemma":0.00090932805,"threshold_uncertainty_score":0.040522814},"labels":[],"label_agreement":null},{"id":"W4380203237","doi":"10.1007/978-3-031-34619-4","title":"Machine Intelligence and Emerging Technologies","year":2023,"lang":"en","type":"book","venue":"Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Texas at El Paso; Karl-Franzens-Universität Graz; Università degli Studi di Torino; Universiti Sains Malaysia; University of Waterloo; Vrije Universiteit Brussel; Mae Fah Luang University; Scuola Superiore Sant'Anna; Università degli Studi di Padova; Sejong University; Universiti Teknologi Petronas; Edith Cowan University; Queensland University of Technology; RMIT University; Oulun Yliopisto; University of New South Wales; Lakehead University; Griffith University; University of Pretoria; La Trobe University; University of Oxford; Trent University; Universitas Muhammadiyah Surakarta; Universiti Malaysia Pahang; Politechnika Warszawska; Nottingham Trent University; Macquarie University; Manchester Metropolitan University; Jagannath University; Technische Universität Berlin; Indian Institute of Technology Kanpur; Missouri University of Science and Technology; Teesside University; Bangladesh University of Engineering and Technology; Canadian Food Inspection Agency; University of South Dakota; University of South Alabama; Xiamen University; TU Graz, Internationale Beziehungen und Mobilitätsprogramme; Novosibirsk State Technical University; King Saud University; Old Dominion University; University of Southampton; Aberystwyth University; City University of Hong Kong","keywords":"Cloud computing; Computer science; Data science; Internet of Things; Computer security; Artificial intelligence; Operating system","score_opus":0.08356282888859354,"score_gpt":0.37586429484460676,"score_spread":0.29230146595601325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380203237","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015851321,0.41729403,0.06983449,0.012760373,0.008967572,0.00012765446,0.00043750397,0.0006493459,0.48834386],"genre_scores_gemma":[0.03144148,0.2530652,0.06068309,0.0065400926,0.010237155,0.00038515622,0.0013592803,0.00063051895,0.63565797],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99906355,0.0001971785,0.00004941672,0.00013551427,0.0004994655,0.000054867924],"domain_scores_gemma":[0.9987974,0.0006776568,0.000060022692,0.00020680249,0.00017125555,0.0000868482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013676293,0.0015524233,0.0016724373,0.0019903318,0.00059213425,0.004866357,0.0011338524,0.0015029036,0.024795841],"category_scores_gemma":[0.0019388562,0.00070609734,0.0004482158,0.0026325677,0.0026612645,0.0060669025,0.0022265106,0.003987552,0.01646643],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036318244,0.000092437076,0.00030992896,0.0006936289,0.00005242986,0.00011245627,0.00048055412,0.0011519432,0.0009995454,0.4347277,0.28970632,0.27163675],"study_design_scores_gemma":[0.000010265072,0.000036916797,0.00045936208,0.0005248589,0.000011682533,0.00024443242,0.000110807276,0.0015007196,0.00021939195,0.2279832,0.7688871,0.000011252053],"about_ca_topic_score_codex":0.0007851109,"about_ca_topic_score_gemma":0.0015573277,"teacher_disagreement_score":0.024795841,"about_ca_system_score_codex":0.0011159069,"about_ca_system_score_gemma":0.0011090994,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4380272131","doi":"10.23977/jeis.2023.080205","title":"The Application of Software Engineering Technology in the Era of Big Data","year":2023,"lang":"en","type":"article","venue":"Journal of Electronics and Information Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Big data; Software development; Computer science; Social software engineering; Context (archaeology); Software; Product (mathematics); Software development process; Personal software process; Software engineering; Data science; Engineering management; Engineering; Software construction; Data mining","score_opus":0.09415903223177018,"score_gpt":0.43764692688146317,"score_spread":0.343487894649693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380272131","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039994296,0.10188631,0.60468143,0.08447537,0.005353819,0.00034380195,0.0003484735,0.0016861584,0.16123027],"genre_scores_gemma":[0.31160265,0.1500206,0.4963321,0.01253044,0.0057793674,0.0003439974,0.0005639757,0.00080828177,0.022018649],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99516714,0.0018183194,0.00030367167,0.00041401456,0.0021277932,0.00016900132],"domain_scores_gemma":[0.98491466,0.009022122,0.00063061336,0.0019525005,0.002900181,0.00057995104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005200734,0.0006236103,0.00056554563,0.0034305428,0.0010265211,0.00530319,0.000894844,0.001932948,0.0031055403],"category_scores_gemma":[0.013081215,0.00043366186,0.0009218187,0.0036522436,0.0035384072,0.0078114932,0.002913598,0.004045844,0.0017717581],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049720456,0.0001711892,0.0052351356,0.0016824361,0.00011815135,0.0004226674,0.0018903586,0.0039111767,0.0076586837,0.5194446,0.020732073,0.43868375],"study_design_scores_gemma":[0.000019635689,0.00022130784,0.0041391235,0.0016854431,0.00005298007,0.001080272,0.001572345,0.013999811,0.0051616086,0.5086015,0.4633616,0.00010453543],"about_ca_topic_score_codex":0.000912669,"about_ca_topic_score_gemma":0.0007910121,"teacher_disagreement_score":0.00530319,"about_ca_system_score_codex":0.001280865,"about_ca_system_score_gemma":0.0028476422,"threshold_uncertainty_score":0.027504385},"labels":[],"label_agreement":null},{"id":"W4381951082","doi":"10.21037/cdt-22-438","title":"Cardiovascular disease/stroke risk stratification in deep learning framework: a review","year":2023,"lang":"en","type":"review","venue":"Cardiovascular Diagnosis and Therapy","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Medicine; Artificial intelligence; Machine learning; Risk stratification; Disease; Deep learning; Risk assessment; Selection bias; Segmentation; Intensive care medicine; Internal medicine; Computer science; Pathology","score_opus":0.22579565368258195,"score_gpt":0.46723090876539036,"score_spread":0.24143525508280841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381951082","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041663076,0.997442,0.0010429157,0.00043790674,0.00009228841,0.000013162509,0.00006088744,0.000014450867,0.00047973392],"genre_scores_gemma":[0.0066129044,0.9909922,0.0015631226,0.00028866436,0.00018762783,0.00003422837,0.00009789479,0.00000458393,0.00021882552],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99954456,0.00013180944,0.00010319206,0.000077209195,0.000119079334,0.000024217596],"domain_scores_gemma":[0.99839103,0.001238236,0.000119434655,0.000022272905,0.00019649163,0.00003252355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016226665,0.00084648345,0.0014063529,0.0023950215,0.00016462282,0.0010330589,0.0010128784,0.0009073603,0.0019227957],"category_scores_gemma":[0.0035724961,0.00030005226,0.001476956,0.002013561,0.0002966447,0.0011121226,0.0006026214,0.0009816132,0.00044579766],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010690266,0.00005892313,0.0012068393,0.032248255,0.0005794409,0.00007865769,0.000060477705,0.0022346107,0.00022474714,0.0024093383,0.009445358,0.9513464],"study_design_scores_gemma":[0.0001847853,0.0012643889,0.014808248,0.12803853,0.009161711,0.0026261671,0.00034177164,0.017117666,0.0023849225,0.023289917,0.8005086,0.00027332138],"about_ca_topic_score_codex":0.0033862477,"about_ca_topic_score_gemma":0.003142262,"teacher_disagreement_score":0.0033862477,"about_ca_system_score_codex":0.0007241185,"about_ca_system_score_gemma":0.0019643444,"threshold_uncertainty_score":0.008581579},"labels":[],"label_agreement":null},{"id":"W4382279009","doi":"10.1007/978-981-95-6013-4","title":"Proceedings of Trends in Electronics and Health Informatics","year":2023,"lang":"en","type":"book","venue":"Lecture notes in networks and systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Informatics; Electronics; Health informatics; Engineering ethics; Library science; Engineering; Data science; Computer science; Medicine; Electrical engineering; Public health; Nursing","score_opus":0.09072688241479239,"score_gpt":0.41175328356870444,"score_spread":0.32102640115391207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382279009","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00601016,0.18055364,0.03357672,0.016064566,0.10414387,0.00019861391,0.0016786688,0.0018005848,0.6559732],"genre_scores_gemma":[0.009361467,0.056736115,0.0066586016,0.0018557586,0.01165039,0.000060090228,0.0014702632,0.00045397913,0.9117533],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99920684,0.00009511919,0.00003906931,0.000087349385,0.00050449604,0.00006714974],"domain_scores_gemma":[0.99827397,0.00036355865,0.000075368895,0.00014423631,0.0006954226,0.00044748615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00139417,0.001347078,0.001229472,0.0028267389,0.00069416256,0.0040191384,0.001053649,0.0010040877,0.114709154],"category_scores_gemma":[0.0016764387,0.00039163255,0.0006394827,0.0033950242,0.00061030575,0.0025891315,0.0014129868,0.002108889,0.04860456],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047027155,0.000065047985,0.00020722463,0.0003611858,0.000022645883,0.00007518818,0.00006747182,0.00027491694,0.0010998754,0.0058852774,0.706414,0.2854802],"study_design_scores_gemma":[0.000005236182,0.00003709493,0.00075945456,0.00013753973,0.000014837427,0.00015774783,0.000051689665,0.0005223312,0.00040868315,0.0020012436,0.99589527,0.00000895195],"about_ca_topic_score_codex":0.001968212,"about_ca_topic_score_gemma":0.0060132924,"teacher_disagreement_score":0.114709154,"about_ca_system_score_codex":0.000770935,"about_ca_system_score_gemma":0.0013466945,"threshold_uncertainty_score":0.38374037},"labels":[],"label_agreement":null},{"id":"W4382657768","doi":"10.2139/ssrn.4493924","title":"Establishing Medical Intelligence - Leveraging FHIR to Improve Clinical Management","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Business intelligence; Knowledge management; Process management; Data science; Business","score_opus":0.20889313559214637,"score_gpt":0.527008264461972,"score_spread":0.3181151288698256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382657768","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07931847,0.004025148,0.6929913,0.045235716,0.0019537862,0.002032566,0.0022089693,0.011692694,0.1605414],"genre_scores_gemma":[0.53838944,0.0013014307,0.4407724,0.0054699606,0.0012823002,0.0003154747,0.0021979192,0.00035197908,0.009919194],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98349863,0.008605771,0.0011230068,0.0016237223,0.0038615935,0.0012871593],"domain_scores_gemma":[0.9472052,0.026938206,0.0032296593,0.009103251,0.01140175,0.0021219703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024187861,0.0009187086,0.0009786115,0.0067667477,0.0018455627,0.009808881,0.0024479365,0.0022026908,0.007936848],"category_scores_gemma":[0.052812953,0.0005500973,0.0010534177,0.0030280366,0.0016733451,0.007771052,0.005873366,0.0027039691,0.0039613764],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034810937,0.0015358193,0.031808358,0.0007092899,0.00024893493,0.0003080677,0.0015220069,0.007074133,0.008411531,0.025996933,0.032964487,0.8890723],"study_design_scores_gemma":[0.00036082286,0.0026918254,0.06120423,0.0020747562,0.00085963664,0.0015857125,0.008456282,0.33535463,0.061410114,0.22080356,0.3046855,0.00051295257],"about_ca_topic_score_codex":0.007646044,"about_ca_topic_score_gemma":0.008831801,"teacher_disagreement_score":0.024187861,"about_ca_system_score_codex":0.0021894316,"about_ca_system_score_gemma":0.0074070618,"threshold_uncertainty_score":0.1279192},"labels":[],"label_agreement":null},{"id":"W4383676048","doi":"10.5281/zenodo.8127909","title":"Using computer expert system to solve complications primarily due to low and excessive birth weights at delivery: Strategies to reviving the ageing and diminishing population","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Population ageing; Ageing; Population; Gerontology; Medicine; Computer science; Environmental health; Internal medicine","score_opus":0.16076154212763288,"score_gpt":0.39901424475658565,"score_spread":0.23825270262895276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383676048","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.504427,0.0045648036,0.38248557,0.017074415,0.00042268512,0.002123034,0.00031885202,0.00592767,0.08265597],"genre_scores_gemma":[0.6571928,0.0025353036,0.3277505,0.0012779048,0.00008724549,0.00043422935,0.0002779391,0.00008144461,0.010362592],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818194,0.0010430397,0.00011993864,0.00018589645,0.00036118046,0.000108085536],"domain_scores_gemma":[0.9948778,0.0023665158,0.00062271836,0.0005001111,0.0011952117,0.00043759175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036579948,0.00039261498,0.0002938781,0.0012069759,0.00051568385,0.0018761301,0.0014814707,0.00083114684,0.0025645446],"category_scores_gemma":[0.012091234,0.00015945894,0.00030941938,0.00064463814,0.00050423044,0.0018737279,0.0012982257,0.0006978252,0.0008209516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003040874,0.0017475924,0.03318038,0.0009855557,0.000078138866,0.0008863229,0.008532251,0.014561736,0.012453834,0.008717146,0.013055832,0.90549725],"study_design_scores_gemma":[0.0006441482,0.0052738306,0.11205381,0.004837066,0.0007748466,0.0055465647,0.045185845,0.37379238,0.033414897,0.058014207,0.3599896,0.00047281297],"about_ca_topic_score_codex":0.0043794247,"about_ca_topic_score_gemma":0.006921295,"teacher_disagreement_score":0.0043794247,"about_ca_system_score_codex":0.00081493566,"about_ca_system_score_gemma":0.0033908903,"threshold_uncertainty_score":0.019345582},"labels":[],"label_agreement":null},{"id":"W4384210476","doi":"10.5958/2347-7202.2023.00004.x","title":"Heart disease prediction using machine learning","year":2023,"lang":"en","type":"article","venue":"JIMS8I - International Journal of Information Communication and Computing Technology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Forces College","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Disease; Medicine; Internal medicine","score_opus":0.08833279982864652,"score_gpt":0.4556932008833723,"score_spread":0.3673604010547258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384210476","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5290977,0.010942982,0.42376572,0.0033308023,0.0008086192,0.00049603655,0.016610056,0.0056856857,0.009262372],"genre_scores_gemma":[0.938963,0.0015470128,0.048091132,0.0002727384,0.00037016586,0.00015285441,0.00891353,0.000044342338,0.001645322],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991392,0.0002352786,0.000109644825,0.00022765437,0.00019141736,0.00009675254],"domain_scores_gemma":[0.99682105,0.0018036078,0.00040545838,0.00017451074,0.0006365132,0.00015898435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015373806,0.00085354,0.00093233166,0.003506513,0.0002938686,0.00123754,0.00078454625,0.0009999003,0.0016614082],"category_scores_gemma":[0.0063541676,0.00025826533,0.0011120829,0.0015640424,0.00020785654,0.00073323946,0.0005207103,0.0011015817,0.0012550266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006235215,0.000943546,0.30193582,0.00036123345,0.00059795874,0.00067610596,0.00008404859,0.27721083,0.0015593674,0.0014457105,0.015941763,0.39862004],"study_design_scores_gemma":[0.000019751351,0.00012839898,0.018647855,0.00005636497,0.00005329301,0.00021091588,0.000028745253,0.9751923,0.00091227173,0.003377075,0.0013496389,0.000023492583],"about_ca_topic_score_codex":0.007960511,"about_ca_topic_score_gemma":0.005773958,"teacher_disagreement_score":0.007960511,"about_ca_system_score_codex":0.0005269598,"about_ca_system_score_gemma":0.00071351614,"threshold_uncertainty_score":0.015828311},"labels":[],"label_agreement":null},{"id":"W4384820370","doi":"10.2196/48795","title":"Effective Prediction of Mortality by Heart Disease Among Women in Jordan Using the Chi-Squared Automatic Interaction Detection Model: Retrospective Validation Study","year":2023,"lang":"en","type":"article","venue":"JMIR Cardio","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Cutoff; Heart failure; Receiver operating characteristic; Blood pressure; Angina; Retrospective cohort study; Population; Medical record; Artificial intelligence; Machine learning; Internal medicine; Computer science","score_opus":0.09858131930949941,"score_gpt":0.462821780952782,"score_spread":0.36424046164328255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384820370","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99850476,0.000068672234,0.0009942296,0.000039527542,0.000006048758,0.000025225498,0.00025406078,0.000008669636,0.00009882448],"genre_scores_gemma":[0.99791485,0.000062011466,0.0010749901,0.000019433272,0.000009571756,0.0000406711,0.00073043816,0.000004376201,0.00014375673],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981937,0.0010077686,0.00015788783,0.00027842837,0.00024097667,0.00012123356],"domain_scores_gemma":[0.98756486,0.007337068,0.0014829612,0.0010413978,0.0021084195,0.00046527846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00851493,0.0006435859,0.0005103452,0.0013054911,0.00038053206,0.0006881006,0.0009391616,0.00048903696,0.0010816967],"category_scores_gemma":[0.014302934,0.0003306993,0.0013391204,0.00078148034,0.0003902073,0.0005616479,0.0006794326,0.0008490814,0.00035210833],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022299397,0.00017642225,0.99524057,0.000011285765,0.000117817464,0.00006408118,0.00015680729,0.0009798994,0.00008796922,0.000037644375,0.00016956689,0.0027349254],"study_design_scores_gemma":[0.00009851861,0.0021925613,0.8753968,0.00005350248,0.00032348713,0.0005214871,0.0013523883,0.11809116,0.0007760993,0.00027855037,0.00088484556,0.00003067602],"about_ca_topic_score_codex":0.0057452843,"about_ca_topic_score_gemma":0.0036995292,"teacher_disagreement_score":0.00851493,"about_ca_system_score_codex":0.00051606365,"about_ca_system_score_gemma":0.0010654564,"threshold_uncertainty_score":0.045031786},"labels":[],"label_agreement":null},{"id":"W4385078057","doi":"10.18280/isi.280322","title":"Evaluative Study of Machine Learning Classifiers in Predicting Heart Failure: A Focus on Imbalanced Datasets","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Machine learning; Focus (optics); Artificial intelligence; Computer science","score_opus":0.09081469399695635,"score_gpt":0.4164349675309405,"score_spread":0.32562027353398415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385078057","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9251187,0.010161971,0.05863625,0.0009864317,0.00027625996,0.00032756818,0.00072936626,0.00041833147,0.0033451328],"genre_scores_gemma":[0.9630286,0.0014958575,0.032920107,0.0001369643,0.00015767259,0.000117590105,0.0015325252,0.000032047923,0.0005786721],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9857108,0.009126868,0.0009929298,0.0014258901,0.0023999575,0.0003436043],"domain_scores_gemma":[0.94924265,0.042653147,0.0018897494,0.0023842196,0.0032723858,0.00055785925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02494785,0.0016532715,0.0012843822,0.002758168,0.0005907952,0.0017470082,0.0008610287,0.0013300335,0.00037652388],"category_scores_gemma":[0.037298016,0.0001880682,0.000662916,0.0016512485,0.00066296686,0.002064128,0.0011155126,0.001000332,0.0002126127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037175517,0.002707179,0.1408056,0.0010422453,0.0015493116,0.0002790719,0.00045266617,0.3548975,0.0072645666,0.0025683613,0.0050548646,0.4796611],"study_design_scores_gemma":[0.00013033758,0.0038772647,0.039457534,0.00012921933,0.00022854611,0.00018154575,0.0004110526,0.9459339,0.0061658868,0.0016351324,0.0018021044,0.000047468373],"about_ca_topic_score_codex":0.0024343033,"about_ca_topic_score_gemma":0.0020186326,"teacher_disagreement_score":0.02494785,"about_ca_system_score_codex":0.0009061542,"about_ca_system_score_gemma":0.00090716797,"threshold_uncertainty_score":0.13193846},"labels":[],"label_agreement":null},{"id":"W4385462213","doi":"10.1038/s41598-023-39138-x","title":"Author Correction: Predicting Alzheimer’s disease progression using multi-modal deep learning approach","year":2023,"lang":"en","type":"erratum","venue":"Scientific Reports","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St Joseph's Health Care; Sunnybrook Health Science Centre; St Joseph's Health Centre; McGill University; Jewish General Hospital","funders":"National Institute on Aging","keywords":"Modal; Computer science; Artificial intelligence; Alzheimer's disease; Deep learning; Disease; Natural language processing; Data science; Medicine; Pathology; Chemistry","score_opus":0.246284739670476,"score_gpt":0.4924754308641694,"score_spread":0.24619069119369338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385462213","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017109636,0.00048542413,0.00088880217,0.054344177,0.939499,0.000024310355,0.0018032227,0.00048947986,0.0022943637],"genre_scores_gemma":[0.0257156,0.006616497,0.009007865,0.1468727,0.4557462,0.00037156054,0.005214403,0.0027669647,0.34768814],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945121,0.0007895562,0.0012174491,0.0008905901,0.0021707464,0.00041962095],"domain_scores_gemma":[0.9466256,0.01405887,0.002093093,0.0035162563,0.031780608,0.0019255078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046625086,0.00211406,0.0022327271,0.0037392534,0.003354751,0.0037393903,0.00351381,0.007571298,0.06121417],"category_scores_gemma":[0.08799116,0.00097514,0.0020208047,0.0027875141,0.0024418868,0.002079186,0.0021554735,0.010608457,0.054700907],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003021906,0.0000051548463,0.00007838885,0.000079353886,0.000010761321,0.00026062847,0.000029428416,0.000028346356,0.0000390606,0.000451404,0.99522036,0.0037667747],"study_design_scores_gemma":[0.00009865316,0.00003646246,0.001046194,0.0004989989,0.000086525826,0.0019135379,0.00017088641,0.00052180875,0.00083943916,0.0038641866,0.9908597,0.00006370438],"about_ca_topic_score_codex":0.01413904,"about_ca_topic_score_gemma":0.017746985,"teacher_disagreement_score":0.06121417,"about_ca_system_score_codex":0.0029575892,"about_ca_system_score_gemma":0.0062380983,"threshold_uncertainty_score":0.20478183},"labels":[],"label_agreement":null},{"id":"W4385545464","doi":"10.58530/2022/3640","title":"Correlation between Iron Burden and Cognitive Status in Type 2 Diabetes Mellitus Patients Using Quantitative Susceptibility Mapping","year":2023,"lang":"en","type":"article","venue":"Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Correlation; Type 2 Diabetes Mellitus; Cognition; Diabetes mellitus; Positive correlation; Montreal Cognitive Assessment; Internal medicine; Negative correlation; Cognitive impairment; Medicine; Endocrinology; Psychology; Psychiatry; Mathematics","score_opus":0.07363715060381258,"score_gpt":0.3687555073236115,"score_spread":0.2951183567197989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385545464","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99914813,0.00016190064,0.00020811919,0.00002169955,0.0000031713723,0.0000045432535,0.000090992544,0.0000050784674,0.00035635894],"genre_scores_gemma":[0.99951017,0.000047369238,0.00021009262,0.000007324181,0.0000046453633,0.0000046300775,0.00008838226,9.0020296e-7,0.00012657349],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9998293,0.00006434619,0.00002220189,0.000034437962,0.000033265667,0.000016514896],"domain_scores_gemma":[0.99935526,0.00020750509,0.0002466928,0.00004905887,0.00006832274,0.00007306934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005281241,0.000242325,0.00016476195,0.0010071228,0.0001316393,0.00045424965,0.00014565742,0.0002668063,0.00077770575],"category_scores_gemma":[0.0014479209,0.000107163825,0.00020362511,0.00060126255,0.000128651,0.00021296227,0.000250573,0.00025472383,0.0001045701],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042184975,0.00007648753,0.99250317,0.000014702141,0.000100412755,0.000075349046,0.00007287509,0.00018793631,0.0010186066,0.000031540763,0.00008494608,0.005412153],"study_design_scores_gemma":[0.000012465267,0.00017744812,0.99725914,0.0000063079515,0.000043563276,0.00030852083,0.000111003326,0.0016101876,0.00024098674,0.00010404196,0.00011899961,0.0000072802513],"about_ca_topic_score_codex":0.0013866284,"about_ca_topic_score_gemma":0.0015175923,"teacher_disagreement_score":0.0013866284,"about_ca_system_score_codex":0.00012590122,"about_ca_system_score_gemma":0.00009863604,"threshold_uncertainty_score":0.002793014},"labels":[],"label_agreement":null},{"id":"W4385693906","doi":"10.1155/2023/6442756","title":"Towards Diagnostic Aided Systems in Coronary Artery Disease Detection: A Comprehensive Multiview Survey of the State of the Art","year":2023,"lang":"en","type":"article","venue":"International Journal of Intelligent Systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"CAD; Support vector machine; Computer science; Machine learning; Artificial intelligence; Field (mathematics); Random forest; Artificial neural network; Coronary artery disease; Feature extraction; Data mining; Data extraction; Pattern recognition (psychology); Medicine; MEDLINE; Mathematics; Internal medicine; Engineering drawing","score_opus":0.17777504142200737,"score_gpt":0.44229123227928785,"score_spread":0.2645161908572805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385693906","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036570835,0.9912116,0.0012136048,0.001718367,0.0001370844,0.000049583803,0.00030743642,0.000034035802,0.0016710655],"genre_scores_gemma":[0.021117399,0.97263473,0.0042283074,0.0009930527,0.00016585134,0.000061255545,0.0004922045,0.000018116725,0.0002891277],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945575,0.0016468652,0.0014720587,0.0005100571,0.0016560914,0.00015753547],"domain_scores_gemma":[0.95906746,0.029076071,0.00325572,0.0007038357,0.0073544057,0.0005425758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0155754,0.0005705457,0.0013153928,0.020255685,0.0004365214,0.0037156013,0.0012269234,0.0015550992,0.0030406003],"category_scores_gemma":[0.025539828,0.0005062068,0.0017515061,0.0120907845,0.0010718916,0.0046201427,0.0016558416,0.0011175446,0.0007128549],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017709563,0.00009549684,0.010084848,0.09268752,0.0008269889,0.00017842861,0.001489972,0.0005297544,0.0011508901,0.004997075,0.011047908,0.87673396],"study_design_scores_gemma":[0.00007264106,0.00093464187,0.07125077,0.3542295,0.005347726,0.002956418,0.005486596,0.0025507864,0.002022025,0.008233073,0.54671013,0.00020568985],"about_ca_topic_score_codex":0.0040911613,"about_ca_topic_score_gemma":0.0049381824,"teacher_disagreement_score":0.020255685,"about_ca_system_score_codex":0.0021863917,"about_ca_system_score_gemma":0.004583557,"threshold_uncertainty_score":0.08237153},"labels":[],"label_agreement":null},{"id":"W4385849703","doi":"10.5281/zenodo.8252499","title":"Supplementary Information for: Reducing Training Data Needs with Minimal Multilevel Machine Learning (M3L)","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Vector Institute","funders":"","keywords":"Training (meteorology); Computer science; Machine learning; Artificial intelligence; Training set; Geography","score_opus":0.30823961816106227,"score_gpt":0.4235564814636357,"score_spread":0.11531686330257346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385849703","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009612597,0.0001825755,0.03147919,0.00043785098,0.0006765684,0.00016785944,0.91795903,0.040758125,0.007377512],"genre_scores_gemma":[0.010055892,0.0002744574,0.09111503,0.00082373846,0.00029458854,0.0013647857,0.83783376,0.046793975,0.011443825],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987902,0.00021232202,0.00015199055,0.0003299802,0.00037555274,0.0001399148],"domain_scores_gemma":[0.9908117,0.0055612996,0.00032229658,0.0014394001,0.0013922256,0.00047304845],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017138582,0.0029507522,0.0021197451,0.0020063024,0.0008786659,0.0023609598,0.0039497623,0.0016151337,0.7959443],"category_scores_gemma":[0.018236456,0.001440521,0.0015098477,0.0028407695,0.0004866004,0.002309485,0.0020663864,0.0022761985,0.4218875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024097894,0.0000958186,0.00036290914,0.0010143521,0.000040209565,0.000057245048,0.000029939974,0.0014948995,0.0013618453,0.002314892,0.9723737,0.020613164],"study_design_scores_gemma":[0.0018332349,0.00030197302,0.003399271,0.00077079976,0.00013526375,0.0004007901,0.00012785305,0.03428918,0.019989584,0.048075564,0.890399,0.00027751437],"about_ca_topic_score_codex":0.0039458866,"about_ca_topic_score_gemma":0.009605813,"teacher_disagreement_score":0.7959443,"about_ca_system_score_codex":0.0010524517,"about_ca_system_score_gemma":0.001979761,"threshold_uncertainty_score":0.2910607},"labels":[],"label_agreement":null},{"id":"W4385863356","doi":"10.2196/48290","title":"Title: Prediction of Diabetes Using Machine Learning and Data Mining Algorithm: Cross-sectional study (Preprint)","year":2023,"lang":"en","type":"article","venue":"Interactive Journal of Medical Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprint; Computer science; Machine learning; Algorithm; Artificial intelligence; Data mining; World Wide Web","score_opus":0.5610001828273812,"score_gpt":0.6600243471782699,"score_spread":0.09902416435088868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385863356","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99645185,0.00025233522,0.0003292321,0.0002589489,0.00020007748,0.000021057003,0.0018290482,0.000019142108,0.0006383573],"genre_scores_gemma":[0.9919865,0.00022982583,0.00028703257,0.00019024307,0.00026408277,0.000046661637,0.0024573554,0.000021483263,0.00451667],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99954945,0.00010062251,0.000075758246,0.00014944316,0.00007911286,0.000045543005],"domain_scores_gemma":[0.9957924,0.0019154333,0.00061315607,0.00034898252,0.00087664445,0.0004534003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010465762,0.00031889457,0.00047101584,0.00050914683,0.00043036055,0.00094476267,0.00039584414,0.000985541,0.01246362],"category_scores_gemma":[0.005573209,0.00036068357,0.00048717606,0.00064119295,0.00020688749,0.0006715395,0.0002632012,0.0011893337,0.002424401],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020911698,0.0009529029,0.9882224,0.00008008601,0.00026187667,0.00020335603,0.00028196973,0.00009860551,0.00076963153,0.000060995008,0.0026323204,0.004344566],"study_design_scores_gemma":[0.000078091354,0.0012292591,0.99569017,0.000022745873,0.00019052115,0.00048967253,0.00035496175,0.00057537045,0.0004152318,0.00010177624,0.0008421044,0.000010085221],"about_ca_topic_score_codex":0.0015123204,"about_ca_topic_score_gemma":0.0005688128,"teacher_disagreement_score":0.01246362,"about_ca_system_score_codex":0.00012631343,"about_ca_system_score_gemma":0.000290575,"threshold_uncertainty_score":0.041695},"labels":[],"label_agreement":null},{"id":"W4386096679","doi":"10.5539/cis.v16n3p22","title":"Improving the Classification Ability of Delegating Classifiers Using Different Supervised Machine Learning Algorithms","year":2023,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Classifier (UML); Computer science; Machine learning; Support vector machine; Linear discriminant analysis; Linear classifier; Pattern recognition (psychology)","score_opus":0.19122544782073314,"score_gpt":0.43214959586915275,"score_spread":0.2409241480484196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386096679","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2581288,0.00145793,0.7298361,0.00056975364,0.0005023047,0.00023494572,0.00017052221,0.0024204738,0.006679148],"genre_scores_gemma":[0.7698505,0.00058161275,0.22346017,0.00020579582,0.0002463361,0.00019309808,0.00054490333,0.000105124454,0.0048126318],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968064,0.00068158977,0.00030876743,0.0007102237,0.0012371716,0.0002559367],"domain_scores_gemma":[0.9927892,0.0022107249,0.0007110913,0.0010336973,0.0030736874,0.00018169888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037598764,0.0011391779,0.001405361,0.0016021377,0.00075037044,0.0015123053,0.0013454797,0.0011440591,0.0012930606],"category_scores_gemma":[0.009798161,0.00028847717,0.0010687852,0.0009637553,0.00045239087,0.0017310459,0.0008439509,0.001296368,0.0008324748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047884285,0.0006688894,0.010582307,0.00025113352,0.00022258898,0.00013365588,0.00020058079,0.11304092,0.018363325,0.0025287122,0.003683139,0.8498458],"study_design_scores_gemma":[0.00002183612,0.00025620704,0.0027605575,0.000024197043,0.00006601191,0.00008131724,0.00005894257,0.9790248,0.014141483,0.0013653765,0.0021713672,0.000027798349],"about_ca_topic_score_codex":0.0029214977,"about_ca_topic_score_gemma":0.0023363614,"teacher_disagreement_score":0.0037598764,"about_ca_system_score_codex":0.0007774871,"about_ca_system_score_gemma":0.0010928994,"threshold_uncertainty_score":0.019884348},"labels":[],"label_agreement":null},{"id":"W4386213614","doi":"10.1109/icirca57980.2023.10220710","title":"Big Data Analytics with Wild Horse Optimizer based Deep Learning Model for Healthcare Management","year":2023,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Hyperparameter; Big data; Computer science; Health care; Analytics; Machine learning; Artificial intelligence; Data science; Data modeling; Deep learning; Field (mathematics); Classifier (UML); Data analysis; Data mining; Database","score_opus":0.5176481570217603,"score_gpt":0.5066391185955186,"score_spread":0.01100903842624168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386213614","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.080536075,0.0014131862,0.91034794,0.001294263,0.00014177502,0.00009327024,0.00037385887,0.0016374395,0.004162168],"genre_scores_gemma":[0.89344853,0.00053274503,0.09939439,0.0004470843,0.000060477207,0.00012594402,0.00066273636,0.00008359061,0.0052444115],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99979204,0.000044752276,0.0000155194,0.000060293867,0.000046749672,0.00004074601],"domain_scores_gemma":[0.99973005,0.000102230224,0.00003067787,0.000029799077,0.00008326014,0.000023934963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061633036,0.000612566,0.00059417175,0.00035367135,0.0002520055,0.0008023091,0.00082050887,0.00068035396,0.0017435845],"category_scores_gemma":[0.0014008285,0.00027222728,0.00054545415,0.00042218843,0.0003852487,0.0009407816,0.0007470865,0.001398715,0.0003241369],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014911425,0.0002135918,0.003425168,0.00008653435,0.000083294384,0.000113310496,0.00007156197,0.8477603,0.0025898337,0.0053978213,0.004369159,0.13574034],"study_design_scores_gemma":[0.0000018234717,0.000010749157,0.00009361567,0.000002651603,0.0000027345375,0.0000035638163,0.0000033316837,0.99839455,0.0002146879,0.0011329788,0.00013771206,0.0000014769362],"about_ca_topic_score_codex":0.009004254,"about_ca_topic_score_gemma":0.012492441,"teacher_disagreement_score":0.009004254,"about_ca_system_score_codex":0.00079602835,"about_ca_system_score_gemma":0.0011546572,"threshold_uncertainty_score":0.017903686},"labels":[],"label_agreement":null},{"id":"W4386304424","doi":"10.18280/mmep.100401","title":"Lung-Related Diseases Classification Using Deep Convolutional Neural Network","year":2023,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Covenant University Centre for Research, Innovation and Discovery; Covenant University","keywords":"Convolutional neural network; Artificial intelligence; Lung; Computer science; Pattern recognition (psychology); Medicine; Internal medicine","score_opus":0.1734565709887589,"score_gpt":0.3873554961787848,"score_spread":0.21389892519002587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386304424","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6551408,0.008452833,0.31603,0.0014555163,0.00048240402,0.00029465914,0.0038200794,0.005524562,0.008799087],"genre_scores_gemma":[0.9466268,0.0015109791,0.04025437,0.00034931433,0.00009362979,0.000082711726,0.0045854407,0.000040779418,0.00645599],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997631,0.000024661618,0.000017706168,0.000060425322,0.00006097124,0.000073012285],"domain_scores_gemma":[0.9997819,0.00005618417,0.00004008422,0.00002478502,0.000073513715,0.000023509934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039725326,0.0009334939,0.0004576491,0.0010224043,0.00023086589,0.0005810925,0.000778,0.00076923356,0.0012323457],"category_scores_gemma":[0.0007302114,0.00027886164,0.0006963723,0.0005477632,0.00020605573,0.0005528908,0.00061997015,0.0007153374,0.00053393224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00085223233,0.0007135776,0.037757784,0.00029477075,0.00031978695,0.0008453728,0.0000965138,0.35931835,0.041339062,0.0021540194,0.012022145,0.5442864],"study_design_scores_gemma":[0.0000076073657,0.0000471669,0.0035580501,0.000014819631,0.000026595551,0.00006657888,0.000012013486,0.99082476,0.004097111,0.00056096143,0.0007745957,0.000009769579],"about_ca_topic_score_codex":0.020450747,"about_ca_topic_score_gemma":0.028113203,"teacher_disagreement_score":0.020450747,"about_ca_system_score_codex":0.00091658096,"about_ca_system_score_gemma":0.0009199594,"threshold_uncertainty_score":0.04066342},"labels":[],"label_agreement":null},{"id":"W4386405219","doi":"","title":"Complete Platform for Remote Health Management","year":2013,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Business; Process management","score_opus":0.6896309124301134,"score_gpt":0.6891539923983298,"score_spread":0.0004769200317836786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386405219","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018243881,0.0033999877,0.6140136,0.0034442907,0.0026681414,0.0021961918,0.007814324,0.0898999,0.2583196],"genre_scores_gemma":[0.23729473,0.0037949958,0.29618886,0.003744511,0.0019420495,0.0033817883,0.022983437,0.0036583585,0.42701125],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99919146,0.0001007005,0.000059515885,0.0001888354,0.0003435426,0.00011597942],"domain_scores_gemma":[0.99931026,0.000078430916,0.00003272163,0.00027646174,0.00017229059,0.00012978265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011079082,0.0008832247,0.0007436642,0.0011127637,0.00060953957,0.0018046098,0.0020712446,0.0011003761,0.08613496],"category_scores_gemma":[0.0012300969,0.00033964321,0.0004982354,0.00058426167,0.00033174892,0.002047364,0.0043850816,0.0009972308,0.069035225],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006923992,0.00043608312,0.001631244,0.00068223814,0.00009504791,0.0007247067,0.00045145644,0.001970015,0.05490623,0.035042513,0.23532921,0.6680388],"study_design_scores_gemma":[0.00012919075,0.0004053101,0.0037098709,0.00021651601,0.00006803655,0.00084999355,0.00013697702,0.013298209,0.02084696,0.012778638,0.9474686,0.00009170987],"about_ca_topic_score_codex":0.000552504,"about_ca_topic_score_gemma":0.00044639112,"teacher_disagreement_score":0.08613496,"about_ca_system_score_codex":0.0002838514,"about_ca_system_score_gemma":0.00075745466,"threshold_uncertainty_score":0.2881502},"labels":[],"label_agreement":null},{"id":"W4386499055","doi":"10.1117/12.2692214","title":"Heart disease prediction using machine learning models","year":2023,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence","score_opus":0.44580091287904616,"score_gpt":0.5205755946972299,"score_spread":0.07477468181818375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386499055","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4890769,0.005591751,0.44806,0.009111327,0.0011668017,0.00038182992,0.015718361,0.0070659667,0.02382707],"genre_scores_gemma":[0.8988724,0.0011137428,0.0828998,0.00037950152,0.00024584006,0.00011559482,0.010737648,0.0000797807,0.0055557075],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99947673,0.00016143375,0.000044259938,0.00013965613,0.00010977605,0.00006824098],"domain_scores_gemma":[0.9977582,0.0015116623,0.00012961766,0.0001273754,0.00039116855,0.00008199064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010944767,0.0006393413,0.0005275091,0.0015769018,0.00028441055,0.0012244689,0.0006582886,0.0008801474,0.0030641959],"category_scores_gemma":[0.005346022,0.000274456,0.0010242362,0.0011226888,0.00012130777,0.0008229606,0.00036368455,0.0011596539,0.0016487758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005698847,0.0008697698,0.09074348,0.00024058118,0.00033942965,0.00032727057,0.000102196835,0.57052684,0.0011488913,0.0028605177,0.030571315,0.3016998],"study_design_scores_gemma":[0.000015576885,0.00005700353,0.0044227014,0.000031423922,0.000021190746,0.000050659295,0.000030202109,0.99041677,0.0004339051,0.0029574186,0.0015505425,0.000012575412],"about_ca_topic_score_codex":0.015274965,"about_ca_topic_score_gemma":0.015133115,"teacher_disagreement_score":0.015274965,"about_ca_system_score_codex":0.00067520485,"about_ca_system_score_gemma":0.00063588994,"threshold_uncertainty_score":0.030372143},"labels":[],"label_agreement":null},{"id":"W4386549326","doi":"10.1007/978-981-99-3982-4_20","title":"Monitor the Effectiveness of Cardiovascular Disease Illness Diagnostics Utilizing AI and Supervised Machine Learning Classifiers","year":2023,"lang":"en","type":"book-chapter","venue":"Smart innovation, systems and technologies","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lambton College","funders":"","keywords":"Machine learning; Artificial intelligence; Random forest; Computer science; Python (programming language); Heart disease; Header; Decision tree; Classifier (UML); Medicine","score_opus":0.10620428109041345,"score_gpt":0.3618283072652734,"score_spread":0.2556240261748599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386549326","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3820726,0.008560063,0.5237306,0.0021425236,0.0006180173,0.00025637547,0.002311073,0.006244838,0.07406392],"genre_scores_gemma":[0.76783144,0.0024250592,0.20152572,0.0005447702,0.0003097546,0.00011398984,0.0018403839,0.00016921385,0.025239559],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99965537,0.00006765527,0.000013451092,0.000058115398,0.00018236031,0.000023023576],"domain_scores_gemma":[0.9985373,0.0011313774,0.000068086905,0.000055341912,0.00018921582,0.000018658713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006876837,0.00040190667,0.00041116378,0.0008388754,0.00014015539,0.00092707534,0.00047884698,0.0006205607,0.002047551],"category_scores_gemma":[0.0021813293,0.00016108512,0.00028554923,0.00047470356,0.00016046836,0.0007127513,0.00018356374,0.00047284813,0.0013512785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004770973,0.0004142943,0.018852198,0.00020436679,0.00016310487,0.0001224877,0.00009399442,0.05300467,0.04705095,0.0045559644,0.015374731,0.8596861],"study_design_scores_gemma":[0.000036541922,0.0005411809,0.022755511,0.000053052092,0.00009574299,0.000287993,0.00008442169,0.89895755,0.061148632,0.0062170965,0.009779975,0.000042285363],"about_ca_topic_score_codex":0.0013807327,"about_ca_topic_score_gemma":0.002317029,"teacher_disagreement_score":0.002047551,"about_ca_system_score_codex":0.0003036579,"about_ca_system_score_gemma":0.00027439135,"threshold_uncertainty_score":0.006849706},"labels":[],"label_agreement":null},{"id":"W4386629058","doi":"10.18280/isi.280423","title":"An Enhanced Approach to Liver Disease Classification: Implementing Convolutional Neural Network with Attention Layer Gated Recurrent Unit","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Layer (electronics); Unit (ring theory); Computer science; Artificial intelligence; Psychology; Materials science; Nanotechnology; Mathematics education","score_opus":0.15471447238375868,"score_gpt":0.4061197342516835,"score_spread":0.25140526186792483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386629058","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13552022,0.0019175757,0.85513926,0.0005701855,0.00024095671,0.00010052591,0.00021998274,0.0025753675,0.003715914],"genre_scores_gemma":[0.8904242,0.00053972634,0.104238786,0.0002771903,0.00008070529,0.00005582375,0.00033708423,0.000050785562,0.003995821],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997929,0.00004173973,0.000013811363,0.000055728786,0.000051735966,0.000044128803],"domain_scores_gemma":[0.9997906,0.00005875918,0.00002369358,0.00002951924,0.000081691695,0.000015755444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005674276,0.0006153935,0.00049763784,0.0004747228,0.00017955416,0.00044512062,0.0009946711,0.000629311,0.00085868785],"category_scores_gemma":[0.0010451464,0.00021381497,0.0004983907,0.0004643412,0.00020535612,0.0007287445,0.00052380713,0.00053371396,0.00034337465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028178288,0.00034370966,0.008074767,0.00014018826,0.00027218432,0.00039612254,0.0001187005,0.29241747,0.042358648,0.004822733,0.0051521948,0.6456215],"study_design_scores_gemma":[0.000003955402,0.00007705121,0.0006825379,0.000005393807,0.000030443018,0.000049205853,0.0000067755,0.9931699,0.004642002,0.00076212065,0.0005619895,0.000008550213],"about_ca_topic_score_codex":0.008657219,"about_ca_topic_score_gemma":0.013158388,"teacher_disagreement_score":0.008657219,"about_ca_system_score_codex":0.00047398757,"about_ca_system_score_gemma":0.000660995,"threshold_uncertainty_score":0.017213643},"labels":[],"label_agreement":null},{"id":"W4386834293","doi":"10.18280/ria.370418","title":"Enhanced Cardiovascular Disease Classification: Optimizing LSTM-Based Model with Ant-Lion Algorithm for Improved Accuracy","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; ANT; Ant colony optimization algorithms; Algorithm; Disease; Machine learning; Pattern recognition (psychology); Medicine; Internal medicine","score_opus":0.19200240023257983,"score_gpt":0.42355312115163773,"score_spread":0.2315507209190579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386834293","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1863669,0.0024441474,0.7974921,0.0015611848,0.00043572093,0.00016492032,0.00027224157,0.0030494963,0.008213183],"genre_scores_gemma":[0.88774115,0.00036607933,0.106906354,0.0006422687,0.00009225659,0.00018222768,0.00034232336,0.000120991426,0.0036062438],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997569,0.000052588704,0.00002122568,0.00007403723,0.00004258657,0.00005279614],"domain_scores_gemma":[0.999464,0.0002792832,0.00005153918,0.00002620159,0.00014691698,0.00003201145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076255325,0.0012934691,0.0009813921,0.00054268003,0.00039058508,0.0010703492,0.0011986295,0.0016970194,0.0017954226],"category_scores_gemma":[0.002253382,0.00038089848,0.000662389,0.0004926771,0.00037269757,0.0008524046,0.00065408414,0.0011881092,0.0005858674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014325946,0.00013881065,0.0021950544,0.000076074364,0.000084386564,0.0001282269,0.000076745426,0.85804296,0.004922042,0.001181873,0.002123067,0.1308875],"study_design_scores_gemma":[0.0000045238526,0.000018243336,0.00008104906,0.0000042709676,0.0000070076226,0.000011724987,0.0000039992256,0.99892884,0.00046997538,0.00036277025,0.00010485798,0.0000027171077],"about_ca_topic_score_codex":0.009341692,"about_ca_topic_score_gemma":0.011398209,"teacher_disagreement_score":0.009341692,"about_ca_system_score_codex":0.0007733201,"about_ca_system_score_gemma":0.0014392999,"threshold_uncertainty_score":0.018574595},"labels":[],"label_agreement":null},{"id":"W4386838547","doi":"10.18280/ria.370410","title":"Fuzzy Rule Based- Model for Proficient Heart Disease Prediction in Data Lake","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Fuzzy logic; Artificial intelligence; Data mining; Machine learning","score_opus":0.33481895593829064,"score_gpt":0.4752674191997794,"score_spread":0.14044846326148874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386838547","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07621327,0.00088105694,0.91151285,0.00053979823,0.00013370019,0.00020185643,0.00057716115,0.0011751292,0.008765163],"genre_scores_gemma":[0.9431575,0.00029379892,0.05096304,0.00013668861,0.000042210864,0.00024652592,0.00049091777,0.000025680874,0.0046436074],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994723,0.000102662125,0.000046640685,0.00015771767,0.00012790503,0.0000928275],"domain_scores_gemma":[0.9989943,0.000559697,0.000081889775,0.000039697356,0.00029097806,0.000033433145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011893298,0.00065606856,0.0010988682,0.0006794847,0.00060100935,0.0015774672,0.0013196499,0.0013648993,0.0040717],"category_scores_gemma":[0.0027097433,0.0003450446,0.0010201378,0.00050496875,0.00043174898,0.00074683205,0.0006727602,0.0013169051,0.00069989095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012787589,0.000087682034,0.001794231,0.00006211732,0.000049705606,0.00021684714,0.000074918644,0.96227187,0.0010033994,0.0043474217,0.00085989636,0.029103996],"study_design_scores_gemma":[0.0000041975936,0.000014168121,0.00014151682,0.0000043015607,0.0000067055157,0.000009614227,0.0000039928245,0.9988758,0.00012316248,0.0006984557,0.0001153205,0.0000028621444],"about_ca_topic_score_codex":0.029927082,"about_ca_topic_score_gemma":0.020662768,"teacher_disagreement_score":0.029927082,"about_ca_system_score_codex":0.0011041868,"about_ca_system_score_gemma":0.0012573746,"threshold_uncertainty_score":0.05950576},"labels":[],"label_agreement":null},{"id":"W4386843074","doi":"10.18280/ria.370429","title":"Improving Cardiovascular Disease Prognosis Using Outlier Detection and Hyperparameter Optimization of Machine Learning Models","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hyperparameter; Machine learning; Artificial intelligence; Outlier; Anomaly detection; Computer science; Disease; Hyperparameter optimization; Medicine; Support vector machine; Internal medicine","score_opus":0.19047534520391482,"score_gpt":0.3806853233173924,"score_spread":0.1902099781134776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386843074","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08313859,0.0007132272,0.91376275,0.00033352053,0.00004486368,0.000050192783,0.00011448708,0.00085717306,0.0009852161],"genre_scores_gemma":[0.8738144,0.0003981656,0.12470463,0.00008320899,0.000060339455,0.000071735216,0.00027303764,0.000060744074,0.0005337499],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989003,0.00043404437,0.00009611763,0.00022508392,0.00027075785,0.00007362449],"domain_scores_gemma":[0.9972983,0.0013649004,0.00035719963,0.00033973696,0.0005770204,0.0000627367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002459186,0.0009663878,0.00096376904,0.0012015244,0.00034635214,0.0014289254,0.0009596161,0.00073029107,0.00040772156],"category_scores_gemma":[0.00975932,0.0002560748,0.00068569096,0.00094753556,0.00033750595,0.0013354506,0.0011484392,0.0011618088,0.0002645832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000116863564,0.00011105542,0.010850182,0.000060261915,0.00010734112,0.00007830136,0.000109016524,0.7784496,0.004289368,0.0019203769,0.0008787834,0.20302877],"study_design_scores_gemma":[0.000002535523,0.00004069919,0.00081114535,0.00000961164,0.000009887546,0.000024036583,0.000015286656,0.9959079,0.0012756217,0.0016555581,0.00023957776,0.000008194797],"about_ca_topic_score_codex":0.0032030237,"about_ca_topic_score_gemma":0.0028972493,"teacher_disagreement_score":0.0032030237,"about_ca_system_score_codex":0.00051971065,"about_ca_system_score_gemma":0.00093399076,"threshold_uncertainty_score":0.013005555},"labels":[],"label_agreement":null},{"id":"W4386869120","doi":"10.33424/futurum426","title":"How can intelligent systems revolutionise healthcare?","year":2023,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University; Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Health care; Computer science; Healthcare system; Data science; Political science","score_opus":0.2744239037495642,"score_gpt":0.48407163807007647,"score_spread":0.20964773432051226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386869120","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042648907,0.13043766,0.030999435,0.718684,0.0105391545,0.000050541425,0.00022895994,0.00067140505,0.104123965],"genre_scores_gemma":[0.33883756,0.29127428,0.063534774,0.22009073,0.028990215,0.00029182987,0.00050439284,0.0005187846,0.055957563],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963761,0.001642465,0.00011296256,0.0003041084,0.0011122061,0.00045213557],"domain_scores_gemma":[0.9926852,0.0046583684,0.0003028675,0.0007431737,0.0009625237,0.00064789155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007499688,0.0010843462,0.0008412853,0.0012675142,0.0015302226,0.008992207,0.0014069745,0.0072693094,0.01141757],"category_scores_gemma":[0.015158722,0.00043542444,0.0009532193,0.00081561075,0.00858588,0.018160315,0.0034795646,0.0068729343,0.0064886473],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013832553,0.00013249449,0.00077109056,0.0008397633,0.0001480011,0.00015201756,0.00082207343,0.0020301372,0.00077998877,0.7370535,0.14316149,0.113971114],"study_design_scores_gemma":[0.000031729596,0.000060278267,0.00033279095,0.0005676055,0.000036470075,0.00014290695,0.0005633336,0.001455493,0.00047550004,0.5743911,0.421905,0.0000377612],"about_ca_topic_score_codex":0.0020302536,"about_ca_topic_score_gemma":0.0015197739,"teacher_disagreement_score":0.01141757,"about_ca_system_score_codex":0.0018351349,"about_ca_system_score_gemma":0.0020959745,"threshold_uncertainty_score":0.03966266},"labels":[],"label_agreement":null},{"id":"W4386952254","doi":"10.1109/iceccme57830.2023.10252636","title":"Chatbot for Disease Prediction Using Classification Based Machine Learning Algorithms","year":2023,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Privy Council Office","funders":"","keywords":"Computer science; Chatbot; Artificial intelligence; Machine learning; Algorithm; Statistical classification","score_opus":0.42699250160549723,"score_gpt":0.5298330109141036,"score_spread":0.10284050930860639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386952254","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17523073,0.0063303453,0.7408644,0.0039545405,0.0016238305,0.0012988804,0.008687412,0.052182145,0.009827754],"genre_scores_gemma":[0.70797616,0.0006307209,0.27463755,0.0010844416,0.00046710958,0.00071294146,0.006749154,0.00017508876,0.0075667934],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989592,0.0003064909,0.000099597775,0.00031441118,0.00022225123,0.00009810847],"domain_scores_gemma":[0.9958801,0.0029991027,0.00023343206,0.00020399081,0.0004796716,0.00020377907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018042385,0.0013442035,0.0015122605,0.0026626026,0.0007774738,0.0010274872,0.0017172595,0.0015439763,0.0041164514],"category_scores_gemma":[0.0056554233,0.00032106106,0.0008146337,0.0010355356,0.0003167656,0.0010552055,0.0009643239,0.0014245835,0.0024039918],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022865608,0.0024349415,0.03292297,0.0010304137,0.00044681015,0.0015501241,0.00047440716,0.07991373,0.008862557,0.0048411246,0.056940068,0.8082964],"study_design_scores_gemma":[0.00007174269,0.00022663678,0.0030402618,0.00004905428,0.00005089987,0.00023245405,0.000095946845,0.9840539,0.0027299682,0.00655413,0.0028614255,0.000033671065],"about_ca_topic_score_codex":0.0070287543,"about_ca_topic_score_gemma":0.0072362567,"teacher_disagreement_score":0.0070287543,"about_ca_system_score_codex":0.0009244856,"about_ca_system_score_gemma":0.0009633202,"threshold_uncertainty_score":0.01397568},"labels":[],"label_agreement":null},{"id":"W4387224562","doi":"10.1504/ijbra.2023.133695","title":"Development of predictive model of diabetic using supervised machine learning classification algorithm of ensemble voting","year":2023,"lang":"en","type":"article","venue":"International Journal of Bioinformatics Research and Applications","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Heritage College","funders":"","keywords":"Ensemble learning; Machine learning; Artificial intelligence; Voting; Computer science; Algorithm; Majority rule; Pattern recognition (psychology)","score_opus":0.3620262230677922,"score_gpt":0.5221333505155732,"score_spread":0.160107127447781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387224562","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07674012,0.00053344097,0.91914254,0.00036985896,0.00013555688,0.00007125296,0.00022721887,0.0008684635,0.0019115282],"genre_scores_gemma":[0.8581011,0.00045301512,0.13700403,0.00014421943,0.00009581275,0.00015742185,0.000677675,0.000055213066,0.0033114715],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99956626,0.00009442245,0.000037995735,0.00012715154,0.000110581954,0.00006360637],"domain_scores_gemma":[0.99899787,0.0003779653,0.00007077431,0.00006748773,0.00045330886,0.00003272251],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014352069,0.0005479204,0.0010928072,0.0009580809,0.0004508817,0.0007782829,0.0013929365,0.00071051397,0.0012511673],"category_scores_gemma":[0.0026504656,0.00029908892,0.00092912064,0.00080610556,0.0002056663,0.00088593195,0.0004262877,0.0009367584,0.00038351657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011310081,0.0001066514,0.010734826,0.00005295113,0.00010275401,0.00015247619,0.0000726124,0.79288816,0.0025069586,0.0032539999,0.002636982,0.18737856],"study_design_scores_gemma":[0.0000018108809,0.000008449159,0.00026779092,0.0000023309453,0.000005421539,0.000011977042,0.000002595593,0.99887794,0.0002593883,0.00044171224,0.00011800361,0.0000025357056],"about_ca_topic_score_codex":0.01356913,"about_ca_topic_score_gemma":0.00933191,"teacher_disagreement_score":0.01356913,"about_ca_system_score_codex":0.0006607833,"about_ca_system_score_gemma":0.0010034556,"threshold_uncertainty_score":0.02698028},"labels":[],"label_agreement":null},{"id":"W4387239246","doi":"","title":"Prediction of cardiovascular outcomes with machine learning techniques: application to the Cardiovascular Outcomes in Renal Atherosclerotic Lesions (CORAL) study","year":2019,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Coral; Cardiology; Internal medicine; Intensive care medicine; Oceanography; Geology","score_opus":0.382770393658523,"score_gpt":0.5778877293526324,"score_spread":0.19511733569410944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387239246","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9838005,0.00081014045,0.006390399,0.0006040726,0.000051311014,0.0010229573,0.0057595647,0.00011474575,0.0014461342],"genre_scores_gemma":[0.96599466,0.0008610036,0.021294707,0.00018931425,0.0001597688,0.0016140417,0.00918255,0.000037776685,0.00066621875],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980209,0.0013811165,0.00012401203,0.00014012819,0.00028529504,0.000048640755],"domain_scores_gemma":[0.99493814,0.0031630974,0.0005444913,0.00070853776,0.00045509482,0.0001906527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008473436,0.0007589228,0.00068796065,0.001351117,0.00023843802,0.0005960592,0.0007062844,0.00043068948,0.0010918233],"category_scores_gemma":[0.014393615,0.00025062702,0.0010439946,0.0011416776,0.00022235466,0.00027295394,0.0010518098,0.0009612962,0.00016831796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012658206,0.0027530647,0.8549495,0.0005503097,0.0035567794,0.000495528,0.00035419938,0.018820444,0.0014979499,0.0005994612,0.00922866,0.0945359],"study_design_scores_gemma":[0.008305449,0.008354807,0.84590703,0.00017671521,0.0022323756,0.0009973699,0.00040404793,0.1207964,0.0021777,0.0016043477,0.008905609,0.00013811453],"about_ca_topic_score_codex":0.004593218,"about_ca_topic_score_gemma":0.0055465233,"teacher_disagreement_score":0.008473436,"about_ca_system_score_codex":0.0002638489,"about_ca_system_score_gemma":0.00077469787,"threshold_uncertainty_score":0.04481238},"labels":[],"label_agreement":null},{"id":"W4387342293","doi":"10.1007/s12599-023-00835-6","title":"Challenges and Outcomes Using Big Data as a Service","year":2023,"lang":"en","type":"article","venue":"Business & Information Systems Engineering","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Big data; Service (business); Computer science; Data science; Data mining; Business","score_opus":0.4245542171318078,"score_gpt":0.4498036626769966,"score_spread":0.02524944554518882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387342293","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01753492,0.014498464,0.023157272,0.89867586,0.0069711986,0.00010954225,0.0014690653,0.00057287596,0.03701087],"genre_scores_gemma":[0.7372739,0.057022233,0.06934126,0.0887955,0.020604623,0.00058040366,0.0059767175,0.0007791642,0.01962622],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9814755,0.007871427,0.0012713929,0.0009920924,0.0064079566,0.0019816754],"domain_scores_gemma":[0.92227566,0.03352971,0.0038749843,0.0051639588,0.020987937,0.014167793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0279315,0.0008703906,0.0012422594,0.0027388898,0.003267176,0.023836272,0.0042756987,0.0070451046,0.013332015],"category_scores_gemma":[0.06167043,0.00040725892,0.0009984766,0.006173355,0.005228727,0.031862907,0.010461092,0.009129303,0.0052841757],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046767056,0.00037516543,0.02252235,0.0019373427,0.0001907377,0.0007760542,0.0019644278,0.0050633717,0.0015920016,0.4048045,0.32140532,0.23890117],"study_design_scores_gemma":[0.00006214929,0.00020738965,0.0059047686,0.0021494317,0.000069934526,0.0005426517,0.020270618,0.019867232,0.0014507025,0.6120666,0.33724746,0.00016109634],"about_ca_topic_score_codex":0.00640719,"about_ca_topic_score_gemma":0.006015596,"teacher_disagreement_score":0.0279315,"about_ca_system_score_codex":0.0036546127,"about_ca_system_score_gemma":0.012379621,"threshold_uncertainty_score":0.14771765},"labels":[],"label_agreement":null},{"id":"W4387345674","doi":"10.20944/preprints202310.0109.v1","title":"Machine Learning Based Approach for Predicting Diabetes Employing Socio-demographic Characteristics","year":2023,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Polyuria; Diabetes mellitus; Polydipsia; Machine learning; Classifier (UML); Artificial intelligence; Medicine; Computer science; Gerontology; Endocrinology","score_opus":0.4280772098357785,"score_gpt":0.48578382325249525,"score_spread":0.057706613416716734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387345674","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5532176,0.0020696314,0.4227561,0.0033012552,0.0004999548,0.0005770107,0.0042524943,0.0020733848,0.011252654],"genre_scores_gemma":[0.93264157,0.00048941304,0.061463863,0.00020519432,0.00016192162,0.00016839225,0.0015466968,0.000014692314,0.0033083241],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99960905,0.00012772577,0.000039358463,0.000084746425,0.000082414226,0.00005667035],"domain_scores_gemma":[0.99899226,0.00063762744,0.00007809387,0.000039247698,0.00020652844,0.000046235742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010347221,0.000577279,0.00052702334,0.002232912,0.00029382264,0.0008015541,0.00067394966,0.00084937393,0.0019580873],"category_scores_gemma":[0.0026442497,0.00012945937,0.00070344034,0.0010088811,0.00012124543,0.00051959476,0.00028985532,0.00078841345,0.00094935816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051611924,0.0020418433,0.26666084,0.00027299608,0.0004487503,0.00054730196,0.00026109256,0.23801991,0.003925438,0.0027118693,0.008511734,0.47608212],"study_design_scores_gemma":[0.000015241435,0.00017445526,0.01958882,0.000039457416,0.00006113108,0.00013669573,0.000096353,0.97539943,0.0010729908,0.0021499393,0.0012457748,0.000019606163],"about_ca_topic_score_codex":0.005169658,"about_ca_topic_score_gemma":0.004095839,"teacher_disagreement_score":0.005169658,"about_ca_system_score_codex":0.00046462228,"about_ca_system_score_gemma":0.0007755288,"threshold_uncertainty_score":0.010279119},"labels":[],"label_agreement":null},{"id":"W4387377612","doi":"10.59934/jaiea.v3i1.272","title":"Comparison Of K-Nearest Neighbor And CNN Classification Methods In Diabetic Data Sets","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Diabetes mellitus; Medicine; Incidence (geometry); k-nearest neighbors algorithm; Disease; Computer science; Artificial intelligence; Mathematics; Internal medicine","score_opus":0.4373307123951116,"score_gpt":0.5767059050888049,"score_spread":0.1393751926936933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387377612","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9008258,0.012303113,0.06109162,0.0015524363,0.0016658872,0.00042042788,0.0059136776,0.0020540173,0.014173051],"genre_scores_gemma":[0.92990327,0.002305015,0.054310907,0.0002521854,0.00016480277,0.00011630464,0.008665368,0.000073705625,0.0042084246],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99760985,0.00040339818,0.00038637652,0.0003898424,0.0009261622,0.00028430313],"domain_scores_gemma":[0.9959258,0.0016980289,0.00025746558,0.0003736985,0.0015574084,0.00018755758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034424851,0.0009495002,0.0011544554,0.0031706928,0.00068187225,0.0016289891,0.0011720083,0.0012013859,0.0012551999],"category_scores_gemma":[0.008739851,0.00021342837,0.0011855074,0.0023273495,0.00035595626,0.0015392818,0.0006732743,0.00083102525,0.0006960422],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024597056,0.0011959928,0.08918712,0.0007586874,0.00080383575,0.00046573582,0.00028775635,0.119609155,0.0036663162,0.0016710962,0.018280758,0.7616138],"study_design_scores_gemma":[0.000056449142,0.00057034125,0.0421822,0.00014385486,0.00014850555,0.0004153193,0.0008334976,0.94148386,0.007910897,0.0016133867,0.0045518433,0.00008995685],"about_ca_topic_score_codex":0.03972467,"about_ca_topic_score_gemma":0.030007817,"teacher_disagreement_score":0.03972467,"about_ca_system_score_codex":0.0017910873,"about_ca_system_score_gemma":0.00084887794,"threshold_uncertainty_score":0.07898688},"labels":[],"label_agreement":null},{"id":"W4387422232","doi":"10.3390/technologies11050138","title":"Heuristic Weight Initialization for Diagnosing Heart Diseases Using Feature Ranking","year":2023,"lang":"en","type":"article","venue":"Technologies","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Computer science; Initialization; Artificial intelligence; Heuristic; Machine learning; Classifier (UML); Feature (linguistics); Feature engineering; Deep learning","score_opus":0.23713293152877538,"score_gpt":0.5158390178956147,"score_spread":0.27870608636683936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387422232","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056947578,0.0010078986,0.93621695,0.00052337686,0.00017248112,0.00023609369,0.00020463562,0.0021252932,0.0025655814],"genre_scores_gemma":[0.7153607,0.000386904,0.2781799,0.00050467346,0.00021137299,0.00034327942,0.00084691704,0.00020624077,0.003959919],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994154,0.00013866775,0.000047333633,0.00014859239,0.00013538306,0.00011468825],"domain_scores_gemma":[0.99888426,0.00055963884,0.000103705184,0.00006948639,0.00031712244,0.00006584099],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013729858,0.0014083574,0.0016063276,0.001715671,0.0006843836,0.0010964135,0.0018229609,0.0018656373,0.0029849084],"category_scores_gemma":[0.004664177,0.0006121189,0.0008543729,0.0011289766,0.00054763764,0.0008786011,0.00069053983,0.001469401,0.0015258763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004138238,0.00042016624,0.0041496116,0.00015363246,0.00010951277,0.00021329835,0.000094498864,0.48544556,0.007865306,0.003774924,0.008543399,0.48881632],"study_design_scores_gemma":[0.000023920604,0.000054776272,0.0004487732,0.000011519294,0.0000142732815,0.000039062776,0.000010439569,0.9966949,0.0009549809,0.0012995787,0.0004386505,0.000009055172],"about_ca_topic_score_codex":0.01068769,"about_ca_topic_score_gemma":0.010401788,"teacher_disagreement_score":0.01068769,"about_ca_system_score_codex":0.0009022558,"about_ca_system_score_gemma":0.0017603348,"threshold_uncertainty_score":0.021250963},"labels":[],"label_agreement":null},{"id":"W4387442026","doi":"10.32604/cmc.2023.039020","title":"Detection of Different Stages of Alzheimer’s Disease Using CNN Classifier","year":2023,"lang":"en","type":"article","venue":"Computers, materials & continua/Computers, materials & continua (Print)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Overfitting; Computer science; Artificial intelligence; Support vector machine; Random forest; Machine learning; Cognitive impairment; Binary classification; Preprocessor; Convolutional neural network; Oversampling; Deep learning; Pattern recognition (psychology); Prodromal Stage; Cognition; Artificial neural network; Psychology; Neuroscience","score_opus":0.13106549311525564,"score_gpt":0.4005705361449948,"score_spread":0.2695050430297392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387442026","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8931869,0.0047509004,0.07094001,0.00061373395,0.0005684925,0.00040029566,0.014368275,0.003563568,0.01160782],"genre_scores_gemma":[0.9332591,0.001301793,0.04515839,0.0002957,0.00012923562,0.00015553196,0.014340777,0.00006808764,0.0052912594],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99952865,0.000024712426,0.000042201984,0.0001572908,0.00011526147,0.00013200684],"domain_scores_gemma":[0.9995053,0.00007085971,0.000059949918,0.00005504945,0.00026617118,0.000042725456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005120953,0.0010687241,0.0006895061,0.0023919835,0.000359827,0.00068594556,0.0007106067,0.0007075004,0.0010559493],"category_scores_gemma":[0.0012601478,0.0002601016,0.0007860613,0.0009283353,0.00019427575,0.00060070294,0.00046643463,0.0006740945,0.00067337824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018936375,0.0008532537,0.19483314,0.00049357937,0.0004937557,0.0021405206,0.0003121394,0.027994428,0.045799132,0.0013587414,0.03598049,0.68784726],"study_design_scores_gemma":[0.0000679632,0.00043265466,0.16326775,0.00021919423,0.00038432493,0.0016951269,0.00032207943,0.7621455,0.056367442,0.0024167493,0.012566666,0.000114486116],"about_ca_topic_score_codex":0.025909984,"about_ca_topic_score_gemma":0.034347195,"teacher_disagreement_score":0.025909984,"about_ca_system_score_codex":0.0009073439,"about_ca_system_score_gemma":0.00068529963,"threshold_uncertainty_score":0.05151838},"labels":[],"label_agreement":null},{"id":"W4387506384","doi":"10.23977/acss.2023.070804","title":"Application of XGBoost Model in the Field of Diabetes Prediction","year":2023,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Diabetes mellitus; Field (mathematics); Computer science; Medicine; Process (computing); Artificial intelligence; Statistics; Machine learning; Mathematics; Endocrinology","score_opus":0.08958641983617358,"score_gpt":0.4521006640052247,"score_spread":0.3625142441690511,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387506384","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19215079,0.0063114497,0.7879986,0.002187425,0.0009540471,0.00021292076,0.0004401256,0.0025868444,0.007157784],"genre_scores_gemma":[0.8758481,0.0019694997,0.11125471,0.00075481,0.00034513057,0.00019850043,0.00079469604,0.0001235491,0.008710928],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930704,0.00017469938,0.000047107987,0.00015027977,0.00018654294,0.00013441913],"domain_scores_gemma":[0.99935967,0.00029037028,0.00005412163,0.000026200903,0.00022439274,0.00004523769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014448308,0.00075264316,0.0013847537,0.0010804917,0.00072360557,0.0009779759,0.0011301414,0.0012694442,0.001630666],"category_scores_gemma":[0.0016005009,0.0003217468,0.0008169596,0.0011826268,0.00043693956,0.0006911333,0.00049032614,0.0011713175,0.0004417306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000511741,0.000431045,0.013547816,0.00023147397,0.0002682396,0.00027104004,0.00010823234,0.70192516,0.0027455832,0.0030017453,0.007213804,0.26974416],"study_design_scores_gemma":[0.000016173359,0.000076608434,0.0015736707,0.000019542387,0.00002452109,0.000041767988,0.000022100752,0.99524814,0.00077422406,0.0012646191,0.0009269382,0.0000116516],"about_ca_topic_score_codex":0.020886527,"about_ca_topic_score_gemma":0.009431473,"teacher_disagreement_score":0.020886527,"about_ca_system_score_codex":0.00070428377,"about_ca_system_score_gemma":0.001656989,"threshold_uncertainty_score":0.041529953},"labels":[],"label_agreement":null},{"id":"W4387744393","doi":"10.21203/rs.3.rs-3446513/v1","title":"Personalized Medicine for Cardiovascular Disease Risk in Artificial Intelligence Framework","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Personalized medicine; Modalities; Precision medicine; Artificial intelligence; Disease; Psychological intervention; Applications of artificial intelligence; Field (mathematics); Computer science; Risk analysis (engineering); Medicine; Management science; Engineering; Bioinformatics; Pathology","score_opus":0.5530833297547393,"score_gpt":0.6113671717274382,"score_spread":0.05828384197269887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387744393","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018414242,0.092709765,0.8050632,0.027702285,0.00045613493,0.0012624882,0.0044617727,0.0007858878,0.049144126],"genre_scores_gemma":[0.46962616,0.028035054,0.49176696,0.0030344012,0.00040776198,0.002378213,0.0026116497,0.00004385631,0.0020959054],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9916632,0.0063249455,0.000532434,0.00054651254,0.00077316165,0.0001597324],"domain_scores_gemma":[0.99098283,0.0074807364,0.00055459223,0.00022950463,0.0006056678,0.00014659943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010014521,0.0007519442,0.00094431854,0.006091981,0.00055222516,0.0029899718,0.0014687966,0.0014683581,0.0035286876],"category_scores_gemma":[0.014887051,0.000277372,0.001991341,0.004243017,0.0014300054,0.0017025141,0.0026281655,0.0015086541,0.00041924266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000145727,0.00015863882,0.011269723,0.011535903,0.0018229187,0.00054305856,0.0009611481,0.08345445,0.0004296377,0.5822689,0.018067395,0.28934255],"study_design_scores_gemma":[0.00011471052,0.00022496335,0.009675111,0.007593517,0.0013874779,0.00054526766,0.0011846384,0.18062715,0.0006675951,0.6953672,0.102500975,0.0001113317],"about_ca_topic_score_codex":0.004835574,"about_ca_topic_score_gemma":0.004805938,"teacher_disagreement_score":0.010014521,"about_ca_system_score_codex":0.0027353314,"about_ca_system_score_gemma":0.004443852,"threshold_uncertainty_score":0.052962482},"labels":[],"label_agreement":null},{"id":"W4387832644","doi":"10.21065/advjbiomedsci.5.1","title":"COVID-19: RELIABLE SCIENTIFIC KNOWLEDGE AMID UNCERTAIN AND COMPLEX INFORMATION","year":2020,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Data science; Virology; Computer science; Epistemology; Medicine; Philosophy; Outbreak; Infectious disease (medical specialty)","score_opus":0.3686656086016869,"score_gpt":0.5169381065006352,"score_spread":0.1482724978989483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387832644","genre_codex":"methods","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028323405,0.005457954,0.722041,0.015089847,0.0027194656,0.0022113349,0.07803632,0.06707968,0.1045321],"genre_scores_gemma":[0.042669594,0.009479337,0.6999178,0.0021029895,0.0013086569,0.0013700344,0.17692193,0.01244256,0.05378714],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97976077,0.003066085,0.0026329153,0.0015492317,0.011911401,0.0010796038],"domain_scores_gemma":[0.89159983,0.033869416,0.004127611,0.02817529,0.03637526,0.005852587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02395991,0.0019218471,0.0027419028,0.017067006,0.004806905,0.02689904,0.0064600795,0.003813845,0.049079467],"category_scores_gemma":[0.096193254,0.0025045935,0.0019918962,0.019495882,0.0045972033,0.013014653,0.014631632,0.0042441115,0.041102305],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029835093,0.00008918763,0.0022068298,0.0024986262,0.000186904,0.00082168076,0.00061563175,0.005236419,0.0021399204,0.11120331,0.576126,0.2985771],"study_design_scores_gemma":[0.00009209136,0.000040142855,0.0011882224,0.0014471896,0.00006725209,0.00052413985,0.00042585516,0.019619934,0.0031066625,0.09421811,0.879136,0.00013436067],"about_ca_topic_score_codex":0.08923705,"about_ca_topic_score_gemma":0.10439682,"teacher_disagreement_score":0.08923705,"about_ca_system_score_codex":0.006967361,"about_ca_system_score_gemma":0.050459154,"threshold_uncertainty_score":0.17743522},"labels":[],"label_agreement":null},{"id":"W4387933953","doi":"10.1016/j.jcjd.2023.10.193","title":"DEVELOPMENT OF DIABETES HEALTH LITERACY ASSESSMENT TOOL TO SUPPORT HEALTH-CARE PROVIDERS DURING VIRTUAL VISITS","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Diabetes","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Health literacy; Diabetes mellitus; Literacy; Pandemic; Health care; Patient education; Health education; Gerontology; Family medicine; Coronavirus disease 2019 (COVID-19); Nursing; Public health; Internal medicine; Disease; Endocrinology","score_opus":0.0666655892313024,"score_gpt":0.43027757304442543,"score_spread":0.36361198381312304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387933953","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.917424,0.00093052187,0.044564527,0.004168148,0.0005232169,0.0054768794,0.00235832,0.0037785422,0.020775875],"genre_scores_gemma":[0.7770853,0.00090841885,0.20606843,0.0015416582,0.000104025356,0.0042907516,0.0026682185,0.00011748942,0.007215679],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987245,0.0005166065,0.0001943303,0.00012441719,0.00029988188,0.00014027917],"domain_scores_gemma":[0.9931411,0.0040946873,0.0004924581,0.00015213681,0.0015181035,0.0006014689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021481377,0.000435517,0.0004628124,0.0011551264,0.00037760983,0.001105513,0.0007825941,0.00062253926,0.003573199],"category_scores_gemma":[0.014472602,0.00027860436,0.0006502942,0.0004740014,0.000118728174,0.0009681835,0.0009125055,0.0008626752,0.00099182],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007465143,0.006397369,0.21056874,0.00093129644,0.00011865686,0.00086793624,0.0041971197,0.00080690015,0.0064906836,0.00063173886,0.02918871,0.7390543],"study_design_scores_gemma":[0.0012812028,0.007430135,0.7714523,0.003877755,0.0013114267,0.005354342,0.019009164,0.06072224,0.037401993,0.0032748156,0.08830352,0.0005810454],"about_ca_topic_score_codex":0.0028390882,"about_ca_topic_score_gemma":0.004460498,"teacher_disagreement_score":0.003573199,"about_ca_system_score_codex":0.0005214829,"about_ca_system_score_gemma":0.0019510922,"threshold_uncertainty_score":0.011953592},"labels":[],"label_agreement":null},{"id":"W4387947420","doi":"10.48550/arxiv.2310.15719","title":"Recurrent Linear Transformers","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; University of Alberta; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Inference; Computer science; Transformer; Leverage (statistics); Architecture; Reinforcement learning; Artificial intelligence; Machine learning; Engineering","score_opus":0.4979293358280025,"score_gpt":0.38548788961338076,"score_spread":0.11244144621462171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387947420","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012718982,0.0003070356,0.97432023,0.0002680064,0.00009292807,0.00008139956,0.0003654211,0.004155836,0.007690175],"genre_scores_gemma":[0.7438093,0.000465538,0.22731824,0.00056621945,0.0001199595,0.00021473708,0.0010516328,0.0004806175,0.025973825],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995061,0.00009358022,0.000035090576,0.00015942125,0.00012254264,0.00008324007],"domain_scores_gemma":[0.9989926,0.00041405862,0.000071644405,0.00019724011,0.00026175287,0.00006257285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075118995,0.00075414655,0.0006978605,0.0005160922,0.0003582361,0.0012044017,0.0019391091,0.00087993196,0.014548712],"category_scores_gemma":[0.0031676514,0.0004942319,0.0008321373,0.00052041013,0.0006948857,0.002336256,0.0014558203,0.0011910956,0.003370642],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045325566,0.00017780422,0.0021445064,0.00033908113,0.00013763487,0.00049852685,0.00028573518,0.36831802,0.019319227,0.10472311,0.018296137,0.48530698],"study_design_scores_gemma":[0.000020659092,0.00006148432,0.0001529896,0.000011908929,0.00002581483,0.000107066255,0.00002399076,0.9658897,0.0043672845,0.026374573,0.002953044,0.000011445935],"about_ca_topic_score_codex":0.0057106544,"about_ca_topic_score_gemma":0.010159857,"teacher_disagreement_score":0.014548712,"about_ca_system_score_codex":0.00095665385,"about_ca_system_score_gemma":0.0012928187,"threshold_uncertainty_score":0.048670292},"labels":[],"label_agreement":null},{"id":"W4387950320","doi":"10.1371/journal.pdig.0000354","title":"Artificial intelligence with temporal features outperforms machine learning in predicting diabetes","year":2023,"lang":"en","type":"article","venue":"PLOS Digital Health","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University; York University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Overfitting; Machine learning; Deep learning; Computer science; Diabetes mellitus; Predictive modelling; Body mass index; Medicine; Artificial neural network; Internal medicine","score_opus":0.13506351911255118,"score_gpt":0.41615261337992043,"score_spread":0.2810890942673693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387950320","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83523405,0.016414963,0.10524338,0.009041933,0.0011072193,0.00013237841,0.0016639815,0.0015846667,0.029577456],"genre_scores_gemma":[0.9826249,0.0012189014,0.01343655,0.00035667815,0.00014642629,0.000013236306,0.0007161049,0.00002271623,0.0014644836],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897623,0.00036979202,0.00007775449,0.00021100092,0.0002647206,0.00010051006],"domain_scores_gemma":[0.99575496,0.0031353903,0.00021336468,0.00033214054,0.00041470045,0.00014953296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036889215,0.000800397,0.0005872073,0.0008134921,0.00035148486,0.0016511556,0.0005197912,0.0009565796,0.0012813215],"category_scores_gemma":[0.009460191,0.00016878676,0.0005830425,0.0008100133,0.00038989534,0.001748032,0.0007946744,0.001576044,0.00045791487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008789419,0.00064688147,0.07520431,0.00026924838,0.00040111545,0.00018636459,0.0001405323,0.56659514,0.0013560867,0.007340401,0.007969974,0.33901104],"study_design_scores_gemma":[0.000013543317,0.00017429522,0.0073178257,0.00005959617,0.000044645683,0.000028039665,0.000045826808,0.98551416,0.00053640566,0.0051959045,0.0010540528,0.000015676504],"about_ca_topic_score_codex":0.0213887,"about_ca_topic_score_gemma":0.016372379,"teacher_disagreement_score":0.0213887,"about_ca_system_score_codex":0.0010453674,"about_ca_system_score_gemma":0.0013100978,"threshold_uncertainty_score":0.04252845},"labels":[],"label_agreement":null},{"id":"W4388095729","doi":"10.5267/j.ijdns.2023.10.006","title":"Diagnosing diabetes mellitus using machine learning techniques","year":2023,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Classifier (UML); Blindness; Machine learning; Feature selection; Computer science; Diabetes mellitus; Medicine; Seriousness; Pattern recognition (psychology); Optometry","score_opus":0.23152349928090468,"score_gpt":0.5234032326575142,"score_spread":0.29187973337660955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388095729","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2538145,0.015462248,0.7137452,0.0015857734,0.00056596735,0.00055997894,0.0021916118,0.0032892777,0.0087854],"genre_scores_gemma":[0.71655273,0.0050273393,0.27356553,0.00038851786,0.0002721007,0.00017788238,0.0022016347,0.000043859538,0.0017705273],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9987691,0.00030476146,0.00018052316,0.0002277018,0.00039730157,0.00012061029],"domain_scores_gemma":[0.99783933,0.001208084,0.00026565912,0.00010505324,0.0005241645,0.000057643363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018163164,0.0010037324,0.0012181236,0.0035784454,0.00038342847,0.001749438,0.00074822974,0.0008809382,0.0009000384],"category_scores_gemma":[0.0048588095,0.00016713973,0.0010730748,0.0023049344,0.00017702072,0.00091110234,0.00051584875,0.0009627862,0.0007036723],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037038972,0.00055708794,0.045310978,0.00060533494,0.0003753785,0.00043085855,0.00010749688,0.040903706,0.010923872,0.0012190981,0.005410709,0.8937851],"study_design_scores_gemma":[0.00006307763,0.00055664586,0.034236196,0.0005026359,0.00046239962,0.0012038243,0.00041384654,0.9210517,0.023918398,0.0073666726,0.010119854,0.00010480517],"about_ca_topic_score_codex":0.0024553838,"about_ca_topic_score_gemma":0.001901966,"teacher_disagreement_score":0.0035784454,"about_ca_system_score_codex":0.00044853656,"about_ca_system_score_gemma":0.00067270856,"threshold_uncertainty_score":0.009605706},"labels":[],"label_agreement":null},{"id":"W4388107968","doi":"10.3390/a16110503","title":"Machine Learning-Based Approach for Predicting Diabetes Employing Socio-Demographic Characteristics","year":2023,"lang":"en","type":"article","venue":"Algorithms","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Polyuria; Polydipsia; Diabetes mellitus; Machine learning; Artificial intelligence; Medicine; Classifier (UML); Computer science","score_opus":0.12617736418784742,"score_gpt":0.4190133564460259,"score_spread":0.29283599225817847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388107968","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5226435,0.0018104308,0.45951644,0.0025352458,0.00035366774,0.0005095193,0.002256854,0.0015705373,0.008803747],"genre_scores_gemma":[0.9340128,0.0003935022,0.062143665,0.00018766613,0.00010915236,0.00016698567,0.0008982975,0.000012163044,0.0020757508],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999605,0.00013630194,0.000042140055,0.00008355811,0.00008062679,0.000052306834],"domain_scores_gemma":[0.9988335,0.00076248264,0.00009460317,0.00003812804,0.00022703213,0.00004417332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011512066,0.0005676359,0.0005275541,0.0019870517,0.0003086725,0.00080661185,0.0006996905,0.00080426637,0.0016034388],"category_scores_gemma":[0.0031100651,0.00012349462,0.00065779185,0.00088582054,0.00014132063,0.0005556412,0.0003067173,0.0007753474,0.00066712877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038974814,0.0016368481,0.18835893,0.00020797204,0.0003498379,0.00036779192,0.00019312497,0.3844377,0.0029931613,0.0025159232,0.0052009406,0.41334793],"study_design_scores_gemma":[0.000010003044,0.00011557973,0.009601504,0.00002674713,0.00003571115,0.00007607611,0.000056399746,0.9874527,0.0006554091,0.0012655571,0.000691765,0.0000125329],"about_ca_topic_score_codex":0.005625758,"about_ca_topic_score_gemma":0.004275297,"teacher_disagreement_score":0.005625758,"about_ca_system_score_codex":0.00049434917,"about_ca_system_score_gemma":0.00085492834,"threshold_uncertainty_score":0.011186004},"labels":[],"label_agreement":null},{"id":"W4388188064","doi":"10.36948/ijfmr.2023.v05i05.7715","title":"Cardiovascular Disease (CVD) Prediction Using Machine Learning Techniques With XGBoost Feature Importance Analysis","year":2023,"lang":"en","type":"article","venue":"International Journal For Multidisciplinary Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Random forest; Support vector machine; Logistic regression; Machine learning; Feature (linguistics); Benchmark (surveying); Artificial intelligence; Disease; Preprocessor; Data pre-processing; Computer science; Medicine; Data mining; Internal medicine","score_opus":0.3025652953901585,"score_gpt":0.5685306917909563,"score_spread":0.2659653964007978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388188064","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23544605,0.0010731736,0.75823015,0.00036087297,0.00017562036,0.00021237604,0.00036754322,0.0017243095,0.0024099464],"genre_scores_gemma":[0.751188,0.00031348935,0.2450291,0.00008930867,0.00007078028,0.0001811951,0.00076524285,0.000054853877,0.0023080318],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996816,0.00007533523,0.00002766205,0.00006171623,0.00010230388,0.00005141989],"domain_scores_gemma":[0.9994874,0.0002342452,0.000059751925,0.000027383598,0.0001709674,0.000020284253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086352427,0.0004879322,0.000721404,0.001597513,0.00036202118,0.0004596287,0.00062247104,0.0005390646,0.00098914],"category_scores_gemma":[0.0015671871,0.00021550184,0.0005801064,0.0011803006,0.00014497017,0.00041519327,0.00029741693,0.00065963913,0.00030273432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033867155,0.00078510516,0.030115193,0.00016376641,0.0001681836,0.00024659507,0.0000978588,0.40536755,0.0068735713,0.0018977762,0.0052199494,0.5487257],"study_design_scores_gemma":[0.000008828425,0.00005268916,0.0032188005,0.000009493509,0.000011155779,0.000035025787,0.000011218448,0.9948067,0.0009473143,0.000509623,0.00038369835,0.0000054403263],"about_ca_topic_score_codex":0.006984888,"about_ca_topic_score_gemma":0.0066148443,"teacher_disagreement_score":0.006984888,"about_ca_system_score_codex":0.00034438208,"about_ca_system_score_gemma":0.0007779418,"threshold_uncertainty_score":0.013888478},"labels":[],"label_agreement":null},{"id":"W4388200291","doi":"10.1007/978-3-031-41925-6_2","title":"Obesity Level Prediction Using Multinomial Logistic Regression","year":2023,"lang":"en","type":"book-chapter","venue":"˜The œSpringer series in applied machine learning","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Multinomial logistic regression; Logistic regression; Obesity; Statistics; Multinomial distribution; Medicine; Econometrics; Mathematics; Internal medicine","score_opus":0.22912215426518398,"score_gpt":0.41264193896282575,"score_spread":0.18351978469764177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388200291","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11970899,0.00927063,0.8516094,0.0028584104,0.0008109494,0.00005382965,0.002285952,0.004005292,0.009396629],"genre_scores_gemma":[0.70640033,0.0052182917,0.23964177,0.00060717564,0.0010084502,0.00017046559,0.0054861256,0.00066559616,0.04080181],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99962616,0.00017891626,0.000024961852,0.000079995014,0.000056014822,0.000033941415],"domain_scores_gemma":[0.99832183,0.0013318015,0.00008756899,0.000093585295,0.00013455888,0.000030536943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014694072,0.00082665175,0.0007663282,0.0009359011,0.00020860384,0.00094435,0.00096445665,0.00062094943,0.004112864],"category_scores_gemma":[0.0040021306,0.00047871505,0.0010503047,0.0010793338,0.00015501947,0.0008581578,0.00074873836,0.0015423049,0.003834177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000458702,0.00030153833,0.055593476,0.00019013858,0.0005509823,0.00038641115,0.00007989037,0.16553883,0.0019971477,0.004500112,0.03058564,0.73981714],"study_design_scores_gemma":[0.000010504919,0.00003940203,0.00589658,0.000047027006,0.000057471945,0.00012962538,0.000020608355,0.98627824,0.0005527284,0.0045635425,0.0023823483,0.000022014352],"about_ca_topic_score_codex":0.0029366296,"about_ca_topic_score_gemma":0.003911406,"teacher_disagreement_score":0.004112864,"about_ca_system_score_codex":0.00025705373,"about_ca_system_score_gemma":0.0002652986,"threshold_uncertainty_score":0.013758898},"labels":[],"label_agreement":null},{"id":"W4388203123","doi":"10.18280/mmep.100538","title":"An Automated System for Osteoarthritis Severity Scoring Using Residual Neural Networks","year":2023,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Residual; Artificial neural network; Osteoarthritis; Computer science; Artificial intelligence; Scoring system; Medicine; Internal medicine; Pathology","score_opus":0.15635468234958996,"score_gpt":0.4022517819595283,"score_spread":0.24589709960993836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388203123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26468474,0.0013461777,0.7002997,0.0005406881,0.0002750418,0.0009218441,0.0064728316,0.01845063,0.0070084212],"genre_scores_gemma":[0.7477474,0.0005935975,0.23744597,0.00020879554,0.0001166842,0.0004278445,0.0073741334,0.0001481534,0.0059375204],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994049,0.00009820279,0.000074565825,0.0001598446,0.0001953333,0.00006714051],"domain_scores_gemma":[0.99911624,0.00013771873,0.00012878845,0.00008805664,0.00047971794,0.000049436723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097329105,0.00082159374,0.0005491119,0.001955894,0.00020694766,0.00055937335,0.00069682277,0.000482974,0.0020699538],"category_scores_gemma":[0.0022520132,0.00021437103,0.00046076268,0.000597447,0.00013886807,0.00041089163,0.00071440404,0.00037800855,0.0016763774],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00087566243,0.00035862255,0.04074561,0.0002992594,0.00015493364,0.00048077913,0.0001208761,0.03285984,0.035506804,0.0011561516,0.014477097,0.8729644],"study_design_scores_gemma":[0.00006859976,0.0002989139,0.031039419,0.00009563471,0.00008292224,0.00037878478,0.0001006734,0.9335683,0.0267983,0.0016994439,0.005805815,0.00006315784],"about_ca_topic_score_codex":0.0080018705,"about_ca_topic_score_gemma":0.011190524,"teacher_disagreement_score":0.0080018705,"about_ca_system_score_codex":0.0005338526,"about_ca_system_score_gemma":0.0006588933,"threshold_uncertainty_score":0.015910566},"labels":[],"label_agreement":null},{"id":"W4388264150","doi":"10.1016/j.jcjd.2023.10.218","title":"SOCIAL SUPPORT IN A VIRTUAL WORLD: NETWORK ANALYSIS AND DIRECTED CONTENT ANALYSIS OF A PEER NETWORK FOR YOUTH WITH TYPE 1 DIABETES","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Diabetes","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Toronto Public Health","funders":"","keywords":"Centrality; Thematic analysis; Social network analysis; Content analysis; Medicine; Peer support; Social network (sociolinguistics); General partnership; Social support; Peer-to-peer; Network analysis; Internet privacy; World Wide Web; Data science; Computer science; Social media; Social psychology; Psychology; Qualitative research; Nursing; Sociology; Engineering; Business","score_opus":0.14014028281830673,"score_gpt":0.39347774725457224,"score_spread":0.2533374644362655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388264150","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9986526,0.000060847553,0.00046345,0.00010116169,0.0000050326116,0.00002394063,0.00022380521,0.000005933724,0.0004632158],"genre_scores_gemma":[0.9987484,0.00006231331,0.0007130319,0.000010280701,0.000007862598,0.00003476593,0.00027254608,0.0000024731137,0.00014827699],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993761,0.0003610371,0.000042745854,0.00007522054,0.000079168196,0.00006561797],"domain_scores_gemma":[0.99590415,0.0026657328,0.0005508983,0.00013491037,0.0003744733,0.00036997025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010158399,0.00017695558,0.00019192275,0.0022423463,0.00093449594,0.001182833,0.00047265977,0.0004295357,0.0013312851],"category_scores_gemma":[0.008068786,0.00008485173,0.00030993487,0.001687337,0.00023423205,0.0014475776,0.0010282663,0.00037176232,0.00012842644],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040517203,0.0007166896,0.91289574,0.00022432816,0.00022932753,0.00041004445,0.020483263,0.001811745,0.0011927439,0.0015306141,0.0016641165,0.05843615],"study_design_scores_gemma":[0.000026986203,0.00035420182,0.88302463,0.00011404747,0.00037774592,0.0004384228,0.066112556,0.042006258,0.0008493871,0.0028864525,0.0037590668,0.00005017407],"about_ca_topic_score_codex":0.012165917,"about_ca_topic_score_gemma":0.019433312,"teacher_disagreement_score":0.012165917,"about_ca_system_score_codex":0.0007685313,"about_ca_system_score_gemma":0.00055827317,"threshold_uncertainty_score":0.024190187},"labels":[],"label_agreement":null},{"id":"W4388273445","doi":"10.1016/j.jcjd.2023.10.086","title":"COMPARISON OF MACHINE LEARNING AND CONVENTIONAL STATISTICAL MODELING FOR PREDICTING READMISSION FOLLOWING ACUTE HEART FAILURE HOSPITALIZATION","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Diabetes","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Toronto Public Health","funders":"","keywords":"Medicine; Heart failure; Intensive care medicine; Machine learning; Emergency medicine; Cardiology","score_opus":0.09181456231609039,"score_gpt":0.44924866930637414,"score_spread":0.3574341069902838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388273445","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9334527,0.002164514,0.060086302,0.00092403556,0.00025181452,0.00009044848,0.00094586506,0.0004866496,0.0015976878],"genre_scores_gemma":[0.98683095,0.0004369409,0.011217703,0.00009454188,0.00010414266,0.000043173408,0.0008334676,0.000029814844,0.0004093201],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99732363,0.0017009684,0.00022068464,0.00032828524,0.00030457007,0.00012183867],"domain_scores_gemma":[0.9652215,0.031453636,0.0006883622,0.0007310379,0.0016047949,0.0003006611],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008789111,0.0011702541,0.001314277,0.0013988734,0.00033933803,0.0014665052,0.0012587346,0.001035402,0.0010568389],"category_scores_gemma":[0.022637216,0.00023075256,0.0011241329,0.00097467046,0.00029422969,0.0015704287,0.00069268624,0.0010795308,0.00027431495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009931781,0.0025841417,0.2751186,0.00051051634,0.0019805087,0.00018047943,0.00027038553,0.4678041,0.0010419968,0.0027732125,0.003630148,0.23417416],"study_design_scores_gemma":[0.00006342155,0.00048470334,0.011005359,0.00001978728,0.000091709655,0.000024288545,0.000061055165,0.98710513,0.00013064712,0.00086320407,0.00013840775,0.000012302956],"about_ca_topic_score_codex":0.010917429,"about_ca_topic_score_gemma":0.005304282,"teacher_disagreement_score":0.010917429,"about_ca_system_score_codex":0.0008980775,"about_ca_system_score_gemma":0.0014080395,"threshold_uncertainty_score":0.04648179},"labels":[],"label_agreement":null},{"id":"W4388338486","doi":"10.1007/978-981-19-4804-6_24","title":"Web Design","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Breakout; Sprocket; Computer science; Analytics; World Wide Web; Web application; Multimedia; Engineering; Database","score_opus":0.5238228624050797,"score_gpt":0.5180518116899957,"score_spread":0.005771050715083992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388338486","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010478911,0.0030574475,0.060761537,0.002242496,0.00064712187,0.00011153247,0.00034390972,0.00129156,0.93049645],"genre_scores_gemma":[0.0076136296,0.002709293,0.015877265,0.0008630594,0.00019514836,0.00010105777,0.0005299899,0.00056221295,0.97154826],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992887,0.00015169446,0.000028102215,0.000097487384,0.00038369274,0.00005028333],"domain_scores_gemma":[0.9994702,0.00015985,0.000016503973,0.00015393911,0.0001500478,0.000049430375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006992555,0.0007152863,0.0003505355,0.0016426336,0.0010573469,0.0055449507,0.000910416,0.0014626329,0.102571465],"category_scores_gemma":[0.0017588431,0.0006152839,0.00045441877,0.0017439905,0.001055193,0.0046893433,0.0015871602,0.0017674984,0.06338383],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012454165,0.000096194235,0.00015392684,0.00027957367,0.000008085906,0.00009002515,0.0006733676,0.0007090871,0.0018779313,0.29468742,0.34226623,0.35914567],"study_design_scores_gemma":[0.00000242155,0.00000700475,0.00009897522,0.00011015443,0.0000030283616,0.000117947755,0.00010269745,0.0006284541,0.00046764518,0.038361844,0.9600945,0.0000052157693],"about_ca_topic_score_codex":0.0024147872,"about_ca_topic_score_gemma":0.003790678,"teacher_disagreement_score":0.102571465,"about_ca_system_score_codex":0.0015718387,"about_ca_system_score_gemma":0.0012287397,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4388443664","doi":"10.18280/isi.280407","title":"Feature Importance Analysis for Glucose Level Detection in Type 2 Diabetes using Machine Learning","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Random forest; Logistic regression; Receiver operating characteristic; Artificial intelligence; Machine learning; Type 2 diabetes; Support vector machine; Body mass index; Computer science; Diabetes mellitus; Predictive modelling; Classifier (UML); Medicine; Internal medicine; Endocrinology","score_opus":0.1204048617906611,"score_gpt":0.3972895774949019,"score_spread":0.2768847157042408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388443664","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32603067,0.0035397813,0.66594243,0.0005774851,0.00017965563,0.000211498,0.0008897425,0.0011986316,0.0014300991],"genre_scores_gemma":[0.86082685,0.00058689597,0.1371655,0.0001257394,0.0001443947,0.00008256287,0.0007515668,0.000022908302,0.00029358245],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991122,0.00031776342,0.000092307986,0.000174073,0.00022774156,0.00007588486],"domain_scores_gemma":[0.9973978,0.0017133872,0.0003672506,0.00012244425,0.00032400238,0.000075070704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015392407,0.0007176043,0.00086950447,0.0026863867,0.00024135195,0.0006570347,0.0005320647,0.0004714855,0.00055496267],"category_scores_gemma":[0.0056427326,0.00015861822,0.00065415434,0.0015275584,0.0001843557,0.0005399774,0.00036751665,0.0007047807,0.00026382375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072332215,0.0007367715,0.19747911,0.00031246027,0.00034109238,0.00060641015,0.00013838563,0.039361015,0.01709279,0.0012795966,0.0031370563,0.738792],"study_design_scores_gemma":[0.000049927286,0.0004536289,0.08407421,0.00007123614,0.00016637763,0.00082484155,0.000077697034,0.8975154,0.010698284,0.00418834,0.0018090331,0.000071079645],"about_ca_topic_score_codex":0.0019027701,"about_ca_topic_score_gemma":0.001995776,"teacher_disagreement_score":0.0026863867,"about_ca_system_score_codex":0.00029190307,"about_ca_system_score_gemma":0.00048568746,"threshold_uncertainty_score":0.008140385},"labels":[],"label_agreement":null},{"id":"W4388473936","doi":"10.18280/ria.370528","title":"A Comparative study on Continuous Glucose Monitoring Devices for Managing Diabetes Mellitus","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"SRM Institute of Science and Technology","keywords":"Continuous glucose monitoring; Diabetes mellitus; Medicine; Internal medicine; Intensive care medicine; Endocrinology; Type 1 diabetes","score_opus":0.25782138029640744,"score_gpt":0.48320571947904567,"score_spread":0.22538433918263823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388473936","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90341157,0.072232895,0.0024981948,0.0015442692,0.00048915803,0.0004922264,0.0007125904,0.00002335176,0.0185957],"genre_scores_gemma":[0.959857,0.03256014,0.0035122915,0.0011695569,0.00025830365,0.00031081185,0.00052189716,0.000009997817,0.001800008],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99712974,0.001140116,0.00041983044,0.00027214148,0.00088578975,0.00015243843],"domain_scores_gemma":[0.99441046,0.0027107196,0.0007491856,0.00019012029,0.0015995397,0.00033996717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034579262,0.0002913109,0.0006168134,0.0011676891,0.0004348651,0.0010668305,0.0003370505,0.00061712565,0.00280583],"category_scores_gemma":[0.009281412,0.00009102555,0.0008439377,0.0018068117,0.0003098935,0.0009440634,0.0005694067,0.00046560878,0.00034026275],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.019604579,0.0035448633,0.23272572,0.010357001,0.0013647344,0.001984239,0.0059564337,0.00027569165,0.006735767,0.0036566413,0.008023942,0.70577043],"study_design_scores_gemma":[0.0008755875,0.052756492,0.74697787,0.00852802,0.005648047,0.011417854,0.02686756,0.0014928553,0.009641196,0.001583069,0.13394004,0.00027145876],"about_ca_topic_score_codex":0.0007150321,"about_ca_topic_score_gemma":0.00088319357,"teacher_disagreement_score":0.0034579262,"about_ca_system_score_codex":0.0005304203,"about_ca_system_score_gemma":0.0006306244,"threshold_uncertainty_score":0.01828742},"labels":[],"label_agreement":null},{"id":"W4388483017","doi":"10.2196/51388","title":"Enriching Data Science and Health Care Education: Application and Impact of Synthetic Data Sets Through the Health Gym Project","year":2023,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Wellcome Trust","keywords":"Health care; Data science; Health science; Computer science; Psychology; Medical education; Medicine; Political science","score_opus":0.2861359864077737,"score_gpt":0.6359624549223465,"score_spread":0.3498264685145728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388483017","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5095159,0.0007928797,0.4136439,0.015383338,0.000900869,0.0028963943,0.022014756,0.011474259,0.023377776],"genre_scores_gemma":[0.48517683,0.00038290766,0.48921782,0.0010435729,0.000114490496,0.0016777685,0.017529722,0.0007096383,0.0041472437],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99305975,0.0051768143,0.00028511838,0.00047056604,0.00083818694,0.00016963026],"domain_scores_gemma":[0.96102196,0.03152845,0.00080434675,0.0031850813,0.0022046755,0.0012555148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012175629,0.0007131582,0.0003326756,0.0013864065,0.0007417203,0.0015284393,0.001552804,0.0012332891,0.005187109],"category_scores_gemma":[0.03542334,0.00036650116,0.00094923616,0.0012376168,0.001125356,0.0012527519,0.004062394,0.0016942694,0.0009893124],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020582993,0.00451864,0.05799472,0.0022520677,0.0003840476,0.0019921088,0.0112907,0.3380636,0.008549373,0.031898312,0.097552165,0.443446],"study_design_scores_gemma":[0.0009130321,0.0020267884,0.02496042,0.00069316913,0.00010818813,0.0009748157,0.0053800303,0.6545699,0.026208224,0.07140356,0.21248654,0.00027538594],"about_ca_topic_score_codex":0.0037299497,"about_ca_topic_score_gemma":0.0053259064,"teacher_disagreement_score":0.012175629,"about_ca_system_score_codex":0.001089292,"about_ca_system_score_gemma":0.0017937082,"threshold_uncertainty_score":0.06439167},"labels":[],"label_agreement":null},{"id":"W4388925164","doi":"10.23977/acss.2023.070912","title":"Prediction of Alzheimer's Disease Based on Random Forest Model","year":2023,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Random forest; Logistic regression; Computer science; Preprocessor; Artificial intelligence; Disease; Statistics; Machine learning; Mathematics; Medicine; Pathology","score_opus":0.1813545777965299,"score_gpt":0.4353052293867127,"score_spread":0.2539506515901828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388925164","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40322688,0.0025249845,0.58699095,0.0007260629,0.00024528799,0.00016115706,0.001971188,0.0017721778,0.0023813213],"genre_scores_gemma":[0.92470497,0.0008078875,0.07025106,0.00008819455,0.0001196205,0.00011216172,0.002176022,0.00004870687,0.0016913858],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99950755,0.00012292438,0.000035827114,0.00013789031,0.00009177769,0.00010404735],"domain_scores_gemma":[0.99926776,0.00039158648,0.000065691434,0.000032504147,0.00021239801,0.000030150743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012539141,0.0007950447,0.0008330707,0.0013485689,0.0003062647,0.000548821,0.0007465627,0.00075263664,0.0009842522],"category_scores_gemma":[0.0021028337,0.00019675888,0.0011214382,0.0007997105,0.00018079505,0.00075534836,0.00026270802,0.00056886324,0.0004521641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041557796,0.00030350074,0.03532627,0.00012645134,0.0001520342,0.00034637708,0.0000623212,0.7939127,0.0027414616,0.0014438573,0.0057897842,0.15937969],"study_design_scores_gemma":[0.000007802926,0.000027981565,0.0020010513,0.0000073820765,0.00001810187,0.00003440275,0.000008545574,0.9967764,0.0002537185,0.0006919388,0.00016436177,0.000008303739],"about_ca_topic_score_codex":0.012995659,"about_ca_topic_score_gemma":0.009326308,"teacher_disagreement_score":0.012995659,"about_ca_system_score_codex":0.00031161364,"about_ca_system_score_gemma":0.0006321143,"threshold_uncertainty_score":0.025840044},"labels":[],"label_agreement":null},{"id":"W4388982272","doi":"10.2196/49113","title":"A Machine Learning Web App to Predict Diabetic Blood Glucose Based on a Basic Noninvasive Health Checkup, Sociodemographic Characteristics, and Dietary Information: Case Study","year":2023,"lang":"en","type":"article","venue":"JMIR Diabetes","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Multimedia University","keywords":"Decision tree; Linear regression; Medicine; Diabetes mellitus; Regression analysis; Population; Regression; Artificial intelligence; Machine learning; Statistics; Computer science; Environmental health; Mathematics; Endocrinology","score_opus":0.05677314022216912,"score_gpt":0.3814811412672563,"score_spread":0.3247080010450872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388982272","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8946414,0.001183212,0.057838798,0.0062484355,0.00030653007,0.0014643415,0.0055116722,0.012625599,0.020180067],"genre_scores_gemma":[0.87560374,0.0010471536,0.09803079,0.0012479688,0.00013418477,0.0007140585,0.0036249536,0.00028349325,0.019313585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997603,0.00008243818,0.000028057675,0.00004545376,0.000054342385,0.000029449937],"domain_scores_gemma":[0.9983241,0.0012580673,0.000081369304,0.000062746265,0.00013638366,0.00013731813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082810404,0.00080023304,0.0004279879,0.00097555586,0.0003977779,0.0005567295,0.0009295673,0.0012229035,0.007061381],"category_scores_gemma":[0.0021665567,0.00023912989,0.0004433482,0.0006443774,0.00017693905,0.0006927256,0.0005377393,0.0007002889,0.0022968987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016539599,0.011313262,0.24547555,0.00085871265,0.0002004578,0.050883923,0.002088368,0.035263587,0.0055424,0.0017529927,0.06932388,0.5756428],"study_design_scores_gemma":[0.00070529524,0.0036222332,0.12967141,0.00057513296,0.00030579578,0.023482611,0.0033200225,0.7531384,0.011648698,0.0049839374,0.06821766,0.00032884593],"about_ca_topic_score_codex":0.0042134007,"about_ca_topic_score_gemma":0.006953291,"teacher_disagreement_score":0.007061381,"about_ca_system_score_codex":0.0003774306,"about_ca_system_score_gemma":0.00050506793,"threshold_uncertainty_score":0.023622692},"labels":[],"label_agreement":null},{"id":"W4389162853","doi":"10.53829/ntr201612gls","title":"Report on Apache Big Data North America 2016 and Spark Summit 2016","year":2016,"lang":"en","type":"article","venue":"NTT technical review","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Summit; SPARK (programming language); Big data; Computer science; Geography; Operating system; Cartography; Programming language","score_opus":0.40541809488598424,"score_gpt":0.5235726369743068,"score_spread":0.11815454208832255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389162853","genre_codex":"review","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00050091976,0.90855557,0.0010387701,0.04541059,0.021250267,0.00032498443,0.0026234996,0.00033508064,0.019960294],"genre_scores_gemma":[0.0036095127,0.94362223,0.0016588769,0.017720869,0.010946939,0.0007913006,0.0073103304,0.00023089118,0.01410923],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9908568,0.0010008605,0.0012475346,0.00060715905,0.005611396,0.00067618483],"domain_scores_gemma":[0.9601754,0.0058061723,0.0036784732,0.0006834114,0.026486756,0.0031697466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016148357,0.0012981817,0.0015130615,0.008629333,0.0011004941,0.004047118,0.0020227134,0.002142043,0.015739216],"category_scores_gemma":[0.028095912,0.00090570626,0.002250183,0.0083441585,0.0007137746,0.00520466,0.003987448,0.0034433606,0.010969024],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000076946286,0.000034387474,0.00029559166,0.008119973,0.00008485817,0.000051715582,0.00007006219,0.00012279282,0.00028358607,0.0014894784,0.79549736,0.19387318],"study_design_scores_gemma":[0.000011028371,0.00003641996,0.00083191076,0.0059795952,0.00007049879,0.000048212267,0.000058111633,0.000019073788,0.0001358134,0.00033754233,0.99245703,0.000014701724],"about_ca_topic_score_codex":0.012629585,"about_ca_topic_score_gemma":0.020839835,"teacher_disagreement_score":0.016148357,"about_ca_system_score_codex":0.0049606347,"about_ca_system_score_gemma":0.024795473,"threshold_uncertainty_score":0.085401714},"labels":[],"label_agreement":null},{"id":"W4389304750","doi":"10.1016/j.asoc.2023.111123","title":"A disease diagnosis system for smart healthcare based on fuzzy clustering and battle royale optimization","year":2023,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Department of Science and Technology of Jilin Province","keywords":"Computer science; Cluster analysis; Fuzzy logic; Data mining; Artificial intelligence; Machine learning; Fuzzy clustering; Precision and recall; Identification (biology)","score_opus":0.09620213078304012,"score_gpt":0.40271474974615373,"score_spread":0.3065126189631136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389304750","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05654013,0.00062808325,0.9232695,0.00060449925,0.00019896247,0.00043210058,0.00108882,0.012075472,0.0051624067],"genre_scores_gemma":[0.5129409,0.00043358165,0.47568932,0.0004757961,0.00011677879,0.00041160407,0.0018847296,0.00021208526,0.00783515],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99972504,0.000030630068,0.0000264284,0.0000950816,0.00008587147,0.00003682081],"domain_scores_gemma":[0.99980026,0.00004265736,0.00001983619,0.000018892044,0.00009191259,0.000026552669],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004718083,0.0006530025,0.0012106329,0.0016213421,0.0007749242,0.0007919506,0.00086670707,0.00090744294,0.0038967342],"category_scores_gemma":[0.0005992094,0.00027182294,0.0007927763,0.00085591944,0.00019588845,0.00076413434,0.0007006177,0.0003660289,0.0011642289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011034845,0.00058241544,0.013374206,0.00033676674,0.00032223426,0.00045103946,0.0001897147,0.12267578,0.047494967,0.004004692,0.024949996,0.78451467],"study_design_scores_gemma":[0.00007292077,0.00014990664,0.005148481,0.000018836148,0.00010556246,0.00024404991,0.000055782577,0.97457707,0.011918796,0.0025920684,0.005058498,0.00005794477],"about_ca_topic_score_codex":0.009047728,"about_ca_topic_score_gemma":0.009581814,"teacher_disagreement_score":0.009047728,"about_ca_system_score_codex":0.00072620576,"about_ca_system_score_gemma":0.0011104293,"threshold_uncertainty_score":0.017990112},"labels":[],"label_agreement":null},{"id":"W4389333195","doi":"10.1063/5.0179733","title":"An ensemble classification approach for diabetics prediction using machine learning","year":2023,"lang":"en","type":"article","venue":"AIP conference proceedings","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Computer science; Ensemble learning; Machine learning; Artificial intelligence","score_opus":0.313894891931912,"score_gpt":0.45820326758042396,"score_spread":0.14430837564851196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389333195","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18630387,0.0028962276,0.80189735,0.0008550903,0.0008192802,0.00013689509,0.0011692309,0.001846434,0.0040756804],"genre_scores_gemma":[0.8300426,0.00090717856,0.16115323,0.0002966682,0.0005140813,0.00013731168,0.002335814,0.00006361419,0.0045495355],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991516,0.0002015508,0.00008128794,0.00020983806,0.0002199063,0.00013588263],"domain_scores_gemma":[0.9982089,0.0006718922,0.00007502364,0.00014926807,0.000806421,0.00008858614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019792796,0.0009029558,0.0016847831,0.0023008282,0.00069635076,0.00095601514,0.001472683,0.0011213681,0.0016290668],"category_scores_gemma":[0.002624682,0.00031464786,0.0015709081,0.001628728,0.00014408445,0.0009928746,0.0007389685,0.0012433206,0.00071627746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049259106,0.0009453997,0.030779516,0.00007081817,0.00081190135,0.00026462326,0.00010663296,0.16980793,0.0037086045,0.0015932182,0.0093152905,0.7821034],"study_design_scores_gemma":[0.00000776339,0.000072389994,0.002209847,0.0000097103575,0.00009464126,0.00005239892,0.000019320638,0.99531806,0.00071413524,0.0009055599,0.0005848893,0.000011320222],"about_ca_topic_score_codex":0.012496788,"about_ca_topic_score_gemma":0.014415055,"teacher_disagreement_score":0.012496788,"about_ca_system_score_codex":0.0004730334,"about_ca_system_score_gemma":0.0007897749,"threshold_uncertainty_score":0.024848104},"labels":[],"label_agreement":null},{"id":"W4389464760","doi":"10.1212/wnl.92.15_supplement.p3.1-029","title":"Identification and Preliminary Validation of a Plasma Profile Associated with Cognitive Decline in Dementia and At-risk Individuals: A Retrospective Cohort Analysis (P3.1-029)","year":2019,"lang":"en","type":"article","venue":"Neurology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal; University of Calgary","funders":"","keywords":"Dementia; Retrospective cohort study; Cohort; Rowan; Medicine; Cognitive decline; Gerontology; Internal medicine; Disease","score_opus":0.03695959571407347,"score_gpt":0.3790093677448366,"score_spread":0.34204977203076314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389464760","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99844766,0.000092774615,0.0003078404,0.00001889993,0.0000071673876,0.000032838376,0.00088118267,0.000005223887,0.00020635857],"genre_scores_gemma":[0.9972838,0.00007858053,0.0006229344,0.000060802646,0.00001584227,0.000058607046,0.0014003159,0.000008010071,0.00047109398],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9996587,0.00006957682,0.000031004143,0.000117582495,0.00007093779,0.0000522025],"domain_scores_gemma":[0.9993648,0.00007415012,0.0001415977,0.0001388636,0.00015539012,0.00012525757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076668465,0.0004010872,0.00029657458,0.0006174083,0.0006325382,0.0007339484,0.00040748902,0.0005154654,0.00085909624],"category_scores_gemma":[0.0013784714,0.00026895912,0.0004310797,0.0008196348,0.00020558006,0.000298819,0.0004812172,0.0007113073,0.00039295363],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013775551,0.000286498,0.9811286,0.000019507406,0.00015553499,0.00041265134,0.00028199682,0.000063152416,0.012536635,0.00004624959,0.00027458233,0.0034169634],"study_design_scores_gemma":[0.00004382475,0.000596669,0.99691015,0.0000044601475,0.000060553935,0.0007875617,0.00013257867,0.00015005106,0.0007945497,0.000031533444,0.0004824055,0.0000056281137],"about_ca_topic_score_codex":0.0036771179,"about_ca_topic_score_gemma":0.002945398,"teacher_disagreement_score":0.0036771179,"about_ca_system_score_codex":0.00021352079,"about_ca_system_score_gemma":0.00037158516,"threshold_uncertainty_score":0.0073114634},"labels":[],"label_agreement":null},{"id":"W4390143137","doi":"10.18280/isi.280607","title":"Predictive Modelling of Glycated Hemoglobin Levels Using Machine Learning Regressors","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Glycated hemoglobin; Machine learning; Econometrics; Artificial intelligence; Hemoglobin; Computer science; Economics; Internal medicine; Diabetes mellitus; Medicine; Endocrinology; Type 2 diabetes","score_opus":0.18820808741370743,"score_gpt":0.3980303475232409,"score_spread":0.20982226010953348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390143137","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40218794,0.00187629,0.5897501,0.00075849605,0.00018802333,0.00011104289,0.00056555396,0.0018076174,0.0027548866],"genre_scores_gemma":[0.9687838,0.0005719954,0.028476287,0.00005346408,0.000043490327,0.00007545773,0.00039435137,0.000031593147,0.001569526],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99942845,0.00024764342,0.00003840453,0.00011393948,0.00011015982,0.000061311],"domain_scores_gemma":[0.99730206,0.0020012516,0.00022962422,0.00007693289,0.0003600245,0.000030204972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020532962,0.0008421034,0.0007007472,0.00078677066,0.0002256047,0.0010209156,0.0006897752,0.00074239186,0.00090476737],"category_scores_gemma":[0.0052746795,0.0003755272,0.0008848002,0.0006495181,0.00024382494,0.0006304038,0.00031940115,0.0012123482,0.00044763106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010861086,0.00009351392,0.008904931,0.000048971513,0.000089880785,0.00007511196,0.000040606395,0.96144193,0.0013641224,0.00058173324,0.00038486524,0.026865717],"study_design_scores_gemma":[0.0000022017089,0.00001538593,0.0006672334,0.0000044795074,0.0000058201463,0.000005541919,0.0000027528106,0.9988532,0.00024985248,0.00013167167,0.000058463673,0.000003331263],"about_ca_topic_score_codex":0.020079955,"about_ca_topic_score_gemma":0.008995604,"teacher_disagreement_score":0.020079955,"about_ca_system_score_codex":0.00070136884,"about_ca_system_score_gemma":0.000900137,"threshold_uncertainty_score":0.03992617},"labels":[],"label_agreement":null},{"id":"W4390204972","doi":"10.1016/j.jacadv.2023.100801","title":"Machine Learning Informed Diagnosis for Congenital Heart Disease in Large Claims Data Source","year":2023,"lang":"en","type":"article","venue":"JACC Advances","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"HEC Montréal; McGill University; Université de Montréal; McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; McGill University; Heart and Stroke Foundation of Canada","keywords":"Gradient boosting; Decision tree; Machine learning; Artificial intelligence; Logistic regression; Precision and recall; Computer science; Decision tree learning; Audit; Support vector machine; Boosting (machine learning); Random forest; Heart disease; Metric (unit); Data mining; Medicine; Internal medicine","score_opus":0.2012801566200996,"score_gpt":0.5183804850484445,"score_spread":0.3171003284283449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390204972","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75838464,0.0036780555,0.19298485,0.0059444085,0.00016317505,0.0008128356,0.02841206,0.0024499916,0.007169959],"genre_scores_gemma":[0.9258261,0.00039156817,0.06254071,0.00025563678,0.00010290687,0.000115612296,0.010306123,0.000029769182,0.00043175046],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969097,0.0014104558,0.00027140888,0.00043785112,0.00083997566,0.0001306081],"domain_scores_gemma":[0.9741643,0.016901271,0.0023823453,0.0020261842,0.004213103,0.00031274167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007893676,0.00060333003,0.00058579503,0.004557011,0.00053760427,0.0013084194,0.0008988125,0.0007400058,0.0014309714],"category_scores_gemma":[0.028014762,0.00016415023,0.00049735873,0.0025085267,0.0003346427,0.00055579876,0.0009690703,0.0008102622,0.0005318421],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005642599,0.00050504296,0.670282,0.0004429741,0.00044172144,0.0007241537,0.0003395934,0.070864715,0.0031605097,0.002589597,0.018411601,0.23167384],"study_design_scores_gemma":[0.000093451716,0.00016140418,0.3201243,0.0002754563,0.00017145883,0.00047537606,0.00033908096,0.6562146,0.005522598,0.007648365,0.008905366,0.000068612026],"about_ca_topic_score_codex":0.049587257,"about_ca_topic_score_gemma":0.06643923,"teacher_disagreement_score":0.049587257,"about_ca_system_score_codex":0.0022854873,"about_ca_system_score_gemma":0.0031040409,"threshold_uncertainty_score":0.09859723},"labels":[],"label_agreement":null},{"id":"W4390262243","doi":"10.1016/j.jns.2023.121363","title":"Comparison of metrological qualities of the Moroccan versions of MMSE (MMSE-MA) and MOCA (MOCA-MA) for detecting mild cognitive impairment and Alzheimer's disease in Moroccan population","year":2023,"lang":"en","type":"article","venue":"Journal of the Neurological Sciences","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Montreal Cognitive Assessment; Cognitive impairment; Gerontology; Disease; Cognition; Population; Medicine; Psychology; Internal medicine; Psychiatry; Environmental health","score_opus":0.34781004709860636,"score_gpt":0.5204771362448397,"score_spread":0.17266708914623335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390262243","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.996342,0.0010979857,0.0006157127,0.00010439123,0.00003587583,0.000015130708,0.00051999814,0.000013764137,0.0012551133],"genre_scores_gemma":[0.998914,0.00013745142,0.00047655922,0.000036437745,0.000012902685,0.000009940628,0.00020229153,0.000003010868,0.00020748944],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99842274,0.00057638716,0.0001802638,0.0002747992,0.000387668,0.00015811816],"domain_scores_gemma":[0.9967248,0.00089482847,0.0005877421,0.00018977423,0.001497982,0.00010488887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031773187,0.0005879166,0.0004026867,0.0012362106,0.00044822396,0.00087034004,0.000517901,0.000605806,0.00074853713],"category_scores_gemma":[0.008664575,0.00026981338,0.00048004548,0.00085913506,0.00036471503,0.00035366797,0.0005456778,0.00032892652,0.00025718487],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005264516,0.00004096072,0.9815947,0.00007623378,0.00021031845,0.00015573506,0.0009831192,0.00031780012,0.002988826,0.00015460124,0.00039239408,0.012558834],"study_design_scores_gemma":[0.000011466013,0.00025728348,0.9939182,0.00004400619,0.00011421884,0.00037708523,0.0009860173,0.0014018274,0.0016218174,0.00008871897,0.0011623576,0.000016945783],"about_ca_topic_score_codex":0.035713486,"about_ca_topic_score_gemma":0.027950712,"teacher_disagreement_score":0.035713486,"about_ca_system_score_codex":0.0008365262,"about_ca_system_score_gemma":0.00048889103,"threshold_uncertainty_score":0.071011245},"labels":[],"label_agreement":null},{"id":"W4390273464","doi":"10.18280/ria.370616","title":"Apache Spark for Analysis of Electronic Health Records: A Case Study of Diabetes Management","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Health records; SPARK (programming language); Diabetes mellitus; Diabetes management; Medicine; Electronic health record; Data science; Medical emergency; Business; Computer science; Type 2 diabetes; Political science; Health care; Endocrinology","score_opus":0.22395235616811998,"score_gpt":0.480949450543276,"score_spread":0.256997094375156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390273464","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8794983,0.0022506854,0.07092494,0.02338191,0.00032521284,0.00081905135,0.0026941109,0.0019478699,0.018158024],"genre_scores_gemma":[0.88229513,0.0017495049,0.10732492,0.0018891662,0.00021252716,0.00016716898,0.0017973772,0.0005102303,0.004053938],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9921502,0.0034977463,0.000724999,0.00076760794,0.0022715458,0.00058783585],"domain_scores_gemma":[0.98383397,0.009832016,0.0009735126,0.0018888528,0.002102751,0.0013689062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007952032,0.0005108171,0.00043265274,0.0018247545,0.0022270128,0.0031234212,0.0015867159,0.0015343796,0.0012642816],"category_scores_gemma":[0.022494433,0.0003147766,0.000858694,0.0036430224,0.001215275,0.0020487322,0.0021253605,0.001881806,0.00071022654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018069367,0.0040356484,0.25254864,0.001944628,0.0005110385,0.06934793,0.033830475,0.019538172,0.015547879,0.026879953,0.08107828,0.49293047],"study_design_scores_gemma":[0.00074081856,0.0018750462,0.18150192,0.0015195052,0.00052822474,0.05485792,0.071288556,0.17896986,0.059314363,0.0496968,0.3990828,0.00062417035],"about_ca_topic_score_codex":0.008829601,"about_ca_topic_score_gemma":0.013425039,"teacher_disagreement_score":0.008829601,"about_ca_system_score_codex":0.0018594301,"about_ca_system_score_gemma":0.0030832319,"threshold_uncertainty_score":0.04205489},"labels":[],"label_agreement":null},{"id":"W4390483489","doi":"10.23977/cpcs.2023.070115","title":"Optimization and Use of Cloud Computing in Big Data Science","year":2023,"lang":"en","type":"article","venue":"Computing Performance and Communication systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cloud computing; Big data; Computer science; Data science; Key (lock); Utility computing; Cloud computing security; Computer security; Data mining","score_opus":0.4672031048822616,"score_gpt":0.4858844733562521,"score_spread":0.018681368473990545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390483489","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11730668,0.02308519,0.74980754,0.011913353,0.0009092211,0.00035655816,0.00027236526,0.0004252281,0.095923916],"genre_scores_gemma":[0.9267097,0.0060367337,0.0633834,0.00033317506,0.00022862465,0.00008571855,0.00009285956,0.00010793616,0.0030217639],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99792224,0.00091798365,0.00008646498,0.0001637075,0.0006435162,0.00026610238],"domain_scores_gemma":[0.99680436,0.0019182933,0.00022920997,0.00024725264,0.00059860694,0.0002022252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029301404,0.0006633947,0.00090993074,0.0011500146,0.0010977068,0.0039025245,0.0010474774,0.00086279114,0.0018298083],"category_scores_gemma":[0.008650457,0.0004576526,0.00088325754,0.002442528,0.0009864231,0.003525021,0.0012571801,0.0010556742,0.00030752606],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025372976,0.0001860857,0.006400605,0.0003263642,0.00014031904,0.00020318812,0.00007422003,0.7668574,0.0034275248,0.14300613,0.0043491274,0.074775234],"study_design_scores_gemma":[0.000012152387,0.000045297373,0.0012991674,0.000049395338,0.00002952333,0.000042735996,0.000064980355,0.951024,0.0015051711,0.042488858,0.003422287,0.000016432743],"about_ca_topic_score_codex":0.0083016185,"about_ca_topic_score_gemma":0.006926305,"teacher_disagreement_score":0.0083016185,"about_ca_system_score_codex":0.002686604,"about_ca_system_score_gemma":0.0042528138,"threshold_uncertainty_score":0.019492745},"labels":[],"label_agreement":null},{"id":"W4390550959","doi":"10.1109/rmkmate59243.2023.10369394","title":"Boruta Feature Selection for Prediction of Coronary Artery Disease","year":2023,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Feature selection; Computer science; Feature (linguistics); Selection (genetic algorithm); Artificial intelligence; Decision tree; Coronary artery disease; Rough set; Data mining; Set (abstract data type); Feature extraction; Pattern recognition (psychology); Machine learning; Cardiology; Medicine","score_opus":0.1712584157690517,"score_gpt":0.474358137716327,"score_spread":0.3030997219472753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390550959","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6371021,0.0027631936,0.35376793,0.00055870455,0.0003090056,0.00018144865,0.0010091586,0.001748833,0.0025596698],"genre_scores_gemma":[0.9360401,0.0003020946,0.06098131,0.000058793867,0.00005998854,0.00010764048,0.0008685612,0.000042469088,0.0015390991],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99957734,0.00013739115,0.000036455614,0.000084958185,0.00008741195,0.00007636227],"domain_scores_gemma":[0.99945027,0.00025842426,0.000034989906,0.000030141156,0.00019488517,0.000031206346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008628606,0.00045339204,0.00089462125,0.0014958149,0.00042396254,0.0006260695,0.00036067358,0.00042857867,0.0011770698],"category_scores_gemma":[0.0018296543,0.00018968323,0.0007827992,0.00092066574,0.00015071622,0.00031317337,0.00024622603,0.0004237983,0.00041554507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014076403,0.00064305944,0.08742614,0.00022237509,0.00033255166,0.00042574873,0.00018157173,0.13665381,0.022617042,0.0013502655,0.008703834,0.74003595],"study_design_scores_gemma":[0.00008545167,0.00041201338,0.031630997,0.000042667183,0.00010901246,0.0002942155,0.00007431509,0.953639,0.009007796,0.0015113542,0.003156467,0.00003667192],"about_ca_topic_score_codex":0.0044533513,"about_ca_topic_score_gemma":0.0028914597,"teacher_disagreement_score":0.0044533513,"about_ca_system_score_codex":0.00025764827,"about_ca_system_score_gemma":0.0006865701,"threshold_uncertainty_score":0.008854866},"labels":[],"label_agreement":null},{"id":"W4390705191","doi":"10.1007/978-3-031-23161-2_522","title":"Human Interaction in Machine Learning (ML) for Healthcare","year":2024,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Computer Graphics and Games","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Health care; Computer science; Human–computer interaction; Artificial intelligence; Psychology; Political science","score_opus":0.076747821137936,"score_gpt":0.4113874631528769,"score_spread":0.3346396420149409,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390705191","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041812584,0.17727903,0.41407675,0.0123116765,0.0038634103,0.00010306255,0.00025871946,0.001781557,0.38614455],"genre_scores_gemma":[0.13296813,0.11111546,0.21659671,0.004671426,0.004925077,0.00027292763,0.00062148226,0.0006569349,0.52817184],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99959904,0.0001600717,0.000015344585,0.000052031693,0.00014796462,0.000025469877],"domain_scores_gemma":[0.99937433,0.00047535775,0.000015951071,0.000053662276,0.000051060073,0.000029647053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059046136,0.0005640612,0.00047093906,0.0005334632,0.0004299255,0.0027497318,0.0008069236,0.0014413402,0.024990177],"category_scores_gemma":[0.0012953578,0.00023447942,0.00031630992,0.00093094155,0.0011752386,0.0027584105,0.0015430085,0.0018316602,0.0066768927],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028912193,0.00007712544,0.0002004144,0.00056427764,0.00002079899,0.00006566784,0.00039866628,0.0042209676,0.0012795032,0.24214494,0.14116311,0.6098356],"study_design_scores_gemma":[0.0000091219235,0.000073549745,0.0005970674,0.0004961529,0.000016759619,0.00042590598,0.00026108557,0.025479473,0.0015104336,0.25566834,0.71543497,0.000027151737],"about_ca_topic_score_codex":0.001136994,"about_ca_topic_score_gemma":0.0019468331,"teacher_disagreement_score":0.024990177,"about_ca_system_score_codex":0.00070559117,"about_ca_system_score_gemma":0.0007420099,"threshold_uncertainty_score":0.08360046},"labels":[],"label_agreement":null},{"id":"W4390905267","doi":"10.1109/tase.2024.3350894","title":"A Novel Hybrid Ordinal Learning Model With Health Care Application","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Automation Science and Engineering","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institutes of Health; H. Lundbeck A/S; Servier; Eisai; Genentech; IXICO; Banner Alzheimer’s Foundation; Northern California Institute for Research and Education; University of Southern California; Biogen; BioClinica; Meso Scale Diagnostics; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; Eli Lilly and Company; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Canadian Institutes of Health Research; National Science Foundation","keywords":"Computer science; HOL; Artificial intelligence; Machine learning; Ordinal regression; Set (abstract data type); Interval (graph theory); Focus (optics); Data mining; Mathematics","score_opus":0.05388135887039508,"score_gpt":0.3954082732373139,"score_spread":0.34152691436691884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390905267","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029277164,0.00096670544,0.9638872,0.0015086215,0.00009443391,0.00011720009,0.0005830627,0.00060214364,0.0029635087],"genre_scores_gemma":[0.78019375,0.000808154,0.20339169,0.0013350174,0.00026040428,0.00065731443,0.001463002,0.00012463714,0.01176606],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985165,0.0006034713,0.00008600199,0.00036277162,0.00026426642,0.00016699785],"domain_scores_gemma":[0.9973316,0.0016081798,0.00025537307,0.00012919198,0.00051465706,0.00016093603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030369153,0.0008941678,0.0014001576,0.0010208582,0.0004518041,0.0018089165,0.0032305263,0.0020114025,0.0047577596],"category_scores_gemma":[0.006865127,0.00045132355,0.0009974712,0.0012483608,0.0007872326,0.0025385355,0.0020348714,0.002471734,0.0010025158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039085932,0.00035669067,0.010650751,0.0002485908,0.0001325824,0.00033551521,0.00021566187,0.8018633,0.0009846408,0.0310393,0.006816665,0.14696546],"study_design_scores_gemma":[0.000012359049,0.00002840117,0.00018467735,0.000009832016,0.000010195502,0.000022454386,0.00001008951,0.99342877,0.000104346596,0.005591443,0.00059086893,0.000006550222],"about_ca_topic_score_codex":0.0047732354,"about_ca_topic_score_gemma":0.004019694,"teacher_disagreement_score":0.0047732354,"about_ca_system_score_codex":0.0012072255,"about_ca_system_score_gemma":0.0012319678,"threshold_uncertainty_score":0.016060948},"labels":[],"label_agreement":null},{"id":"W4390992059","doi":"10.1109/bibm58861.2023.10385770","title":"M2-DIA: Enhancing Diagnostic Capabilities in Imbalanced Disease Data using Multimodal Diagnostic Ensemble Framework","year":2023,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Hanyang University","keywords":"Computer science; Ensemble learning; Artificial intelligence; Machine learning; Data mining","score_opus":0.19852799418173497,"score_gpt":0.49195487904424007,"score_spread":0.2934268848625051,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390992059","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13267109,0.005314042,0.84086096,0.0021069723,0.00043044347,0.0003010565,0.00484567,0.009013544,0.0044562826],"genre_scores_gemma":[0.71654683,0.0011032113,0.2682786,0.0010652482,0.00054392614,0.00022024199,0.009120031,0.00019300598,0.0029289622],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990048,0.0002457273,0.000074033545,0.00032200044,0.00022817253,0.00012520648],"domain_scores_gemma":[0.99847394,0.0006749623,0.00015835807,0.00021836559,0.00033536425,0.00013894413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019233586,0.0014116102,0.001396433,0.0038375915,0.00055980455,0.0009564803,0.0011684591,0.0013416685,0.0011145916],"category_scores_gemma":[0.0040087625,0.0002648692,0.0013235058,0.0016741339,0.0003420085,0.0011209383,0.0016286054,0.0014968193,0.00078947016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007158474,0.00076981913,0.06153901,0.0003066191,0.00080528687,0.0009171974,0.00041601944,0.09074886,0.019767288,0.002528808,0.025474928,0.7960103],"study_design_scores_gemma":[0.00003647323,0.00022102911,0.007302637,0.000045160403,0.00026148118,0.00066374,0.00014506064,0.97019064,0.00708899,0.00793211,0.006062916,0.0000497283],"about_ca_topic_score_codex":0.0054796017,"about_ca_topic_score_gemma":0.009466991,"teacher_disagreement_score":0.0054796017,"about_ca_system_score_codex":0.0006176605,"about_ca_system_score_gemma":0.0009838617,"threshold_uncertainty_score":0.010895431},"labels":[],"label_agreement":null},{"id":"W4391175008","doi":"10.56367/oag-041-10846","title":"Reducing data volume in big data: Parallel processing based data filtering techniques","year":2024,"lang":"en","type":"article","venue":"Open Access Government","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Volume (thermodynamics); Big data; Computer science; Data processing; Data mining; Database","score_opus":0.6516426195564557,"score_gpt":0.5994076944851713,"score_spread":0.052234925071284466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391175008","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006419741,0.0033972012,0.98148924,0.0028251146,0.00047010314,0.00019800509,0.0002140917,0.0015202839,0.0034661943],"genre_scores_gemma":[0.1464052,0.0071995724,0.8343651,0.0014095642,0.0014997288,0.00048796326,0.001264352,0.0005159712,0.0068524494],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969292,0.0005231416,0.00023264645,0.000491305,0.0016009759,0.0002227091],"domain_scores_gemma":[0.9929375,0.003007907,0.0006299061,0.0013936016,0.0018677034,0.00016329168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030456334,0.0013925246,0.0019609465,0.003713962,0.0016243398,0.0033968464,0.0021783072,0.0013839211,0.0029513189],"category_scores_gemma":[0.010053379,0.0008275415,0.002289136,0.007502542,0.0014036916,0.005260755,0.0018033439,0.0025596446,0.0018132611],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004247475,0.0004741619,0.0047113807,0.00068768783,0.00043059324,0.0003209809,0.00048822185,0.066587314,0.015195717,0.04760333,0.033809107,0.8292668],"study_design_scores_gemma":[0.00015972432,0.0003570387,0.004192385,0.00021585816,0.00027472145,0.00085866003,0.00044792163,0.6773463,0.027524235,0.21376184,0.074720316,0.00014105209],"about_ca_topic_score_codex":0.004441149,"about_ca_topic_score_gemma":0.0031167443,"teacher_disagreement_score":0.004441149,"about_ca_system_score_codex":0.0012775669,"about_ca_system_score_gemma":0.0020642988,"threshold_uncertainty_score":0.016107023},"labels":[],"label_agreement":null},{"id":"W4391229437","doi":"10.3233/shti231094","title":"Characterizing Cluster-Based Frailty Phenotypes in a Multicenter Prospective Cohort of Kidney Transplant Candidates","year":2024,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Regina General Hospital; Centre Hospitalier de l’Université de Montréal; McGill University; McMaster University; London Health Sciences Centre; Dalhousie University","funders":"","keywords":"Cluster analysis; Cohort; Hierarchical clustering; Kidney transplant; Cluster (spacecraft); Computer science; Medicine; Data mining; Kidney transplantation; Transplantation; Artificial intelligence; Internal medicine","score_opus":0.07840493995042132,"score_gpt":0.44446013117192873,"score_spread":0.3660551912215074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391229437","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99968445,0.000010725778,0.0001962988,0.000006622419,6.1174137e-7,0.0000045943475,0.00007258182,0.0000022314769,0.000021913473],"genre_scores_gemma":[0.99935395,0.0000074692653,0.0003495415,0.000004929985,0.0000017797896,0.000009737319,0.00023193473,0.0000022575769,0.00003836243],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99963284,0.00014295525,0.00002793689,0.000104652754,0.000045953482,0.000045604353],"domain_scores_gemma":[0.9985324,0.0003368353,0.00043439667,0.0003094948,0.00021620584,0.00017075111],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014739836,0.00024342518,0.00034221236,0.00094576314,0.0004868604,0.00048166967,0.00029684725,0.00032530865,0.00057262165],"category_scores_gemma":[0.0034797597,0.00013206388,0.00051589863,0.00077319774,0.00023774224,0.0001957626,0.0005362677,0.00033433308,0.00011121042],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036125205,0.000067723166,0.994433,0.000005994892,0.00008487967,0.000082210776,0.0002848322,0.00038495168,0.0018018439,0.00004708329,0.0001179184,0.0023282086],"study_design_scores_gemma":[0.000011888133,0.000211645,0.9961971,0.0000031652428,0.000039256083,0.0002078622,0.00038331325,0.0024215,0.00033874455,0.00007551856,0.00010246652,0.000007476551],"about_ca_topic_score_codex":0.0038462034,"about_ca_topic_score_gemma":0.004395213,"teacher_disagreement_score":0.0038462034,"about_ca_system_score_codex":0.00022968621,"about_ca_system_score_gemma":0.00026211608,"threshold_uncertainty_score":0.0077952147},"labels":[],"label_agreement":null},{"id":"W4391439764","doi":"10.2139/ssrn.4713084","title":"Supervised Sequential Contrastive Regression: Improving Performance on Imbalanced Rehabilitation Exercises Datasets","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University Health Network; Toronto Rehabilitation Institute; University of Toronto","funders":"","keywords":"Rehabilitation; Regression; Computer science; Artificial intelligence; Machine learning; Physical medicine and rehabilitation; Physical therapy; Medicine; Mathematics; Statistics","score_opus":0.05495385026074862,"score_gpt":0.42144063150571365,"score_spread":0.36648678124496503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391439764","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6038418,0.008813093,0.32219255,0.00219793,0.001936565,0.00066101854,0.014295229,0.038699683,0.0073622037],"genre_scores_gemma":[0.7055917,0.00072665105,0.24046578,0.0007593401,0.00071878964,0.0003559058,0.038249698,0.0016191085,0.011513047],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982475,0.00051748374,0.000106244224,0.00073326274,0.00022638409,0.00016916219],"domain_scores_gemma":[0.99555016,0.0025536988,0.00017403463,0.0007641053,0.00071077235,0.00024736725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004031017,0.0029124247,0.0020796787,0.0017806311,0.0007486466,0.0012373514,0.0027933696,0.0022448376,0.0041322527],"category_scores_gemma":[0.0089266375,0.0006408066,0.0012361376,0.0015746286,0.00051160966,0.0014476866,0.0017670939,0.003002591,0.0035806324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005050687,0.0025507694,0.0153635675,0.00058096636,0.00094062224,0.00048694288,0.00017140739,0.094641276,0.01972389,0.0011248009,0.066697136,0.792668],"study_design_scores_gemma":[0.00026012794,0.0003907466,0.004122923,0.000031376298,0.00012131976,0.0001169933,0.00007437774,0.9853188,0.005195261,0.0012893415,0.0030528537,0.000025811063],"about_ca_topic_score_codex":0.011613831,"about_ca_topic_score_gemma":0.021286631,"teacher_disagreement_score":0.011613831,"about_ca_system_score_codex":0.00054831407,"about_ca_system_score_gemma":0.0015913888,"threshold_uncertainty_score":0.023092508},"labels":[],"label_agreement":null},{"id":"W4391529461","doi":"10.1101/2024.02.03.24302301","title":"Identifying Prediabetes in Canadian Populations Using Machine Learning","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University; Ted Rogers Centre for Heart Research; York University; Public Health Ontario; University of Toronto","funders":"","keywords":"Prediabetes; Type 2 diabetes; Machine learning; Medicine; Health care; Artificial intelligence; Identification (biology); Computer science; Diabetes mellitus; Biology; Endocrinology","score_opus":0.3588045041989029,"score_gpt":0.5207921480066552,"score_spread":0.16198764380775227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391529461","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91909987,0.008243709,0.017690651,0.008211746,0.00016249497,0.00034901794,0.030789891,0.0002904072,0.015162203],"genre_scores_gemma":[0.9728373,0.003094071,0.010596112,0.00065270264,0.000040219184,0.000085000334,0.010850646,0.00002901029,0.0018148032],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990453,0.00018095494,0.000053495634,0.00017563645,0.00036395874,0.0001806246],"domain_scores_gemma":[0.9975134,0.0007315945,0.000273833,0.0001341231,0.0011748327,0.00017210844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028680407,0.00059512025,0.00035596048,0.0020720894,0.0016513679,0.0011950652,0.0012514235,0.00044778446,0.0019760882],"category_scores_gemma":[0.01096334,0.00021335838,0.0009897971,0.0033843317,0.00046176076,0.00042963852,0.0009020391,0.0009903385,0.00030243432],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004073834,0.00016289378,0.7948947,0.0005554208,0.00044435807,0.00036243384,0.0012215636,0.020013968,0.0005960094,0.006292456,0.022195663,0.15285319],"study_design_scores_gemma":[0.0001204178,0.00014557054,0.7897163,0.0007719578,0.0006865489,0.00032048387,0.0032271496,0.16523881,0.0013719978,0.0069321003,0.031249886,0.0002187341],"about_ca_topic_score_codex":0.987344,"about_ca_topic_score_gemma":0.9903222,"teacher_disagreement_score":0.01965697,"about_ca_system_score_codex":0.01965697,"about_ca_system_score_gemma":0.03604941,"threshold_uncertainty_score":0.142622},"labels":[],"label_agreement":null},{"id":"W4391529487","doi":"10.1101/2024.02.03.24302302","title":"Predicting Diabetes in Canadian Adults Using Machine Learning","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University; Ted Rogers Centre for Heart Research; York University; Public Health Ontario; University of Toronto","funders":"","keywords":"Diabetes mellitus; Machine learning; Computer science; Artificial intelligence; Psychology; Medicine; Endocrinology","score_opus":0.12315546262974596,"score_gpt":0.44210766399422313,"score_spread":0.31895220136447716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391529487","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93424416,0.0015627979,0.008356495,0.0035455762,0.00012986337,0.00020597449,0.04199126,0.0006293719,0.009334519],"genre_scores_gemma":[0.9722214,0.00059316907,0.010145231,0.0002864029,0.000035305064,0.00004277751,0.014460753,0.0000177525,0.0021971364],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994747,0.000082106555,0.00002848415,0.000117890035,0.00018836024,0.000108516244],"domain_scores_gemma":[0.9982369,0.00041785426,0.00016661356,0.00006794398,0.00093788945,0.00017287704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013948851,0.0006879007,0.00035986459,0.0015963576,0.00076077104,0.00092153676,0.00095460156,0.00040741113,0.002900102],"category_scores_gemma":[0.00507298,0.00018226457,0.0005982233,0.0021208124,0.00020770598,0.00024871124,0.00043315598,0.0006225769,0.0006341418],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030447473,0.00017765988,0.8640833,0.00018031998,0.00021166113,0.00009746208,0.00017647614,0.03818155,0.0004997075,0.0009408251,0.022048373,0.07309818],"study_design_scores_gemma":[0.00008059248,0.00011349592,0.5161089,0.00014583592,0.00013625277,0.0001089751,0.00054623105,0.47008514,0.0013720819,0.0009341762,0.01031261,0.00005561011],"about_ca_topic_score_codex":0.9801777,"about_ca_topic_score_gemma":0.97013783,"teacher_disagreement_score":0.0198223,"about_ca_system_score_codex":0.010785972,"about_ca_system_score_gemma":0.014448647,"threshold_uncertainty_score":0.07825804},"labels":[],"label_agreement":null},{"id":"W4391694904","doi":"10.1002/9781119825883.ch10","title":"Computer‐aided Diagnosis and Healthcare","year":2024,"lang":"en","type":"other","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Calgary","funders":"","keywords":"Health care; Computer science; Data science; Political science","score_opus":0.2292811136983211,"score_gpt":0.5194350204589689,"score_spread":0.29015390676064784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391694904","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007386026,0.39553297,0.1293142,0.016815549,0.0045160227,0.00029581093,0.001125089,0.0026248666,0.44238952],"genre_scores_gemma":[0.21267961,0.36676577,0.15760322,0.0062436447,0.0043355506,0.00035791032,0.0021630162,0.0002742204,0.24957697],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984642,0.0003858601,0.00008978882,0.00017682128,0.0007674762,0.00011585489],"domain_scores_gemma":[0.99844617,0.0008445259,0.00011448342,0.000110690555,0.0004205459,0.000063651896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011432992,0.00073619315,0.0006612625,0.0026691176,0.00064638746,0.004285188,0.000985435,0.0021504273,0.028943455],"category_scores_gemma":[0.0035948202,0.00018874723,0.0002889842,0.0028545097,0.0015649542,0.0020075487,0.0016850284,0.0011081605,0.011136933],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006653306,0.00004884039,0.00092748,0.0010923403,0.000037219364,0.00026879873,0.00019086296,0.0029938207,0.001517709,0.09680704,0.0964974,0.79955196],"study_design_scores_gemma":[0.000020842604,0.00008509546,0.0019840924,0.0010360676,0.000026138096,0.0017932449,0.00042945464,0.007688006,0.0019917686,0.10371321,0.8811696,0.00006247128],"about_ca_topic_score_codex":0.0023482353,"about_ca_topic_score_gemma":0.0016357889,"teacher_disagreement_score":0.028943455,"about_ca_system_score_codex":0.00101274,"about_ca_system_score_gemma":0.0010987336,"threshold_uncertainty_score":0.09682548},"labels":[],"label_agreement":null},{"id":"W4391892277","doi":"10.2139/ssrn.4726271","title":"Digital Innovation in Healthcare: Quantifying the Impact of Digital Sepsis Screening Tools on Patient Outcomes, a Multisite Natural Experiment","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Cancer Research","funders":"","keywords":"Natural experiment; Health care; Sepsis; Digital health; Natural (archaeology); Medicine; Business; Internal medicine; Economics; Geography; Economic growth","score_opus":0.16076040595375543,"score_gpt":0.49080965229060697,"score_spread":0.3300492463368515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391892277","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9964557,0.000028152648,0.0019165665,0.00014349165,0.000044398763,0.0005473838,0.00023387681,0.000023179058,0.00060728093],"genre_scores_gemma":[0.9894823,0.000056115343,0.0065354044,0.00027494738,0.00006108645,0.0020016446,0.00031608122,0.00001150111,0.0012609118],"study_design_codex":"nonrandomized_trial","study_design_gemma":"observational","domain_scores_codex":[0.99373925,0.0039978637,0.00038488733,0.00085710565,0.0006525903,0.00036831573],"domain_scores_gemma":[0.9423175,0.045593146,0.004747404,0.004186853,0.0013757625,0.0017794217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011744445,0.0006450631,0.00060522807,0.0005053373,0.00068991986,0.0016637897,0.00083800295,0.0019967572,0.0031226182],"category_scores_gemma":[0.03788278,0.0005229152,0.0011880973,0.00036840854,0.001634254,0.0016568628,0.0016114439,0.0018924024,0.00058252097],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.17223056,0.3602428,0.19419372,0.0021826772,0.0031321754,0.00045439127,0.0075794673,0.056966428,0.047850676,0.009244249,0.0046636974,0.14125915],"study_design_scores_gemma":[0.02185746,0.4480588,0.33989483,0.0003169932,0.00237649,0.00044232525,0.0031250902,0.12375806,0.031823125,0.020846356,0.0069008702,0.0005996183],"about_ca_topic_score_codex":0.002328017,"about_ca_topic_score_gemma":0.0017092127,"teacher_disagreement_score":0.011744445,"about_ca_system_score_codex":0.0008207971,"about_ca_system_score_gemma":0.0018599895,"threshold_uncertainty_score":0.06211126},"labels":[],"label_agreement":null},{"id":"W4391916407","doi":"","title":"Adaptation de domaine par une méthode d'apprentissage profond parcimonieuse. Application à la segmentation d'images biomédicales.","year":2023,"lang":"fr","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"French Infrastructure for Integrated Structural Biology; Centre National de la Recherche Scientifique; Université de Strasbourg; Institute of Genetics; Institut National de la Santé et de la Recherche Médicale; Agence Nationale de la Recherche","keywords":"Computer science","score_opus":0.06812015622039959,"score_gpt":0.36559891639782277,"score_spread":0.2974787601774232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391916407","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03530754,0.0010954924,0.9536717,0.0004049775,0.0004002777,0.00014613014,0.0003681854,0.0053245425,0.0032810909],"genre_scores_gemma":[0.21440125,0.0008665161,0.7590397,0.00034145822,0.00015853421,0.00024514133,0.0012549602,0.0014432676,0.022249093],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992879,0.00013540607,0.000041360094,0.00028028068,0.00018643566,0.000068683046],"domain_scores_gemma":[0.9985489,0.0005864916,0.00006278824,0.0002766542,0.00047100696,0.000054162727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012923965,0.0011843838,0.0011001151,0.0011768389,0.0006254161,0.0018393944,0.0011649594,0.002309428,0.006876424],"category_scores_gemma":[0.00364404,0.00059747655,0.0009778221,0.0012442903,0.0006157491,0.0012743985,0.0012006058,0.0012761987,0.00312017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035854962,0.00023157235,0.001956673,0.00031915714,0.0001251445,0.00041927592,0.00042274172,0.08235189,0.10899191,0.0025506457,0.010417312,0.79185516],"study_design_scores_gemma":[0.000059603502,0.0001300158,0.0036423863,0.00008135606,0.000057501024,0.00065440894,0.00019540814,0.88286936,0.07754865,0.0028742303,0.031830434,0.000056632558],"about_ca_topic_score_codex":0.015005682,"about_ca_topic_score_gemma":0.011918362,"teacher_disagreement_score":0.015005682,"about_ca_system_score_codex":0.0005960924,"about_ca_system_score_gemma":0.0009539438,"threshold_uncertainty_score":0.029836655},"labels":[],"label_agreement":null},{"id":"W4391980936","doi":"10.31031/sbb.2024.06.000646","title":"Prediction and Survival Analysis of Head and Neck Cancer in Patients Using Epigenomics Data and Advanced Machine Learning Methods","year":2024,"lang":"en","type":"article","venue":"Significances of Bioengineering & Biosciences","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Epigenomics; Head and neck cancer; Head and neck; Computer science; Cancer; Oncology; Machine learning; Artificial intelligence; Medicine; Internal medicine; Biology; Surgery; Genetics; DNA methylation","score_opus":0.15321647251859594,"score_gpt":0.4810765349604092,"score_spread":0.32786006244181326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391980936","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9853199,0.00090808666,0.0053169425,0.00063115754,0.000040537674,0.00002808035,0.007087871,0.00008266453,0.0005848746],"genre_scores_gemma":[0.98873514,0.00034896095,0.0020367685,0.0000568864,0.000033483848,0.000028870609,0.008342348,0.000007888886,0.00040973385],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99974495,0.00006839098,0.000028532259,0.000075637116,0.000038927483,0.000043554326],"domain_scores_gemma":[0.99890995,0.0006362355,0.00014453274,0.00008311889,0.00015145644,0.000074671756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00091980165,0.00033662355,0.00040091784,0.0014693877,0.00021598318,0.000565918,0.00036851325,0.00059076276,0.001526438],"category_scores_gemma":[0.0028401278,0.00012140406,0.0006518485,0.0008323947,0.00013857876,0.00040631116,0.00043540928,0.00053419516,0.000378791],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003578611,0.00010600712,0.954356,0.000047503094,0.00018624784,0.00013412932,0.000041914376,0.009727297,0.000999733,0.0001948877,0.0017074365,0.032141034],"study_design_scores_gemma":[0.000044683533,0.00032343864,0.6625158,0.00006775299,0.00043130518,0.00057561597,0.0004338193,0.3281801,0.0023568675,0.001991828,0.0030330124,0.00004573667],"about_ca_topic_score_codex":0.008697411,"about_ca_topic_score_gemma":0.010203014,"teacher_disagreement_score":0.008697411,"about_ca_system_score_codex":0.00041572872,"about_ca_system_score_gemma":0.00044644938,"threshold_uncertainty_score":0.017293572},"labels":[],"label_agreement":null},{"id":"W4392108757","doi":"10.3389/fpubh.2024.1328353","title":"A feature optimization study based on a diabetes risk questionnaire","year":2024,"lang":"en","type":"article","venue":"Frontiers in Public Health","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Centers for Disease Control and Prevention; National Natural Science Foundation of China","keywords":"Medicine; Diabetes mellitus; Disease; Univariate; Feature selection; Standardization; Ranking (information retrieval); Risk factor; Computer science; Machine learning; Data mining; Environmental health; Internal medicine; Multivariate statistics","score_opus":0.07253092882360608,"score_gpt":0.42579909899871543,"score_spread":0.35326817017510936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392108757","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97015095,0.00015514827,0.028276147,0.00009346894,0.000039140705,0.0001345963,0.00047580502,0.00012161409,0.000553113],"genre_scores_gemma":[0.9755288,0.00006629346,0.02246998,0.000029631936,0.000015141557,0.000100685524,0.0013916157,0.000010265085,0.0003875475],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933976,0.00028882644,0.00004790569,0.0001345192,0.00011426843,0.00007475541],"domain_scores_gemma":[0.9963691,0.0024859316,0.0001476254,0.00028387102,0.0006453676,0.00006811768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018723818,0.0005784693,0.0005827425,0.00069988857,0.0002493535,0.000480755,0.00047236384,0.00042166072,0.0009169316],"category_scores_gemma":[0.0046470305,0.00013822838,0.0008209234,0.0005660394,0.00019622475,0.0003833095,0.00034074837,0.0004045349,0.00014410327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003326096,0.0057694386,0.15283763,0.000821057,0.00068017334,0.00084169087,0.00046963952,0.39511755,0.025482235,0.002211924,0.00621936,0.40622315],"study_design_scores_gemma":[0.00008958082,0.001052019,0.048747737,0.00001636933,0.00012633826,0.00010786196,0.00019618045,0.94226146,0.0062833745,0.00029555403,0.00079436036,0.000029180374],"about_ca_topic_score_codex":0.006899001,"about_ca_topic_score_gemma":0.0029535592,"teacher_disagreement_score":0.006899001,"about_ca_system_score_codex":0.00052457635,"about_ca_system_score_gemma":0.00035643624,"threshold_uncertainty_score":0.013717711},"labels":[],"label_agreement":null},{"id":"W4392191574","doi":"10.2196/52289","title":"Mining Clinical Notes for Physical Rehabilitation Exercise Information: Natural Language Processing Algorithm Development and Validation Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences","keywords":"Rehabilitation; Computer science; Physical medicine and rehabilitation; Natural language processing; Stroke (engine); Artificial intelligence; Physical therapy; Machine learning; Medicine; Engineering","score_opus":0.09547172184478496,"score_gpt":0.5283818912335683,"score_spread":0.4329101693887833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392191574","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79851854,0.0024590294,0.18326649,0.00057022896,0.00018570287,0.0040310235,0.0051178215,0.0037665025,0.0020846338],"genre_scores_gemma":[0.6211846,0.00070121384,0.36051124,0.00027236363,0.000054224405,0.0019224588,0.014173143,0.00009726969,0.0010836145],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9938432,0.002575917,0.0009661891,0.0012763418,0.0010870778,0.000251283],"domain_scores_gemma":[0.9739896,0.019576594,0.00082470145,0.0012443308,0.00408731,0.00027755267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011646857,0.0012623834,0.00089156243,0.002985154,0.000592721,0.0014961397,0.0020764552,0.0017350337,0.0011789876],"category_scores_gemma":[0.02495437,0.00035098643,0.0012172288,0.0017868571,0.0005899489,0.0012826885,0.0011383661,0.0012665656,0.00077928026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014450008,0.0061148643,0.12155072,0.0018842068,0.001007539,0.001455585,0.0015449848,0.10570223,0.016595693,0.0013556072,0.010119959,0.7312235],"study_design_scores_gemma":[0.00048192716,0.0013774675,0.041317213,0.0002875077,0.00038029967,0.001428422,0.000980304,0.92094785,0.023433002,0.0012338283,0.008056685,0.000075539676],"about_ca_topic_score_codex":0.006132899,"about_ca_topic_score_gemma":0.005061703,"teacher_disagreement_score":0.011646857,"about_ca_system_score_codex":0.0010805113,"about_ca_system_score_gemma":0.0023836847,"threshold_uncertainty_score":0.0615952},"labels":[],"label_agreement":null},{"id":"W4392209953","doi":"10.1109/iccit60459.2023.10441358","title":"Coronary Heart Disease Prediction On Small Datasets: A Comparative Analysis","year":2023,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Cardiology; Internal medicine; Medicine","score_opus":0.3783455982196718,"score_gpt":0.536371327162202,"score_spread":0.15802572894253025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392209953","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89868325,0.018169701,0.010990879,0.0025510131,0.000937097,0.00035402502,0.059527885,0.001615546,0.007170545],"genre_scores_gemma":[0.8601892,0.0033075847,0.012440743,0.0003214051,0.00033702483,0.00019272952,0.121901244,0.000118120224,0.0011918063],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99715304,0.0008748687,0.00032772863,0.00067497,0.00080902944,0.0001603831],"domain_scores_gemma":[0.98591423,0.0098753115,0.0005533088,0.0015455978,0.0017413854,0.00037001085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005236864,0.0008835605,0.0012323093,0.0033211159,0.00048658412,0.001454914,0.0014140981,0.0013769167,0.0015644708],"category_scores_gemma":[0.01575415,0.00021464242,0.0013860684,0.003111674,0.0003969417,0.0015892644,0.0010254248,0.0008451669,0.0006688269],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0076669734,0.0027281842,0.4117531,0.0031003987,0.0052713607,0.001371392,0.00043526443,0.084094286,0.0034533427,0.0023621593,0.08868041,0.38908303],"study_design_scores_gemma":[0.0006141972,0.0029253045,0.53495175,0.00074365194,0.0017318861,0.0027031589,0.001732285,0.39878297,0.00618512,0.0049134702,0.0444714,0.00024491752],"about_ca_topic_score_codex":0.010781301,"about_ca_topic_score_gemma":0.012833671,"teacher_disagreement_score":0.010781301,"about_ca_system_score_codex":0.0009181131,"about_ca_system_score_gemma":0.00070490193,"threshold_uncertainty_score":0.027695537},"labels":[],"label_agreement":null},{"id":"W4392306974","doi":"10.1007/978-981-97-0827-7_8","title":"A Critical Review of Multi Criteria Decision Analysis Method for Decision Making and Prediction in Big Data Healthcare Applications","year":2024,"lang":"en","type":"review","venue":"Communications in computer and information science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Big data; Health care; Data science; Data mining; Operations research; Engineering; Political science","score_opus":0.6335345748561209,"score_gpt":0.6751389515833436,"score_spread":0.041604376727222725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392306974","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007543375,0.9964677,0.001442476,0.0013028851,0.0002690008,0.000023797276,0.00005884296,0.000006379359,0.00035354114],"genre_scores_gemma":[0.0022041951,0.9910767,0.0048406906,0.0010957194,0.00045844683,0.000065020686,0.000082353756,0.000006863241,0.00017007605],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99415815,0.0022629693,0.0012915042,0.00044203192,0.0017215303,0.00012373581],"domain_scores_gemma":[0.96357,0.029426022,0.0012885378,0.00042140033,0.005073576,0.00022046237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013641923,0.0012894493,0.003417872,0.0064960876,0.00050975406,0.003060283,0.002628768,0.0020285626,0.00288836],"category_scores_gemma":[0.029661039,0.00065813266,0.0023246252,0.007547845,0.0011539151,0.0026464185,0.000975508,0.003132092,0.000763161],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013933727,0.00011813892,0.00053269014,0.08787256,0.00084921665,0.000118013486,0.00013225041,0.0015858588,0.0002823829,0.012461878,0.034213465,0.8616942],"study_design_scores_gemma":[0.00010923302,0.0004361902,0.0032918314,0.13912363,0.0029427442,0.0010059502,0.00034315558,0.003739842,0.0009649981,0.030756485,0.8170682,0.00021782539],"about_ca_topic_score_codex":0.0046418547,"about_ca_topic_score_gemma":0.0081665665,"teacher_disagreement_score":0.013641923,"about_ca_system_score_codex":0.002691325,"about_ca_system_score_gemma":0.0069500585,"threshold_uncertainty_score":0.07214624},"labels":[],"label_agreement":null},{"id":"W4392365979","doi":"10.18280/ria.380132","title":"Designing a Smart IoT Environment by Predicting Chronic Kidney Disease Using Kernel Based Xception Deep Learning Model","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Deep learning; Computer science; Artificial intelligence; Kernel (algebra); Kidney disease; Internet of Things; Machine learning; Medicine; Internal medicine; World Wide Web; Mathematics","score_opus":0.11805497751041329,"score_gpt":0.3932729225809824,"score_spread":0.2752179450705691,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392365979","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19128676,0.0006439479,0.80088943,0.00072206976,0.00009519852,0.00008024489,0.0003218593,0.0012489776,0.004711581],"genre_scores_gemma":[0.9583511,0.00021920224,0.03848262,0.00014402118,0.000020539785,0.00010900034,0.00029947195,0.000023524066,0.0023505925],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99986625,0.000024124962,0.000008608347,0.000040201692,0.000028822242,0.000031941065],"domain_scores_gemma":[0.9998441,0.00006222742,0.000016355754,0.000009393733,0.000052707117,0.000015230589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003456527,0.00052428315,0.00054990564,0.00031104553,0.0002555365,0.0006628216,0.00078987685,0.000800754,0.0011753018],"category_scores_gemma":[0.00074948434,0.0003006175,0.00052471086,0.00027233813,0.000301282,0.00056814577,0.00074431754,0.00069682044,0.00025042446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042421492,0.000037127294,0.0023851737,0.000019622823,0.00001917956,0.00006421932,0.00001974098,0.9775064,0.0009621752,0.00070506614,0.0005051934,0.017733788],"study_design_scores_gemma":[0.0000012444359,0.0000039324354,0.000080898186,0.0000010166616,0.0000014897527,0.0000021145727,0.0000018532423,0.9996456,0.000083676176,0.00013938418,0.0000379664,8.892598e-7],"about_ca_topic_score_codex":0.017637555,"about_ca_topic_score_gemma":0.00986256,"teacher_disagreement_score":0.017637555,"about_ca_system_score_codex":0.0004738561,"about_ca_system_score_gemma":0.000873756,"threshold_uncertainty_score":0.035069764},"labels":[],"label_agreement":null},{"id":"W4392385740","doi":"10.18280/ria.380120","title":"A Review of Machine Learning Techniques Used in the Prediction of Heart Disease","year":2024,"lang":"en","type":"review","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Disease; Artificial intelligence; Computer science; Machine learning; Medicine; Internal medicine","score_opus":0.27930248616974146,"score_gpt":0.5069400755232342,"score_spread":0.2276375893534927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392385740","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006876333,0.9894733,0.0061078435,0.0009434269,0.00057664094,0.000021099388,0.00017623662,0.000059941474,0.0019538968],"genre_scores_gemma":[0.0037539331,0.9899933,0.004206291,0.00038146146,0.00085873494,0.000027885104,0.00019922647,0.000011775641,0.0005674687],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990971,0.00023371514,0.00018338599,0.00016293602,0.0002824444,0.000040405637],"domain_scores_gemma":[0.9972349,0.0020257744,0.00019811661,0.00007362424,0.00042020358,0.000047369478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015753612,0.0011412308,0.0010675432,0.0031341966,0.0002817994,0.0012740466,0.0010405167,0.001085587,0.0026354163],"category_scores_gemma":[0.0038352828,0.0004077039,0.0010755304,0.0041252826,0.0004364394,0.0016506794,0.0005124081,0.0015762922,0.0015682179],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000649228,0.00010209155,0.0015515947,0.020792866,0.00026751927,0.00018030002,0.000112199545,0.003961994,0.001418386,0.0073563317,0.033001345,0.9311905],"study_design_scores_gemma":[0.00001803457,0.00039051144,0.0075023975,0.01600961,0.00060612074,0.0014739287,0.00016318623,0.0077156937,0.0016586395,0.013088925,0.9512508,0.00012215163],"about_ca_topic_score_codex":0.002266604,"about_ca_topic_score_gemma":0.0022372324,"teacher_disagreement_score":0.0031341966,"about_ca_system_score_codex":0.00057472265,"about_ca_system_score_gemma":0.0014133966,"threshold_uncertainty_score":0.008816361},"labels":[],"label_agreement":null},{"id":"W4392502603","doi":"10.1201/9781003466949-1","title":"Lung Disease Diagnosis Using Machine Learning from a Bibliometric Perspective","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); Lung disease; Disease; Computer science; Artificial intelligence; Lung; Machine learning; Medicine; Pathology; Internal medicine","score_opus":0.2649009489066629,"score_gpt":0.49932741395916175,"score_spread":0.23442646505249887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392502603","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10636596,0.25968176,0.0571676,0.03081591,0.0027023808,0.0002720449,0.021143876,0.0028445763,0.5190059],"genre_scores_gemma":[0.7002657,0.13735545,0.07728967,0.001337825,0.0045688297,0.00018213897,0.013422083,0.00024598293,0.065332375],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980459,0.00034536136,0.00015273382,0.00013313236,0.0012210453,0.000101736165],"domain_scores_gemma":[0.99579275,0.0026616345,0.00054536347,0.00013232199,0.00075561274,0.00011242024],"candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.0015741407,0.00054091413,0.0007249242,0.042593516,0.0005059634,0.0056773135,0.00074563915,0.0006605797,0.008863712],"category_scores_gemma":[0.0061970884,0.00017425683,0.0006671183,0.064239375,0.0006200094,0.0053322306,0.00068537804,0.0005581742,0.0034500381],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032095468,0.00007526796,0.034530718,0.0023223276,0.00017900544,0.00022836527,0.00048308913,0.0031405333,0.00082207465,0.042533714,0.08806488,0.8275878],"study_design_scores_gemma":[0.00002680556,0.0001657006,0.16732009,0.0048699193,0.00037442762,0.0027542308,0.0039540883,0.065430745,0.0034108367,0.11500416,0.6364849,0.0002040601],"about_ca_topic_score_codex":0.0041095586,"about_ca_topic_score_gemma":0.0070774034,"teacher_disagreement_score":0.95740646,"about_ca_system_score_codex":0.0023101203,"about_ca_system_score_gemma":0.001424218,"threshold_uncertainty_score":0.02965206},"labels":[],"label_agreement":null},{"id":"W4392768149","doi":"10.4271/j3248_202402","title":"Worldwide On-Board Diagnostic Requirements Overview","year":2024,"lang":"en","type":"standard","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Business","score_opus":0.30523371352987166,"score_gpt":0.5515955339948775,"score_spread":0.24636182046500582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392768149","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035684898,0.002718269,0.074977964,0.013825397,0.002442536,0.002490086,0.010442683,0.009993775,0.8795408],"genre_scores_gemma":[0.036427893,0.006127136,0.055908274,0.008094336,0.0011043733,0.0018256425,0.046603385,0.0044510593,0.8394578],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9886049,0.0018206484,0.0009386098,0.000540354,0.0071687847,0.00092685985],"domain_scores_gemma":[0.98176897,0.0016590228,0.00086656533,0.0016206101,0.013150241,0.0009345905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011295053,0.0010322256,0.00045525076,0.0041658287,0.0013950797,0.006494054,0.0030490565,0.004296866,0.114730105],"category_scores_gemma":[0.015024215,0.00060078746,0.00080679636,0.0023733939,0.0006907419,0.0038451492,0.0025952465,0.002326206,0.15224008],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056895286,0.0001450369,0.00073669665,0.0004645211,0.000006754147,0.00027929482,0.00024849587,0.0015606966,0.0056074783,0.02489862,0.7784635,0.187532],"study_design_scores_gemma":[0.000008090786,0.000023694889,0.00055416714,0.0001932312,0.0000032838275,0.00015301409,0.000114087765,0.0005539528,0.0013512786,0.0012313451,0.9958015,0.000012440117],"about_ca_topic_score_codex":0.011784699,"about_ca_topic_score_gemma":0.010147252,"teacher_disagreement_score":0.114730105,"about_ca_system_score_codex":0.003342837,"about_ca_system_score_gemma":0.010197901,"threshold_uncertainty_score":0.38381046},"labels":[],"label_agreement":null},{"id":"W4392820586","doi":"10.62667/begawe.v1i2.41","title":"APLIKASI SOFTWARE DETEKSI DINI FAKTOR RISIKO DIABETES MELLITUS PADA DEWASA DI PUSKESMAS KERTASMAYA KABUPATEN INDRAMAYU","year":2023,"lang":"id","type":"article","venue":"BEGAWE Jurnal Pengabdian Masyarakat","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Diabetes mellitus; Gynecology; Internal medicine; Endocrinology","score_opus":0.0904178652761529,"score_gpt":0.3796907267433692,"score_spread":0.28927286146721626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392820586","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20003158,0.012647325,0.33266622,0.009994872,0.002610452,0.004764137,0.045745026,0.24715604,0.14438438],"genre_scores_gemma":[0.6393289,0.008618827,0.2069076,0.0034547797,0.0008239749,0.0041934564,0.04048944,0.010420402,0.08576273],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978897,0.0004533366,0.00032867183,0.000548811,0.0006104411,0.00016903883],"domain_scores_gemma":[0.99134725,0.004450265,0.00063682173,0.00095516606,0.002203648,0.00040673706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033944661,0.0015455796,0.0011653817,0.001880678,0.00071015547,0.0037700478,0.0012940759,0.0010314608,0.022895323],"category_scores_gemma":[0.014764459,0.00065284944,0.0016109524,0.0012803783,0.00035199404,0.0018684987,0.001627229,0.0015119936,0.012980482],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035964353,0.0008813103,0.067238204,0.0026120308,0.00070797716,0.00070610404,0.002268331,0.0064956523,0.01177863,0.0050821844,0.118612684,0.7800205],"study_design_scores_gemma":[0.0012229658,0.0019412298,0.13448161,0.0024294653,0.002027212,0.0023564652,0.0021013664,0.13960259,0.048736013,0.026708795,0.63770485,0.0006874534],"about_ca_topic_score_codex":0.005261691,"about_ca_topic_score_gemma":0.0034679638,"teacher_disagreement_score":0.022895323,"about_ca_system_score_codex":0.0007228702,"about_ca_system_score_gemma":0.0018730359,"threshold_uncertainty_score":0.076592505},"labels":[],"label_agreement":null},{"id":"W4393047893","doi":"10.17148/ijarcce.2024.13315","title":"Heart Disease Prediction System Using Machine Learning","year":2024,"lang":"en","type":"article","venue":"IJARCCE","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Disease; Medicine; Internal medicine","score_opus":0.1979801443706748,"score_gpt":0.49882188982242437,"score_spread":0.3008417454517496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393047893","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3299846,0.0054055355,0.49011663,0.0062139975,0.0018543716,0.0017625594,0.047668822,0.0911982,0.02579523],"genre_scores_gemma":[0.83013475,0.0015375494,0.121476434,0.0011839586,0.00069410726,0.0006826694,0.029168688,0.0002581622,0.014863713],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995364,0.000052879925,0.000066465655,0.00016784623,0.00013284988,0.00004360109],"domain_scores_gemma":[0.9990927,0.000276632,0.000098990604,0.000094478215,0.0003414067,0.000095813135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073108,0.0006312428,0.0009527785,0.0024097818,0.0005285872,0.00097624434,0.000779124,0.00073327584,0.0065271487],"category_scores_gemma":[0.0020770933,0.00024462666,0.000651883,0.0011435378,0.00010748005,0.00072840886,0.00059817143,0.0007166717,0.004329695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015067497,0.0016855774,0.1361581,0.00060566375,0.0004384017,0.0020899854,0.00013832172,0.046139106,0.0098295575,0.0016691643,0.09043779,0.7093016],"study_design_scores_gemma":[0.00018953135,0.00069130777,0.04283033,0.00012999692,0.0002671266,0.0015308275,0.00009483705,0.91015893,0.013813998,0.004605379,0.025573965,0.00011378038],"about_ca_topic_score_codex":0.004769483,"about_ca_topic_score_gemma":0.003934325,"teacher_disagreement_score":0.0065271487,"about_ca_system_score_codex":0.000502927,"about_ca_system_score_gemma":0.0007362559,"threshold_uncertainty_score":0.021835506},"labels":[],"label_agreement":null},{"id":"W4393238008","doi":"10.1016/j.compbiomed.2024.108345","title":"Cardiovascular disease detection using a novel stack-based ensemble classifier with aggregation layer, DOWA operator, and feature transformation","year":2024,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Classifier (UML); Artificial intelligence; Computer science; Support vector machine; Receiver operating characteristic; Pattern recognition (psychology); Ensemble learning; Random subspace method; Cascading classifiers; Machine learning","score_opus":0.10749231213980219,"score_gpt":0.4286043422778698,"score_spread":0.3211120301380676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393238008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16261055,0.0013186879,0.828765,0.0003368608,0.00036932566,0.00014880624,0.000700062,0.002963157,0.0027875972],"genre_scores_gemma":[0.6616308,0.0007219125,0.32898125,0.0002210738,0.00025501652,0.00019807082,0.0017502302,0.00010297764,0.006138641],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99949217,0.000038585404,0.000039911658,0.000109560926,0.00022610977,0.00009361042],"domain_scores_gemma":[0.9994949,0.00006852865,0.00002236374,0.00004634555,0.0003304086,0.000037392118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00091843464,0.0008397019,0.0016402425,0.0015329228,0.0006236448,0.0008472403,0.001013585,0.00076707086,0.001090354],"category_scores_gemma":[0.00092390087,0.0002790768,0.0012478343,0.0009793806,0.00013385505,0.0010206777,0.001007438,0.0008128572,0.00065003266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042932393,0.00056878995,0.017086921,0.00006542959,0.0005242208,0.00015630644,0.000060518483,0.020266382,0.037639905,0.0011615759,0.006163015,0.9158776],"study_design_scores_gemma":[0.000028214961,0.00027243965,0.01102177,0.0000151392105,0.00030808928,0.00031324616,0.000039643837,0.96976054,0.014655149,0.0010382646,0.00249556,0.00005206822],"about_ca_topic_score_codex":0.0072468766,"about_ca_topic_score_gemma":0.010783351,"teacher_disagreement_score":0.0072468766,"about_ca_system_score_codex":0.00026980616,"about_ca_system_score_gemma":0.0009951176,"threshold_uncertainty_score":0.014409423},"labels":[],"label_agreement":null},{"id":"W4393246003","doi":"10.37964/cr24776","title":"HEALTH INFORMATICS: AI in health care: a tool for physician leaders","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Physician Leadership","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Health informatics; Health care; Informatics; Medicine; Health Administration Informatics; Family medicine; Nursing; Medical education; Data science; Computer science; Political science; Public health","score_opus":0.2211521202425484,"score_gpt":0.45739575453274844,"score_spread":0.23624363429020004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393246003","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005799443,0.009850708,0.34407526,0.49113837,0.008318093,0.0012053585,0.0011559095,0.012827024,0.12562978],"genre_scores_gemma":[0.06818987,0.005519831,0.8402323,0.04469821,0.0050947084,0.0017672415,0.0010829187,0.00072582345,0.032689005],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98808855,0.008528462,0.0008356686,0.00034893784,0.0017985436,0.0003998643],"domain_scores_gemma":[0.9721247,0.015958523,0.001366332,0.0020320327,0.0035434007,0.0049749776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018977104,0.0012772055,0.00088208803,0.0050787595,0.004095191,0.012972498,0.0028181286,0.005391206,0.016346192],"category_scores_gemma":[0.035462543,0.0006032159,0.00056632026,0.003984385,0.007600854,0.014912639,0.008490456,0.0064569185,0.007964101],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000080250065,0.00024655138,0.001878047,0.0013391931,0.000034801425,0.00036493762,0.012034254,0.00058706943,0.0012317045,0.16242035,0.47789448,0.34188837],"study_design_scores_gemma":[0.00006150038,0.00010478363,0.0011028495,0.0015937503,0.000034153883,0.0007528099,0.00875252,0.0022618547,0.0005981165,0.10544754,0.8792101,0.00008008123],"about_ca_topic_score_codex":0.0030549006,"about_ca_topic_score_gemma":0.0051244535,"teacher_disagreement_score":0.018977104,"about_ca_system_score_codex":0.003304545,"about_ca_system_score_gemma":0.010717605,"threshold_uncertainty_score":0.100361705},"labels":[],"label_agreement":null},{"id":"W4393284069","doi":"10.2316/j.2024.206-0915","title":"CIOT-BASED EARLY DIAGNOSIS OF HEART FAILURE FROM MULTIMODAL DATA USING CHI-SQUARE-BASED DEEP NEURAL CLASSIFIER, 464-472.","year":2024,"lang":"en","type":"article","venue":"International Journal of Robotics and Automation","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Classifier (UML); Pattern recognition (psychology); Artificial intelligence; Artificial neural network; Computer science; Speech recognition; Medicine","score_opus":0.14994753560571433,"score_gpt":0.4560037271018872,"score_spread":0.30605619149617286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393284069","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62198836,0.009760522,0.34358206,0.002257247,0.0012187564,0.000353046,0.009913934,0.0038366902,0.0070894687],"genre_scores_gemma":[0.9356727,0.0011503488,0.051525567,0.000380257,0.0003861531,0.00015502407,0.006351436,0.00009896488,0.004279548],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996476,0.000056530516,0.000035631598,0.00008768579,0.00009078677,0.00008177798],"domain_scores_gemma":[0.99884737,0.00044032323,0.000059569193,0.00005033471,0.00046746386,0.00013497451],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009468177,0.0008434678,0.0011331216,0.0014951335,0.00037401004,0.0008370198,0.000795033,0.0008567223,0.0021857615],"category_scores_gemma":[0.0027875288,0.00019047924,0.00066872814,0.0007144854,0.00020677647,0.0006316864,0.000682484,0.0008926207,0.00091769727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033201103,0.0010700872,0.16210769,0.0004167039,0.0004721966,0.00081033044,0.00015622306,0.03585132,0.022072375,0.0011767328,0.039218128,0.733328],"study_design_scores_gemma":[0.000080073994,0.00037940935,0.052520435,0.00007080051,0.00023837975,0.00047115318,0.0001967572,0.93449026,0.007480474,0.0016503762,0.0023616392,0.000060229948],"about_ca_topic_score_codex":0.012562346,"about_ca_topic_score_gemma":0.026434064,"teacher_disagreement_score":0.012562346,"about_ca_system_score_codex":0.0005483742,"about_ca_system_score_gemma":0.0012785833,"threshold_uncertainty_score":0.0249784},"labels":[],"label_agreement":null},{"id":"W4393567813","doi":"10.5281/zenodo.7569672","title":"DACOS - Dataset","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science","score_opus":0.25255802908072666,"score_gpt":0.45796443850075513,"score_spread":0.20540640942002847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393567813","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006856658,0.000139945,0.0006602835,0.00015069866,0.000083344676,0.00005664425,0.9901128,0.005338929,0.0027716313],"genre_scores_gemma":[0.0008813905,0.00005191817,0.0011533747,0.000091940536,0.000010735573,0.00011259419,0.99666035,0.00039227004,0.00064545864],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965352,0.00044837128,0.00047760608,0.0010230389,0.0011864312,0.00032938214],"domain_scores_gemma":[0.99294394,0.0013977641,0.00043354864,0.0020132537,0.0026863343,0.0005250879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016711465,0.0026437757,0.0012447496,0.005756206,0.0011978409,0.0033672012,0.0027840687,0.0019453012,0.045304235],"category_scores_gemma":[0.010911509,0.0007367985,0.0019324825,0.006677048,0.0005488503,0.003082993,0.002728808,0.0024569996,0.06806631],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014459388,0.00004504477,0.0018715116,0.00092233525,0.000044138662,0.000057152745,0.00005534344,0.00081923336,0.0006177402,0.0012849567,0.98634964,0.0077882097],"study_design_scores_gemma":[0.00011241115,0.000035396777,0.0039900984,0.00021968898,0.00002260844,0.00012102355,0.00013887703,0.0017758046,0.0012791012,0.0018802154,0.9903728,0.000052009254],"about_ca_topic_score_codex":0.017224073,"about_ca_topic_score_gemma":0.0320204,"teacher_disagreement_score":0.045304235,"about_ca_system_score_codex":0.0021501316,"about_ca_system_score_gemma":0.0030370338,"threshold_uncertainty_score":0.1515578},"labels":[],"label_agreement":null},{"id":"W4393622043","doi":"10.5281/zenodo.7569671","title":"DACOS - Dataset","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science","score_opus":0.25255802908072666,"score_gpt":0.45796443850075513,"score_spread":0.20540640942002847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393622043","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006856658,0.000139945,0.0006602835,0.00015069866,0.000083344676,0.00005664425,0.9901128,0.005338929,0.0027716313],"genre_scores_gemma":[0.0008813905,0.00005191817,0.0011533747,0.000091940536,0.000010735573,0.00011259419,0.99666035,0.00039227004,0.00064545864],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965352,0.00044837128,0.00047760608,0.0010230389,0.0011864312,0.00032938214],"domain_scores_gemma":[0.99294394,0.0013977641,0.00043354864,0.0020132537,0.0026863343,0.0005250879],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016711465,0.0026437757,0.0012447496,0.005756206,0.0011978409,0.0033672012,0.0027840687,0.0019453012,0.045304235],"category_scores_gemma":[0.010911509,0.0007367985,0.0019324825,0.006677048,0.0005488503,0.003082993,0.002728808,0.0024569996,0.06806631],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014459388,0.00004504477,0.0018715116,0.00092233525,0.000044138662,0.000057152745,0.00005534344,0.00081923336,0.0006177402,0.0012849567,0.98634964,0.0077882097],"study_design_scores_gemma":[0.00011241115,0.000035396777,0.0039900984,0.00021968898,0.00002260844,0.00012102355,0.00013887703,0.0017758046,0.0012791012,0.0018802154,0.9903728,0.000052009254],"about_ca_topic_score_codex":0.017224073,"about_ca_topic_score_gemma":0.0320204,"teacher_disagreement_score":0.95469576,"about_ca_system_score_codex":0.0021501316,"about_ca_system_score_gemma":0.0030370338,"threshold_uncertainty_score":0.1515578},"labels":[],"label_agreement":null},{"id":"W4393687373","doi":"10.5281/zenodo.6376543","title":"MaMI dataset","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; McGill University","funders":"","keywords":"Computer science","score_opus":0.20315194048613203,"score_gpt":0.43871970721891895,"score_spread":0.23556776673278693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393687373","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012576419,0.00077516184,0.0004903649,0.0003386176,0.00012054241,0.00007492998,0.993757,0.0013477104,0.0018379883],"genre_scores_gemma":[0.00087610516,0.0001683974,0.0009561038,0.00010465859,0.0000146074135,0.00013593945,0.9969875,0.00005046495,0.0007061256],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99880075,0.0002287409,0.00013472092,0.00039855987,0.00028252305,0.00015478166],"domain_scores_gemma":[0.9989833,0.0002468205,0.000079347854,0.00028416724,0.00027976325,0.00012662832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011782555,0.0032166003,0.0018746521,0.0031075235,0.0013278915,0.0020980611,0.0046320455,0.0030994078,0.027053108],"category_scores_gemma":[0.0044107563,0.00056373066,0.0021240634,0.004388664,0.00054086105,0.0014624685,0.002203002,0.0024436703,0.054093774],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017796604,0.00010624892,0.0010832362,0.00094874174,0.00009964632,0.00009703568,0.000031526193,0.0011052429,0.00044437635,0.0007470379,0.9874236,0.007735223],"study_design_scores_gemma":[0.00040383308,0.00009634185,0.005414102,0.00034452847,0.00011211452,0.00044254446,0.00015966463,0.004851442,0.0013264014,0.0028836685,0.98388404,0.00008133318],"about_ca_topic_score_codex":0.020880057,"about_ca_topic_score_gemma":0.047833428,"teacher_disagreement_score":0.027053108,"about_ca_system_score_codex":0.0017879988,"about_ca_system_score_gemma":0.0022888102,"threshold_uncertainty_score":0.090501666},"labels":[],"label_agreement":null},{"id":"W4393771324","doi":"10.5281/zenodo.7626109","title":"Dataset from Shrestha et al., JCI Insight (2021)","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science","score_opus":0.20882779665140902,"score_gpt":0.4433724478715013,"score_spread":0.2345446512200923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393771324","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002746942,0.00019390773,0.000102657374,0.00013296817,0.00006449401,0.00001854353,0.9978071,0.0004528763,0.0009528625],"genre_scores_gemma":[0.0002973989,0.00005421302,0.00025132764,0.00006486988,0.000008449859,0.00004373313,0.99881387,0.000047490976,0.00041868893],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99898976,0.00017170396,0.00012726097,0.00028004372,0.0002618073,0.0001693834],"domain_scores_gemma":[0.9979965,0.0005499292,0.0001508763,0.00046653056,0.0005343828,0.00030169345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011461475,0.0023611845,0.0014252343,0.0034911146,0.0013514052,0.0026052014,0.0033679374,0.0028933233,0.053879328],"category_scores_gemma":[0.005298589,0.00064362795,0.0016899558,0.004981648,0.0005694881,0.0010964439,0.0020967578,0.0021830301,0.083493724],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006130084,0.000029066223,0.0006110828,0.0004825549,0.000031480817,0.000045902445,0.000020907124,0.00023770958,0.00020677516,0.00031084794,0.9961248,0.0018375851],"study_design_scores_gemma":[0.00033538963,0.00003534886,0.004850576,0.00036939015,0.000058026635,0.00023525477,0.000096129224,0.00076273084,0.00066481665,0.0013784927,0.9911737,0.000040138944],"about_ca_topic_score_codex":0.02336395,"about_ca_topic_score_gemma":0.057824828,"teacher_disagreement_score":0.053879328,"about_ca_system_score_codex":0.0015254398,"about_ca_system_score_gemma":0.002843264,"threshold_uncertainty_score":0.18024427},"labels":[],"label_agreement":null},{"id":"W4393850412","doi":"10.1016/j.ekir.2024.02.1030","title":"WCN24-2399 PREDICTORS OF WEIGHT GAIN AFTER ONE YEAR OF KIDNEY TRANSPLANTATION: AN EXPLORATORY STUDY USING MACHINE LEARNING METHOD","year":2024,"lang":"en","type":"article","venue":"Kidney International Reports","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Medicine; Kidney transplantation; Exploratory research; Transplantation; Internal medicine","score_opus":0.10814161497549149,"score_gpt":0.46079319340973957,"score_spread":0.3526515784342481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393850412","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99862504,0.00007292153,0.0004390877,0.000033737495,0.00001729445,0.000015848847,0.0005629723,0.00000976151,0.00022346567],"genre_scores_gemma":[0.9975303,0.000044522625,0.00045877564,0.000014131722,0.000022973032,0.00004659243,0.001177484,0.000009862672,0.000695473],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930215,0.00029589227,0.00006522332,0.00012779071,0.00010479238,0.00010399642],"domain_scores_gemma":[0.9970071,0.0015240754,0.0004359359,0.00026238637,0.00027593848,0.000494604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018835219,0.0005615459,0.00060154434,0.0013120351,0.0005704519,0.00076781644,0.0005859157,0.00054739683,0.0038904329],"category_scores_gemma":[0.00407986,0.00021393977,0.0012778322,0.0013103299,0.0002627351,0.0003448831,0.0005224877,0.0009223506,0.0009139651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00093948294,0.0005233041,0.9927505,0.00001330297,0.00022044126,0.0001136712,0.00004807696,0.0003815107,0.00024845768,0.000029518433,0.00025908495,0.0044725863],"study_design_scores_gemma":[0.000048384987,0.0006895778,0.9913727,0.000011857217,0.00018790567,0.00025647163,0.0002385416,0.0064841923,0.00020455895,0.00006454984,0.00042712613,0.000014299438],"about_ca_topic_score_codex":0.0054209935,"about_ca_topic_score_gemma":0.003105942,"teacher_disagreement_score":0.0054209935,"about_ca_system_score_codex":0.00028063447,"about_ca_system_score_gemma":0.0007307324,"threshold_uncertainty_score":0.013014793},"labels":[],"label_agreement":null},{"id":"W4393856313","doi":"10.1016/j.ekir.2024.02.182","title":"WCN24-987 ORGANIZATION AND STRUCTURES FOR DETECTION AND MONITORING OF CHRONIC KIDNEY DISEASE ACROSS WORLD COUNTRIES AND REGIONS: AN OBSERVATIONAL DATA FROM GLOBAL SURVEY","year":2024,"lang":"en","type":"article","venue":"Kidney International Reports","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; University of Alberta","funders":"","keywords":"Medicine; Observational study; Kidney disease; Intensive care medicine; Environmental health; Internal medicine","score_opus":0.24865076467409872,"score_gpt":0.5037953241138148,"score_spread":0.25514455943971603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393856313","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75632024,0.00054518593,0.0026593553,0.0015364124,0.00010825791,0.0010544056,0.22836414,0.00011576515,0.00929624],"genre_scores_gemma":[0.84581137,0.00048053695,0.0049457173,0.00079833576,0.0001011598,0.0037462325,0.13958228,0.00009140926,0.004442984],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99625057,0.0017875741,0.00048182273,0.00038742635,0.0007017513,0.00039087035],"domain_scores_gemma":[0.9824171,0.0022032887,0.0070173224,0.0024292974,0.0037695174,0.0021635508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004250389,0.0003579456,0.0004221202,0.0023365738,0.00062324334,0.000979194,0.0008768878,0.00058175914,0.0028165313],"category_scores_gemma":[0.014542335,0.00037350244,0.00061730744,0.0065275505,0.0003753783,0.00071107445,0.0015710277,0.000853717,0.0013917185],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051769595,0.00007733335,0.98903906,0.000044500295,0.00006516365,0.000016410386,0.00017674471,0.00010996329,0.000046143956,0.000082409686,0.007177544,0.0031129683],"study_design_scores_gemma":[0.00002344344,0.00007361643,0.99388415,0.000039058446,0.000029899065,0.000045714496,0.00050751324,0.00018931387,0.000056476467,0.00003295211,0.0051100887,0.000007758182],"about_ca_topic_score_codex":0.10641104,"about_ca_topic_score_gemma":0.09387865,"teacher_disagreement_score":0.10641104,"about_ca_system_score_codex":0.0011916732,"about_ca_system_score_gemma":0.003765795,"threshold_uncertainty_score":0.21158332},"labels":[],"label_agreement":null},{"id":"W4393874216","doi":"10.5281/zenodo.7570428","title":"DACOS - Dataset","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science","score_opus":0.25255802908072666,"score_gpt":0.45796443850075513,"score_spread":0.20540640942002847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393874216","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006856658,0.000139945,0.0006602835,0.00015069866,0.000083344676,0.00005664425,0.9901128,0.005338929,0.0027716313],"genre_scores_gemma":[0.0008813905,0.00005191817,0.0011533747,0.000091940536,0.000010735573,0.00011259419,0.99666035,0.00039227004,0.00064545864],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965352,0.00044837128,0.00047760608,0.0010230389,0.0011864312,0.00032938214],"domain_scores_gemma":[0.99294394,0.0013977641,0.00043354864,0.0020132537,0.0026863343,0.0005250879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016711465,0.0026437757,0.0012447496,0.005756206,0.0011978409,0.0033672012,0.0027840687,0.0019453012,0.045304235],"category_scores_gemma":[0.010911509,0.0007367985,0.0019324825,0.006677048,0.0005488503,0.003082993,0.002728808,0.0024569996,0.06806631],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014459388,0.00004504477,0.0018715116,0.00092233525,0.000044138662,0.000057152745,0.00005534344,0.00081923336,0.0006177402,0.0012849567,0.98634964,0.0077882097],"study_design_scores_gemma":[0.00011241115,0.000035396777,0.0039900984,0.00021968898,0.00002260844,0.00012102355,0.00013887703,0.0017758046,0.0012791012,0.0018802154,0.9903728,0.000052009254],"about_ca_topic_score_codex":0.017224073,"about_ca_topic_score_gemma":0.0320204,"teacher_disagreement_score":0.045304235,"about_ca_system_score_codex":0.0021501316,"about_ca_system_score_gemma":0.0030370338,"threshold_uncertainty_score":0.1515578},"labels":[],"label_agreement":null},{"id":"W4393950257","doi":"","title":"Reporting and Methods in Developing Prognostic Prediction Models for Metabolic Syndrome: A Systematic Review and Critical Appraisal","year":2020,"lang":"en","type":"review","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Critical appraisal; Computer science; Management science; Computational biology; Data science; Econometrics; Medicine; Biology; Engineering; Mathematics; Pathology; Alternative medicine","score_opus":0.7484379450799407,"score_gpt":0.7506962437840632,"score_spread":0.00225829870412253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393950257","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039216336,0.57870346,0.05933497,0.0174184,0.0054616216,0.31851333,0.01279292,0.00090291636,0.0029507326],"genre_scores_gemma":[0.0353192,0.17107554,0.13014048,0.004637031,0.0009235504,0.65447056,0.0025200509,0.00018326112,0.0007303186],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.44402,0.26979825,0.2291584,0.013709819,0.040627446,0.002686148],"domain_scores_gemma":[0.31806016,0.48453426,0.08682366,0.02596778,0.08179347,0.0028206997],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.39886728,0.006598699,0.019722925,0.039327055,0.005235798,0.009527011,0.00954884,0.0064465906,0.009817694],"category_scores_gemma":[0.621399,0.0053376276,0.019885998,0.030806597,0.006848427,0.014086655,0.0074562803,0.005102451,0.0011983333],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002775939,0.00002657923,0.0010085534,0.9464469,0.0077428506,0.0001208443,0.0016502797,0.0003186633,0.00014095668,0.0015622323,0.006400557,0.03430402],"study_design_scores_gemma":[0.0008697132,0.00016120261,0.001240299,0.9527796,0.021436287,0.00010269347,0.0011587929,0.0007018601,0.00034533013,0.0030648755,0.017969092,0.00017026778],"about_ca_topic_score_codex":0.011458287,"about_ca_topic_score_gemma":0.018467022,"teacher_disagreement_score":0.60113275,"about_ca_system_score_codex":0.022844879,"about_ca_system_score_gemma":0.083928615,"threshold_uncertainty_score":0.7413037},"labels":[],"label_agreement":null},{"id":"W4394051994","doi":"10.5281/zenodo.6382987","title":"Clinical Dataset SE objects - GSE25066","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Computer science; Information retrieval","score_opus":0.32449775944404347,"score_gpt":0.5041622567121173,"score_spread":0.17966449726807387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394051994","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00076331844,0.00038955084,0.00019802371,0.00024860367,0.00006992916,0.000057748068,0.99631965,0.0006939463,0.0012592665],"genre_scores_gemma":[0.0007609632,0.00009403553,0.00039515184,0.00012839804,0.000018337743,0.00012727533,0.99775606,0.00007727712,0.00064257794],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99766785,0.000506069,0.0002851071,0.00080611074,0.00044461037,0.00029033964],"domain_scores_gemma":[0.9963187,0.0009640938,0.00032775872,0.0008726224,0.0010033139,0.0005133538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002250773,0.00363087,0.0028826569,0.0049648825,0.0015115329,0.0029363264,0.0043588895,0.0043594795,0.04590857],"category_scores_gemma":[0.01062197,0.0008553443,0.0023162717,0.00642346,0.000759869,0.0009892168,0.003062635,0.002329965,0.06555478],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003179005,0.00006725337,0.0015228905,0.0012412833,0.00015126036,0.00009870768,0.000029568057,0.00041394838,0.00045004388,0.00043321346,0.99179405,0.0034798014],"study_design_scores_gemma":[0.0018561018,0.0001645109,0.01415594,0.00074888446,0.00044481276,0.00077587087,0.00017691153,0.0011116407,0.0017190028,0.0029691115,0.97578514,0.00009213172],"about_ca_topic_score_codex":0.028831182,"about_ca_topic_score_gemma":0.044141185,"teacher_disagreement_score":0.04590857,"about_ca_system_score_codex":0.0023714856,"about_ca_system_score_gemma":0.0056975107,"threshold_uncertainty_score":0.15357947},"labels":[],"label_agreement":null},{"id":"W4394079474","doi":"10.6084/m9.figshare.20677966","title":"Additional file 1 of Opening the black box: interpretable machine learning for predictor finding of metabolic syndrome","year":2022,"lang":"en","type":"dataset","venue":"Open MIND","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Black box; Metabolic syndrome; Computer science; Machine learning; Artificial intelligence; Biology; Endocrinology; Diabetes mellitus","score_opus":0.15319171930700784,"score_gpt":0.4548649496319371,"score_spread":0.3016732303249292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394079474","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009615853,0.000023120345,0.00008535781,0.000050905546,0.000017526358,0.00003383775,0.99931216,0.00008773129,0.0002930932],"genre_scores_gemma":[0.002014021,0.00007233475,0.000989709,0.00023160654,0.000046678066,0.0006756337,0.9938834,0.00015866614,0.0019281082],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99906594,0.00019741079,0.00014923733,0.00031089317,0.00013844222,0.00013820121],"domain_scores_gemma":[0.99083906,0.006210845,0.00051676104,0.00080603,0.0012308648,0.00039636917],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018252999,0.0017525885,0.0014760653,0.0022929497,0.0007837169,0.001993553,0.002407607,0.0018558151,0.5604545],"category_scores_gemma":[0.019244034,0.0005765815,0.0011707268,0.0034668352,0.00043588853,0.001401633,0.0012537237,0.0015154702,0.124854706],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016537607,0.000074124364,0.0016015628,0.0010470881,0.000035861536,0.000022013099,0.000017400946,0.00024456737,0.000044453263,0.00035589805,0.9933374,0.0030542293],"study_design_scores_gemma":[0.0038549323,0.00024447733,0.018141879,0.002161083,0.00026031453,0.00040082526,0.00030928772,0.0024456515,0.0008746783,0.011690613,0.95947856,0.00013780472],"about_ca_topic_score_codex":0.010173307,"about_ca_topic_score_gemma":0.020793224,"teacher_disagreement_score":0.5604545,"about_ca_system_score_codex":0.0013574589,"about_ca_system_score_gemma":0.0022861713,"threshold_uncertainty_score":0.6269583},"labels":[],"label_agreement":null},{"id":"W4394085177","doi":"10.6084/m9.figshare.13020607.v1","title":"Identifying cases of chronic pain using health administrative data: A validation study","year":2020,"lang":"en","type":"dataset","venue":"Figshare","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Chronic pain; Computer science; Data mining; Medicine; Physical therapy","score_opus":0.7841448146903695,"score_gpt":0.6255339922057733,"score_spread":0.15861082248459613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394085177","genre_codex":"empirical","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99468,0.00006797652,0.0027410495,0.00007032621,0.0000116964475,0.0009875742,0.00070341915,0.000023150862,0.0007148184],"genre_scores_gemma":[0.9905844,0.000067222034,0.00545969,0.00012412155,0.000015352734,0.0005485689,0.0030024014,0.000015190954,0.00018312864],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9826135,0.010205093,0.0009948224,0.0016193279,0.003721933,0.0008453314],"domain_scores_gemma":[0.9315202,0.030639783,0.006819535,0.012019546,0.017557306,0.0014435558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031297818,0.00073985,0.0004894221,0.0015759713,0.0010607222,0.0010167481,0.002055934,0.0010785476,0.0007419933],"category_scores_gemma":[0.07003011,0.0004946558,0.0011734806,0.0011531871,0.0017433398,0.0008323895,0.0013374322,0.0010030384,0.000489268],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007421394,0.0015627714,0.9853829,0.00006203013,0.00017293081,0.00010402099,0.00095012545,0.001047072,0.00050955755,0.0001753187,0.0006720037,0.008619204],"study_design_scores_gemma":[0.00054084294,0.0023136553,0.9814276,0.00007717695,0.00017402912,0.00036014273,0.00068243104,0.011488387,0.0011262422,0.00016414716,0.0016112026,0.00003400856],"about_ca_topic_score_codex":0.048327263,"about_ca_topic_score_gemma":0.03825956,"teacher_disagreement_score":0.048327263,"about_ca_system_score_codex":0.0027925225,"about_ca_system_score_gemma":0.0051180837,"threshold_uncertainty_score":0.16552067},"labels":[],"label_agreement":null},{"id":"W4394180035","doi":"10.6084/m9.figshare.22599464","title":"Additional file 4 of Machine learning of plasma metabolome identifies biomarker panels for metabolic syndrome: findings from the China Suboptimal Health Cohort","year":2023,"lang":"en","type":"dataset","venue":"Open MIND","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Centre for Addiction and Mental Health; University of Alberta; University of Ottawa","funders":"","keywords":"Metabolome; Biomarker; Cohort; Metabolomics; Metabolic syndrome; Computational biology; Computer science; Bioinformatics; Medicine; Biology; Internal medicine; Genetics; Obesity","score_opus":0.15210808531978742,"score_gpt":0.4444829218603849,"score_spread":0.2923748365405975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394180035","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020031935,0.000013653293,0.000044020944,0.000041333424,0.000007986569,0.000016954858,0.99948585,0.0000441259,0.00014580674],"genre_scores_gemma":[0.0027062169,0.000040813036,0.0003785275,0.00011979852,0.000022443646,0.00041569528,0.99494994,0.00004579814,0.0013208305],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99935585,0.00009678016,0.00010532895,0.00020980313,0.00010662055,0.00012565702],"domain_scores_gemma":[0.99597824,0.0021323236,0.00041915147,0.00048036114,0.0007187995,0.00027111365],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012862111,0.0015406675,0.0013539554,0.0018984862,0.0007492543,0.0015985036,0.0023462311,0.0017164996,0.34269413],"category_scores_gemma":[0.012016009,0.00053799996,0.0012896353,0.0030698779,0.00035569692,0.0010343781,0.0011420149,0.001266357,0.05175383],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025372647,0.00008845454,0.008232856,0.001093765,0.000094527626,0.000062843406,0.000029840214,0.0005275335,0.00007821048,0.00039333134,0.9857848,0.0033600687],"study_design_scores_gemma":[0.007752873,0.00034929873,0.10518441,0.0027552217,0.00065306714,0.00064264494,0.0005475325,0.005501297,0.0013612256,0.0089614475,0.86605644,0.00023459822],"about_ca_topic_score_codex":0.022587407,"about_ca_topic_score_gemma":0.04099396,"teacher_disagreement_score":0.34269413,"about_ca_system_score_codex":0.0013644333,"about_ca_system_score_gemma":0.0022324657,"threshold_uncertainty_score":0.93756706},"labels":[],"label_agreement":null},{"id":"W4394181641","doi":"10.6084/m9.figshare.13020607","title":"Identifying cases of chronic pain using health administrative data: A validation study","year":2020,"lang":"en","type":"dataset","venue":"Figshare","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Chronic pain; Medicine; Computer science; Data mining; Physical therapy","score_opus":0.7841448146903695,"score_gpt":0.6255339922057733,"score_spread":0.15861082248459613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394181641","genre_codex":"empirical","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9913565,0.00011170583,0.00500448,0.000086221095,0.000019321044,0.0015236746,0.0007554507,0.000031755833,0.0011110364],"genre_scores_gemma":[0.9879667,0.00010437414,0.007919989,0.00015189362,0.000020247575,0.00084321306,0.002710672,0.000026478,0.0002564025],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9719315,0.01735479,0.0015461657,0.0019987796,0.0059783263,0.0011903679],"domain_scores_gemma":[0.90965664,0.035081238,0.0072836014,0.018821808,0.027611615,0.0015450626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04833155,0.0007758955,0.0006009263,0.0014632584,0.0012985176,0.0012588066,0.002280426,0.0011170141,0.0006603257],"category_scores_gemma":[0.09223568,0.0006068789,0.0013253576,0.0012787697,0.0019030191,0.00088912895,0.0013370616,0.001088736,0.00043504647],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010597982,0.0017901391,0.9758699,0.000103239916,0.00028829338,0.00015966917,0.0021447113,0.0015812874,0.001031206,0.0003404597,0.00088161766,0.014749653],"study_design_scores_gemma":[0.0005389141,0.0025534295,0.97721237,0.0001152946,0.0002817009,0.00040155588,0.00091497565,0.01311301,0.0018781289,0.00020315948,0.002739017,0.000048458347],"about_ca_topic_score_codex":0.081554204,"about_ca_topic_score_gemma":0.074859485,"teacher_disagreement_score":0.081554204,"about_ca_system_score_codex":0.0034591046,"about_ca_system_score_gemma":0.0068374863,"threshold_uncertainty_score":0.25560468},"labels":[],"label_agreement":null},{"id":"W4394265151","doi":"10.6084/m9.figshare.14937815","title":"Construction of a novel risk model based on the random forest algorithm to distinguish pancreatic cancers with different prognoses and immune microenvironment features","year":2021,"lang":"en","type":"dataset","venue":"Figshare","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Addiction and Mental Health; McGill University; Jewish General Hospital","funders":"","keywords":"Random forest; Immune system; Risk model; Pancreatic cancer; Computer science; Tumor microenvironment; Computational biology; Algorithm; Biology; Artificial intelligence; Medicine; Internal medicine; Mathematics; Statistics; Cancer; Immunology","score_opus":0.07165084257218202,"score_gpt":0.3607142173877942,"score_spread":0.2890633748156122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394265151","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030246377,0.00021032561,0.966933,0.0002638736,0.00007511029,0.00017573764,0.00028481925,0.0013048174,0.0005059321],"genre_scores_gemma":[0.505603,0.00027912637,0.4886009,0.00028340865,0.00015286286,0.0009815319,0.0019088981,0.00024482992,0.0019454993],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99884593,0.0004002362,0.00008222379,0.0003261652,0.00015479221,0.00019059388],"domain_scores_gemma":[0.9983005,0.001002165,0.00012560049,0.00005977085,0.00041501303,0.000097076896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045016333,0.0014960521,0.0018618815,0.002113718,0.0009173078,0.0013164167,0.0017263144,0.001490155,0.0027788775],"category_scores_gemma":[0.005304722,0.0006154129,0.0021684822,0.00080919825,0.00044729112,0.0010773533,0.0011131269,0.0017840976,0.0010037806],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004892237,0.00023821427,0.019203313,0.00013570218,0.000301731,0.0002674854,0.00012224249,0.7612974,0.0022837883,0.0042052735,0.0042397473,0.20721593],"study_design_scores_gemma":[0.000013690889,0.000025553614,0.00029699178,0.0000074665436,0.000015820262,0.00002937178,0.0000061131536,0.99820125,0.0001428701,0.0010690829,0.00018515764,0.0000066117927],"about_ca_topic_score_codex":0.013582963,"about_ca_topic_score_gemma":0.0085718185,"teacher_disagreement_score":0.013582963,"about_ca_system_score_codex":0.00093429827,"about_ca_system_score_gemma":0.0022812681,"threshold_uncertainty_score":0.027007818},"labels":[],"label_agreement":null},{"id":"W4394309186","doi":"10.6084/m9.figshare.20677969","title":"Additional file 2 of Opening the black box: interpretable machine learning for predictor finding of metabolic syndrome","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Black box; Machine learning; Computer science; Metabolic syndrome; Artificial intelligence; Medicine; Internal medicine","score_opus":0.1523991707618875,"score_gpt":0.42413867558244783,"score_spread":0.2717395048205603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394309186","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000079597005,0.00002306287,0.00011883705,0.00004708084,0.000018268938,0.00003332615,0.9992256,0.000182936,0.00027123143],"genre_scores_gemma":[0.002006269,0.00007367328,0.0013687504,0.00024558953,0.00004992939,0.0007926329,0.99286336,0.00037289757,0.0022269024],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991603,0.00016484398,0.00012801019,0.0003093644,0.00011892145,0.00011854778],"domain_scores_gemma":[0.99012333,0.0071102013,0.0004569526,0.00087811827,0.001051407,0.0003799874],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001668833,0.0018269506,0.0015567925,0.002418353,0.0007492136,0.0021803821,0.0025050738,0.0018618266,0.6425289],"category_scores_gemma":[0.020229498,0.0006520262,0.0014706111,0.0033998678,0.0004328363,0.0013796523,0.0012148833,0.0015278836,0.171007],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019862315,0.000058114652,0.0016012805,0.0014925291,0.000053599946,0.000029980203,0.000020214302,0.00030862796,0.000068524525,0.00034812838,0.99205714,0.003763216],"study_design_scores_gemma":[0.0038326564,0.00023298594,0.0150780855,0.0020131099,0.00033888684,0.00042631925,0.00021283826,0.0022758439,0.0010475647,0.010983845,0.9634238,0.00013411499],"about_ca_topic_score_codex":0.007427374,"about_ca_topic_score_gemma":0.01564436,"teacher_disagreement_score":0.6425289,"about_ca_system_score_codex":0.0010416191,"about_ca_system_score_gemma":0.0020842052,"threshold_uncertainty_score":0.5098891},"labels":[],"label_agreement":null},{"id":"W4394389674","doi":"10.6084/m9.figshare.22599458","title":"Additional file 2 of Machine learning of plasma metabolome identifies biomarker panels for metabolic syndrome: findings from the China Suboptimal Health Cohort","year":2023,"lang":"en","type":"dataset","venue":"Figshare","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Centre for Addiction and Mental Health; University of Alberta; University of Ottawa","funders":"","keywords":"Metabolome; Biomarker; Cohort; Computational biology; Metabolomics; Computer science; Medicine; Bioinformatics; Biology; Internal medicine; Genetics","score_opus":0.14608337864570206,"score_gpt":0.4136449999710946,"score_spread":0.2675616213253925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394389674","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017164643,0.000013571416,0.000055843648,0.00003556188,0.000007639027,0.00002167162,0.99949443,0.00004910292,0.00015047776],"genre_scores_gemma":[0.003926093,0.000062650055,0.00062956323,0.00017852719,0.000034946475,0.0006627146,0.9926166,0.00009349862,0.0017954225],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994222,0.00008262459,0.00009569915,0.00020326275,0.000091193964,0.000105083294],"domain_scores_gemma":[0.99451256,0.0033053735,0.0005151716,0.0005730287,0.0008045228,0.00028943052],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012229349,0.0014071373,0.0013880188,0.0019318076,0.00078932836,0.0015699406,0.0021000258,0.0014580882,0.493861],"category_scores_gemma":[0.013857392,0.0005111675,0.0013010268,0.0034271197,0.00033014643,0.001134991,0.0010618996,0.0011866105,0.060356542],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030305953,0.000079664336,0.006687519,0.0013125757,0.00009812113,0.000068071546,0.00003210018,0.0005341114,0.00008506395,0.00046855185,0.98622584,0.004105439],"study_design_scores_gemma":[0.009384199,0.00044245712,0.09661304,0.0031172724,0.0007597512,0.0008619205,0.00055197696,0.0053853905,0.0013106914,0.013497977,0.8678118,0.0002635557],"about_ca_topic_score_codex":0.015336143,"about_ca_topic_score_gemma":0.02386182,"teacher_disagreement_score":0.493861,"about_ca_system_score_codex":0.0010586366,"about_ca_system_score_gemma":0.0020983077,"threshold_uncertainty_score":0.7219459},"labels":[],"label_agreement":null},{"id":"W4394714488","doi":"10.5220/0008986300002513","title":"A Framework for System-level Health Data Sharing","year":2020,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University; University of Ottawa","funders":"","keywords":"Computer science","score_opus":0.8226170150406564,"score_gpt":0.620148697993804,"score_spread":0.20246831704685242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394714488","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014354046,0.00010741215,0.9906641,0.0005544448,0.000084253705,0.00024178615,0.00025595247,0.005024591,0.0016321064],"genre_scores_gemma":[0.09573553,0.00020270741,0.89742506,0.000551337,0.00012171293,0.00045024493,0.001803967,0.000757007,0.0029525317],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98708725,0.0039117136,0.0018287507,0.0021410154,0.0039087343,0.001122594],"domain_scores_gemma":[0.9834821,0.00436359,0.0007271024,0.007956888,0.0021711523,0.0012991157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018686628,0.0009842236,0.0017978743,0.0029826376,0.0030022871,0.010696204,0.006575101,0.0032236332,0.0075587034],"category_scores_gemma":[0.025738114,0.0014970511,0.003514787,0.003583027,0.0029078159,0.012705434,0.014436226,0.004715356,0.0026919611],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005205456,0.00053851324,0.0046898057,0.00056747923,0.00062391884,0.000829737,0.0023091682,0.06140305,0.0073304563,0.6713482,0.029863236,0.21997586],"study_design_scores_gemma":[0.00011497705,0.00013897187,0.000627068,0.00018959149,0.00021404357,0.00039540196,0.00056834775,0.53610176,0.009974617,0.37133998,0.080197416,0.00013781898],"about_ca_topic_score_codex":0.010634846,"about_ca_topic_score_gemma":0.01166345,"teacher_disagreement_score":0.018686628,"about_ca_system_score_codex":0.0023266696,"about_ca_system_score_gemma":0.0066736178,"threshold_uncertainty_score":0.098825514},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4394714600","doi":"10.5220/0008857300002513","title":"Advanced Analytics to Predict Survivability of Breast Cancer Patients","year":2020,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Survivability; Breast cancer; Computer science; Analytics; Cancer; Data science; Medicine; Internal medicine; Computer network","score_opus":0.15591651943234813,"score_gpt":0.4872915018489559,"score_spread":0.3313749824166078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394714600","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9200303,0.0036412526,0.037143636,0.0062883324,0.0003773021,0.00023022073,0.019923031,0.0011459743,0.011219967],"genre_scores_gemma":[0.9846156,0.00047832326,0.006554407,0.00019343119,0.00011734253,0.000032756365,0.0072080814,0.000012758109,0.0007872849],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999466,0.00013201355,0.000057579742,0.000093794646,0.00016330736,0.00008733472],"domain_scores_gemma":[0.99717027,0.0016457787,0.0003999246,0.00015940874,0.00041869635,0.00020597411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072792935,0.00045218822,0.00040500605,0.0022302628,0.00021182577,0.0011497604,0.0003691588,0.00046030764,0.0020417967],"category_scores_gemma":[0.005759187,0.000099105746,0.0004865681,0.0012682842,0.000109254506,0.00071076385,0.0005910052,0.00077318854,0.0006661247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079742586,0.0008788792,0.7004468,0.00024455567,0.00034625106,0.00035321663,0.0002681496,0.033199787,0.0019513109,0.002808347,0.019978013,0.23872735],"study_design_scores_gemma":[0.00008489542,0.0009774511,0.2487244,0.00027909313,0.00032227847,0.0008298203,0.0014993866,0.7030673,0.004348748,0.024474086,0.015332305,0.00006017456],"about_ca_topic_score_codex":0.004609587,"about_ca_topic_score_gemma":0.005523405,"teacher_disagreement_score":0.004609587,"about_ca_system_score_codex":0.00037582498,"about_ca_system_score_gemma":0.00064325513,"threshold_uncertainty_score":0.009165525},"labels":[],"label_agreement":null},{"id":"W4394721809","doi":"10.1016/j.healun.2024.02.1446","title":"Predictive Models Refine Physician Prognostication: A Secondary Analysis Evaluating Integrated Model and Physician Prognostic Estimates in Heart Failure Patients with Reduced Left Ventricular Ejection Fraction","year":2024,"lang":"en","type":"article","venue":"The Journal of Heart and Lung Transplantation","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Ottawa; Toronto General Hospital; McMaster University; Hamilton General Hospital; St. Boniface Hospital; St. Michael's Hospital; Dalhousie University; University Health Network; University of Toronto; Southlake Regional Health Center; Providence Health Care","funders":"","keywords":"Ejection fraction; Cardiology; Heart failure; Internal medicine; Medicine","score_opus":0.03699415290051187,"score_gpt":0.3806740049286774,"score_spread":0.34367985202816553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394721809","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9932019,0.00036521317,0.004266047,0.00024567868,0.000050346265,0.00008135652,0.0011118543,0.00008001565,0.0005975623],"genre_scores_gemma":[0.996766,0.00008140161,0.0013771709,0.00007260129,0.00006204578,0.0000440439,0.0012908505,0.000020088488,0.00028577066],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99625254,0.0021165821,0.00023440472,0.00058941764,0.0005032846,0.00030372813],"domain_scores_gemma":[0.9769027,0.016634092,0.0020031868,0.0016716977,0.0021090664,0.0006792928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009490646,0.0013231856,0.0020490834,0.0009890161,0.00042800562,0.0026227715,0.0010560739,0.0010190231,0.0023631037],"category_scores_gemma":[0.03356869,0.00041678484,0.0027523928,0.0010431146,0.00040751914,0.0022288775,0.0016141743,0.0022765691,0.0004962566],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.036287576,0.003644012,0.8508948,0.00030133539,0.008073564,0.00026351106,0.00044691603,0.032249093,0.0011984414,0.00045208025,0.002258646,0.063930064],"study_design_scores_gemma":[0.0026768723,0.011449688,0.68352824,0.00011510346,0.009645122,0.00050765835,0.0005711031,0.28528517,0.0026712774,0.0017206632,0.0016952392,0.0001338417],"about_ca_topic_score_codex":0.004596891,"about_ca_topic_score_gemma":0.00405087,"teacher_disagreement_score":0.009490646,"about_ca_system_score_codex":0.0009916915,"about_ca_system_score_gemma":0.0014786477,"threshold_uncertainty_score":0.050192},"labels":[],"label_agreement":null},{"id":"W4395078300","doi":"10.18280/ria.380210","title":"Prognostic Evaluation, Prediction and Regimen of Diseases Using SVM, NB and RF Classifiers","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Support vector machine; Regimen; Medicine; Machine learning; Internal medicine; Artificial intelligence; Computer science","score_opus":0.21865172020350132,"score_gpt":0.46522791505109307,"score_spread":0.24657619484759175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395078300","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7915431,0.008793081,0.1850821,0.0014991902,0.0007499787,0.0002283827,0.0037353758,0.0010042383,0.007364509],"genre_scores_gemma":[0.9746727,0.001152593,0.020805603,0.00005970612,0.00018651022,0.00006111076,0.0013610069,0.000025491088,0.0016752935],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939835,0.00020759461,0.0000864437,0.000119686345,0.00012617923,0.0000617224],"domain_scores_gemma":[0.99792105,0.0011548116,0.00017582672,0.00016589504,0.00047881427,0.00010359066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032198369,0.000555083,0.0010420965,0.0013387538,0.00031035414,0.0009653792,0.0004463913,0.00057451613,0.0015114609],"category_scores_gemma":[0.007327477,0.00011294795,0.00095178495,0.00068962894,0.00015434837,0.000672314,0.00031178747,0.00061229133,0.00060862675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029928542,0.0005313764,0.38029265,0.00031888788,0.00050159584,0.00027051583,0.0001807518,0.030677056,0.0068827905,0.0012150289,0.006396262,0.56974024],"study_design_scores_gemma":[0.00017794437,0.0030147969,0.1984717,0.00035231776,0.0019947048,0.0013805444,0.00043114767,0.7691106,0.012051449,0.0054932362,0.0074245273,0.00009697936],"about_ca_topic_score_codex":0.0031880657,"about_ca_topic_score_gemma":0.0021435553,"teacher_disagreement_score":0.0032198369,"about_ca_system_score_codex":0.00033423942,"about_ca_system_score_gemma":0.00060842553,"threshold_uncertainty_score":0.017028332},"labels":[],"label_agreement":null},{"id":"W4395078638","doi":"10.18280/ria.380234","title":"Predicting Emergency Healthcare Requirements Using Deep Learning","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Health care; Computer science; Deep learning; Artificial intelligence; Medical emergency; Medicine; Political science","score_opus":0.25583335691156806,"score_gpt":0.48800914483920393,"score_spread":0.23217578792763588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395078638","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5479313,0.0009865368,0.4307289,0.004108456,0.00022022889,0.00014572812,0.0029466737,0.0015784423,0.011353599],"genre_scores_gemma":[0.9701015,0.00028494297,0.02579602,0.00020304848,0.000043783097,0.000039931896,0.0014727885,0.000022986878,0.0020350153],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997019,0.00007572992,0.000024982795,0.000062112034,0.000076058226,0.000059143273],"domain_scores_gemma":[0.9991443,0.00047114491,0.0001228277,0.00003727765,0.00016867933,0.00005577401],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049107993,0.0005807625,0.00025357233,0.00081263843,0.00018986526,0.0006631457,0.0005285305,0.0007524893,0.0018749939],"category_scores_gemma":[0.0032329345,0.00028414547,0.00032204692,0.0005684843,0.00016764826,0.0011843555,0.00068284775,0.00092476123,0.00039180624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020840917,0.0003973303,0.03760759,0.0001430591,0.000083846724,0.0003108096,0.0001477693,0.8147533,0.0033330524,0.004074541,0.007599138,0.1313411],"study_design_scores_gemma":[0.000002678785,0.000018051642,0.0015060231,0.000008200844,0.0000041409594,0.000016780628,0.000029551193,0.9955712,0.000494101,0.0018868931,0.0004580474,0.000004327224],"about_ca_topic_score_codex":0.010129579,"about_ca_topic_score_gemma":0.016341332,"teacher_disagreement_score":0.010129579,"about_ca_system_score_codex":0.00074831385,"about_ca_system_score_gemma":0.0009396471,"threshold_uncertainty_score":0.020141244},"labels":[],"label_agreement":null},{"id":"W4395093378","doi":"10.2196/56993","title":"Machine Learning–Based Hyperglycemia Prediction: Enhancing Risk Assessment in a Cohort of Undiagnosed Individuals","year":2024,"lang":"en","type":"article","venue":"JMIRx Med","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Fogarty International Center; National Institutes of Health; African Academy of Sciences; Bill and Melinda Gates Foundation","keywords":"Diabetes mellitus; Cohort; Medicine; Risk assessment; Environmental health; Intensive care medicine; Computer science; Internal medicine; Endocrinology; Computer security","score_opus":0.06271680094077546,"score_gpt":0.461596508424928,"score_spread":0.3988797074841525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395093378","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.994145,0.0003435091,0.003721592,0.00042013705,0.00003745412,0.00003954774,0.00038946475,0.000052396892,0.0008509987],"genre_scores_gemma":[0.994348,0.00020857864,0.00464149,0.000080383405,0.000039617804,0.000019447221,0.0004391113,0.0000044110175,0.00021906226],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99961865,0.0001789453,0.000026808038,0.00008336575,0.000051859177,0.00004031816],"domain_scores_gemma":[0.99823713,0.0008670608,0.0003027763,0.00015218218,0.00025822484,0.00018265694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001867023,0.0004158924,0.0004902093,0.0010193499,0.00038671077,0.0010504079,0.00043393645,0.00054716365,0.0008773529],"category_scores_gemma":[0.005015812,0.00015253705,0.0005250726,0.0005677549,0.00012323465,0.00053634105,0.0005542886,0.0010170111,0.00028509388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003412936,0.00047512792,0.96922374,0.00002072651,0.00008939488,0.00008200895,0.00008815636,0.0021880276,0.00034263037,0.0001035074,0.0005037594,0.026541624],"study_design_scores_gemma":[0.00008605973,0.001768719,0.7540374,0.00017007634,0.00042425052,0.0006127716,0.0006290542,0.2361837,0.0016878877,0.0025115598,0.0018299775,0.000058542522],"about_ca_topic_score_codex":0.002938251,"about_ca_topic_score_gemma":0.0035164608,"teacher_disagreement_score":0.002938251,"about_ca_system_score_codex":0.0002746319,"about_ca_system_score_gemma":0.00045309655,"threshold_uncertainty_score":0.009873867},"labels":[],"label_agreement":null},{"id":"W4395112028","doi":"10.18280/ria.380228","title":"Cardiovascular Disease Prediction: Employing Extra Tree Classifier-Based Feature Selection and Optimized RNN with Artificial Bee Colony","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Feature selection; Artificial intelligence; Classifier (UML); Computer science; Machine learning; Pattern recognition (psychology); Selection (genetic algorithm); Artificial bee colony algorithm","score_opus":0.1107248919225176,"score_gpt":0.37633722736650244,"score_spread":0.2656123354439848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395112028","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3067836,0.0016362933,0.68359536,0.00063054316,0.00026622525,0.00022401617,0.00035756297,0.0020099522,0.004496394],"genre_scores_gemma":[0.89080864,0.0002955546,0.10578446,0.00025242326,0.00005260052,0.00011268341,0.00049905723,0.000036328103,0.0021582632],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99962103,0.000078752455,0.00003410386,0.000101844555,0.000109378256,0.00005491294],"domain_scores_gemma":[0.9995826,0.00014326962,0.00004042901,0.000030555922,0.00017927893,0.000023876722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078219594,0.000730138,0.00074164296,0.0007245081,0.00026538054,0.00051852927,0.00095574645,0.00066561124,0.0005743161],"category_scores_gemma":[0.0016631078,0.00023192844,0.0005374357,0.0005794535,0.0001745435,0.00057778246,0.00045785683,0.00052165694,0.00023347998],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003648019,0.00036450647,0.013714689,0.00010232547,0.000190183,0.00029512387,0.00009906996,0.42319715,0.014827666,0.001060253,0.0051265005,0.5406577],"study_design_scores_gemma":[0.00000958789,0.000051823696,0.0009465279,0.000005195154,0.000017008086,0.000027692018,0.000008155379,0.9972899,0.0011919882,0.00021369377,0.00023270998,0.000005787642],"about_ca_topic_score_codex":0.009348706,"about_ca_topic_score_gemma":0.010021462,"teacher_disagreement_score":0.009348706,"about_ca_system_score_codex":0.00044243227,"about_ca_system_score_gemma":0.0006352751,"threshold_uncertainty_score":0.018588603},"labels":[],"label_agreement":null},{"id":"W4395114967","doi":"10.18280/ria.380226","title":"An Enhanced Hybrid Model for Liver Disease Detection Utilizing Deep Learning and Machine Learning","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Deep learning; Computer science; Artificial intelligence; Machine learning","score_opus":0.14061137980201194,"score_gpt":0.42605802436433915,"score_spread":0.2854466445623272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395114967","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10093539,0.002776627,0.8844888,0.0018253587,0.00035832825,0.000088500674,0.0010329868,0.0030743692,0.00541954],"genre_scores_gemma":[0.9102007,0.00090274616,0.07580668,0.0008178039,0.00017658433,0.00021020808,0.0012621954,0.00007646455,0.010546641],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99986124,0.000024901092,0.000009767519,0.000041585477,0.000029214118,0.00003331216],"domain_scores_gemma":[0.9997876,0.00008187341,0.000018921159,0.00001333622,0.00007993289,0.000018303132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047608704,0.0007294223,0.000751827,0.00062677485,0.0002810862,0.0007255922,0.001321113,0.0012047,0.001964766],"category_scores_gemma":[0.00074701785,0.00036873776,0.0009026246,0.00043195958,0.0002554844,0.0006807003,0.0007704198,0.001116664,0.0005018215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020679356,0.00018623164,0.005262472,0.00006813535,0.00016294411,0.00021649715,0.00004478289,0.8551047,0.0031305116,0.002778788,0.004438151,0.12840003],"study_design_scores_gemma":[0.0000032857695,0.000011893546,0.00011738755,0.0000023558239,0.000007224768,0.000012488388,0.000001327881,0.99907935,0.00015787547,0.00043657736,0.00016785543,0.0000024663032],"about_ca_topic_score_codex":0.014865668,"about_ca_topic_score_gemma":0.016053224,"teacher_disagreement_score":0.014865668,"about_ca_system_score_codex":0.0006532774,"about_ca_system_score_gemma":0.0009082738,"threshold_uncertainty_score":0.029558301},"labels":[],"label_agreement":null},{"id":"W4395117249","doi":"10.18280/ria.380223","title":"Classifying Alzheimer's Disease Using Hybrid Model: Xception and Machine Learning","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Disease; Machine learning; Medicine; Pathology","score_opus":0.2959813471863804,"score_gpt":0.4561700545528322,"score_spread":0.1601887073664518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395117249","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79085135,0.004095896,0.19238466,0.0013143466,0.00048232733,0.00023171812,0.0017111849,0.0017089628,0.0072195716],"genre_scores_gemma":[0.9654508,0.0006692952,0.02930017,0.0001829439,0.00012542735,0.00005628862,0.0009343999,0.000037904778,0.003242752],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99947757,0.00013191505,0.000052939682,0.00011925909,0.00013134262,0.00008707277],"domain_scores_gemma":[0.9992009,0.0003419454,0.000043981494,0.00007480142,0.00029122038,0.000047152826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014759318,0.0008843109,0.0008767617,0.002627071,0.00037234864,0.001687198,0.000963372,0.0011474694,0.0014823745],"category_scores_gemma":[0.0016102033,0.00022455207,0.0014083111,0.0008783621,0.00024594026,0.0010455647,0.00055003515,0.00059758505,0.0005750643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017659777,0.0014546507,0.16171092,0.00022225069,0.001175497,0.0005306433,0.00020486802,0.20166181,0.01144056,0.0015898414,0.0070196483,0.61122334],"study_design_scores_gemma":[0.000022198194,0.00021877722,0.0091091655,0.000020569662,0.00019609343,0.00021328006,0.00008327066,0.9860481,0.0026693372,0.0007199356,0.0006758559,0.000023500115],"about_ca_topic_score_codex":0.011722543,"about_ca_topic_score_gemma":0.010054215,"teacher_disagreement_score":0.011722543,"about_ca_system_score_codex":0.0006308558,"about_ca_system_score_gemma":0.0007537248,"threshold_uncertainty_score":0.023308575},"labels":[],"label_agreement":null},{"id":"W4395463615","doi":"10.18280/isi.290228","title":"Predicting Alzheimer's Disease Using a Modified Grey Wolf Optimizer and Support Vector Machine","year":2024,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Support vector machine; Vector (molecular biology); Disease; Artificial intelligence; Computer science; Pattern recognition (psychology); Machine learning; Biology; Medicine; Recombinant DNA; Pathology; Genetics","score_opus":0.0973919921525441,"score_gpt":0.3906002282038953,"score_spread":0.29320823605135116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395463615","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32487932,0.0012108579,0.67070574,0.000555016,0.00008258777,0.00011020124,0.00016140506,0.00060135283,0.0016934499],"genre_scores_gemma":[0.88740057,0.00021320298,0.11013985,0.00015258873,0.00002901819,0.00013224145,0.0002761181,0.00003471201,0.0016218042],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99965775,0.00011830517,0.00002974525,0.00008205098,0.000065414504,0.000046665715],"domain_scores_gemma":[0.99946374,0.00034131046,0.000053260104,0.000028006263,0.000086886175,0.000026791795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011802618,0.0007563575,0.0011145613,0.00065390684,0.00025858489,0.0006340989,0.0007236945,0.0011626586,0.000705733],"category_scores_gemma":[0.0021195626,0.0003422187,0.0008588413,0.0005606063,0.00044389727,0.0004975482,0.0004246803,0.0007011517,0.00014353648],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012457142,0.00006371715,0.003327385,0.00004427474,0.00007718022,0.00010974147,0.000039464263,0.9467799,0.002905527,0.0009766526,0.0004989366,0.04505276],"study_design_scores_gemma":[0.000004173962,0.000025064657,0.00024420177,0.000002339104,0.0000043830105,0.0000065381755,0.000003145592,0.9991436,0.00026767497,0.00025178446,0.00004476285,0.000002334375],"about_ca_topic_score_codex":0.005692575,"about_ca_topic_score_gemma":0.0024387247,"teacher_disagreement_score":0.005692575,"about_ca_system_score_codex":0.00045251832,"about_ca_system_score_gemma":0.0007296448,"threshold_uncertainty_score":0.011318862},"labels":[],"label_agreement":null},{"id":"W4396786975","doi":"10.1016/j.ceh.2024.05.001","title":"Febrile disease modeling and diagnosis system for optimizing medical decisions in resource-scarce settings","year":2024,"lang":"en","type":"article","venue":"Clinical eHealth","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Royal University","funders":"","keywords":"Resource (disambiguation); Disease; Intensive care medicine; Medicine; Computer science; Risk analysis (engineering); Pathology","score_opus":0.30727549833651413,"score_gpt":0.571379011433186,"score_spread":0.2641035130966719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396786975","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21303658,0.003118918,0.72722167,0.0054538106,0.0005149038,0.0013141966,0.012988022,0.021415772,0.014936174],"genre_scores_gemma":[0.7248437,0.0014547546,0.2613353,0.0005921699,0.00014818273,0.00058968045,0.0069118966,0.00012931977,0.003994973],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996424,0.00007194544,0.000057548452,0.00012313128,0.000062267805,0.000042638098],"domain_scores_gemma":[0.9993543,0.00029221913,0.000094642935,0.000041827472,0.00015423234,0.000062786225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083856256,0.001028572,0.0009268651,0.001262517,0.00077189575,0.0012505197,0.00093886536,0.0008397972,0.0038626422],"category_scores_gemma":[0.0021645157,0.00034654455,0.0010159299,0.0007443843,0.00014812859,0.00088997994,0.00093635323,0.0007583419,0.00092515076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018198686,0.0010649477,0.100202255,0.0017889694,0.0004903274,0.0028983322,0.0009870384,0.41138625,0.016250754,0.008531955,0.04186179,0.41271746],"study_design_scores_gemma":[0.00005238611,0.00014477377,0.0059339674,0.00008896902,0.00010958197,0.00029112736,0.00019887839,0.97916836,0.0029361085,0.004234594,0.0068037915,0.000037405403],"about_ca_topic_score_codex":0.012932605,"about_ca_topic_score_gemma":0.016776191,"teacher_disagreement_score":0.012932605,"about_ca_system_score_codex":0.0008948279,"about_ca_system_score_gemma":0.0018369517,"threshold_uncertainty_score":0.025714636},"labels":[],"label_agreement":null},{"id":"W4396992756","doi":"10.1681/asn.20213210s1721c","title":"The Association of CKD Severity with Stroke Subtype Using the TOAST Classification","year":2021,"lang":"en","type":"article","venue":"Journal of the American Society of Nephrology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ottawa Hospital; Institute for Clinical Evaluative Sciences; University of Ottawa","funders":"","keywords":"Medicine; Association (psychology); Stroke (engine); Internal medicine; Psychology; Physics","score_opus":0.10549249205688618,"score_gpt":0.4271276480339477,"score_spread":0.3216351559770615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396992756","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9919817,0.00059144705,0.00023040846,0.00012228303,0.000013617409,0.00010501261,0.004286997,0.000014239559,0.0026543548],"genre_scores_gemma":[0.99722326,0.00012745825,0.00015900239,0.0000209784,0.000008539447,0.000033510187,0.0021453167,0.0000026275254,0.00027930283],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99933845,0.00010198515,0.00009279479,0.0001040897,0.000250774,0.00011192634],"domain_scores_gemma":[0.99852186,0.00010161185,0.0007390463,0.000065883105,0.0003820837,0.00018945793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007914064,0.00024906293,0.00028775635,0.0011745419,0.00038566373,0.00063378894,0.0004218885,0.00024570496,0.0013132554],"category_scores_gemma":[0.002178384,0.000130744,0.00052272284,0.0012698397,0.0002781089,0.0003318764,0.0003654442,0.00039902437,0.00017749939],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010538783,0.000009462678,0.99879175,0.000014879388,0.000067060486,0.000012374328,0.000020640182,0.000040732662,0.000063155894,0.000017939583,0.00031241585,0.00054426806],"study_design_scores_gemma":[0.000014036618,0.000032504693,0.99931216,0.000009022277,0.000039343846,0.00009078496,0.00004234461,0.00016597079,0.00002050497,0.00002352225,0.00024710788,0.0000028591733],"about_ca_topic_score_codex":0.13716932,"about_ca_topic_score_gemma":0.21084428,"teacher_disagreement_score":0.13716932,"about_ca_system_score_codex":0.0010354192,"about_ca_system_score_gemma":0.0016724677,"threshold_uncertainty_score":0.2727418},"labels":[],"label_agreement":null},{"id":"W4396996302","doi":"10.1681/asn.20213210s121c","title":"A Prediction Equation for Incident CKD Using Routinely Collected Data: The Kidney Disease Risk Equation (KDRE)","year":2021,"lang":"en","type":"article","venue":"Journal of the American Society of Nephrology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; Ottawa Hospital","funders":"","keywords":"Kidney disease; Medicine; Disease; Structural equation modeling; Internal medicine; Statistics; Mathematics","score_opus":0.2728712454199081,"score_gpt":0.46115130243732966,"score_spread":0.18828005701742156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396996302","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53112066,0.007451066,0.34765264,0.009183971,0.0011942142,0.0018033248,0.08556116,0.0024553789,0.013577699],"genre_scores_gemma":[0.80040646,0.002049246,0.16165224,0.00079027034,0.00015657823,0.0008641392,0.029767973,0.00008492788,0.004228139],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822205,0.0005247675,0.00018928475,0.00035619436,0.00060190435,0.000105724226],"domain_scores_gemma":[0.99704367,0.00083675113,0.00051780295,0.00019563804,0.0013317369,0.00007433171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038397103,0.00071266433,0.0009011131,0.0015114364,0.00031659473,0.0007393453,0.0011855678,0.0005409623,0.0014933549],"category_scores_gemma":[0.012380174,0.00033413808,0.00097291375,0.0016355406,0.00021434567,0.0005047019,0.0007052224,0.0013455759,0.00079667685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001831187,0.00020131843,0.8503882,0.00030976773,0.0010945086,0.00020347677,0.0002516886,0.01506132,0.000631502,0.00411879,0.039179184,0.08837714],"study_design_scores_gemma":[0.00039574128,0.0002271436,0.67275095,0.0006374551,0.0011879527,0.0010430213,0.00031151218,0.28146815,0.0006573474,0.0049413014,0.03627574,0.000103701816],"about_ca_topic_score_codex":0.20173797,"about_ca_topic_score_gemma":0.17076698,"teacher_disagreement_score":0.20173797,"about_ca_system_score_codex":0.002371086,"about_ca_system_score_gemma":0.005105701,"threshold_uncertainty_score":0.40112746},"labels":[],"label_agreement":null},{"id":"W4397025486","doi":"10.1681/asn.20213210s1717c","title":"A Population Health Survey-Based Prediction Equation for Incident CKD: The CKD Population Risk Tool CKDPort/PREDICT-CKD LIFESTYLE","year":2021,"lang":"en","type":"article","venue":"Journal of the American Society of Nephrology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Medicine; Population; Internal medicine; Environmental health","score_opus":0.11115173767237921,"score_gpt":0.4371027078214334,"score_spread":0.32595097014905416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4397025486","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51614076,0.0030657747,0.060052387,0.0041342005,0.0004838699,0.004709178,0.38419703,0.0030615164,0.024155255],"genre_scores_gemma":[0.787604,0.0011208769,0.066086665,0.00078705756,0.00008564047,0.0031684213,0.13464592,0.00009133733,0.006410155],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875,0.00031562502,0.00012295473,0.00021415872,0.00048837526,0.000108850974],"domain_scores_gemma":[0.9983494,0.00023531311,0.00034161372,0.00011344975,0.0008731918,0.000087044515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019979,0.0007065207,0.00095272897,0.0018234624,0.00035869677,0.00065670477,0.0012802363,0.0005074029,0.0032428175],"category_scores_gemma":[0.005883595,0.00040167893,0.0011146787,0.0022224456,0.000181728,0.00041943157,0.00075190514,0.0014792369,0.0011409965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040093125,0.00049783534,0.8810897,0.0004198631,0.0011826892,0.00008273668,0.00014380079,0.004420188,0.00029434141,0.0012043979,0.05797681,0.052286748],"study_design_scores_gemma":[0.00052839925,0.00021277572,0.9296894,0.00026321117,0.0008342893,0.00036863316,0.00015792482,0.041019794,0.00026640474,0.0014935064,0.02509845,0.000067225534],"about_ca_topic_score_codex":0.24945076,"about_ca_topic_score_gemma":0.29352638,"teacher_disagreement_score":0.24945076,"about_ca_system_score_codex":0.002343567,"about_ca_system_score_gemma":0.0049341656,"threshold_uncertainty_score":0.49599755},"labels":[],"label_agreement":null},{"id":"W4397042047","doi":"10.1681/asn.20233411s1418c","title":"External Validation of a Machine Learning Model for Progression of CKD in the CREDENCE and CANVAS Trials","year":2023,"lang":"en","type":"article","venue":"Journal of the American Society of Nephrology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Credence; Medicine; Medical physics; Intensive care medicine; Computer science; Internal medicine; Machine learning","score_opus":0.2779381744426611,"score_gpt":0.5284539426795082,"score_spread":0.25051576823684707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4397042047","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9200955,0.0038743129,0.060617346,0.0014803865,0.00041333216,0.0019433006,0.0051084924,0.00070440973,0.0057630613],"genre_scores_gemma":[0.9817702,0.0001763114,0.010092894,0.00047147012,0.00007789301,0.00088130526,0.005890025,0.000073568066,0.00056623097],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9375858,0.05337185,0.0019324366,0.0039010223,0.0025425563,0.00066632417],"domain_scores_gemma":[0.8389948,0.12712608,0.009933863,0.015260691,0.0068214014,0.0018631606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15655129,0.0018328164,0.0022068145,0.0010527205,0.0006532771,0.002177212,0.0020014457,0.002301658,0.0026565592],"category_scores_gemma":[0.1347298,0.00051042164,0.0026969379,0.00091160473,0.0016743785,0.0015332468,0.0022684333,0.0029568286,0.0010368777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.058958706,0.0021747744,0.45474967,0.0014545721,0.014530427,0.000541181,0.000632079,0.3639464,0.0017940726,0.004021741,0.020161122,0.07703522],"study_design_scores_gemma":[0.0071889847,0.0067930487,0.089284874,0.0005836543,0.002925881,0.0005511465,0.00013549291,0.87408847,0.0030100003,0.0071342336,0.008139715,0.0001645261],"about_ca_topic_score_codex":0.0015059005,"about_ca_topic_score_gemma":0.0011514171,"teacher_disagreement_score":0.15655129,"about_ca_system_score_codex":0.0010352308,"about_ca_system_score_gemma":0.0021076177,"threshold_uncertainty_score":0.82793224},"labels":[],"label_agreement":null},{"id":"W4397042628","doi":"10.1681/asn.20233411s1914a","title":"Optical System Shows Promise for Online Detection of Peritonitis in Peritoneal Dialysis","year":2023,"lang":"en","type":"article","venue":"Journal of the American Society of Nephrology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"","keywords":"Peritoneal dialysis; Peritonitis; Medicine; Urology; Intensive care medicine; Internal medicine; Gastroenterology","score_opus":0.09657930193404275,"score_gpt":0.4368661290765168,"score_spread":0.34028682714247405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4397042628","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5734659,0.028206753,0.36414373,0.0034793855,0.001783025,0.00085941114,0.0017031286,0.0067655835,0.019593084],"genre_scores_gemma":[0.76082426,0.006758867,0.21892686,0.002332979,0.00040234273,0.0004670633,0.0012552635,0.00020675034,0.008825534],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99943143,0.0001179929,0.000026002293,0.00015049841,0.00023280215,0.000041244548],"domain_scores_gemma":[0.99903095,0.0003743435,0.00013151788,0.00007136374,0.00032393273,0.000067964436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011916482,0.0006551963,0.00037265653,0.00046254357,0.00026157385,0.00095950876,0.00070134277,0.0012566892,0.0044734613],"category_scores_gemma":[0.0014725948,0.00026180764,0.00056373555,0.00033539184,0.00032494226,0.000978193,0.00036273303,0.0007232495,0.0012500159],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064124924,0.00050414976,0.012410384,0.00075915,0.000096748154,0.00017723121,0.000085285305,0.0015621138,0.8280331,0.00096621003,0.003996956,0.15076743],"study_design_scores_gemma":[0.0001416548,0.0039561056,0.025826262,0.0001721664,0.00027681366,0.0014326083,0.0001612324,0.043442693,0.8884473,0.00096750516,0.03504095,0.00013474697],"about_ca_topic_score_codex":0.00054261176,"about_ca_topic_score_gemma":0.0008352808,"teacher_disagreement_score":0.0044734613,"about_ca_system_score_codex":0.00045841341,"about_ca_system_score_gemma":0.0003992909,"threshold_uncertainty_score":0.014965177},"labels":[],"label_agreement":null},{"id":"W4397047994","doi":"10.1681/asn.20233411s196a","title":"Derivation and Validation of Machine Learning Models for the Prevention of Unplanned Dialysis in Advanced CKD Patients","year":2023,"lang":"en","type":"article","venue":"Journal of the American Society of Nephrology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; Carleton University","funders":"","keywords":"Dialysis; Medicine; Intensive care medicine; Medical physics; Computer science; Artificial intelligence; Internal medicine","score_opus":0.10901683086162318,"score_gpt":0.4309890362939344,"score_spread":0.32197220543231125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4397047994","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7838922,0.0006450725,0.210818,0.00063806016,0.00006121392,0.00039347127,0.0008699253,0.0006798279,0.002002196],"genre_scores_gemma":[0.95637,0.00013388607,0.04193813,0.00007480805,0.000019658939,0.00019616248,0.00089698116,0.000029483377,0.00034088644],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979803,0.0011895485,0.00015512633,0.00026735006,0.0002469638,0.00016076987],"domain_scores_gemma":[0.9839675,0.012324185,0.0008756767,0.00044590968,0.0021434622,0.000243271],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011126587,0.0010277281,0.0007554463,0.0009870238,0.00044937478,0.001077749,0.0010152386,0.00072240527,0.00089579483],"category_scores_gemma":[0.023771213,0.00040122124,0.0009164155,0.0005238131,0.00034988963,0.0004978013,0.0008664734,0.0011631475,0.00033294086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029145696,0.0002698553,0.07884011,0.00007512438,0.00022204002,0.00015318753,0.00010550135,0.8744928,0.00057253306,0.00070645177,0.0008897336,0.04338114],"study_design_scores_gemma":[0.000019735788,0.00006942521,0.004847014,0.00002764959,0.000021164567,0.000026798109,0.0000148431245,0.9941214,0.00025057406,0.00046361703,0.00013140909,0.0000063585017],"about_ca_topic_score_codex":0.020471768,"about_ca_topic_score_gemma":0.012260386,"teacher_disagreement_score":0.020471768,"about_ca_system_score_codex":0.0013915264,"about_ca_system_score_gemma":0.0029472262,"threshold_uncertainty_score":0.058843732},"labels":[],"label_agreement":null},{"id":"W4397048097","doi":"10.1681/asn.20233411s1175c","title":"Characteristics of Global Dialysis Data from Multiple Providers in the New MONitoring Dialysis Outcomes (MONDO) Dataset","year":2023,"lang":"en","type":"article","venue":"Journal of the American Society of Nephrology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Dialysis; Medicine; Intensive care medicine; Nephrology; Home dialysis; Internal medicine","score_opus":0.1841195792030918,"score_gpt":0.4720053762408953,"score_spread":0.2878857970378035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4397048097","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19884036,0.0005753408,0.0016992607,0.0011720924,0.00007030315,0.0002079288,0.7950468,0.00027650263,0.0021113171],"genre_scores_gemma":[0.15819232,0.00019040579,0.0026583083,0.00036648443,0.00004703319,0.00050205155,0.8374777,0.000061006216,0.00050464296],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9962978,0.000832786,0.0007140043,0.0007716403,0.0009643411,0.00041932074],"domain_scores_gemma":[0.98743236,0.0040898607,0.0035289666,0.0020015012,0.0021532287,0.000794136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044023967,0.00048278875,0.00060136174,0.0022774236,0.0005249725,0.0011209607,0.00088656903,0.00080914306,0.0022632042],"category_scores_gemma":[0.017084429,0.00020917588,0.00068618223,0.0053828317,0.00047904148,0.0008488889,0.001626995,0.00088572176,0.0010538077],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001207634,0.00026012404,0.75813067,0.00068017415,0.00042385855,0.0005474701,0.0007186764,0.0068442547,0.0009991351,0.0022121123,0.20500453,0.02297131],"study_design_scores_gemma":[0.0003727941,0.00024177192,0.8248469,0.00044860237,0.00016351602,0.0016739108,0.0012480533,0.00805677,0.0017324206,0.0025628463,0.1585359,0.00011640616],"about_ca_topic_score_codex":0.008420539,"about_ca_topic_score_gemma":0.007631163,"teacher_disagreement_score":0.008420539,"about_ca_system_score_codex":0.0011180254,"about_ca_system_score_gemma":0.0017283395,"threshold_uncertainty_score":0.023282409},"labels":[],"label_agreement":null},{"id":"W4399040281","doi":"10.1016/j.eclinm.2024.102660","title":"Artificial intelligence for cardiovascular disease risk assessment in personalised framework: a scoping review","year":2024,"lang":"en","type":"review","venue":"EClinicalMedicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":141,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Queen's University","funders":"","keywords":"Medicine; Disease; Risk assessment; Pathology","score_opus":0.5544843815459898,"score_gpt":0.6603556954839799,"score_spread":0.1058713139379901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399040281","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020322177,0.9979798,0.00038354276,0.0005388412,0.00014830721,0.00019184932,0.000092625516,0.0000071055942,0.0004547056],"genre_scores_gemma":[0.0028912125,0.99482745,0.0010240745,0.00046881346,0.00013908312,0.0004567997,0.00010532712,0.0000037063585,0.000083581486],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9913065,0.0030680285,0.0031906848,0.0006431002,0.0015485506,0.00024321621],"domain_scores_gemma":[0.94255465,0.046481203,0.0048675477,0.0009489434,0.004798092,0.00034961416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015784584,0.0015012459,0.005073751,0.021738248,0.0010210751,0.0044778013,0.0025928013,0.0036979774,0.0052567464],"category_scores_gemma":[0.067589685,0.0010661326,0.006391672,0.017403008,0.0015200581,0.003762687,0.0026034836,0.0021474813,0.0007200619],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001128665,0.0000501232,0.00063293445,0.73932904,0.002344753,0.00015698443,0.00050669635,0.00045143117,0.00016183393,0.002962823,0.0049713226,0.24831915],"study_design_scores_gemma":[0.000034694505,0.000068989524,0.0008963559,0.9475672,0.006939269,0.000245219,0.00024798088,0.0001860425,0.00008927022,0.0014802876,0.04221684,0.000027937676],"about_ca_topic_score_codex":0.0076312963,"about_ca_topic_score_gemma":0.01247377,"teacher_disagreement_score":0.021738248,"about_ca_system_score_codex":0.0050964467,"about_ca_system_score_gemma":0.019967439,"threshold_uncertainty_score":0.083477795},"labels":[],"label_agreement":null},{"id":"W4399140934","doi":"10.5539/jmr.v16n3p1","title":"Prime Number Theorem and Goldbach Conjecture","year":2024,"lang":"en","type":"article","venue":"Journal of Mathematics Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Coronary artery disease; Artificial intelligence; Cardiology; Internal medicine; Medicine; Computer science","score_opus":0.3746523476768755,"score_gpt":0.6264595719002115,"score_spread":0.251807224223336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399140934","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2941675,0.008462349,0.40716374,0.012866272,0.0015922072,0.00010576756,0.00068820384,0.0016968714,0.27325708],"genre_scores_gemma":[0.944687,0.0015373968,0.033985708,0.0014167931,0.0006598434,0.000104998086,0.00041914807,0.00012293867,0.01706623],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99831676,0.00032911584,0.00006968974,0.0005123425,0.00041593905,0.00035615242],"domain_scores_gemma":[0.9965012,0.002282366,0.00021439014,0.00044543188,0.00030921976,0.00024738454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020393003,0.00084413827,0.00084633625,0.0010736709,0.0016346221,0.0018310403,0.0009540179,0.0008175973,0.011784294],"category_scores_gemma":[0.00783368,0.0003115854,0.00096421776,0.0009844769,0.0036919848,0.006908345,0.0028046374,0.002669053,0.002236929],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037242164,0.000035077166,0.0012659577,0.0002024333,0.000023113349,0.00015787745,0.0003076116,0.0088061625,0.0028130515,0.95000374,0.009552328,0.026460225],"study_design_scores_gemma":[0.00004548465,0.00010346094,0.0006500297,0.00005439601,0.00001924188,0.00023465318,0.000098356424,0.020553974,0.0030881853,0.96028554,0.014841906,0.000024710454],"about_ca_topic_score_codex":0.0009019889,"about_ca_topic_score_gemma":0.0005698666,"teacher_disagreement_score":0.011784294,"about_ca_system_score_codex":0.0018844411,"about_ca_system_score_gemma":0.00087782624,"threshold_uncertainty_score":0.039422333},"labels":[],"label_agreement":null},{"id":"W4399162898","doi":"10.5539/ijsp.v13n2p1","title":"Predicting Coronary Artery Disease Using Machine Learning","year":2024,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"CAD; Machine learning; Receiver operating characteristic; Support vector machine; Artificial intelligence; Computer science; Artificial neural network; Coronary artery disease; Logistic regression; Gradient boosting; Medicine; Random forest; Engineering; Internal medicine","score_opus":0.12262084815193318,"score_gpt":0.45984687514916167,"score_spread":0.3372260269972285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399162898","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48241603,0.0030860521,0.50709987,0.0011673844,0.00016537495,0.00010955047,0.0008632423,0.0012553792,0.003837066],"genre_scores_gemma":[0.95691794,0.0005680367,0.040811982,0.000085898544,0.00008967602,0.00005490381,0.0006580997,0.00001269115,0.0008007697],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995347,0.0002023329,0.00003210182,0.000082392624,0.00010767915,0.000040824583],"domain_scores_gemma":[0.9984428,0.0011291014,0.00016467046,0.00007949073,0.00015464476,0.000029231353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015116243,0.00048563493,0.0006209997,0.001117247,0.00018173181,0.0007171069,0.00048617407,0.0006425256,0.0006318363],"category_scores_gemma":[0.0042638592,0.00013094537,0.0005238381,0.00071076583,0.00016209511,0.0005200216,0.00030587308,0.00056940754,0.0003463089],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002687918,0.00047893013,0.100351945,0.00012399795,0.00021977599,0.0002161443,0.000060508704,0.6562098,0.0034373587,0.0015392514,0.0024864632,0.23460706],"study_design_scores_gemma":[0.000003583718,0.000044223965,0.0048540197,0.000010739703,0.000013225577,0.00003379905,0.000009664272,0.99341524,0.00041693312,0.0009956306,0.00019692723,0.0000061313726],"about_ca_topic_score_codex":0.0027723033,"about_ca_topic_score_gemma":0.0021643941,"teacher_disagreement_score":0.0027723033,"about_ca_system_score_codex":0.00028926646,"about_ca_system_score_gemma":0.0004975624,"threshold_uncertainty_score":0.007994294},"labels":[],"label_agreement":null},{"id":"W4399441519","doi":"10.34133/hds.0112","title":"2023 Beijing Health Data Science Summit","year":2024,"lang":"en","type":"article","venue":"Health Data Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Summit; Beijing; Health science; Political science; Geography; China; Medicine; Cartography; Medical education","score_opus":0.6741552806170339,"score_gpt":0.6558769739566774,"score_spread":0.018278306660356458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399441519","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037513021,0.023421718,0.009193024,0.49334618,0.31007314,0.0016897345,0.052166246,0.0036790033,0.10267963],"genre_scores_gemma":[0.033404324,0.021440245,0.015046269,0.1938466,0.13168864,0.0054753157,0.1680278,0.0030668487,0.42800397],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9796651,0.005197705,0.0011403195,0.001625772,0.0095302295,0.002840864],"domain_scores_gemma":[0.95749557,0.005907825,0.0013442641,0.002727298,0.017539825,0.014985284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04092937,0.002564658,0.002319516,0.0065071946,0.0044127456,0.016065754,0.0042514605,0.007362316,0.12914722],"category_scores_gemma":[0.04365009,0.00073825615,0.0029463447,0.0036313236,0.0022213028,0.008279205,0.015308991,0.008197822,0.076854035],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006568491,0.000015756246,0.0001978344,0.00016051505,0.000017538148,0.000045733217,0.00003873204,0.00006965095,0.00012244972,0.0015933587,0.9786512,0.0190215],"study_design_scores_gemma":[0.000044610548,0.00004205314,0.001808095,0.00016809518,0.000011955908,0.000019007475,0.00013069023,0.00023726931,0.00013818959,0.0027880743,0.9945891,0.00002289761],"about_ca_topic_score_codex":0.011761482,"about_ca_topic_score_gemma":0.02091917,"teacher_disagreement_score":0.12914722,"about_ca_system_score_codex":0.00827921,"about_ca_system_score_gemma":0.01903009,"threshold_uncertainty_score":0.43204045},"labels":[],"label_agreement":null},{"id":"W4399508216","doi":"10.1002/cdt3.137","title":"Pathways to chronic disease detection and prediction: Mapping the potential of machine learning to the pathophysiological processes while navigating ethical challenges","year":2024,"lang":"en","type":"review","venue":"Chronic Diseases and Translational Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Edith Cowan University; University of New South Wales","keywords":"Medicine; Disease; Pathophysiology; Bioinformatics; Artificial intelligence; Cognitive science; Computational biology; Neuroscience; Pathology; Computer science","score_opus":0.2059583823820499,"score_gpt":0.4441107484798172,"score_spread":0.2381523660977673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399508216","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028112432,0.97755855,0.0033634913,0.015219141,0.0007177891,0.000021824613,0.00006760818,0.000026667876,0.0027437685],"genre_scores_gemma":[0.003842167,0.98978466,0.0023529897,0.0026663821,0.0008385301,0.0000470762,0.00005482805,0.0000069479265,0.0004064208],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982938,0.0008576575,0.0001633333,0.00020969649,0.0003838474,0.00009178189],"domain_scores_gemma":[0.9896827,0.008560113,0.00038225405,0.00021413462,0.0009118752,0.00024894974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046024956,0.0009753652,0.0013044067,0.0027903018,0.0005802056,0.0034487122,0.0013395841,0.0025689749,0.0032674258],"category_scores_gemma":[0.011731546,0.00036148063,0.0011133405,0.0024071452,0.002364752,0.00416929,0.001977363,0.00438847,0.0012466273],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004757659,0.000065040476,0.001034109,0.018546056,0.00020670213,0.0001289174,0.0003199846,0.0012211876,0.00028798365,0.067499764,0.024376389,0.8862663],"study_design_scores_gemma":[0.000023888031,0.000116480885,0.0021499621,0.035276998,0.0002651251,0.00059975206,0.0006651953,0.0014938972,0.0005016032,0.1416816,0.817159,0.00006642098],"about_ca_topic_score_codex":0.0024467271,"about_ca_topic_score_gemma":0.003414742,"teacher_disagreement_score":0.0046024956,"about_ca_system_score_codex":0.0018410594,"about_ca_system_score_gemma":0.006652835,"threshold_uncertainty_score":0.02434057},"labels":[],"label_agreement":null},{"id":"W4399567230","doi":"10.1145/3650105","title":"Proceedings of the 2024 IEEE/ACM First International Conference on AI Foundation Models and Software Engineering","year":2024,"lang":"en","type":"paratext","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Norges Forskningsråd; National Natural Science Foundation of China; Ant Group; National Security Agency; National Science Foundation","keywords":"Computer science; Foundation (evidence); Software engineering","score_opus":0.2042061880479731,"score_gpt":0.4612063215039524,"score_spread":0.2570001334559793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399567230","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009904653,0.0635003,0.18751547,0.081698895,0.1769625,0.001397735,0.011450414,0.0093214,0.4582486],"genre_scores_gemma":[0.018574247,0.026566554,0.042480133,0.006043111,0.01511107,0.0006821887,0.023397041,0.0036971036,0.86344844],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99556655,0.0014031109,0.00024220994,0.00041411634,0.0020234317,0.00035057738],"domain_scores_gemma":[0.98810697,0.003986556,0.00032677862,0.0012753981,0.0036952957,0.0026091295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008387022,0.0016302685,0.0016856269,0.002771875,0.0013849846,0.00689279,0.0024971827,0.0025942358,0.177262],"category_scores_gemma":[0.013704145,0.0006405071,0.0011214936,0.002493591,0.0012950025,0.006352545,0.004403881,0.004629406,0.06892558],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053102798,0.00008249814,0.00028894012,0.00026231032,0.000027064405,0.00007669868,0.00008802281,0.00033914705,0.00051962695,0.0045449357,0.9039125,0.08980526],"study_design_scores_gemma":[0.000014582932,0.000032336404,0.00043968204,0.00019994182,0.000011692979,0.000108920554,0.00008253195,0.0016036301,0.00029731836,0.0043312847,0.9928631,0.000014986128],"about_ca_topic_score_codex":0.0036852574,"about_ca_topic_score_gemma":0.007959498,"teacher_disagreement_score":0.177262,"about_ca_system_score_codex":0.0026093854,"about_ca_system_score_gemma":0.004949258,"threshold_uncertainty_score":0.5930004},"labels":[],"label_agreement":null},{"id":"W4399571351","doi":"10.5220/0012805000003885","title":"Machine Learing-Based Heart Disease Prediction: Insights and Comparative Analysis","year":2023,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.2567694245422252,"score_gpt":0.49496026128524057,"score_spread":0.2381908367430154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399571351","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9171501,0.015617404,0.040809684,0.0031717308,0.0002813242,0.00018319282,0.0027725697,0.00058137253,0.019432612],"genre_scores_gemma":[0.9898341,0.0014183347,0.005431635,0.00012429869,0.00010025548,0.000021464308,0.0017859957,0.000026812146,0.0012570292],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997544,0.0011181666,0.00018243612,0.00045018428,0.0005193265,0.00018595596],"domain_scores_gemma":[0.9743223,0.02119724,0.0007216602,0.0013310479,0.0020620942,0.00036564286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007941295,0.0006946318,0.0010393655,0.0030930631,0.0006750016,0.0020190976,0.0014292921,0.001273286,0.0040220427],"category_scores_gemma":[0.023143701,0.00020130299,0.0009286471,0.0018547499,0.0007031896,0.002921831,0.00123199,0.0011221932,0.0011907518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038121196,0.0014596953,0.40597552,0.00070228736,0.0012492897,0.0003396009,0.0007790846,0.041184027,0.0028199248,0.0055588707,0.00799026,0.5281293],"study_design_scores_gemma":[0.0001977744,0.0016399255,0.41047245,0.00027315627,0.001082911,0.00068827317,0.0016236913,0.5585889,0.004577923,0.013673037,0.007048041,0.00013384229],"about_ca_topic_score_codex":0.011069289,"about_ca_topic_score_gemma":0.0075582317,"teacher_disagreement_score":0.011069289,"about_ca_system_score_codex":0.0008694726,"about_ca_system_score_gemma":0.0008136806,"threshold_uncertainty_score":0.04199809},"labels":[],"label_agreement":null},{"id":"W4399579111","doi":"10.23977/jaip.2024.070214","title":"Application Research of Machine Learning Algorithms in Medical Diagnosis","year":2024,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Practice","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Algorithm","score_opus":0.3394661028316501,"score_gpt":0.6083834135074792,"score_spread":0.2689173106758291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399579111","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016094893,0.15383397,0.7708315,0.010725465,0.0015637437,0.00020104148,0.00021790988,0.0006076737,0.04592383],"genre_scores_gemma":[0.44414127,0.112257704,0.43172145,0.0022379109,0.0021345837,0.00020442656,0.00039053705,0.00015817226,0.0067539657],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961539,0.0016140138,0.00028455394,0.0004954948,0.0013139357,0.00013813259],"domain_scores_gemma":[0.9899294,0.007733749,0.00033209505,0.00047117853,0.0014217745,0.00011181906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004918418,0.0008340537,0.00092924945,0.0040903497,0.0005751056,0.0031333535,0.0011652851,0.0019350667,0.0026102022],"category_scores_gemma":[0.017342089,0.00034556718,0.0012064897,0.0037531184,0.0015687495,0.002619113,0.0011946225,0.00202872,0.0010077842],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012441681,0.00017414872,0.009053032,0.0023986008,0.0003433696,0.00045155475,0.00045988636,0.059059594,0.0034284722,0.18339692,0.00776363,0.7333464],"study_design_scores_gemma":[0.00006662425,0.00034928828,0.0061065485,0.002237135,0.00031929908,0.0023709496,0.0006250231,0.45823652,0.014391937,0.33740294,0.1777174,0.00017637086],"about_ca_topic_score_codex":0.0017315503,"about_ca_topic_score_gemma":0.0007924311,"teacher_disagreement_score":0.004918418,"about_ca_system_score_codex":0.0015858262,"about_ca_system_score_gemma":0.0017772779,"threshold_uncertainty_score":0.026011348},"labels":[],"label_agreement":null},{"id":"W4399612193","doi":"10.32614/cran.package.naryn","title":"naryn: Native Access Medical Record Retriever for High Yield Analytics","year":2022,"lang":"en","type":"dataset","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Analytics; Labrador Retriever; Yield (engineering); Computer science; Medicine; Data science; Surgery; Materials science","score_opus":0.35178017247986676,"score_gpt":0.5593725950408152,"score_spread":0.2075924225609484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399612193","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013838117,0.00013997883,0.003811824,0.000182691,0.00007138587,0.00015681432,0.979836,0.012682545,0.0017349529],"genre_scores_gemma":[0.0016376202,0.000071676615,0.004544234,0.00008075752,0.000011441909,0.0002456326,0.9923084,0.00034476919,0.00075549487],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985561,0.0002466074,0.00028521888,0.0002909592,0.00045622513,0.00016485131],"domain_scores_gemma":[0.9975,0.0005358248,0.00024667126,0.0008716169,0.0005861804,0.00025974688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017965108,0.0017054715,0.0010558753,0.0035999974,0.0006424314,0.0016846932,0.002451979,0.0010866682,0.025520729],"category_scores_gemma":[0.0068247565,0.00070610945,0.0011118477,0.0034574263,0.000383012,0.0014661282,0.0029644056,0.001489311,0.041975122],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057142205,0.00010390204,0.0026469652,0.0011760851,0.00009948708,0.000111959,0.00010157262,0.00084713986,0.0023068292,0.0018054575,0.97374153,0.016487606],"study_design_scores_gemma":[0.00072441023,0.00012795726,0.010814133,0.00029539168,0.00008410405,0.00038791046,0.00017537885,0.0067553828,0.007153622,0.0048493347,0.9685361,0.000096283526],"about_ca_topic_score_codex":0.011151614,"about_ca_topic_score_gemma":0.022670811,"teacher_disagreement_score":0.025520729,"about_ca_system_score_codex":0.00089879404,"about_ca_system_score_gemma":0.002430973,"threshold_uncertainty_score":0.08537537},"labels":[],"label_agreement":null},{"id":"W4399728776","doi":"10.1007/978-981-97-1841-2_1","title":"Comparative Analysis of Deep Learning-Based Hybrid Algorithms for Liver Disease Prediction","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Algorithm","score_opus":0.09350538660627725,"score_gpt":0.396771484587793,"score_spread":0.3032660979815157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399728776","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7508674,0.042545393,0.18248467,0.001785934,0.00072633306,0.00016832468,0.0025510406,0.0024082672,0.016462559],"genre_scores_gemma":[0.9379328,0.0040031457,0.048951745,0.0002548454,0.0001604195,0.00009639046,0.0030631698,0.00012114967,0.005416356],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925846,0.00025654718,0.0000699887,0.00011911304,0.00020064332,0.00009527335],"domain_scores_gemma":[0.9952624,0.0034731438,0.00011606502,0.00019518222,0.0008596409,0.00009353511],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002761903,0.0009923786,0.0009983919,0.0014610647,0.00032232798,0.0011744536,0.0013184457,0.0011228235,0.0026938706],"category_scores_gemma":[0.004731202,0.00024752275,0.00064140477,0.0012455003,0.00027403893,0.0013907168,0.00070758734,0.0007265194,0.00052477064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025662142,0.0006913548,0.012069395,0.00043616616,0.0007288209,0.000075071046,0.000058897876,0.44794545,0.002066057,0.0025741141,0.0073818043,0.5234067],"study_design_scores_gemma":[0.00003864973,0.00030834432,0.0028596236,0.00003258022,0.00013251296,0.000030068739,0.000038953312,0.99369335,0.0012476597,0.00092830026,0.00067808013,0.0000119504275],"about_ca_topic_score_codex":0.012631298,"about_ca_topic_score_gemma":0.011591082,"teacher_disagreement_score":0.012631298,"about_ca_system_score_codex":0.0010763551,"about_ca_system_score_gemma":0.00095209794,"threshold_uncertainty_score":0.02511555},"labels":[],"label_agreement":null},{"id":"W4399771672","doi":"10.32920/26052736.v1","title":"Management of Type 2 Diabetes -- Applications of Machine Learning and Electronic Medical Records-based Analytics","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Analytics; Type 2 diabetes; Medical record; Computer science; Electronic medical record; Diabetes mellitus; Data analysis; Diabetes management; Data science; Medicine; Data mining; Internal medicine; Endocrinology; Internet privacy","score_opus":0.07375305264344052,"score_gpt":0.46919414887062133,"score_spread":0.3954410962271808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399771672","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07813415,0.08639914,0.7447358,0.03570492,0.0024667715,0.00094852154,0.009171245,0.005658023,0.036781386],"genre_scores_gemma":[0.60003096,0.046780214,0.33739078,0.0026824065,0.0018084465,0.00033139586,0.0059219426,0.00017070302,0.00488316],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984341,0.0005350537,0.00016683032,0.00022677628,0.00057009107,0.000066992696],"domain_scores_gemma":[0.99604166,0.002305479,0.00035189895,0.00038980015,0.00076950615,0.00014161965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002633756,0.0006076307,0.0007724138,0.0018744031,0.00027866283,0.002249193,0.00095548795,0.00089828717,0.0017932362],"category_scores_gemma":[0.0064228964,0.00022730199,0.000756691,0.0032586385,0.00028087647,0.002252774,0.0010984617,0.0012616736,0.0009969501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014317693,0.0002647751,0.028294804,0.00079806335,0.00025615082,0.00021034853,0.00021464912,0.020775555,0.002029982,0.012011267,0.023774447,0.9112268],"study_design_scores_gemma":[0.00008944894,0.0003889207,0.038666714,0.0018814895,0.00027070192,0.0010776264,0.0011738957,0.6924193,0.0086267525,0.1099784,0.14526002,0.00016669718],"about_ca_topic_score_codex":0.0021901785,"about_ca_topic_score_gemma":0.0015762271,"teacher_disagreement_score":0.002633756,"about_ca_system_score_codex":0.000671867,"about_ca_system_score_gemma":0.0007371307,"threshold_uncertainty_score":0.013928771},"labels":[],"label_agreement":null},{"id":"W4399771745","doi":"10.32920/26052736","title":"Management of Type 2 Diabetes -- Applications of Machine Learning and Electronic Medical Records-based Analytics","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Analytics; Medical record; Type 2 diabetes; Computer science; Data science; Data analysis; Learning analytics; Electronic medical record; Diabetes mellitus; Machine learning; Medicine; Data mining; Internet privacy; Internal medicine","score_opus":0.07375305264344052,"score_gpt":0.46919414887062133,"score_spread":0.3954410962271808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399771745","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07813415,0.08639914,0.7447358,0.03570492,0.0024667715,0.00094852154,0.009171245,0.005658023,0.036781386],"genre_scores_gemma":[0.60003096,0.046780214,0.33739078,0.0026824065,0.0018084465,0.00033139586,0.0059219426,0.00017070302,0.00488316],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984341,0.0005350537,0.00016683032,0.00022677628,0.00057009107,0.000066992696],"domain_scores_gemma":[0.99604166,0.002305479,0.00035189895,0.00038980015,0.00076950615,0.00014161965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002633756,0.0006076307,0.0007724138,0.0018744031,0.00027866283,0.002249193,0.00095548795,0.00089828717,0.0017932362],"category_scores_gemma":[0.0064228964,0.00022730199,0.000756691,0.0032586385,0.00028087647,0.002252774,0.0010984617,0.0012616736,0.0009969501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014317693,0.0002647751,0.028294804,0.00079806335,0.00025615082,0.00021034853,0.00021464912,0.020775555,0.002029982,0.012011267,0.023774447,0.9112268],"study_design_scores_gemma":[0.00008944894,0.0003889207,0.038666714,0.0018814895,0.00027070192,0.0010776264,0.0011738957,0.6924193,0.0086267525,0.1099784,0.14526002,0.00016669718],"about_ca_topic_score_codex":0.0021901785,"about_ca_topic_score_gemma":0.0015762271,"teacher_disagreement_score":0.002633756,"about_ca_system_score_codex":0.000671867,"about_ca_system_score_gemma":0.0007371307,"threshold_uncertainty_score":0.013928771},"labels":[],"label_agreement":null},{"id":"W4399809187","doi":"10.1145/3653724.3653741","title":"Predicting Poisonous Mushrooms by Using Confusion Matrix Method","year":2023,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Confusion; Computer science; Confusion matrix; Matrix (chemical analysis); Artificial intelligence; Psychology; Chemistry; Chromatography; Psychoanalysis","score_opus":0.2508423299030224,"score_gpt":0.5783489863148161,"score_spread":0.3275066564117937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399809187","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25778264,0.002851431,0.72516423,0.0014495918,0.00038707076,0.0003836427,0.0024044225,0.0030152835,0.0065616574],"genre_scores_gemma":[0.8728612,0.0008498126,0.12162315,0.00018909205,0.00011516865,0.00014117811,0.0018056795,0.000052429303,0.0023623481],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889934,0.00028955584,0.000103246,0.00025074102,0.000350236,0.000106894215],"domain_scores_gemma":[0.99656576,0.0021864153,0.0002485527,0.00013112683,0.00076610316,0.000102058184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020629242,0.0015348376,0.0008332712,0.0034586769,0.0006777559,0.0020763038,0.0011557753,0.0011723952,0.0022510397],"category_scores_gemma":[0.0074293604,0.00025236473,0.00081339374,0.0013308281,0.00044968456,0.0012794506,0.00090834085,0.0010387508,0.0009162037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074254186,0.00059512723,0.049962014,0.0004976345,0.0003274816,0.0004899157,0.00027580763,0.4660109,0.014676482,0.0055577816,0.008051646,0.4528126],"study_design_scores_gemma":[0.0000067948845,0.000077686236,0.0025430263,0.000028171991,0.000032746313,0.00007497451,0.0000630475,0.9900092,0.003359051,0.0028276495,0.0009502985,0.000027394615],"about_ca_topic_score_codex":0.013134195,"about_ca_topic_score_gemma":0.009730676,"teacher_disagreement_score":0.013134195,"about_ca_system_score_codex":0.0008807992,"about_ca_system_score_gemma":0.0015426794,"threshold_uncertainty_score":0.026115477},"labels":[],"label_agreement":null},{"id":"W4399891523","doi":"10.18280/ria.380329","title":"Assessment of Cardiovascular Disease Using Machine Learning","year":2024,"lang":"fr","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Disease; Computer science; Artificial intelligence; Medicine; Machine learning; Internal medicine","score_opus":0.18558789705575124,"score_gpt":0.4554441810071031,"score_spread":0.26985628395135186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399891523","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26365104,0.0048233997,0.70807636,0.003693844,0.00041193483,0.0004719344,0.009136634,0.002724227,0.0070106336],"genre_scores_gemma":[0.8959929,0.0015020531,0.095802404,0.0003923292,0.00029194803,0.00022437674,0.004606397,0.000044274344,0.0011434195],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984628,0.0005798858,0.0001647424,0.00033202162,0.00038402327,0.00007665984],"domain_scores_gemma":[0.9941549,0.0037427875,0.0008101169,0.00046676284,0.0006768225,0.00014866186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027230137,0.0009606092,0.0009517777,0.0030405803,0.0003074554,0.0015443952,0.0010216093,0.001052156,0.0014878275],"category_scores_gemma":[0.013034444,0.00021902754,0.000904255,0.0016091366,0.00034551314,0.0014080844,0.00083652424,0.0013814284,0.0007832522],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028617756,0.00063086214,0.27509576,0.0003513804,0.000515544,0.00024694976,0.00012325821,0.35534126,0.0019018449,0.0043026065,0.00915374,0.35205054],"study_design_scores_gemma":[0.000011966255,0.00017570188,0.023713173,0.0000782544,0.000053011725,0.00015722051,0.00007022584,0.9650403,0.0011611207,0.007476825,0.002025872,0.000036280442],"about_ca_topic_score_codex":0.0035599794,"about_ca_topic_score_gemma":0.003740808,"teacher_disagreement_score":0.0035599794,"about_ca_system_score_codex":0.0006073409,"about_ca_system_score_gemma":0.00070009404,"threshold_uncertainty_score":0.01440084},"labels":[],"label_agreement":null},{"id":"W4399939200","doi":"10.1109/access.2024.3418974","title":"An Improved Framework for Detecting Thyroid Disease Using Filter-Based Feature Selection and Stacking Ensemble","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Computer science; Stacking; Thyroid disease; Feature selection; Artificial intelligence; Pattern recognition (psychology); Filter (signal processing); Selection (genetic algorithm); Feature (linguistics); Thyroid; Computer vision; Medicine; Internal medicine; Chemistry","score_opus":0.1950238231896898,"score_gpt":0.5262251408942799,"score_spread":0.33120131770459005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399939200","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018469935,0.00048241453,0.97911835,0.0002011328,0.000042922016,0.000040944058,0.00016709421,0.00091926544,0.00055788393],"genre_scores_gemma":[0.582062,0.00071033515,0.41127932,0.00042001263,0.00028847382,0.00027207422,0.0015498642,0.00013478578,0.003283152],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924636,0.00018946652,0.000050871087,0.00018763616,0.00022939644,0.000096261116],"domain_scores_gemma":[0.9992305,0.00029622964,0.00006918035,0.00008663565,0.00026948054,0.000048024405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017695045,0.0010956054,0.0013341074,0.001766548,0.0004978091,0.0008419758,0.0014117035,0.0009024411,0.0010573413],"category_scores_gemma":[0.0024036784,0.00036111378,0.0015140806,0.0012951393,0.00031025565,0.0009377827,0.000969056,0.0009527971,0.00055825105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020976434,0.0002576725,0.013147177,0.0000796361,0.0003212164,0.00032782933,0.00018181677,0.3583805,0.013636342,0.005063661,0.0060656094,0.60232884],"study_design_scores_gemma":[0.0000060742423,0.000052890242,0.0010884531,0.00000599527,0.00003874987,0.000070384565,0.000010669761,0.99439514,0.0014051356,0.0021023864,0.00080916705,0.00001497334],"about_ca_topic_score_codex":0.009028714,"about_ca_topic_score_gemma":0.008957457,"teacher_disagreement_score":0.009028714,"about_ca_system_score_codex":0.00046531216,"about_ca_system_score_gemma":0.0011553554,"threshold_uncertainty_score":0.017952323},"labels":[],"label_agreement":null},{"id":"W4400026235","doi":"10.17615/cm0e-4y75","title":"Cluster Analysis of Cardiovascular Phenotypes in Patients With Type 2 Diabetes and Established Atherosclerotic Cardiovascular Disease: A Potential Approach to Precision Medicine","year":2024,"lang":"en","type":"article","venue":"UNC Libraries","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Sanofi Pasteur; Genentech; Esperion Therapeutics; Daiichi Sankyo Europe; Servier; Alberta Innovates; MannKind Corporation; Eisai; Amgen; European Society of Cardiology; Zafgen; Tenax Therapeutics; Novo Nordisk; National Institutes of Health; Regeneron Pharmaceuticals; Dexcom; Intarcia Therapeutics; Canadian Cardiovascular Society; Orexigen Therapeutics; Bristol-Myers Squibb; Eli Lilly and Company; AstraZeneca; CSL Behring; GlaxoSmithKline; Amylin Pharmaceuticals; Pfizer; Sanofi; American Diabetes Association","keywords":"Atherosclerotic cardiovascular disease; Cluster (spacecraft); Disease; Phenotype; Type 2 diabetes; Medicine; Diabetes mellitus; Clinical phenotype; Internal medicine; Cardiology; Endocrinology; Computer science; Genetics; Biology","score_opus":0.03790479555929941,"score_gpt":0.30437273306175877,"score_spread":0.26646793750245934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400026235","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35292417,0.008349192,0.6239407,0.006292791,0.00050383224,0.0005971515,0.0031682008,0.001067804,0.0031562017],"genre_scores_gemma":[0.8495876,0.0009368659,0.14640142,0.00057423144,0.0004262412,0.00030887665,0.0012743004,0.000088581444,0.00040179942],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.990298,0.006987835,0.00049908663,0.0014052445,0.00062690035,0.00018303117],"domain_scores_gemma":[0.97297835,0.017877318,0.0037556305,0.0036626414,0.001389653,0.00033647602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013309815,0.0010413205,0.0020249363,0.004514415,0.00078941527,0.0023648064,0.0012983637,0.00075195706,0.000990641],"category_scores_gemma":[0.03599257,0.00038972497,0.0016319319,0.0036677856,0.0015370366,0.0012484638,0.0017797847,0.0014660074,0.00019013193],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032159754,0.0005165177,0.62951344,0.0011847302,0.008113804,0.00048986846,0.002537118,0.04815869,0.006736987,0.024535406,0.008839911,0.2661576],"study_design_scores_gemma":[0.0008168978,0.0012569838,0.44325683,0.00050138624,0.0020683042,0.0010447196,0.0020207022,0.30580503,0.0029568267,0.228091,0.01184295,0.00033836276],"about_ca_topic_score_codex":0.0035690013,"about_ca_topic_score_gemma":0.0026985698,"teacher_disagreement_score":0.013309815,"about_ca_system_score_codex":0.0008154705,"about_ca_system_score_gemma":0.0011416178,"threshold_uncertainty_score":0.07038993},"labels":[],"label_agreement":null},{"id":"W4400066325","doi":"10.1016/j.jcct.2024.05.029","title":"Deep Learning-Based Novel Coronary Artery Calcium Dispersion And Density (CAC-DAD) Score For Predicting Myocardial Infarction And Cardiovascular Death","year":2024,"lang":"en","type":"article","venue":"Journal of cardiovascular computed tomography","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Western University; McMaster University; University of Alberta","funders":"","keywords":"Medicine; Coronary artery calcium; Cardiology; Internal medicine; Myocardial infarction; Coronary artery disease","score_opus":0.06036662788922966,"score_gpt":0.33507740032382377,"score_spread":0.27471077243459413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400066325","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9376514,0.0028067823,0.052729562,0.0007939856,0.00014810316,0.000072598,0.0026845706,0.0006834017,0.0024297175],"genre_scores_gemma":[0.9870422,0.00044076217,0.009087526,0.00013742248,0.00008666921,0.00003804914,0.0018983613,0.000012883838,0.0012561247],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997974,0.000032311218,0.0000157234,0.00006130212,0.00004957953,0.000043640597],"domain_scores_gemma":[0.99972373,0.000073853895,0.000042276537,0.00001681893,0.00009104566,0.000052247335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005472682,0.0004823437,0.00060968514,0.0009681097,0.00019782304,0.0005523178,0.0005858523,0.0005838021,0.00096072216],"category_scores_gemma":[0.0009944007,0.00017481566,0.00050788873,0.0004910247,0.00015589136,0.00038312882,0.00062705716,0.0007005372,0.00029635266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022930605,0.0018217936,0.511836,0.0001829483,0.00080994976,0.00043812158,0.00007782432,0.052300774,0.011201359,0.0015107996,0.012699199,0.4048282],"study_design_scores_gemma":[0.00016128676,0.00041119006,0.09173503,0.00004088899,0.00028845307,0.0004247833,0.00005950726,0.90001243,0.0029119046,0.002242318,0.0016568898,0.000055356424],"about_ca_topic_score_codex":0.0072553973,"about_ca_topic_score_gemma":0.012016614,"teacher_disagreement_score":0.0072553973,"about_ca_system_score_codex":0.00041078235,"about_ca_system_score_gemma":0.0007992012,"threshold_uncertainty_score":0.014426351},"labels":[],"label_agreement":null},{"id":"W4400098682","doi":"10.3389/fgene.2024.1409755","title":"Development and evaluation of a chronic kidney disease risk prediction model using random forest","year":2024,"lang":"en","type":"article","venue":"Frontiers in Genetics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Fondation Rideau Hall","keywords":"Random forest; Kidney disease; Computer science; Risk model; Artificial intelligence; Medicine; Risk analysis (engineering); Internal medicine","score_opus":0.13603045443434428,"score_gpt":0.43993652559103635,"score_spread":0.3039060711566921,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400098682","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18044683,0.0016476123,0.8104189,0.0009172399,0.00020533484,0.00035922712,0.0010910488,0.0034556766,0.0014580534],"genre_scores_gemma":[0.7193315,0.0005574552,0.27491683,0.00035613152,0.00011803881,0.00048205137,0.003068231,0.00014228479,0.0010274053],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987858,0.00046321927,0.000088290755,0.0003080234,0.00018525051,0.00016940327],"domain_scores_gemma":[0.9976273,0.0014071407,0.00013090795,0.00008755749,0.0006571291,0.00008985415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055567184,0.0015367747,0.0014819263,0.0012581162,0.0005123971,0.00083047623,0.0012519767,0.0012024736,0.0010769335],"category_scores_gemma":[0.0050812326,0.00040016964,0.0012995574,0.0006823637,0.00032528074,0.0007855158,0.00070944557,0.0014969398,0.000599537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054879265,0.0003458778,0.019252902,0.00016558684,0.00023770213,0.00022909002,0.00006551713,0.8063428,0.0029796024,0.0011874973,0.0044267084,0.16421801],"study_design_scores_gemma":[0.00001353154,0.00004453974,0.00042966334,0.00000895383,0.000015626692,0.000018290495,0.0000053248937,0.9986602,0.00031649062,0.0003344896,0.00014712581,0.000005788022],"about_ca_topic_score_codex":0.013091544,"about_ca_topic_score_gemma":0.005979514,"teacher_disagreement_score":0.013091544,"about_ca_system_score_codex":0.00065959326,"about_ca_system_score_gemma":0.0018026205,"threshold_uncertainty_score":0.029387057},"labels":[],"label_agreement":null},{"id":"W4400217994","doi":"10.3389/fcvm.2024.1360548","title":"Explainable coronary artery disease prediction model based on AutoGluon from AutoML framework","year":2024,"lang":"en","type":"article","venue":"Frontiers in Cardiovascular Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"China Scholarship Council","keywords":"Coronary artery disease; Cardiology; Disease; Medicine; Internal medicine; Computer science","score_opus":0.05232527968017922,"score_gpt":0.36692003842299825,"score_spread":0.31459475874281906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400217994","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32703477,0.0010417874,0.6641342,0.0010477827,0.000069612666,0.00011037568,0.001098798,0.0013574687,0.0041052406],"genre_scores_gemma":[0.94287586,0.00023585372,0.053547572,0.00015881426,0.00005646789,0.00009239988,0.0012607984,0.000037762336,0.0017345818],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995952,0.00015598755,0.000018727604,0.000116934956,0.00006974944,0.000043466975],"domain_scores_gemma":[0.99911875,0.00052729674,0.00008584075,0.00007220462,0.00015965413,0.000036218473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011905885,0.0005920922,0.0005251619,0.00103657,0.00032656777,0.000624242,0.00074533897,0.0005077307,0.0014859268],"category_scores_gemma":[0.0022960585,0.00019456087,0.00087359996,0.00044294368,0.00024882745,0.00062442,0.00081498927,0.00071410526,0.00022700871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001691,0.00013766259,0.029191548,0.00008584924,0.0002637427,0.00028374785,0.0001926286,0.81072587,0.0015752604,0.0104604745,0.0031692889,0.14374483],"study_design_scores_gemma":[0.000005346028,0.000026285306,0.0014060442,0.0000068607383,0.000026788428,0.000030323123,0.000009152638,0.9947996,0.00020051049,0.003064458,0.00041817923,0.0000063669795],"about_ca_topic_score_codex":0.009737253,"about_ca_topic_score_gemma":0.011812431,"teacher_disagreement_score":0.009737253,"about_ca_system_score_codex":0.0007045544,"about_ca_system_score_gemma":0.0010303932,"threshold_uncertainty_score":0.019361138},"labels":[],"label_agreement":null},{"id":"W4400319628","doi":"10.23977/acss.2024.080410","title":"Evaluation and Design of Employment Decision Analysis System Based on Artificial Intelligence","year":2024,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Data pre-processing; Computer science; Preprocessor; Process (computing); Decision tree; Artificial intelligence; Decision support system; Data mining; Machine learning; Data science","score_opus":0.22175839593178923,"score_gpt":0.49577152637747984,"score_spread":0.27401313044569064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400319628","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6240911,0.00041360586,0.35394806,0.00049821136,0.00017551957,0.0016024016,0.00038800965,0.0049277325,0.013955357],"genre_scores_gemma":[0.9060476,0.00013302332,0.090101406,0.00007051379,0.00002211879,0.00042634213,0.00038674966,0.0000391077,0.0027731531],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991623,0.00024996197,0.00006791584,0.00015431318,0.00028151623,0.000083907755],"domain_scores_gemma":[0.9992167,0.0001985463,0.000045981735,0.000056870365,0.00041367402,0.00006822654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001373163,0.0004197271,0.0005214459,0.000809965,0.0004802789,0.0010942416,0.00058531115,0.00041721715,0.0033359749],"category_scores_gemma":[0.0020751522,0.00019429464,0.00037096257,0.00047533863,0.00020675833,0.0008007781,0.00040508207,0.0002752324,0.00063025666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003289545,0.0018163042,0.053100515,0.0009959699,0.00030443328,0.00072855776,0.0007932348,0.12215343,0.10869935,0.0074323122,0.008281612,0.69240487],"study_design_scores_gemma":[0.00027252565,0.0019847057,0.023671012,0.0000614819,0.00025104685,0.00019402005,0.00038257023,0.9040662,0.060577117,0.0012110282,0.0072714477,0.00005669426],"about_ca_topic_score_codex":0.0031154584,"about_ca_topic_score_gemma":0.0017841468,"teacher_disagreement_score":0.0033359749,"about_ca_system_score_codex":0.0007147619,"about_ca_system_score_gemma":0.0011166816,"threshold_uncertainty_score":0.011159956},"labels":[],"label_agreement":null},{"id":"W4400351510","doi":"10.1109/smartnets61466.2024.10577723","title":"Enhancing Diabetes Prediction Based on Pair-Wise Ensemble Learning Model Selection","year":2024,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Selection (genetic algorithm); Ensemble learning; Model selection","score_opus":0.09793808282876212,"score_gpt":0.4263200261243868,"score_spread":0.32838194329562465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400351510","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15601046,0.0027395994,0.8348024,0.0009498515,0.00034361126,0.00010180691,0.00040599314,0.0013810166,0.0032652568],"genre_scores_gemma":[0.9004746,0.001010236,0.095725015,0.00027407857,0.00021592216,0.00010228263,0.00086738,0.00005780595,0.0012727308],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895346,0.0004247582,0.000058691392,0.00022550974,0.00022543555,0.0001121351],"domain_scores_gemma":[0.99818194,0.0009395956,0.00014501868,0.00018758955,0.00046074358,0.00008516879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002646333,0.0012460848,0.0017528597,0.0014611406,0.00043719602,0.0012914133,0.0011395025,0.0007876971,0.00067613734],"category_scores_gemma":[0.004245111,0.00033835985,0.0015043197,0.0010413572,0.0001983447,0.0012656666,0.0011206528,0.00146331,0.00041336456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033092566,0.00038079848,0.025623102,0.00011864519,0.000748803,0.00027633793,0.00015570976,0.606988,0.0057964837,0.0020141013,0.004183259,0.35338387],"study_design_scores_gemma":[0.0000052075197,0.0000683158,0.00094216265,0.000011255377,0.00006267414,0.000040289797,0.000014892108,0.996725,0.00087599515,0.0008584,0.00038366692,0.000012145338],"about_ca_topic_score_codex":0.0039720624,"about_ca_topic_score_gemma":0.0036956472,"teacher_disagreement_score":0.0039720624,"about_ca_system_score_codex":0.00035821923,"about_ca_system_score_gemma":0.0007623404,"threshold_uncertainty_score":0.01399529},"labels":[],"label_agreement":null},{"id":"W4400470487","doi":"10.20944/preprints202407.0425.v1","title":"An Unsupervised Error Detection Methodology for Detecting Mislabels in Healthcare Analytics","year":2024,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Interpretability; Computer science; Cluster analysis; Unsupervised learning; Artificial intelligence; Reliability (semiconductor); Data mining; Machine learning; Pattern recognition (psychology)","score_opus":0.705493801331435,"score_gpt":0.6047276982236441,"score_spread":0.10076610310779088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400470487","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020232763,0.00022904115,0.97642446,0.00023985296,0.00007897497,0.0002498209,0.0002749666,0.0017728094,0.0004973008],"genre_scores_gemma":[0.21393666,0.00018237278,0.7823482,0.00026182932,0.00010821153,0.00038251086,0.0010074661,0.00022880257,0.0015440207],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9906889,0.0019846605,0.0011777849,0.0027433122,0.003077334,0.00032793073],"domain_scores_gemma":[0.9725519,0.010710569,0.0049593276,0.0044458327,0.006952443,0.00037995938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006970004,0.0013078039,0.001392888,0.005696539,0.0016563209,0.002289895,0.0028454643,0.0018483179,0.0006756574],"category_scores_gemma":[0.03038861,0.0005625809,0.0014735837,0.0037436273,0.0012853,0.0022441894,0.0021266462,0.0023202687,0.0007046386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004698554,0.00061012106,0.04468965,0.00042224865,0.0004885858,0.0004782113,0.001119084,0.049801465,0.024451032,0.00893723,0.007993714,0.8605388],"study_design_scores_gemma":[0.00006463328,0.0002403592,0.013755238,0.00013034584,0.00012513224,0.0009766397,0.00029481968,0.8977664,0.058078382,0.020309536,0.008135618,0.00012291389],"about_ca_topic_score_codex":0.0033501752,"about_ca_topic_score_gemma":0.0052749775,"teacher_disagreement_score":0.006970004,"about_ca_system_score_codex":0.0011876118,"about_ca_system_score_gemma":0.003090513,"threshold_uncertainty_score":0.03686136},"labels":[],"label_agreement":null},{"id":"W4400526445","doi":"10.1109/icmi60790.2024.10585703","title":"Optimized Neural Networks for Diabetes Classification Using Pima Indians Diabetes Database","year":2024,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Diabetes mellitus; Artificial neural network; Artificial intelligence; Data mining; Database; Medicine","score_opus":0.2595953411022805,"score_gpt":0.4904251728273193,"score_spread":0.2308298317250388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400526445","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9465479,0.002823126,0.03489374,0.0011417147,0.00029660028,0.0001620799,0.0068482477,0.002255838,0.005030581],"genre_scores_gemma":[0.9560349,0.0006601797,0.031357817,0.00020532153,0.000063063075,0.00012378559,0.009366054,0.00003267989,0.0021563198],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997192,0.00006169954,0.00003079071,0.0000673615,0.00006425179,0.000056685356],"domain_scores_gemma":[0.99962294,0.00015940385,0.00004019283,0.000036549598,0.00011675878,0.000024170346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009387955,0.0007970063,0.0006129868,0.0011102945,0.00036201914,0.0007380142,0.00077806524,0.00052233983,0.0009650315],"category_scores_gemma":[0.0019556223,0.00017556452,0.00061616296,0.0009598393,0.00012288381,0.0003663817,0.0003680033,0.0006659634,0.00033533128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002246308,0.0015362042,0.065502204,0.00036296312,0.0005458987,0.00088577304,0.00010968233,0.4367402,0.0065362533,0.0011343578,0.02437734,0.46002287],"study_design_scores_gemma":[0.000027400507,0.00008220955,0.008160684,0.000011027529,0.00004609788,0.000056785786,0.000052853702,0.98868304,0.0017726192,0.0003304932,0.00076438626,0.000012408284],"about_ca_topic_score_codex":0.040419973,"about_ca_topic_score_gemma":0.02389306,"teacher_disagreement_score":0.040419973,"about_ca_system_score_codex":0.0010685378,"about_ca_system_score_gemma":0.0009411819,"threshold_uncertainty_score":0.08036941},"labels":[],"label_agreement":null},{"id":"W4400563339","doi":"10.54254/2755-2721/74/20240458","title":"Review of the data science in the field of healthcare","year":2024,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Multidisciplinary approach; Data science; Health care; Big data; Computer science; Field (mathematics); Domain (mathematical analysis); Demographics; Data quality; Quality (philosophy); Data analysis; Data mining; Knowledge management; Engineering","score_opus":0.1159029363055489,"score_gpt":0.47530386024268534,"score_spread":0.3594009239371364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400563339","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019001722,0.9878868,0.0017212108,0.0064688157,0.0015942982,0.000019561692,0.00021578948,0.000016245383,0.0018872999],"genre_scores_gemma":[0.001807055,0.99213505,0.0018466708,0.0019019672,0.0016354597,0.000027520495,0.00023502819,0.000010448491,0.00040076795],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99613994,0.0012505056,0.0008408209,0.00036265847,0.0012866263,0.00011941564],"domain_scores_gemma":[0.95533276,0.033407934,0.0023175376,0.00095237215,0.0072931335,0.0006961745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061245626,0.00069948816,0.0016536887,0.011928553,0.00094985217,0.0031655529,0.0014668725,0.001760034,0.0061957664],"category_scores_gemma":[0.022876076,0.000671068,0.0013559143,0.017619684,0.0018322347,0.0042423,0.0013944482,0.002762857,0.001886285],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007529562,0.000058531226,0.0009999132,0.049657702,0.00026716542,0.00020506978,0.00035763782,0.0009082303,0.0005890487,0.02845748,0.13959888,0.77882504],"study_design_scores_gemma":[0.000006199905,0.000035345285,0.0018467243,0.028857112,0.00017830626,0.0004784418,0.0002086294,0.00025728825,0.00019176851,0.010699166,0.95720506,0.000036020792],"about_ca_topic_score_codex":0.004750914,"about_ca_topic_score_gemma":0.007541978,"teacher_disagreement_score":0.011928553,"about_ca_system_score_codex":0.0029649932,"about_ca_system_score_gemma":0.008002052,"threshold_uncertainty_score":0.032390118},"labels":[],"label_agreement":null},{"id":"W4400672427","doi":"10.1201/9781003093091","title":"Analysis of Categorical Data with R","year":2024,"lang":"en","type":"book","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"International Biometric Society; National Institutes of Health; National Science Foundation","keywords":"Categorical variable; Computer science; Statistics; Mathematics","score_opus":0.3617623568579437,"score_gpt":0.5469440924323614,"score_spread":0.1851817355744177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400672427","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026973588,0.0049988376,0.55949455,0.011043908,0.009386887,0.0071280086,0.24499176,0.116173446,0.04408522],"genre_scores_gemma":[0.028223552,0.004841271,0.775045,0.0073711947,0.0023902187,0.034220178,0.06452575,0.054224547,0.029158277],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.93640584,0.028714688,0.009448626,0.008254158,0.01606845,0.0011082345],"domain_scores_gemma":[0.7600022,0.16352989,0.014812716,0.034114372,0.025698662,0.0018420935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030817723,0.003014915,0.004607188,0.009597661,0.0014976157,0.007597991,0.0044331043,0.0023938287,0.22747114],"category_scores_gemma":[0.25559384,0.00266586,0.004921513,0.01238628,0.0033299413,0.004259986,0.004414944,0.008387645,0.101801805],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032686547,0.0000641316,0.0019094145,0.0073411632,0.0008062579,0.0003221381,0.00079452596,0.002410656,0.0006646916,0.019374471,0.8433946,0.12259102],"study_design_scores_gemma":[0.000229061,0.00013912424,0.0034352255,0.004555895,0.00029141468,0.0007151091,0.00037577967,0.0057246657,0.0011137079,0.07094481,0.9122687,0.00020660531],"about_ca_topic_score_codex":0.0022089058,"about_ca_topic_score_gemma":0.0023712262,"teacher_disagreement_score":0.22747114,"about_ca_system_score_codex":0.002229274,"about_ca_system_score_gemma":0.011016641,"threshold_uncertainty_score":0.7609668},"labels":[],"label_agreement":null},{"id":"W4400681535","doi":"10.22541/au.172114866.65779738/v1","title":"Implementation of a Surveillance and Monitoring System for Chronic Disease: A Scoping Review","year":2024,"lang":"en","type":"review","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Disease surveillance; Disease monitoring; Medicine; Process management; Business; Political science; Disease; Pathology","score_opus":0.40427917029841753,"score_gpt":0.6522187193665367,"score_spread":0.2479395490681192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400681535","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016191201,0.9885217,0.0018359857,0.002436036,0.0006133718,0.0027592585,0.0005328141,0.000036557307,0.0016452734],"genre_scores_gemma":[0.014086244,0.97531545,0.0053143036,0.00082198466,0.0001542382,0.0035356896,0.0006117382,0.000014117759,0.00014628097],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9477927,0.021846555,0.018989995,0.0021235377,0.008330057,0.0009171417],"domain_scores_gemma":[0.8683466,0.08659336,0.015894134,0.0031202687,0.02488317,0.0011625406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.077054374,0.002116225,0.005554248,0.028039172,0.0026622103,0.008201494,0.0040606735,0.004396227,0.00274861],"category_scores_gemma":[0.18831904,0.0017637517,0.00718112,0.02856101,0.002324885,0.008388462,0.0042269668,0.0029046088,0.00052992505],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012513834,0.000069170586,0.0027219444,0.76000357,0.0021984258,0.0001509183,0.002125701,0.00052558945,0.00024055988,0.0035305794,0.0059664133,0.22234203],"study_design_scores_gemma":[0.000030331397,0.000068194124,0.0021081327,0.96959275,0.0041212207,0.00009733967,0.00090218807,0.00020804648,0.0001582977,0.00048825925,0.022195205,0.000030071198],"about_ca_topic_score_codex":0.020204492,"about_ca_topic_score_gemma":0.026468828,"teacher_disagreement_score":0.077054374,"about_ca_system_score_codex":0.013894648,"about_ca_system_score_gemma":0.0647122,"threshold_uncertainty_score":0.40750736},"labels":[],"label_agreement":null},{"id":"W4400700531","doi":"10.4995/carma2024.2024.19017","title":"6th International Conference on Advanced Research Methods and Analytics - CARMA 2024","year":2024,"lang":"en","type":"paratext","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fundação para a Ciência e a Tecnologia; Consortium of International Agricultural Research Centers; European Commission; International Development Research Centre","keywords":"Analytics; Computer science; Data science","score_opus":0.6875562833676188,"score_gpt":0.7326804534009861,"score_spread":0.04512417003336733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400700531","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024679734,0.05123914,0.318227,0.039087594,0.06407877,0.0026583653,0.010173563,0.013713814,0.49835378],"genre_scores_gemma":[0.021072414,0.03880517,0.21721506,0.0075292164,0.015785001,0.0027153196,0.024991294,0.006694925,0.66519165],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9822286,0.0056786793,0.0012421214,0.0016387467,0.008303382,0.00090853404],"domain_scores_gemma":[0.96604085,0.009161523,0.0010599247,0.005150544,0.014135901,0.004451218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024975726,0.0018744665,0.0021120019,0.0056244326,0.0016672125,0.015100977,0.0041651307,0.0043059923,0.21416548],"category_scores_gemma":[0.03597621,0.0009311221,0.0018087641,0.0034148947,0.0023685577,0.0085183475,0.007632792,0.006226878,0.14151242],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015631906,0.00018605938,0.0005661887,0.0007784802,0.00007181059,0.0000916723,0.00016331168,0.0006060244,0.0014088642,0.040694993,0.59695905,0.3583173],"study_design_scores_gemma":[0.000010710187,0.00002734942,0.00034493802,0.00036555485,0.000014309021,0.0000869123,0.0000583619,0.0012769817,0.0005096089,0.010669619,0.9866214,0.000014236607],"about_ca_topic_score_codex":0.0033399167,"about_ca_topic_score_gemma":0.002734789,"teacher_disagreement_score":0.21416548,"about_ca_system_score_codex":0.002831439,"about_ca_system_score_gemma":0.0099215405,"threshold_uncertainty_score":0.71645486},"labels":[],"label_agreement":null},{"id":"W4400764140","doi":"10.1101/2024.07.18.24310625","title":"Autoencoder Imputation of Missing Heterogeneous Data for Alzheimer's Disease Classification","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Imputation (statistics); Autoencoder; Missing data; Computer science; Artificial intelligence; Machine learning; Artificial neural network","score_opus":0.42895800568060977,"score_gpt":0.5364994898318968,"score_spread":0.107541484151287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400764140","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.090818286,0.0010421982,0.9053481,0.00041167781,0.000092307746,0.00005352522,0.00052961975,0.0009870538,0.00071716553],"genre_scores_gemma":[0.7602023,0.0007046182,0.23406783,0.00031447076,0.00010077306,0.00017068406,0.002506809,0.000102426115,0.0018300825],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990434,0.0003883445,0.00007647331,0.00024667507,0.00015034777,0.00009482215],"domain_scores_gemma":[0.9966068,0.002082553,0.00028670713,0.0004358931,0.0005235393,0.000064439715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004423163,0.0007985294,0.0011375124,0.00065200945,0.00037808061,0.00063960004,0.00092689553,0.0008018039,0.00076088664],"category_scores_gemma":[0.009372885,0.00043883803,0.0011441044,0.0007773823,0.00047622318,0.00088852254,0.00078814494,0.0022646172,0.00039018813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005617372,0.00030454376,0.017280579,0.00020534778,0.00050228165,0.000260465,0.00022872008,0.6812402,0.007138447,0.004759761,0.004377109,0.28314078],"study_design_scores_gemma":[0.000009732241,0.0000456441,0.002207376,0.000024008335,0.000026185842,0.00003579289,0.000019330228,0.99176896,0.0022693556,0.0030792675,0.0005008677,0.000013512019],"about_ca_topic_score_codex":0.004173543,"about_ca_topic_score_gemma":0.0049825795,"teacher_disagreement_score":0.004423163,"about_ca_system_score_codex":0.0005394897,"about_ca_system_score_gemma":0.0010190799,"threshold_uncertainty_score":0.02339214},"labels":[],"label_agreement":null},{"id":"W4400831116","doi":"10.3724/2096-7004.di.2024.0002","title":"Risk Factors Categorizations of Ischemic Heart Disease in South-Western Bangladesh","year":2024,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Disease; Voting; Population; Actuarial science; Medicine; Geography; Environmental health; Demography; Business; Political science; Pathology; Sociology","score_opus":0.21853472166579566,"score_gpt":0.4789780423696013,"score_spread":0.2604433207038056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400831116","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9967006,0.00007331909,0.00030928987,0.00010405808,0.0000043888954,0.000038052396,0.0010102352,0.0000051523416,0.0017549524],"genre_scores_gemma":[0.9984042,0.00006455396,0.00034665104,0.000010379348,0.0000025312902,0.000026193931,0.0008709954,9.993346e-7,0.0002734762],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9997439,0.00006876106,0.000051430503,0.000043560256,0.00005351309,0.00003882985],"domain_scores_gemma":[0.99931955,0.0001945776,0.00015275223,0.0000553424,0.0001824735,0.000095368996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035316058,0.0002533179,0.00020092656,0.001600379,0.00034623512,0.00056109595,0.00020947005,0.00019176416,0.0019330574],"category_scores_gemma":[0.0019071456,0.00008203823,0.00026763638,0.0011708958,0.0002174733,0.00023886967,0.0004697145,0.00023735111,0.00041672838],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020049652,0.000055157,0.9794672,0.000033007036,0.000035228575,0.00016887815,0.0010085382,0.00033801104,0.0015240089,0.00027280088,0.0005040239,0.016392494],"study_design_scores_gemma":[0.000009665973,0.00009551389,0.9916373,0.000024542327,0.000024194254,0.00020276195,0.004611616,0.0017681948,0.0003593109,0.00035082435,0.0008997966,0.000016325237],"about_ca_topic_score_codex":0.014318302,"about_ca_topic_score_gemma":0.013044258,"teacher_disagreement_score":0.014318302,"about_ca_system_score_codex":0.00048609087,"about_ca_system_score_gemma":0.00034508604,"threshold_uncertainty_score":0.02846992},"labels":[],"label_agreement":null},{"id":"W4400831941","doi":"10.1016/b978-0-323-95686-4.00008-3","title":"Prediction of glucose concentration in type 1 diabetes patients based on machine learning techniques","year":2024,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's Hospital Research Institute of Manitoba","funders":"","keywords":"Type 2 diabetes; Computer science; Machine learning; Artificial intelligence; Diabetes mellitus; Medicine; Endocrinology","score_opus":0.06717994864546857,"score_gpt":0.3653520664895384,"score_spread":0.29817211784406983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400831941","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47483215,0.038826156,0.42725757,0.0040717684,0.0017303578,0.00011544291,0.003001549,0.002235189,0.047929835],"genre_scores_gemma":[0.8334706,0.014992136,0.12354535,0.00053010037,0.00073355087,0.00009249515,0.0022545771,0.000080018035,0.024301136],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999331,0.000019749763,0.000005425309,0.000013100489,0.000022948787,0.000005509474],"domain_scores_gemma":[0.9996351,0.00030463064,0.000018834133,0.0000067502415,0.000027939617,0.000006743717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002477473,0.00041120217,0.00034025917,0.0005271944,0.00007549186,0.00035790415,0.00027823966,0.00030679567,0.0017034092],"category_scores_gemma":[0.00084166817,0.00009551605,0.00041945314,0.00039196014,0.00008215676,0.0002635643,0.00008301255,0.0004719565,0.00060806406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046360045,0.000285298,0.04344191,0.00021701738,0.00018060843,0.0002826788,0.00006857202,0.07207265,0.0038921733,0.0022108264,0.014368069,0.8625165],"study_design_scores_gemma":[0.000039434868,0.00052934827,0.053640343,0.00019629009,0.00015610333,0.0006751666,0.000071513896,0.92380637,0.004050675,0.007807393,0.008981452,0.000045997396],"about_ca_topic_score_codex":0.0022581911,"about_ca_topic_score_gemma":0.0023838198,"teacher_disagreement_score":0.0022581911,"about_ca_system_score_codex":0.00014683578,"about_ca_system_score_gemma":0.00015395341,"threshold_uncertainty_score":0.005698502},"labels":[],"label_agreement":null},{"id":"W4401016221","doi":"10.3390/info15080435","title":"Survey on Knowledge Representation Models in Healthcare","year":2024,"lang":"en","type":"article","venue":"Information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Rimouski; Université du Québec à Chicoutimi","funders":"","keywords":"Health care; Representation (politics); Computer science; Knowledge management; Data science; Political science","score_opus":0.34555287616001806,"score_gpt":0.5487139623426153,"score_spread":0.2031610861825972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401016221","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011690225,0.59049267,0.30650797,0.017109321,0.00093333225,0.00045715514,0.0028362963,0.0011996264,0.06877343],"genre_scores_gemma":[0.08572148,0.7029986,0.19373892,0.0033074098,0.001123855,0.00046473183,0.0059058503,0.00021117133,0.0065280534],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99731183,0.000927073,0.00041800327,0.00031569847,0.00087946374,0.00014794641],"domain_scores_gemma":[0.9897893,0.008081715,0.000365143,0.0005950141,0.0010372441,0.00013146784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003939222,0.0009375526,0.001400501,0.005936208,0.00059701066,0.0042946874,0.0025725106,0.0015885192,0.0064669903],"category_scores_gemma":[0.01299758,0.00063494546,0.0016146471,0.012630056,0.0007765261,0.006697113,0.0013613935,0.0013620212,0.0019585367],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012176821,0.00016004054,0.0018498744,0.0068025477,0.00019638745,0.00022267326,0.00053418684,0.012842186,0.0006102095,0.16432387,0.035085857,0.77725035],"study_design_scores_gemma":[0.000041048,0.00022326979,0.002731613,0.0100837955,0.00040371026,0.001305725,0.0010025792,0.055461317,0.0019007728,0.18451507,0.74221236,0.00011879513],"about_ca_topic_score_codex":0.0053968113,"about_ca_topic_score_gemma":0.0031239397,"teacher_disagreement_score":0.0064669903,"about_ca_system_score_codex":0.0024877624,"about_ca_system_score_gemma":0.002922666,"threshold_uncertainty_score":0.021634221},"labels":[],"label_agreement":null},{"id":"W4401173939","doi":"10.3390/bioengineering11080770","title":"An Unsupervised Error Detection Methodology for Detecting Mislabels in Healthcare Analytics","year":2024,"lang":"en","type":"article","venue":"Bioengineering","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Interpretability; Computer science; Cluster analysis; Unsupervised learning; Artificial intelligence; Data mining; Reliability (semiconductor); Machine learning; Pattern recognition (psychology)","score_opus":0.36774594453655857,"score_gpt":0.5273353419595005,"score_spread":0.15958939742294193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401173939","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022644652,0.00024532492,0.9739424,0.00024036203,0.000078090634,0.00025701275,0.00026663058,0.0017956899,0.0005298361],"genre_scores_gemma":[0.23112492,0.00018630414,0.765297,0.00026235063,0.00009592915,0.00037535813,0.0009664835,0.00020140862,0.0014901517],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9919003,0.0016086692,0.0010631132,0.0023424209,0.0027960972,0.00028931684],"domain_scores_gemma":[0.9762428,0.0090504065,0.0044414103,0.003545255,0.006383717,0.0003363872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062733735,0.0012559844,0.0013472148,0.005542808,0.0016120126,0.002136458,0.0027020061,0.0016582751,0.00063013023],"category_scores_gemma":[0.026754938,0.0005083939,0.0013527889,0.0035635806,0.0011724913,0.0021825908,0.0019519317,0.0021058144,0.0006299789],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044056977,0.00060462026,0.04390409,0.00038528128,0.00043242305,0.00046479912,0.0010144941,0.049265962,0.02355877,0.007813861,0.007197748,0.8649173],"study_design_scores_gemma":[0.000057060894,0.00024078628,0.013124813,0.00012152646,0.00011625445,0.00092703995,0.00028100688,0.90638083,0.054303434,0.016686583,0.0076449187,0.000115712675],"about_ca_topic_score_codex":0.0034177925,"about_ca_topic_score_gemma":0.0054487423,"teacher_disagreement_score":0.0062733735,"about_ca_system_score_codex":0.0011314513,"about_ca_system_score_gemma":0.0029608742,"threshold_uncertainty_score":0.033177197},"labels":[],"label_agreement":null},{"id":"W4401325481","doi":"10.1016/j.cjca.2024.07.028","title":"Artificial Intelligence-Based Digital Biomarkers for Type 2 Diabetes: A Review","year":2024,"lang":"en","type":"review","venue":"Canadian Journal of Cardiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University; Université de Sherbrooke; McGill University Health Centre","funders":"MEDTEQ+; Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Mitacs; Roche; AstraZeneca","keywords":"Medicine; Type 2 diabetes; Diabetes mellitus; Data science; Artificial intelligence; Computational biology; Endocrinology","score_opus":0.39127185979216406,"score_gpt":0.5217508658056496,"score_spread":0.1304790060134855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401325481","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000048176604,0.9987293,0.00017810757,0.00028987596,0.00012775585,0.000007738079,0.000013416888,0.000005479584,0.0006000812],"genre_scores_gemma":[0.00042449313,0.99881953,0.00031829413,0.00015519446,0.00008954195,0.000009134994,0.00002016398,0.0000013265399,0.00016220695],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99946016,0.0001241968,0.00009187177,0.00007335185,0.00021836105,0.000031988468],"domain_scores_gemma":[0.997503,0.0017702925,0.00018574749,0.000041777308,0.00041950363,0.00007972506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015391733,0.000995643,0.0016700036,0.004114962,0.00035967818,0.0014357605,0.0012518788,0.0019484514,0.0036678044],"category_scores_gemma":[0.0034568664,0.00037582926,0.0010454551,0.004077381,0.0006360345,0.0017041814,0.0009333849,0.0019048915,0.0015608855],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040351424,0.00006137994,0.00019507176,0.030970654,0.0001621246,0.00010688857,0.000074202406,0.00033082013,0.0003426451,0.004768312,0.017401118,0.94554645],"study_design_scores_gemma":[0.00002489775,0.00012269545,0.0013166156,0.03010608,0.000432987,0.00091567985,0.00011619374,0.00027716823,0.00036292957,0.0040710294,0.962205,0.00004877449],"about_ca_topic_score_codex":0.0032868285,"about_ca_topic_score_gemma":0.0038959826,"teacher_disagreement_score":0.004114962,"about_ca_system_score_codex":0.00095361855,"about_ca_system_score_gemma":0.0025324589,"threshold_uncertainty_score":0.012270033},"labels":[],"label_agreement":null},{"id":"W4401413465","doi":"10.1109/tcbb.2024.3371808","title":"Editorial Deep Learning-Empowered Big Data Analytics in Biomedical Applications and Digital Healthcare","year":2024,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Big data; Data science; Computer science; Health care; Analytics; Deep learning; Artificial intelligence; Data mining; Political science","score_opus":0.11678102782538329,"score_gpt":0.4370907375663761,"score_spread":0.3203097097409928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401413465","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001196137,0.013107869,0.0011440576,0.06848887,0.91316724,0.000036024834,0.00017434158,0.0001515729,0.0036104391],"genre_scores_gemma":[0.0013196839,0.00988431,0.0003642532,0.018675251,0.9607872,0.000025154908,0.000072504365,0.000059081376,0.0088126175],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99670744,0.00041632133,0.00032959398,0.0005629463,0.001748286,0.00023542176],"domain_scores_gemma":[0.9720553,0.011359357,0.0011954583,0.0007141802,0.010796252,0.003879374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052845185,0.0014239494,0.0016541721,0.0022857112,0.0012233875,0.005621817,0.0026297485,0.007946211,0.016700098],"category_scores_gemma":[0.016229177,0.00058861106,0.0014696578,0.0010428996,0.0023468572,0.0037083186,0.0012616856,0.011880378,0.010688281],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050509352,0.000015307725,0.00005467648,0.00040322504,0.000019500596,0.00010883417,0.000014353093,0.00006495718,0.00011941496,0.0012989689,0.9830025,0.014847825],"study_design_scores_gemma":[0.00003191734,0.00004108865,0.00022388107,0.000399134,0.000027360893,0.0003073085,0.000023938288,0.00030704078,0.00022003124,0.0023191124,0.99607724,0.000021956266],"about_ca_topic_score_codex":0.00061393366,"about_ca_topic_score_gemma":0.0010938351,"teacher_disagreement_score":0.016700098,"about_ca_system_score_codex":0.0012526613,"about_ca_system_score_gemma":0.0016727,"threshold_uncertainty_score":0.055867374},"labels":[],"label_agreement":null},{"id":"W4401653537","doi":"10.30829/zero.v7i1.17339","title":"CLASSIFICATION OF TODDLER NUTRITIONAL STATUS USING A BINARY CLASSIFICATION TREE WITH ALGORITHMSQUICK, UNBIASED, EFFICENT, STATISTICAL TREE","year":2023,"lang":"en","type":"article","venue":"ZERO Jurnal Sains Matematika dan Terapan","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Toddler; Tree (set theory); Mathematics; Statistics; Binary tree; Psychology; Developmental psychology; Combinatorics","score_opus":0.1862458547777023,"score_gpt":0.4415910586638026,"score_spread":0.25534520388610027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401653537","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09275951,0.00066463434,0.8970469,0.00076144334,0.00014975273,0.0007656938,0.0023933214,0.0022907984,0.003167852],"genre_scores_gemma":[0.30447197,0.00046057842,0.6847018,0.0002752795,0.00009316899,0.0009692501,0.005690366,0.00011686566,0.0032207216],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976713,0.0006893549,0.00030421346,0.00047293818,0.0006299387,0.00023219058],"domain_scores_gemma":[0.99635553,0.0017325474,0.00035176988,0.000247883,0.0012066063,0.00010565231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048121363,0.000865508,0.0012813513,0.0042335126,0.0012977207,0.0022651958,0.0014880487,0.001115077,0.0025030416],"category_scores_gemma":[0.009158707,0.00041763834,0.0016917629,0.0027686819,0.000417707,0.0015329242,0.0009890863,0.0012329591,0.0012488877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055706466,0.0005542672,0.101429306,0.0004814191,0.00034391906,0.0003524447,0.000711979,0.092611626,0.006204788,0.008415425,0.012973305,0.7753645],"study_design_scores_gemma":[0.000061308136,0.00036372864,0.020810952,0.00020409613,0.00019418017,0.00029570196,0.0005165255,0.9514899,0.0042050537,0.014704771,0.0070917797,0.00006200721],"about_ca_topic_score_codex":0.007856543,"about_ca_topic_score_gemma":0.008022851,"teacher_disagreement_score":0.007856543,"about_ca_system_score_codex":0.0013454189,"about_ca_system_score_gemma":0.0020108435,"threshold_uncertainty_score":0.025449336},"labels":[],"label_agreement":null},{"id":"W4401726609","doi":"10.1109/tbcas.2024.3434009","title":"Guest Editorial: Special Issue on Selected Articles From IEEE BioCAS 2023","year":2024,"lang":"en","type":"editorial","venue":"IEEE Transactions on Biomedical Circuits and Systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Engineering physics; Engineering","score_opus":0.06787697828538304,"score_gpt":0.39396113378778613,"score_spread":0.3260841555024031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401726609","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000045319,0.0035759418,0.00014105569,0.018342894,0.9728423,0.00002866696,0.000085522544,0.00010050021,0.0048378017],"genre_scores_gemma":[0.00045983188,0.0040822094,0.00014054345,0.012994972,0.953172,0.000032627275,0.00011808846,0.00009752826,0.028902154],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99709177,0.00033858576,0.0002989648,0.00031782838,0.0017227967,0.00023003013],"domain_scores_gemma":[0.9871809,0.0017749902,0.00083495665,0.0002600592,0.0074873734,0.0024617815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033220819,0.0028413355,0.0025655192,0.00393425,0.002762631,0.0076079033,0.0021436654,0.007551289,0.054791503],"category_scores_gemma":[0.012683471,0.00085203635,0.0018813012,0.0016782624,0.0011224059,0.0031740204,0.0013286017,0.008312759,0.04770896],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027127302,0.000008978601,0.000016553658,0.00010135037,0.000006527967,0.00006452286,0.0000034842726,0.000012959825,0.000062639774,0.00008294133,0.99471927,0.0048935954],"study_design_scores_gemma":[0.00004307251,0.000019848938,0.000167037,0.00019143126,0.000020865684,0.00021942554,0.00001840242,0.00007116608,0.00013269582,0.0003608827,0.99874395,0.00001112363],"about_ca_topic_score_codex":0.0011514341,"about_ca_topic_score_gemma":0.004037464,"teacher_disagreement_score":0.054791503,"about_ca_system_score_codex":0.0022879404,"about_ca_system_score_gemma":0.0027714453,"threshold_uncertainty_score":0.18329585},"labels":[],"label_agreement":null},{"id":"W4401768890","doi":"10.18280/isi.290433","title":"Innovative: A Novel Deep Learning-Based Semantic Segmentation Architecture for Medical Applications","year":2024,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Deep learning; Architecture; Computer science; Segmentation; Artificial intelligence; Computer architecture; Natural language processing; Data science; Geography","score_opus":0.04710950111946562,"score_gpt":0.40329724525910715,"score_spread":0.35618774413964155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401768890","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014068457,0.00046455514,0.97810626,0.000701339,0.00009580843,0.000055718156,0.00025119015,0.0019428822,0.004313796],"genre_scores_gemma":[0.4783067,0.00094264274,0.50383097,0.0012176952,0.00011830957,0.00021971826,0.0012039327,0.00031586128,0.013844192],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998242,0.000030024627,0.0000089229925,0.000053981228,0.000055665412,0.000027209375],"domain_scores_gemma":[0.99985635,0.000042270814,0.000017321852,0.00001979801,0.000041605585,0.000022719734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005132136,0.00059423206,0.00037939506,0.0005151891,0.0003471649,0.00093233876,0.0015812622,0.0011296209,0.0033265958],"category_scores_gemma":[0.0010137318,0.00033237445,0.0005621762,0.00044012896,0.00058395404,0.0015722533,0.0015593353,0.0010029696,0.0010991932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045235548,0.0001894613,0.0020950735,0.00032905745,0.00015077638,0.0003417521,0.00021848701,0.3590551,0.0460662,0.06460972,0.01817478,0.50831723],"study_design_scores_gemma":[0.000011657107,0.00007699123,0.0002649785,0.000023109265,0.000028815844,0.00011778595,0.000019551588,0.960816,0.008826096,0.022632241,0.0071684374,0.000014358357],"about_ca_topic_score_codex":0.0023790188,"about_ca_topic_score_gemma":0.004225207,"teacher_disagreement_score":0.0033265958,"about_ca_system_score_codex":0.00090921845,"about_ca_system_score_gemma":0.0010203657,"threshold_uncertainty_score":0.011128545},"labels":[],"label_agreement":null},{"id":"W4401769131","doi":"10.18280/isi.290427","title":"Bridging Data Complexity with GATNet for Learning in Interconnected Electronic Medical Records Graphs","year":2024,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bridging (networking); Computer science; Medical record; Theoretical computer science; Data science; Medicine; Computer network","score_opus":0.12314062652118923,"score_gpt":0.4183928796124183,"score_spread":0.29525225309122904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401769131","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.085729755,0.00060068385,0.9011897,0.003001381,0.00014043496,0.00032490148,0.002583163,0.0031671317,0.0032627624],"genre_scores_gemma":[0.5333425,0.00059939025,0.4548315,0.0006220048,0.000135914,0.00042316882,0.00651127,0.00021517016,0.0033190963],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998052,0.0009059602,0.00015347957,0.0004716003,0.0003006558,0.000116314106],"domain_scores_gemma":[0.9884062,0.008370736,0.0007019136,0.0013058393,0.0009516677,0.0002636886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033992073,0.0009865932,0.0008073105,0.004254906,0.0011052154,0.0017935154,0.0015611345,0.0015254653,0.0027788917],"category_scores_gemma":[0.022634357,0.0006109751,0.0015023964,0.0031803013,0.0010191164,0.0037964822,0.0023751333,0.0024248865,0.00044163945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003179606,0.00025706957,0.01799606,0.0003555089,0.00029136133,0.0005297862,0.0006774425,0.647025,0.0015315865,0.07655478,0.011080544,0.24338286],"study_design_scores_gemma":[0.000012556383,0.000035015488,0.0007231535,0.000025011319,0.000024575955,0.000049729137,0.00008099642,0.94980776,0.00043501225,0.0464673,0.002330271,0.000008573748],"about_ca_topic_score_codex":0.018684503,"about_ca_topic_score_gemma":0.029754646,"teacher_disagreement_score":0.018684503,"about_ca_system_score_codex":0.0025976284,"about_ca_system_score_gemma":0.0015105436,"threshold_uncertainty_score":0.037151515},"labels":[],"label_agreement":null},{"id":"W4401769137","doi":"10.18280/isi.290403","title":"Heart Disease: Application of the K-Nearest Neighbor (KNN) Method","year":2024,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"k-nearest neighbors algorithm; Disease; Pattern recognition (psychology); Artificial intelligence; Computer science; Internal medicine; Medicine","score_opus":0.053862986491590895,"score_gpt":0.40259617956910687,"score_spread":0.348733193077516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401769137","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07008856,0.0034492994,0.9082782,0.00087742443,0.00074032764,0.0007279024,0.0019357086,0.0020167392,0.011885832],"genre_scores_gemma":[0.40295136,0.0016564045,0.5864786,0.00020179972,0.0002067174,0.00029761234,0.001789491,0.00013179806,0.006286214],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99792224,0.00036182257,0.0002691857,0.0004903295,0.00081800844,0.00013838719],"domain_scores_gemma":[0.99859554,0.00044014442,0.0001703387,0.000115293864,0.0006217992,0.000056958506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001556688,0.0005716193,0.0010176537,0.0031331405,0.0009463342,0.0013101652,0.0014757602,0.0012205086,0.0017263801],"category_scores_gemma":[0.0047767772,0.00030248275,0.00089190487,0.0030676008,0.00035253438,0.0013811246,0.00080974016,0.0008628544,0.0012771069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033976103,0.00033639182,0.038635556,0.000719412,0.00041198588,0.00046007952,0.00055536744,0.071478374,0.0034070408,0.005193096,0.013251656,0.86521125],"study_design_scores_gemma":[0.000053856053,0.00025806692,0.026000213,0.00022690989,0.00015619789,0.0017422216,0.0010677716,0.9222544,0.006942519,0.0145079475,0.026625568,0.00016436756],"about_ca_topic_score_codex":0.012889931,"about_ca_topic_score_gemma":0.013422109,"teacher_disagreement_score":0.012889931,"about_ca_system_score_codex":0.00070387986,"about_ca_system_score_gemma":0.0013395961,"threshold_uncertainty_score":0.025629759},"labels":[],"label_agreement":null},{"id":"W4401769144","doi":"10.18280/isi.290428","title":"M-GWO Algorithm to Predict Risk of Silent Heart Attack of Diabetes Patients - Cardidiabetes Model","year":2024,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Diabetes mellitus; Cardiology; Internal medicine; Risk model; Computer science; Medicine; Risk analysis (engineering); Endocrinology","score_opus":0.04501852742757063,"score_gpt":0.3508218918129475,"score_spread":0.30580336438537686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401769144","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33775645,0.0035410724,0.64534456,0.0021058507,0.00033715004,0.00025817665,0.001391518,0.0016336917,0.007631499],"genre_scores_gemma":[0.9184146,0.00060412847,0.0727251,0.00031640392,0.00010863527,0.0002087814,0.0015571727,0.0000625672,0.006002655],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997371,0.000060481114,0.000025151832,0.000076680415,0.000038287242,0.00006238511],"domain_scores_gemma":[0.9996594,0.00017416666,0.000045303077,0.000014510477,0.000077308774,0.00002925073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067430845,0.0006040898,0.0009161208,0.0009272931,0.00031855516,0.00071452494,0.0009938703,0.0009089715,0.0026351407],"category_scores_gemma":[0.0013647595,0.0002738634,0.0008293027,0.00053922593,0.00018793267,0.000389837,0.00045492302,0.00076912617,0.0004909451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005290181,0.00041277727,0.049668606,0.0001308463,0.00029315965,0.0003916084,0.000096246586,0.705937,0.001838132,0.0023260221,0.0071358485,0.23124072],"study_design_scores_gemma":[0.000018241291,0.000043615557,0.0024688735,0.0000146129505,0.000020628386,0.000046107776,0.0000147163,0.9959045,0.00023275088,0.0008194156,0.00041087344,0.0000056754193],"about_ca_topic_score_codex":0.012343736,"about_ca_topic_score_gemma":0.007943197,"teacher_disagreement_score":0.012343736,"about_ca_system_score_codex":0.00043328665,"about_ca_system_score_gemma":0.0008744064,"threshold_uncertainty_score":0.024543762},"labels":[],"label_agreement":null},{"id":"W4401824861","doi":"10.1016/j.heliyon.2024.e36556","title":"Advancing thyroid care: An accurate trustworthy diagnostics system with interpretable AI and hybrid machine learning techniques","year":2024,"lang":"en","type":"article","venue":"Heliyon","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; Lakehead University","funders":"","keywords":"Artificial intelligence; Machine learning; Feature selection; Computer science; Univariate; Triiodothyronine; Preprocessor; Classifier (UML); Naive Bayes classifier; Medical diagnosis; Thyroid; Data mining; Medicine; Internal medicine; Support vector machine; Pathology; Multivariate statistics","score_opus":0.028720695187087007,"score_gpt":0.3981940666927042,"score_spread":0.36947337150561715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401824861","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14168856,0.00086763914,0.84043854,0.002173945,0.00013840571,0.00050277036,0.0007582001,0.009271403,0.0041605313],"genre_scores_gemma":[0.7951645,0.00038089164,0.20072113,0.00046889472,0.00013414823,0.00022793782,0.0010046817,0.000082217965,0.001815665],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991411,0.00018541169,0.00010162581,0.00019795842,0.00028986746,0.00008401703],"domain_scores_gemma":[0.9988158,0.00040978272,0.00016728784,0.00015260388,0.00036435484,0.000090233574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015533201,0.0005999217,0.0006255231,0.0010224398,0.00038672017,0.001362219,0.0011085497,0.0010215446,0.0014005116],"category_scores_gemma":[0.0045765354,0.00022519573,0.00056932506,0.000473904,0.00029671597,0.0012460029,0.0015054431,0.0009577163,0.00086081744],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015660807,0.0007540433,0.05585427,0.00048285336,0.00029290392,0.0016984754,0.00078766263,0.08463801,0.04216257,0.008517062,0.010431,0.792815],"study_design_scores_gemma":[0.00006451609,0.00032632975,0.005656008,0.000059418468,0.00012291907,0.00040775895,0.000155357,0.96944594,0.01302754,0.0061160787,0.00456843,0.00004974328],"about_ca_topic_score_codex":0.0026951763,"about_ca_topic_score_gemma":0.0026487114,"teacher_disagreement_score":0.0026951763,"about_ca_system_score_codex":0.0007520671,"about_ca_system_score_gemma":0.0012959735,"threshold_uncertainty_score":0.008214891},"labels":[],"label_agreement":null},{"id":"W4401831223","doi":"10.18280/ria.380413","title":"Intelligent Deep Learning System for Enhanced Pulmonary Disease Diagnosis Through Five-Class Mode","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mode (computer interface); Class (philosophy); Deep learning; Computer science; Artificial intelligence; Disease; Medicine; Human–computer interaction; Internal medicine","score_opus":0.1196188179616074,"score_gpt":0.43229987237212636,"score_spread":0.31268105441051897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401831223","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15241414,0.0028945373,0.78623676,0.0011046104,0.0005806976,0.00046482487,0.0032455036,0.045418933,0.0076399976],"genre_scores_gemma":[0.7469677,0.00087900535,0.2331602,0.00095083716,0.00013349882,0.00045336882,0.006064594,0.00022655205,0.011164312],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998036,0.000018908042,0.000019767213,0.00006809165,0.000050292547,0.000039281298],"domain_scores_gemma":[0.99980325,0.000041039584,0.000019151363,0.000024089002,0.000087587345,0.000024798788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050731126,0.0007476574,0.00067037,0.0007611836,0.00030683927,0.00055709714,0.0013160293,0.0007532843,0.0036302076],"category_scores_gemma":[0.00072581216,0.00029580732,0.0006574741,0.00030592442,0.0001536258,0.00071528426,0.0008454073,0.00089900295,0.001214332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007284121,0.00060707843,0.008420752,0.00024221232,0.00019019587,0.0005218044,0.00008429587,0.09825911,0.023922479,0.0024821933,0.029272005,0.8352694],"study_design_scores_gemma":[0.000037504014,0.000099201476,0.00093335746,0.000016294956,0.000031109656,0.00010753523,0.000008559343,0.98832184,0.0069130007,0.0010775548,0.002436432,0.000017479651],"about_ca_topic_score_codex":0.008806351,"about_ca_topic_score_gemma":0.010182093,"teacher_disagreement_score":0.008806351,"about_ca_system_score_codex":0.00095656636,"about_ca_system_score_gemma":0.0009959708,"threshold_uncertainty_score":0.017510176},"labels":[],"label_agreement":null},{"id":"W4401854925","doi":"10.1101/2024.08.23.24312060","title":"Health Data Nexus: An Open Data Platform for AI Research and Education in Medicine","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Centre for Addiction and Mental Health; Toronto Public Health; University of Toronto","funders":"","keywords":"Nexus (standard); Data science; Open data; Health data; Computer science; Political science; World Wide Web; Health care","score_opus":0.8339818708179229,"score_gpt":0.7162761550054962,"score_spread":0.11770571581242661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401854925","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017244844,0.0029704631,0.59593606,0.05182701,0.0033414047,0.0032064302,0.048794124,0.13076334,0.14591633],"genre_scores_gemma":[0.1671495,0.0031645617,0.6681185,0.011118937,0.0021894258,0.004025467,0.06555115,0.017260337,0.06142206],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99455523,0.0021954014,0.0005792404,0.00073747925,0.0015820094,0.00035057348],"domain_scores_gemma":[0.9810837,0.007365737,0.00093428924,0.0052336925,0.0016003557,0.0037822588],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.011681438,0.0005266452,0.0006031828,0.0022071062,0.001317257,0.0053439736,0.0026110339,0.0019083794,0.036509708],"category_scores_gemma":[0.02929103,0.00062084704,0.0007454903,0.001971389,0.0018921837,0.006962292,0.013277466,0.0030187673,0.016713455],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016270011,0.00041730364,0.0060096537,0.0011700217,0.00010892392,0.00085207657,0.0034469804,0.0050579845,0.007022194,0.32516685,0.3596304,0.28949058],"study_design_scores_gemma":[0.00021605179,0.00010594008,0.0019839865,0.00036730507,0.000015405953,0.0003117588,0.00035005235,0.008583746,0.0034665246,0.10036323,0.8841604,0.00007563878],"about_ca_topic_score_codex":0.0017579165,"about_ca_topic_score_gemma":0.0018880203,"teacher_disagreement_score":0.99738896,"about_ca_system_score_codex":0.00152679,"about_ca_system_score_gemma":0.0057227453,"threshold_uncertainty_score":0.12213719},"labels":[],"label_agreement":null},{"id":"W4401946092","doi":"10.3390/diagnostics14171894","title":"Cardiovascular Disease Risk Stratification Using Hybrid Deep Learning Paradigm: First of Its Kind on Canadian Trial Data","year":2024,"lang":"en","type":"article","venue":"Diagnostics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University; University of Toronto","funders":"National Cancer Institute","keywords":"Artificial intelligence; Deep learning; Random forest; Machine learning; Computer science; Medicine; Regression; Feature selection; Statistics; Mathematics","score_opus":0.25100846369389185,"score_gpt":0.451387958447192,"score_spread":0.20037949475330014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401946092","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9346247,0.006748631,0.013599641,0.0019533297,0.00027171447,0.0007916581,0.03628412,0.00038963917,0.005336545],"genre_scores_gemma":[0.94070935,0.0014025304,0.01366992,0.0006985749,0.00009931388,0.00035344434,0.039369494,0.00007942693,0.0036179929],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997959,0.0010027962,0.000106974105,0.0002962338,0.00044691685,0.00018807496],"domain_scores_gemma":[0.994114,0.0024170596,0.00037334752,0.0013056765,0.00139248,0.00039756816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006768927,0.0008829512,0.0014180872,0.00061666174,0.0006085829,0.00076104363,0.0013380209,0.0007779759,0.0022181652],"category_scores_gemma":[0.013783562,0.00027205655,0.0014271261,0.001100678,0.00045442028,0.00046814236,0.0008932188,0.0013264504,0.00054804474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.023108881,0.0019474702,0.61622864,0.0023989384,0.0064902985,0.0011235228,0.0003729189,0.041516613,0.003085255,0.0024534517,0.092808165,0.20846584],"study_design_scores_gemma":[0.00787525,0.00565277,0.54431576,0.0009064801,0.0077009895,0.0013065557,0.0006767845,0.3572601,0.006310455,0.0060849385,0.061395038,0.0005149191],"about_ca_topic_score_codex":0.23136055,"about_ca_topic_score_gemma":0.40260416,"teacher_disagreement_score":0.76863945,"about_ca_system_score_codex":0.0020102714,"about_ca_system_score_gemma":0.005576249,"threshold_uncertainty_score":0.46002775},"labels":[],"label_agreement":null},{"id":"W4402020858","doi":"10.1136/bmjhci-2023-100869","title":"Designing and validating a clinical decision support algorithm for diabetic nephroprotection in older patients","year":2024,"lang":"en","type":"article","venue":"BMJ Health & Care Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut national de psychiatrie légale Philippe-Pinel; University of Waterloo; McGill University; Hôpital Maisonneuve-Rosemont; University of Alberta; Université de Montréal","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Algorithm; Artificial intelligence","score_opus":0.13300475745092477,"score_gpt":0.5341393525221337,"score_spread":0.40113459507120897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402020858","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15043844,0.0030113438,0.7734469,0.016781798,0.000414839,0.03756882,0.0034784668,0.0027720432,0.012087308],"genre_scores_gemma":[0.08461558,0.00032234564,0.9082437,0.00074073445,0.000032545853,0.005074641,0.0007763557,0.000026103311,0.0001679347],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.91410726,0.06117132,0.015503161,0.003423142,0.004953965,0.00084112486],"domain_scores_gemma":[0.6753887,0.2730774,0.017419439,0.0067172623,0.0248834,0.0025137633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.093963034,0.0016454143,0.0016954925,0.0067618974,0.0018291441,0.0048811655,0.0027506563,0.003468755,0.006046676],"category_scores_gemma":[0.2667075,0.0011267365,0.003921035,0.0037246908,0.0014625445,0.0039388407,0.0042323833,0.0025627608,0.00097286556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028030265,0.0019518997,0.04821309,0.017815739,0.0023132411,0.00086450716,0.010575222,0.16471736,0.0032104184,0.023223227,0.020091072,0.7042213],"study_design_scores_gemma":[0.00563612,0.002947407,0.018834459,0.024548255,0.0044694385,0.0014805857,0.008657727,0.6914861,0.014683868,0.10636816,0.1200602,0.00082762516],"about_ca_topic_score_codex":0.002758677,"about_ca_topic_score_gemma":0.0031191467,"teacher_disagreement_score":0.093963034,"about_ca_system_score_codex":0.0040966147,"about_ca_system_score_gemma":0.014385323,"threshold_uncertainty_score":0.49692994},"labels":[],"label_agreement":null},{"id":"W4402126492","doi":"10.29375/01237047.4634","title":"The Use of Artificial Intelligence Techniques in Nursing Data Systems: Scoping Review","year":2024,"lang":"en","type":"article","venue":"Medunab","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Registered Nurses' Association of Ontario","funders":"Government of Ontario; Registered Nurses' Association of Ontario","keywords":"Computer science; Artificial intelligence; Data science; Health care; Adaptation (eye); Psychology","score_opus":0.5722884003930415,"score_gpt":0.6020597859951267,"score_spread":0.029771385602085143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402126492","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034757605,0.9959514,0.0006799023,0.0012126021,0.0004020242,0.00033049242,0.00011481972,0.0000098758965,0.00095115165],"genre_scores_gemma":[0.0041500805,0.99166095,0.0021128713,0.00062384864,0.00021546918,0.0008899568,0.00016113151,0.0000082141305,0.0001774749],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.96753377,0.012304382,0.011506341,0.0014420539,0.0066552395,0.0005581966],"domain_scores_gemma":[0.8175287,0.14859077,0.012781732,0.002429013,0.017934227,0.0007355852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031526115,0.001788673,0.0040681106,0.026110293,0.001873595,0.006802179,0.00256869,0.0047624786,0.0036245894],"category_scores_gemma":[0.14109258,0.0013310036,0.003936985,0.031158064,0.0027071175,0.0069004884,0.0033288999,0.0028543836,0.0007891204],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007534913,0.000047469104,0.0007007599,0.6953998,0.000767938,0.00020706422,0.0018537634,0.00057401456,0.00030456652,0.0049466207,0.009737113,0.2853855],"study_design_scores_gemma":[0.000016440452,0.000054531713,0.0008115309,0.93161243,0.0012489745,0.00022362499,0.00077796483,0.00018528171,0.00019750783,0.0019392909,0.06290196,0.000030496569],"about_ca_topic_score_codex":0.009772347,"about_ca_topic_score_gemma":0.013389379,"teacher_disagreement_score":0.031526115,"about_ca_system_score_codex":0.00681236,"about_ca_system_score_gemma":0.028422948,"threshold_uncertainty_score":0.16672802},"labels":[],"label_agreement":null},{"id":"W4402146335","doi":"10.47191/ijcsrr/v7-i9-01","title":"A Review of AI-powered Diagnosis of Rare Diseases","year":2024,"lang":"en","type":"review","venue":"International Journal of Current Science Research and Review","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadore College","funders":"","keywords":"Medicine","score_opus":0.5974570008315025,"score_gpt":0.7123102062755675,"score_spread":0.11485320544406497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402146335","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000054061908,0.9983398,0.0001740076,0.00040344626,0.00016019787,0.000009484808,0.000027987044,0.0000066765024,0.0008242781],"genre_scores_gemma":[0.00039264548,0.9986609,0.00029257053,0.00026429808,0.00016334926,0.000010575633,0.000031788488,0.0000014894083,0.00018231533],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99924755,0.00018810132,0.00017092538,0.00010173555,0.00025003147,0.000041717798],"domain_scores_gemma":[0.9965048,0.0025918526,0.00028435866,0.000057039848,0.00045976375,0.00010225233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016088455,0.00089507946,0.0016468265,0.004658938,0.00041187517,0.0014159159,0.0011669087,0.0016013904,0.006228274],"category_scores_gemma":[0.004779952,0.00037643217,0.0012331189,0.003946083,0.0005531563,0.0017564688,0.0009372392,0.0016407626,0.002225078],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055710927,0.000056107136,0.00024351665,0.06797742,0.00022416438,0.00020445057,0.000128524,0.00035490643,0.00043954176,0.0044913115,0.03177808,0.8940461],"study_design_scores_gemma":[0.0000199214,0.00009353197,0.0010224249,0.035744365,0.00036751985,0.00132068,0.00010237807,0.00012481738,0.00023306285,0.0026755494,0.95826316,0.000032607328],"about_ca_topic_score_codex":0.0020438342,"about_ca_topic_score_gemma":0.0029435067,"teacher_disagreement_score":0.006228274,"about_ca_system_score_codex":0.00093121175,"about_ca_system_score_gemma":0.0029156157,"threshold_uncertainty_score":0.020835638},"labels":[],"label_agreement":null},{"id":"W4402306697","doi":"10.18280/ts.410438","title":"Fetal Heart Abnormality Detection in Prior Stage Using LeNet 20 Deep Learning Architecture","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Abnormality; Stage (stratigraphy); Artificial intelligence; Fetus; Computer science; Fetal heart; Pattern recognition (psychology); Medicine; Biology; Pregnancy; Paleontology","score_opus":0.10218533726149477,"score_gpt":0.43031959842113277,"score_spread":0.328134261159638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402306697","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47170413,0.0027222706,0.49426475,0.0011106599,0.00039593678,0.00035881292,0.004056168,0.012316262,0.013071013],"genre_scores_gemma":[0.8392487,0.0009730255,0.13913055,0.0005333589,0.000057040786,0.0002055421,0.0079250755,0.0001669518,0.011759864],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99974185,0.000037473797,0.000022070462,0.000065973356,0.000079334604,0.000053257398],"domain_scores_gemma":[0.9996859,0.00008738902,0.00003864275,0.000035864276,0.0001230594,0.00002912899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064017606,0.0009008719,0.0004353325,0.0010632261,0.00022731304,0.0006649259,0.00087831396,0.00069237076,0.002484937],"category_scores_gemma":[0.001608278,0.00027060657,0.0005398876,0.0004259069,0.0001906804,0.0008303714,0.0007832817,0.0008232618,0.000942978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00096413505,0.0005989406,0.030225016,0.00023712045,0.00022826908,0.000939862,0.00013301746,0.22302906,0.030559812,0.002139678,0.016252408,0.6946926],"study_design_scores_gemma":[0.000015708567,0.00016702486,0.0037519718,0.00004383562,0.00003158954,0.0001947942,0.000032595628,0.9770371,0.015631033,0.0009324169,0.0021408177,0.00002114367],"about_ca_topic_score_codex":0.008531535,"about_ca_topic_score_gemma":0.012391549,"teacher_disagreement_score":0.008531535,"about_ca_system_score_codex":0.00077702117,"about_ca_system_score_gemma":0.0008346357,"threshold_uncertainty_score":0.01696378},"labels":[],"label_agreement":null},{"id":"W4402405698","doi":"10.23889/ijpds.v9i5.2759","title":"Automated Translation of Chronic Disease Diagnosis Codes using the ChatGPT Large Language Model","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Translation (biology); Computer science; Natural language processing; Artificial intelligence; Biology; Genetics","score_opus":0.31777447285582566,"score_gpt":0.5882422206241901,"score_spread":0.2704677477683644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402405698","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20015605,0.00063948275,0.6626164,0.0014490375,0.0010379117,0.0018063512,0.025112562,0.1004999,0.006682321],"genre_scores_gemma":[0.41466334,0.00029541893,0.5305506,0.00063277123,0.0001372094,0.0016690852,0.045236096,0.0015324233,0.005283128],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976336,0.0012201673,0.00018726723,0.0006124863,0.00023463902,0.00011180372],"domain_scores_gemma":[0.99216366,0.0052215876,0.00029730392,0.0007031193,0.0014334081,0.00018087337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031339522,0.0018954048,0.0007056762,0.001318744,0.00063076685,0.0013222458,0.0011819218,0.0009345257,0.007921028],"category_scores_gemma":[0.015383005,0.00056443067,0.0013100043,0.00079870934,0.0004278698,0.001733509,0.0020549763,0.0021910311,0.005652533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017532469,0.00092503213,0.021929579,0.0013399943,0.00027907616,0.0013207089,0.0022829869,0.07102502,0.025360614,0.005118908,0.10456129,0.76410353],"study_design_scores_gemma":[0.00027583257,0.0003100358,0.0059702895,0.00013239957,0.000094903844,0.00039795306,0.0005900983,0.9496842,0.015784843,0.008899302,0.01774312,0.00011698681],"about_ca_topic_score_codex":0.016793093,"about_ca_topic_score_gemma":0.017509615,"teacher_disagreement_score":0.016793093,"about_ca_system_score_codex":0.0015475501,"about_ca_system_score_gemma":0.0030406655,"threshold_uncertainty_score":0.0333907},"labels":[],"label_agreement":null},{"id":"W4402405709","doi":"10.23889/ijpds.v9i5.2755","title":"Roadmap for Linking Registry Data with Health Services Data to Support Evidence-Informed Decision-Making.","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Agency for Drugs and Technologies in Health","funders":"","keywords":"Business; Decision support system; Data science; Knowledge management; Process management; Computer science; Data mining","score_opus":0.5105961349505728,"score_gpt":0.6361266784025941,"score_spread":0.1255305434520213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402405709","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057994258,0.012457942,0.6909081,0.082230836,0.0043605096,0.044937782,0.06901306,0.01597782,0.07431447],"genre_scores_gemma":[0.012864545,0.0032493009,0.93583626,0.0020919896,0.00021203353,0.014270449,0.027639918,0.0006679944,0.003167472],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.90543795,0.054314565,0.013372752,0.005468355,0.017684354,0.003722109],"domain_scores_gemma":[0.64843905,0.13082664,0.020469295,0.043756757,0.14245082,0.014057503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1613084,0.0027800866,0.0022608184,0.022579959,0.0055513517,0.012126342,0.010187535,0.006526536,0.04346099],"category_scores_gemma":[0.25467548,0.0025504357,0.006008176,0.018375244,0.0029206977,0.011398205,0.020308787,0.0076315957,0.015985068],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038732195,0.00043791407,0.0067554396,0.014068171,0.00070891157,0.00060907216,0.0032029743,0.01063145,0.000862063,0.08642957,0.30168375,0.5742234],"study_design_scores_gemma":[0.0004122524,0.00028193608,0.0049809027,0.017703695,0.0005302454,0.00037524052,0.0026439338,0.01335501,0.0015475514,0.08353821,0.87430835,0.00032273508],"about_ca_topic_score_codex":0.06955827,"about_ca_topic_score_gemma":0.07027778,"teacher_disagreement_score":0.1613084,"about_ca_system_score_codex":0.014085821,"about_ca_system_score_gemma":0.12704696,"threshold_uncertainty_score":0.8530905},"labels":[],"label_agreement":null},{"id":"W4402406008","doi":"10.23889/ijpds.v9i5.2800","title":"Transparent reporting on multi-site studies about algorithms for linked health data: A systematic review of Health Data Research Network Canada’s Algorithms Inventory","year":2024,"lang":"en","type":"review","venue":"International Journal for Population Data Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Algorithm; Computer science; Data mining; Health data; Data science; Health care; Political science","score_opus":0.9185031121271087,"score_gpt":0.7259421849331035,"score_spread":0.1925609271940052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402406008","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009993068,0.88535964,0.023264898,0.026742995,0.0038410889,0.030917227,0.014396247,0.00035908972,0.0051257224],"genre_scores_gemma":[0.1796862,0.58979124,0.11405448,0.01615363,0.0011371499,0.087093085,0.010114494,0.00048725193,0.0014825205],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.27861372,0.31854692,0.25929534,0.016976899,0.12269323,0.0038739562],"domain_scores_gemma":[0.07416112,0.5347529,0.1386106,0.048104767,0.20149563,0.002875036],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.57927585,0.0025975099,0.0086447215,0.03604106,0.005907506,0.015893484,0.01056977,0.0046089008,0.0032465064],"category_scores_gemma":[0.83195037,0.0039296206,0.009150164,0.055308037,0.009877318,0.01039721,0.01027282,0.005310739,0.00055621425],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005707549,0.00004909287,0.014668088,0.78925437,0.0088215945,0.00017307044,0.009387305,0.0006090258,0.0004189224,0.005261356,0.0258171,0.14496931],"study_design_scores_gemma":[0.00049970014,0.000090761554,0.011255236,0.9161896,0.010488458,0.0001683861,0.0020017724,0.00056711526,0.00062048464,0.0016626414,0.056234486,0.00022136724],"about_ca_topic_score_codex":0.3237773,"about_ca_topic_score_gemma":0.42410433,"teacher_disagreement_score":0.9451476,"about_ca_system_score_codex":0.054852422,"about_ca_system_score_gemma":0.2667237,"threshold_uncertainty_score":0.64378536},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"systematic_review","genre":"review","about_ca_system":true,"about_ca_topic":true,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"reporting","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4402406124","doi":"10.23889/ijpds.v9i5.2677","title":"Cardiovascular disease surveillance using electronic medical records: a scoping study","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Alberta Health Services; Libin Cardiovascular Institute of Alberta; University of Calgary","funders":"","keywords":"Medical record; Disease; Health records; Medicine; Electronic medical record; Environmental health; Business; Medical emergency; Computer science; Data science; Internal medicine; Political science; Health care","score_opus":0.3164783667786538,"score_gpt":0.5857902917225579,"score_spread":0.2693119249439041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402406124","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008351034,0.97207415,0.0024806887,0.002140892,0.0004157794,0.00823243,0.003715783,0.000033981803,0.0025552139],"genre_scores_gemma":[0.052447677,0.9163855,0.00834777,0.0014721473,0.00028696872,0.017004339,0.0036162639,0.000025320638,0.0004140322],"study_design_codex":"systematic_review","study_design_gemma":"observational","domain_scores_codex":[0.9357538,0.02355696,0.029715013,0.0024342514,0.0075808377,0.0009590322],"domain_scores_gemma":[0.820057,0.12498526,0.026956474,0.0038811401,0.023196414,0.00092369085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07145111,0.0017950013,0.0055092634,0.04249966,0.001870028,0.006248145,0.002264628,0.0033441447,0.0059197163],"category_scores_gemma":[0.18434566,0.0015969488,0.0062811216,0.045820598,0.0016611353,0.0068042246,0.004530074,0.0015287721,0.0008868137],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020324855,0.000060925035,0.0065374123,0.89763856,0.0045297155,0.0003047689,0.0018699392,0.00024566238,0.00021297806,0.0013918037,0.003420854,0.083584145],"study_design_scores_gemma":[0.00007274893,0.00012158152,0.0051568006,0.9693049,0.008790696,0.0002189904,0.001018835,0.00012295852,0.00009606716,0.00043258246,0.014636274,0.000027604798],"about_ca_topic_score_codex":0.008224343,"about_ca_topic_score_gemma":0.018911114,"teacher_disagreement_score":0.07145111,"about_ca_system_score_codex":0.006001146,"about_ca_system_score_gemma":0.02470781,"threshold_uncertainty_score":0.37787414},"labels":[],"label_agreement":null},{"id":"W4402406507","doi":"10.23889/ijpds.v9i5.2849","title":"Identifying patterns of co-occurring chronic conditions preceding dementia: An unsupervised machine learning approach using health administrative data ","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute of Health Services and Policy Research; Regional Municipality of Waterloo; Sunnybrook Health Science Centre; University of Manitoba; Trillium Health Centre","funders":"","keywords":"Dementia; Unsupervised learning; Computer science; Artificial intelligence; Psychology; Machine learning; Data science; Medicine; Disease","score_opus":0.6244747597443215,"score_gpt":0.6384524637883252,"score_spread":0.01397770404400367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402406507","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.836719,0.000625086,0.15389578,0.0009078656,0.000034675653,0.00069857255,0.0051998184,0.0005079273,0.0014111554],"genre_scores_gemma":[0.8925588,0.00015186411,0.10145332,0.00009552005,0.000056241777,0.0004081555,0.0047410056,0.000025990052,0.00050905446],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971576,0.0014123641,0.00027197882,0.0006398923,0.00033810828,0.00018017279],"domain_scores_gemma":[0.9913914,0.0056036822,0.0014305711,0.0005777423,0.000809275,0.00018726804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038925407,0.0005659272,0.0008867752,0.0048920633,0.0008354397,0.0014543842,0.0013117772,0.0007256748,0.0007319207],"category_scores_gemma":[0.012989019,0.00040109275,0.0011057778,0.0028857272,0.00055085466,0.00067663175,0.0010143777,0.000860098,0.0002127232],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003423928,0.0007506173,0.8098713,0.00026376813,0.0009082085,0.00037107329,0.0007463295,0.061859913,0.0014830515,0.0015854927,0.0026984161,0.11911953],"study_design_scores_gemma":[0.00006141742,0.00013605328,0.28221393,0.00009194226,0.00014118635,0.0002718071,0.0005241168,0.7065114,0.00071889313,0.007680445,0.0015777978,0.00007099051],"about_ca_topic_score_codex":0.02751155,"about_ca_topic_score_gemma":0.036091406,"teacher_disagreement_score":0.02751155,"about_ca_system_score_codex":0.0014467163,"about_ca_system_score_gemma":0.0022885676,"threshold_uncertainty_score":0.05470282},"labels":[],"label_agreement":null},{"id":"W4402424046","doi":"10.23977/acss.2024.080515","title":"An Expert System for Health Diagnosis Based on Natural Language Processing and Reasoning Engine","year":2024,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Natural language processing; Expert system; Natural (archaeology); Artificial intelligence; History","score_opus":0.061473013783340406,"score_gpt":0.4710641335212584,"score_spread":0.409591119737918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402424046","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009000521,0.0008746847,0.9539259,0.0012049618,0.0002439731,0.0007295969,0.0013084228,0.01914384,0.013568179],"genre_scores_gemma":[0.0970562,0.00058668246,0.88859427,0.001265028,0.000093737865,0.00052657677,0.0019506676,0.00031463252,0.009612159],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989279,0.0002227361,0.00016665229,0.00028632465,0.00033298033,0.000063465915],"domain_scores_gemma":[0.9980615,0.0010491012,0.000088869616,0.00015277801,0.00057352765,0.00007423302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021453889,0.00066693075,0.0009088036,0.0013189581,0.0006936554,0.0016193512,0.0016260536,0.0016011815,0.009078828],"category_scores_gemma":[0.005004497,0.00039154018,0.00077043707,0.00070798566,0.00043086667,0.0016735371,0.00081444974,0.0011704642,0.0034101626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009835602,0.0007026987,0.0034129312,0.0016545207,0.0002925723,0.002797405,0.0008304507,0.03780531,0.054370333,0.053016238,0.079349056,0.76478493],"study_design_scores_gemma":[0.0007683835,0.0003615431,0.0028367972,0.00036699482,0.00052349054,0.0033959688,0.00022290804,0.71006256,0.043335784,0.06751688,0.17039269,0.00021597714],"about_ca_topic_score_codex":0.0050355834,"about_ca_topic_score_gemma":0.0053054867,"teacher_disagreement_score":0.009078828,"about_ca_system_score_codex":0.0008028525,"about_ca_system_score_gemma":0.0023568885,"threshold_uncertainty_score":0.030371726},"labels":[],"label_agreement":null},{"id":"W4402475035","doi":"10.1109/ccece59415.2024.10667100","title":"Efficient Machine Learning Model Deployment in Clinical Decision Support Systems","year":2024,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Langara College","funders":"","keywords":"Software deployment; Computer science; Decision support system; Decision model; Artificial intelligence; Clinical decision support system; Machine learning; Software engineering","score_opus":0.2662688734158786,"score_gpt":0.5582197893743303,"score_spread":0.29195091595845163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402475035","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06593693,0.00084543455,0.92066705,0.0016273627,0.00020311338,0.00032197346,0.00047565313,0.0068374323,0.0030850526],"genre_scores_gemma":[0.75610274,0.0005089721,0.23962346,0.00032327994,0.00011679727,0.00032867538,0.0011026075,0.00017625203,0.001717346],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981996,0.00087944773,0.00015818099,0.00025252142,0.00034121572,0.00016913713],"domain_scores_gemma":[0.9971654,0.0014958006,0.00012996262,0.00041025548,0.00066532067,0.0001333502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029500227,0.00075470086,0.0009794818,0.00077556574,0.00050399714,0.0018291753,0.0013066069,0.0010852133,0.003142446],"category_scores_gemma":[0.011386369,0.00062332174,0.0005416302,0.00084086374,0.00033611958,0.0021132918,0.0016978728,0.0013922421,0.0021726876],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007690161,0.00037484284,0.006145694,0.000193527,0.00011698958,0.0004727724,0.00023388199,0.58102477,0.0059869452,0.007920668,0.009669325,0.3870916],"study_design_scores_gemma":[0.000018158335,0.00004562393,0.00023031086,0.00001081425,0.000006013575,0.000028437737,0.000031931508,0.9941094,0.0013564394,0.002849154,0.0013081235,0.0000056658273],"about_ca_topic_score_codex":0.005425675,"about_ca_topic_score_gemma":0.0030893,"teacher_disagreement_score":0.005425675,"about_ca_system_score_codex":0.00089426915,"about_ca_system_score_gemma":0.001701154,"threshold_uncertainty_score":0.015601397},"labels":[],"label_agreement":null},{"id":"W4402571491","doi":"10.1109/snpd61259.2024.10673905","title":"Cloud-Enabled Blood Bank Management for an Efficient Healthcare System","year":2024,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Algoma University; Lakehead University","funders":"","keywords":"Cloud computing; Health care; Computer science; Blood bank; Business; Medical emergency; Medicine; Operating system; Political science","score_opus":0.15220393133855223,"score_gpt":0.47902890964625755,"score_spread":0.3268249783077053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402571491","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09163919,0.007111442,0.7684443,0.03349343,0.0041267998,0.0021397562,0.0036935918,0.035179913,0.0541715],"genre_scores_gemma":[0.71169615,0.0027046755,0.261656,0.005167576,0.0012612569,0.00040860282,0.0034880245,0.00074984744,0.012867881],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980306,0.00034290535,0.0002186086,0.0003661117,0.00060881616,0.00043304323],"domain_scores_gemma":[0.9965228,0.00041880994,0.00029362366,0.0007009951,0.0011236011,0.0009401819],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002301033,0.00043783057,0.0006754777,0.0007688789,0.0017321751,0.0039290385,0.0023275975,0.001126554,0.00647186],"category_scores_gemma":[0.003886455,0.00040450945,0.0005618101,0.0012527322,0.00047497515,0.003133726,0.003692346,0.0014277548,0.0033341013],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018303003,0.0011059598,0.020393059,0.0008114364,0.00027631203,0.0026741447,0.00095624075,0.04113512,0.031205548,0.0785388,0.38503227,0.43604082],"study_design_scores_gemma":[0.00032673404,0.00022833142,0.007639329,0.00029497518,0.00012676783,0.0010295198,0.000813134,0.64375913,0.017851891,0.050126098,0.2776346,0.0001695041],"about_ca_topic_score_codex":0.007358396,"about_ca_topic_score_gemma":0.0064730844,"teacher_disagreement_score":0.007358396,"about_ca_system_score_codex":0.0017068613,"about_ca_system_score_gemma":0.004650413,"threshold_uncertainty_score":0.021650553},"labels":[],"label_agreement":null},{"id":"W4402580791","doi":"10.1007/s10278-024-01258-9","title":"Automated ASPECTS Segmentation and Scoring Tool: a Method Tailored for a Colombian Telestroke Network","year":2024,"lang":"en","type":"article","venue":"Journal of Imaging Informatics in Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Universidad de los Andes; Ministerio de Ciencia, Tecnología e Innovación Productiva; Ministerio de Ciencia, Tecnología e Innovación","keywords":"Segmentation; Computer science; Artificial intelligence; Medicine; Cartography; Data science; Geography","score_opus":0.08696447620957938,"score_gpt":0.5065071262144344,"score_spread":0.419542650004855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402580791","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5254165,0.00036514437,0.45217022,0.00026234804,0.000120626246,0.0019512466,0.003441266,0.008907074,0.0073655965],"genre_scores_gemma":[0.6385039,0.00015539535,0.35358655,0.00009809752,0.00006650656,0.0012510112,0.0034945807,0.00048045514,0.0023635235],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99862206,0.0003804922,0.00016851317,0.0003761124,0.00037721466,0.00007554747],"domain_scores_gemma":[0.99821067,0.00043178018,0.00019782728,0.00025032528,0.0007965668,0.00011288382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020025375,0.00081518653,0.0004941756,0.0038004266,0.00041228236,0.0009340068,0.0007578102,0.0005707102,0.0034280755],"category_scores_gemma":[0.0073060836,0.0002812827,0.00039295998,0.0013059785,0.0002746764,0.00055066386,0.0009027236,0.00029694632,0.0011578287],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081762916,0.00037074348,0.24310425,0.00028463925,0.00022775028,0.00072988315,0.00059963786,0.026606182,0.029497176,0.0011156932,0.008202896,0.6884436],"study_design_scores_gemma":[0.0002825815,0.0009645163,0.3822638,0.00017613287,0.00030440057,0.003913234,0.00088088197,0.560707,0.029947363,0.0020892029,0.018186664,0.00028417248],"about_ca_topic_score_codex":0.009391291,"about_ca_topic_score_gemma":0.015452653,"teacher_disagreement_score":0.009391291,"about_ca_system_score_codex":0.0006604213,"about_ca_system_score_gemma":0.0010304796,"threshold_uncertainty_score":0.018673241},"labels":[],"label_agreement":null},{"id":"W4402609881","doi":"10.1097/01.hjh.0001063496.16640.61","title":"P156 HYPERTENSIVES USERS OF A HEALTH WEB PORTAL","year":2024,"lang":"en","type":"article","venue":"Journal of Hypertension","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke; Université du Québec à Trois-Rivières","funders":"","keywords":"Medicine; Patient portal; World Wide Web; Health care","score_opus":0.23307673490487363,"score_gpt":0.4601806480027354,"score_spread":0.22710391309786176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402609881","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98569703,0.00042388652,0.00015961901,0.001061039,0.000060625756,0.000108924745,0.0010058788,0.00003941259,0.011443546],"genre_scores_gemma":[0.99223024,0.00048185696,0.000301932,0.00076379447,0.00007519675,0.000117065116,0.00037607347,0.000008514162,0.0056452677],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99950695,0.000116039504,0.000045160385,0.0000491494,0.00016642956,0.00011623199],"domain_scores_gemma":[0.99822265,0.0004801632,0.00056843297,0.000055316617,0.00016386755,0.0005094992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005039568,0.000110980225,0.00021660456,0.00044422873,0.00076685747,0.0009259348,0.00020185635,0.00042462384,0.036196325],"category_scores_gemma":[0.0030712178,0.00016395815,0.0002991742,0.00045024412,0.00021017868,0.0006119611,0.00067953585,0.00046977046,0.0037211461],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004453743,0.00088180415,0.9178645,0.00037650275,0.00004435912,0.0015545803,0.004796104,0.000021151727,0.0013935892,0.00021838656,0.008936808,0.06346676],"study_design_scores_gemma":[0.000049913124,0.00067422574,0.98029846,0.00020942847,0.00004419625,0.0025152168,0.006544256,0.00015506778,0.0002424314,0.00011791557,0.00913181,0.000017057624],"about_ca_topic_score_codex":0.0054544793,"about_ca_topic_score_gemma":0.0069170683,"teacher_disagreement_score":0.036196325,"about_ca_system_score_codex":0.000354815,"about_ca_system_score_gemma":0.00079920347,"threshold_uncertainty_score":0.12108874},"labels":[],"label_agreement":null},{"id":"W4402620424","doi":"10.1038/s41564-024-01815-6","title":"Lessons from a data scientist during COVID-19","year":2024,"lang":"en","type":"article","venue":"Nature Microbiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Public Health Agency of Canada","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Virology; Computational biology; Biology; Medicine; Internal medicine; Infectious disease (medical specialty); Outbreak","score_opus":0.20099241614028227,"score_gpt":0.5557541714054769,"score_spread":0.3547617552651946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402620424","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035957184,0.002083309,0.006040742,0.96960753,0.008980728,0.0000283139,0.000089113906,0.00010168115,0.009472797],"genre_scores_gemma":[0.20334597,0.0053152326,0.025673993,0.70837915,0.013564529,0.00019313558,0.00038195946,0.0008598187,0.04228627],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9374377,0.03389653,0.0033601501,0.0066197375,0.013857311,0.0048286295],"domain_scores_gemma":[0.6646638,0.177858,0.0049220077,0.020235982,0.07730592,0.05501428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1424508,0.0007784969,0.0010059979,0.0028284383,0.014764918,0.029066052,0.0043784226,0.021384818,0.007974701],"category_scores_gemma":[0.26103532,0.0012477546,0.001349798,0.0023183455,0.023875,0.032813877,0.015170414,0.04882298,0.0032947673],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002676499,0.00027674754,0.0059197,0.00026007622,0.00008060306,0.00157699,0.028398842,0.0007854708,0.0005784023,0.23489177,0.62509626,0.10186748],"study_design_scores_gemma":[0.00008620428,0.00009475503,0.00075235876,0.0006631661,0.000018951185,0.0005864044,0.013234893,0.0011994286,0.0008026679,0.11837713,0.8640686,0.00011544752],"about_ca_topic_score_codex":0.01982923,"about_ca_topic_score_gemma":0.017531613,"teacher_disagreement_score":0.1424508,"about_ca_system_score_codex":0.016484518,"about_ca_system_score_gemma":0.03716771,"threshold_uncertainty_score":0.7533608},"labels":[],"label_agreement":null},{"id":"W4402674311","doi":"10.1109/seai62072.2024.10674494","title":"Wound Semantic Segmentation Framework with Encoder-Decoder Architecture","year":2024,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Encoder; Architecture; Segmentation; Artificial intelligence; Image segmentation","score_opus":0.09408809454017884,"score_gpt":0.47578968268897737,"score_spread":0.3817015881487985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402674311","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006381535,0.00075786724,0.9795432,0.0003755697,0.0001215081,0.00017535906,0.00076862157,0.008866401,0.003010073],"genre_scores_gemma":[0.22576804,0.0008077397,0.75726914,0.0006257344,0.00010898612,0.0003380932,0.0044168863,0.0006791654,0.009986242],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999582,0.00007266344,0.0000313026,0.00013023235,0.00012718422,0.00005662895],"domain_scores_gemma":[0.99971026,0.00006339284,0.00001842653,0.000055424473,0.00012341888,0.000028943836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085523666,0.001034834,0.00075846654,0.0011767178,0.00041564295,0.0010961655,0.0015290013,0.001615126,0.005239142],"category_scores_gemma":[0.0013536427,0.0003446775,0.0009799877,0.0006967753,0.00046552427,0.0013589335,0.0012426404,0.0013162192,0.002677915],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065062323,0.00039886739,0.0021207186,0.00044689034,0.00018960834,0.00053664675,0.00017836361,0.11498939,0.036649104,0.039397873,0.03203481,0.77240705],"study_design_scores_gemma":[0.000042377425,0.00016765889,0.00048018058,0.000034972934,0.000088864224,0.00036514472,0.000054729648,0.9331126,0.027471496,0.019627707,0.018517178,0.00003711594],"about_ca_topic_score_codex":0.0100372955,"about_ca_topic_score_gemma":0.01754133,"teacher_disagreement_score":0.0100372955,"about_ca_system_score_codex":0.00080780685,"about_ca_system_score_gemma":0.0024003205,"threshold_uncertainty_score":0.01995778},"labels":[],"label_agreement":null},{"id":"W4402809248","doi":"10.1109/tcss.2024.3449748","title":"Advances in Artificial Intelligence and Blockchain Technologies for Early Detection of Human Diseases","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Computational Social Systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Blockchain; Computer science; Artificial intelligence; Computer security; Data science","score_opus":0.10447575288551383,"score_gpt":0.4437751951281108,"score_spread":0.339299442242597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402809248","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033080608,0.07959385,0.79865474,0.027209477,0.0015646332,0.00037949914,0.0016508384,0.0015572275,0.056309115],"genre_scores_gemma":[0.6122695,0.09022616,0.276084,0.003554074,0.0027910736,0.0005112354,0.0018747732,0.00013642704,0.01255269],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969112,0.0012917552,0.00023131618,0.0004871011,0.00094848225,0.00013026287],"domain_scores_gemma":[0.98778194,0.008570841,0.0010598205,0.0011321037,0.0012343075,0.00022107323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004578604,0.0007326514,0.00079076365,0.0029117547,0.0004998856,0.0025202455,0.0011375161,0.0015918132,0.005678961],"category_scores_gemma":[0.012155664,0.00033805016,0.00071513397,0.0024659564,0.0015157784,0.0053452025,0.002077134,0.0019742646,0.0017208642],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020380697,0.00020889315,0.011212362,0.0017517696,0.0001719856,0.0003147777,0.00039451558,0.030435976,0.0052566873,0.27664068,0.01847471,0.65493387],"study_design_scores_gemma":[0.0000822209,0.00031477728,0.0047599897,0.0013059343,0.00015867063,0.0009347157,0.0002685742,0.21154363,0.008362763,0.6011012,0.17103736,0.0001301114],"about_ca_topic_score_codex":0.0013153314,"about_ca_topic_score_gemma":0.0012919571,"teacher_disagreement_score":0.005678961,"about_ca_system_score_codex":0.0011199868,"about_ca_system_score_gemma":0.0017632222,"threshold_uncertainty_score":0.024214268},"labels":[],"label_agreement":null},{"id":"W4402812859","doi":"10.1201/9781003476207-6","title":"Uncovering Machine Learning Trends in Biomedical","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Data science","score_opus":0.15852225254560884,"score_gpt":0.4745987155469646,"score_spread":0.3160764630013557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402812859","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12764557,0.48824793,0.09381711,0.069087826,0.004609912,0.0001903113,0.007418253,0.0017899818,0.20719318],"genre_scores_gemma":[0.46840632,0.35212255,0.08914074,0.008024655,0.005349467,0.00022266414,0.008535609,0.00045944587,0.06773857],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9993414,0.00012637905,0.000054071683,0.000121391706,0.00031291382,0.00004376082],"domain_scores_gemma":[0.9949033,0.003495749,0.0005119064,0.00025940992,0.00071985304,0.00010988214],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.0017442044,0.00036903124,0.00043763695,0.0071021924,0.000436955,0.004001281,0.0007270641,0.0010171952,0.006635387],"category_scores_gemma":[0.008352705,0.0002312704,0.00041721773,0.010843271,0.00083722523,0.004714524,0.0007956556,0.0014479506,0.0024418752],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006870762,0.000072811505,0.01922494,0.0031535653,0.000105727755,0.0005582559,0.0017825079,0.0031231109,0.0025493978,0.13486148,0.0741892,0.76031023],"study_design_scores_gemma":[0.000017390425,0.00014241833,0.05386374,0.0036174606,0.00012764118,0.0020928022,0.0026700867,0.034537647,0.0037376396,0.203297,0.6958089,0.00008728678],"about_ca_topic_score_codex":0.0017989393,"about_ca_topic_score_gemma":0.0034953775,"teacher_disagreement_score":0.9982558,"about_ca_system_score_codex":0.0014475666,"about_ca_system_score_gemma":0.0013056906,"threshold_uncertainty_score":0.022197604},"labels":[],"label_agreement":null},{"id":"W4402907175","doi":"10.1016/j.ijrobp.2024.07.1343","title":"Validation of Multi-Modal Artificial Intelligence Biomarker for Predicting Biochemical Recurrence in Patients with Prostate Cancer Undergoing Prostatectomy","year":2024,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital; University Health Network; Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Prostate cancer; Prostatectomy; Medicine; Biomarker; Biochemical recurrence; Oncology; Internal medicine; Urology; Cancer; Biology","score_opus":0.09182825772670788,"score_gpt":0.4614976904140786,"score_spread":0.36966943268737074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402907175","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99440044,0.00053987856,0.0035282655,0.0001504151,0.00004330439,0.000042697222,0.0005170756,0.000050092363,0.0007277953],"genre_scores_gemma":[0.99738795,0.0001035758,0.0017958536,0.000048644877,0.000021605763,0.000027107453,0.0004167697,0.0000029043179,0.00019558954],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993364,0.00020827678,0.00008056417,0.00013291935,0.00016090636,0.000080891135],"domain_scores_gemma":[0.99864095,0.0004981185,0.00029150554,0.00008804724,0.0003901854,0.000091120506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015865518,0.00037115908,0.000508707,0.0010913496,0.0002946617,0.0011418582,0.00041875974,0.0007083714,0.0008715123],"category_scores_gemma":[0.0046352455,0.00016352425,0.0005754585,0.0005633332,0.00021751372,0.00046335204,0.0005902374,0.00046235116,0.00024097902],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008172676,0.00041339558,0.93529993,0.00009539288,0.00035263892,0.0001321002,0.00017030939,0.0045408257,0.008288274,0.00016776464,0.00068319,0.049039084],"study_design_scores_gemma":[0.000071983,0.0018806211,0.8594673,0.0000844286,0.00076271506,0.00097536366,0.0006296109,0.122942805,0.010034864,0.0009797574,0.002088549,0.00008189745],"about_ca_topic_score_codex":0.0012948157,"about_ca_topic_score_gemma":0.0016925691,"teacher_disagreement_score":0.0015865518,"about_ca_system_score_codex":0.00022370006,"about_ca_system_score_gemma":0.0004332499,"threshold_uncertainty_score":0.008390605},"labels":[],"label_agreement":null},{"id":"W4402947505","doi":"10.18280/mmep.110916","title":"An Application of Traditional and Ensemble Machine Learning Approaches to Redefine Thyroid Disorder Diagnosis","year":2024,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Thyroid disorder; Ensemble learning; Artificial intelligence; Thyroid; Computer science; Machine learning; Medicine; Endocrinology","score_opus":0.22436773243250277,"score_gpt":0.34729132251979083,"score_spread":0.12292359008728806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402947505","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12549265,0.0032416251,0.86494887,0.001033096,0.00023300624,0.00017444005,0.0003042106,0.00069502305,0.003877174],"genre_scores_gemma":[0.55538696,0.0011015321,0.44167522,0.00021176453,0.00017017087,0.000089656394,0.00030066076,0.000048230115,0.0010158466],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971558,0.0010816947,0.00021186304,0.00052337104,0.0008560391,0.00017137894],"domain_scores_gemma":[0.993508,0.003548397,0.00056253205,0.00061587285,0.001598018,0.00016711131],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005835157,0.00068969734,0.0009407668,0.002790002,0.0005971028,0.0013620303,0.0009981062,0.0008882178,0.00092557],"category_scores_gemma":[0.014367818,0.0002869843,0.0010473422,0.0015465438,0.00035590027,0.0014060797,0.0012059732,0.00092179765,0.00025745502],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035524878,0.00022127383,0.04899153,0.00023309805,0.00059572683,0.00031975727,0.00043532942,0.14265192,0.004175549,0.0049611274,0.0022195408,0.79483986],"study_design_scores_gemma":[0.000039116792,0.00038021323,0.016601149,0.00012471569,0.00031647325,0.0007570975,0.00023364222,0.95732814,0.00615065,0.013795696,0.004195311,0.000077784054],"about_ca_topic_score_codex":0.0031419084,"about_ca_topic_score_gemma":0.006304385,"teacher_disagreement_score":0.005835157,"about_ca_system_score_codex":0.00067220774,"about_ca_system_score_gemma":0.0010460065,"threshold_uncertainty_score":0.03085965},"labels":[],"label_agreement":null},{"id":"W4402951689","doi":"10.18280/mmep.110911","title":"Multiclass Logistic Regression Classification with PCA for Imbalanced Medical Datasets","year":2024,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Logistic regression; Multiclass classification; Artificial intelligence; Logistic model tree; Computer science; Pattern recognition (psychology); Statistics; Machine learning; Support vector machine; Mathematics","score_opus":0.22037337400442764,"score_gpt":0.4347770850511091,"score_spread":0.2144037110466815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402951689","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34953216,0.0043667816,0.62329686,0.003781353,0.0011157726,0.00046472973,0.007374965,0.0064974353,0.0035698833],"genre_scores_gemma":[0.83397263,0.0009754697,0.15038529,0.0002553324,0.00065657415,0.0004632732,0.009149391,0.0002319433,0.0039100475],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959996,0.001548872,0.0003266653,0.00071720843,0.00097093655,0.0004367163],"domain_scores_gemma":[0.99506384,0.002273126,0.00043421413,0.0012854988,0.0007880987,0.0001551632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055064196,0.0012134226,0.0014039335,0.0021604688,0.0007251892,0.002009772,0.0012961519,0.0009842991,0.0018105642],"category_scores_gemma":[0.018213924,0.00032841985,0.0015782124,0.0029418685,0.00051608135,0.0014013468,0.0017929672,0.0020316474,0.0013524629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001749238,0.0010442567,0.026970496,0.00047616145,0.00053806865,0.0004065956,0.0003411886,0.06379633,0.0073815584,0.0037143133,0.03081627,0.86276543],"study_design_scores_gemma":[0.00008971078,0.00030293016,0.017887402,0.00006856601,0.00016164534,0.00044487312,0.00023756656,0.9585862,0.0054387595,0.010308828,0.0064183855,0.000055119985],"about_ca_topic_score_codex":0.0030531469,"about_ca_topic_score_gemma":0.0030715056,"teacher_disagreement_score":0.0055064196,"about_ca_system_score_codex":0.0005385667,"about_ca_system_score_gemma":0.0016785996,"threshold_uncertainty_score":0.0291211},"labels":[],"label_agreement":null},{"id":"W4402956148","doi":"10.5376/bm.2024.15.0014","title":"Development of AI-Based Diagnostic Systems for Hypertensive Heart Disease","year":2024,"lang":"en","type":"article","venue":"Bioscience Methods","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Disease; Cardiology; Internal medicine; Computer science","score_opus":0.3637384486169956,"score_gpt":0.5965465518661779,"score_spread":0.23280810324918227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402956148","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028570592,0.0053006997,0.92525244,0.008412624,0.0010805237,0.0007129461,0.0010269831,0.00773426,0.021908883],"genre_scores_gemma":[0.33381048,0.0035753143,0.65238434,0.0024652618,0.00059957185,0.0004944004,0.0010985208,0.00020513961,0.005367006],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983134,0.00058723695,0.00017867483,0.00030588818,0.0005376398,0.00007718841],"domain_scores_gemma":[0.99289036,0.0032473244,0.00047520848,0.0006856197,0.0024035142,0.00029787375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004069823,0.00058478786,0.00051179156,0.0019532468,0.00055529625,0.0024699394,0.0014820062,0.001065018,0.0042307274],"category_scores_gemma":[0.015369772,0.0003683134,0.0005771792,0.00083189714,0.00063907326,0.0017145755,0.0017324266,0.0013316148,0.0022858593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036372512,0.0003116094,0.016162632,0.00083692,0.00024120198,0.00038561574,0.0007111266,0.018540774,0.015362613,0.03746329,0.01888627,0.8907342],"study_design_scores_gemma":[0.00022854422,0.00067428354,0.017479923,0.0011021347,0.00042861237,0.0012087844,0.0007945567,0.6908594,0.04561065,0.093623005,0.14778522,0.00020493606],"about_ca_topic_score_codex":0.0031680593,"about_ca_topic_score_gemma":0.0028231174,"teacher_disagreement_score":0.0042307274,"about_ca_system_score_codex":0.0011615936,"about_ca_system_score_gemma":0.0024897463,"threshold_uncertainty_score":0.021523535},"labels":[],"label_agreement":null},{"id":"W4402987528","doi":"10.1200/op.2024.20.10_suppl.409","title":"Impact of applying machine learning to the electronic medical record on prediction of cancer-associated thrombosis.","year":2024,"lang":"en","type":"article","venue":"JCO Oncology Practice","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University of Toronto; Princess Margaret Cancer Centre; Health Sciences Centre; University Health Network","funders":"Princess Margaret Cancer Foundation; TD Bank","keywords":"Thrombosis; Cancer; Electronic medical record; Medical record; Machine learning; Artificial intelligence; Computer science; Medicine; Medical emergency; Internal medicine","score_opus":0.15873656898952337,"score_gpt":0.5772817834033115,"score_spread":0.4185452144137881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402987528","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9561892,0.0030509045,0.024258222,0.0039514843,0.00034560647,0.00027913507,0.0072203716,0.00259725,0.0021078754],"genre_scores_gemma":[0.9752898,0.0002716892,0.017973773,0.0003983489,0.00014220807,0.000053983305,0.005473254,0.000027808319,0.00036915406],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99464536,0.002806034,0.00066821685,0.0011583968,0.000562134,0.00015988063],"domain_scores_gemma":[0.94747746,0.043167155,0.003753467,0.0018821438,0.0030389978,0.0006807967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010584576,0.00074903877,0.00063565996,0.0025987679,0.00039425865,0.0016794365,0.00071060535,0.0010086487,0.00069191895],"category_scores_gemma":[0.042941578,0.0003431758,0.0010759456,0.0011505837,0.00030381163,0.0014638995,0.001009647,0.0012610459,0.00056479016],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010433536,0.0006826573,0.7580826,0.00030686564,0.00072725577,0.0002274498,0.00019701454,0.077927515,0.0013919947,0.00018586745,0.0047099465,0.15451752],"study_design_scores_gemma":[0.00005826466,0.00063864526,0.095178425,0.000116450174,0.00019132545,0.00023067428,0.00010480101,0.89918995,0.0018207447,0.00079137797,0.0016315635,0.00004777547],"about_ca_topic_score_codex":0.01619822,"about_ca_topic_score_gemma":0.015995346,"teacher_disagreement_score":0.01619822,"about_ca_system_score_codex":0.0014597289,"about_ca_system_score_gemma":0.0012566198,"threshold_uncertainty_score":0.055977285},"labels":[],"label_agreement":null},{"id":"W4403060086","doi":"10.1109/jbhi.2024.3472462","title":"Longitudinal Alzheimer's Disease Progression Prediction With Modality Uncertainty and Optimization of Information Flow","year":2024,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Chonnam National University Hwasun Hospital; Ministry of Science and ICT, South Korea; H. Lundbeck A/S; Servier; Iran Telecommunication Research Center; Eisai; Meso Scale Diagnostics; National Research Foundation of Korea; National Institutes of Health; Mike and Josie Harper Cancer Research Institute; Northern California Institute for Research and Education; National Research Foundation; IXICO; Takeda Pharmaceutical Company; Institute for Information and Communications Technology Promotion; Pfizer; Biogen; BioClinica; Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; GE Healthcare; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; Alzheimer's Drug Discovery Foundation; Genentech; Chonnam National University; Alzheimer's Association","keywords":"Computer science; Information flow; Modality (human–computer interaction); Disease; Flow (mathematics); Artificial intelligence; Medicine; Internal medicine; Mathematics","score_opus":0.10153297816030145,"score_gpt":0.44085192012587493,"score_spread":0.3393189419655735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403060086","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24473166,0.0017402238,0.74914557,0.0014172301,0.000071824674,0.00007674552,0.0005132371,0.0008523204,0.0014511958],"genre_scores_gemma":[0.9587113,0.00033767975,0.039031643,0.00017167028,0.00005928943,0.0000770984,0.0002975833,0.000034422384,0.0012792066],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999613,0.00011463022,0.000022716304,0.00014190814,0.000046735862,0.00006104668],"domain_scores_gemma":[0.99867743,0.00091311306,0.00014391654,0.0000647646,0.00013899205,0.000061793566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001889802,0.0007814019,0.0010617989,0.0007433783,0.00037465416,0.0009138589,0.0009863696,0.0011051418,0.0006689449],"category_scores_gemma":[0.0039902176,0.00044247444,0.0009837301,0.0005726227,0.0005543362,0.0014171373,0.0007900478,0.0014428872,0.00015026765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002479492,0.00012631259,0.004997392,0.000043909156,0.00007743811,0.00011523718,0.00009613471,0.9228872,0.001967203,0.0025665474,0.0010098923,0.0658648],"study_design_scores_gemma":[0.0000032990718,0.000019501193,0.00027542707,0.0000028387694,0.000009289574,0.000009753028,0.0000031501195,0.9979886,0.00021898626,0.0013943908,0.000070718925,0.0000040597083],"about_ca_topic_score_codex":0.011812747,"about_ca_topic_score_gemma":0.009248017,"teacher_disagreement_score":0.011812747,"about_ca_system_score_codex":0.0010385988,"about_ca_system_score_gemma":0.0012029043,"threshold_uncertainty_score":0.023487985},"labels":[],"label_agreement":null},{"id":"W4403119080","doi":"10.1101/2024.10.02.24314019","title":"LMP-TX: An AI-driven Integrated Longitudinal Multi-modal Platform for Early Prognosis of Late Onset Alzheimer’s Disease","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; Canadian Institutes of Health Research; National Institutes of Health; University of Pittsburgh; Alzheimer's Disease Neuroimaging Initiative; Alzheimer's Association; Northern California Institute for Research and Education; Foundation for the National Institutes of Health","keywords":"Modal; Disease; Medicine; Internal medicine; Materials science; Composite material","score_opus":0.3168225656179809,"score_gpt":0.5015951311185594,"score_spread":0.18477256550057847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403119080","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13132922,0.0011173032,0.820228,0.0008416348,0.00028841483,0.000442377,0.00487663,0.037630554,0.0032458606],"genre_scores_gemma":[0.8307557,0.00036817108,0.16171543,0.00038859178,0.000116137664,0.00033415813,0.0041205296,0.00024489884,0.001956349],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997181,0.000061020797,0.000021415046,0.000092039496,0.00007847819,0.000028861263],"domain_scores_gemma":[0.9995073,0.00015017435,0.00007535191,0.00008170859,0.00012007063,0.00006538494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010817169,0.0006955297,0.00047489052,0.0006718241,0.00014993631,0.0007017677,0.0009958213,0.00050403294,0.0020215213],"category_scores_gemma":[0.002155813,0.00019544254,0.00045952442,0.00033554668,0.00016529823,0.00079473224,0.001066426,0.00060470274,0.0009066214],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004400189,0.0009135137,0.04399134,0.0005368319,0.0006603951,0.0014311421,0.00032129243,0.19064279,0.0653425,0.0069077197,0.028062543,0.6567897],"study_design_scores_gemma":[0.0000682142,0.00024328078,0.0036684524,0.000014337936,0.000051628707,0.00014433634,0.000027011074,0.98145974,0.0070764357,0.004632492,0.0025858004,0.000028279408],"about_ca_topic_score_codex":0.0019687384,"about_ca_topic_score_gemma":0.0015385579,"teacher_disagreement_score":0.0020215213,"about_ca_system_score_codex":0.00035859147,"about_ca_system_score_gemma":0.0005582923,"threshold_uncertainty_score":0.0067626834},"labels":[],"label_agreement":null},{"id":"W4403289769","doi":"10.1186/s12982-024-00245-3","title":"Efficient detection of data entry errors in large-scale public health surveys: an unsupervised machine learning approach","year":2024,"lang":"en","type":"article","venue":"Discover Public Health","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Ministry of Labour","funders":"Ministry of Health and Family Welfare; Indian Council of Medical Research","keywords":"Scale (ratio); Computer science; Unsupervised learning; Machine learning; Public health; Artificial intelligence; Data science; Medicine; Geography; Cartography; Nursing","score_opus":0.28329863549679324,"score_gpt":0.467259722435846,"score_spread":0.18396108693905278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403289769","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.104703516,0.00037510108,0.8896248,0.00056615943,0.000059848935,0.00037839002,0.0006574684,0.0028083313,0.0008264175],"genre_scores_gemma":[0.59050006,0.00016814207,0.40632853,0.00021248349,0.00006914476,0.00029179975,0.0017852109,0.000095094365,0.00054964377],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99377877,0.0027769154,0.00071938056,0.0013445534,0.0010917152,0.00028867795],"domain_scores_gemma":[0.9705404,0.016824039,0.0044435672,0.0032618216,0.004607255,0.00032284306],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007913313,0.0008297801,0.0012803284,0.0031935468,0.00080420123,0.001470653,0.0020707292,0.0010776992,0.00028607214],"category_scores_gemma":[0.029555082,0.00042294833,0.000865687,0.0023725315,0.00076122576,0.0015680253,0.0013141067,0.0014889664,0.0003360049],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005098152,0.0007929985,0.12568654,0.00048869173,0.0004967635,0.0002469633,0.0007600811,0.16599828,0.007328727,0.004805895,0.005738926,0.68714625],"study_design_scores_gemma":[0.000020570147,0.00010519772,0.016158208,0.00005550413,0.00003890279,0.00013697008,0.00027053378,0.96901065,0.005217732,0.0073063634,0.0016403157,0.000038984792],"about_ca_topic_score_codex":0.0082787825,"about_ca_topic_score_gemma":0.009349479,"teacher_disagreement_score":0.9920867,"about_ca_system_score_codex":0.00091266545,"about_ca_system_score_gemma":0.002648597,"threshold_uncertainty_score":0.04185009},"labels":[],"label_agreement":null},{"id":"W4403370586","doi":"10.1038/s41598-024-74741-6","title":"Characterizing cognitive phenotypes and clinical correlates in type 2 diabetes using fuzzy clustering and decision tree analysis","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Computer science; Decision tree; Fuzzy cognitive map; Cognition; Type 2 diabetes; Fuzzy clustering; Phenotype; Tree (set theory); Data mining; Bioinformatics; Fuzzy logic; Artificial intelligence; Machine learning; Computational biology; Diabetes mellitus; Medicine; Fuzzy set; Biology; Mathematics; Fuzzy classification; Genetics; Psychiatry; Endocrinology","score_opus":0.14399860540188583,"score_gpt":0.4822757727034597,"score_spread":0.33827716730157387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403370586","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96750766,0.0002999685,0.030965408,0.00015354839,0.000013233033,0.00013623161,0.00032526744,0.00004202522,0.0005566315],"genre_scores_gemma":[0.982627,0.00009627182,0.01684513,0.000021404152,0.0000071252966,0.000046734476,0.0002704414,0.0000026801429,0.00008323356],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99888533,0.0006098331,0.00011607022,0.00012272023,0.00017619343,0.00008978601],"domain_scores_gemma":[0.9964631,0.002455681,0.0003952239,0.00010520471,0.00043119944,0.00014965757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032120612,0.0004270389,0.00057507766,0.0033966787,0.0004653907,0.0010196913,0.00040429493,0.0004849938,0.00059012964],"category_scores_gemma":[0.0081363525,0.00013372849,0.00094308757,0.0014673616,0.00027103908,0.00041221513,0.00037499843,0.0004325478,0.00009941242],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027916362,0.00058547384,0.7408686,0.00023857849,0.000712976,0.0005565885,0.0010579666,0.07938322,0.0030523106,0.0014507244,0.0009617547,0.16834012],"study_design_scores_gemma":[0.000095962976,0.00056479214,0.2779581,0.00010133865,0.0002797663,0.00049959944,0.0010850149,0.7114627,0.0012780686,0.0061664656,0.00042820224,0.00008001767],"about_ca_topic_score_codex":0.013121506,"about_ca_topic_score_gemma":0.008972916,"teacher_disagreement_score":0.013121506,"about_ca_system_score_codex":0.00072832766,"about_ca_system_score_gemma":0.0007021902,"threshold_uncertainty_score":0.026090264},"labels":[],"label_agreement":null},{"id":"W4403420028","doi":"10.1016/j.jtho.2024.09.106","title":"MA02.11 Validation of the Sybil Deep Learning Lung Cancer Risk Prediction Model in Three Independent Screening Studies","year":2024,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Foundation; University of Calgary; Lunenfeld-Tanenbaum Research Institute","funders":"","keywords":"Medicine; Lung cancer; Artificial intelligence; Oncology","score_opus":0.18419420653255297,"score_gpt":0.5764971891287354,"score_spread":0.3923029825961824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403420028","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94495666,0.00382516,0.033419166,0.0014073992,0.00048344434,0.00064215076,0.009168232,0.0018553145,0.0042423927],"genre_scores_gemma":[0.9564329,0.00040150748,0.01591848,0.0005134242,0.00011131356,0.0006043324,0.023296637,0.00014867201,0.0025727595],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943995,0.0036258649,0.00033307998,0.0009946236,0.0004138485,0.00023305634],"domain_scores_gemma":[0.9877901,0.007510597,0.00068631925,0.0013129467,0.0020948048,0.00060520286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026061172,0.0020000907,0.0016402119,0.001865274,0.00089609664,0.0020170663,0.0027316136,0.0018375148,0.003864505],"category_scores_gemma":[0.024205288,0.00067198835,0.0024952153,0.0008757986,0.0009583119,0.0008449563,0.002276318,0.0016991462,0.0020418405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015998254,0.0031775613,0.52643037,0.0014088212,0.01121941,0.00076297374,0.0003926383,0.19428019,0.008382944,0.001746346,0.038773324,0.1974272],"study_design_scores_gemma":[0.0019947384,0.003301572,0.07841714,0.0002520428,0.0019035743,0.00051689154,0.0001581734,0.8976535,0.0063660806,0.0018953993,0.00739136,0.00014951538],"about_ca_topic_score_codex":0.0089950645,"about_ca_topic_score_gemma":0.0070806383,"teacher_disagreement_score":0.026061172,"about_ca_system_score_codex":0.0010289978,"about_ca_system_score_gemma":0.0024348162,"threshold_uncertainty_score":0.13782632},"labels":[],"label_agreement":null},{"id":"W4403570710","doi":"10.48550/arxiv.2410.10374","title":"Class Balancing Diversity Multimodal Ensemble for Alzheimer's Disease Diagnosis and Early Detection","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Università Campus Bio-Medico di Roma; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; Biogen; BioClinica; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Class (philosophy); Diversity (politics); Computer science; Artificial intelligence; Disease; Machine learning; Medicine; Sociology; Internal medicine; Anthropology","score_opus":0.2458194905120243,"score_gpt":0.3369340499919445,"score_spread":0.09111455947992017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403570710","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23493087,0.00629423,0.748431,0.0014880174,0.00048907346,0.00018522411,0.0011191706,0.0027721224,0.0042903256],"genre_scores_gemma":[0.9173116,0.0008744003,0.07619723,0.00048144863,0.0004474189,0.00013774337,0.0021955092,0.00009759181,0.002257053],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882096,0.0004661836,0.000046412904,0.000278273,0.00025885037,0.00012923211],"domain_scores_gemma":[0.9984383,0.0006642502,0.00011679348,0.00022360784,0.0004244493,0.00013268419],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036729926,0.00136854,0.0014957963,0.0015577475,0.0006876467,0.0008770491,0.0010818358,0.0010733457,0.0010503998],"category_scores_gemma":[0.0046503553,0.00026185907,0.001138655,0.00087562826,0.00031110307,0.0011422166,0.001406862,0.0014926213,0.00057072786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009201985,0.0005810752,0.023437455,0.00011580579,0.0007644255,0.0001768421,0.00021091182,0.27907297,0.010130359,0.0016369305,0.011220458,0.6717326],"study_design_scores_gemma":[0.000019803598,0.0001801551,0.0032749395,0.00002181165,0.00009900166,0.00005896946,0.000051263367,0.9884574,0.0026500032,0.0036895215,0.0014753527,0.00002181581],"about_ca_topic_score_codex":0.0036295988,"about_ca_topic_score_gemma":0.0037740613,"teacher_disagreement_score":0.0036729926,"about_ca_system_score_codex":0.0005908467,"about_ca_system_score_gemma":0.00077503675,"threshold_uncertainty_score":0.019424856},"labels":[],"label_agreement":null},{"id":"W4403793228","doi":"10.53555/ajbr.v27i3s.2891","title":"Heart Disease Prediction: A Machine Learning Model for Evaluation and Hyperparameter Tuning","year":2024,"lang":"en","type":"article","venue":"African Journal of Biomedical Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Hyperparameter; Machine learning; Artificial intelligence; Hyperparameter optimization; Computer science; Support vector machine","score_opus":0.4226268472239919,"score_gpt":0.5932676309198393,"score_spread":0.17064078369584734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403793228","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14383355,0.0031665277,0.8338833,0.0010098347,0.00041157662,0.0006693401,0.002062814,0.009073392,0.0058897045],"genre_scores_gemma":[0.7461858,0.00073252607,0.24497977,0.00022076198,0.00011952624,0.0010324038,0.0024033773,0.00030598044,0.004019832],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915934,0.0003730156,0.000079047684,0.00017272764,0.00015145524,0.00006428266],"domain_scores_gemma":[0.99744344,0.0017804027,0.00012542494,0.00015767981,0.00043696727,0.00005602406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038511904,0.0012335001,0.0012369297,0.0013130214,0.0004771918,0.0011081838,0.0014075321,0.0017248794,0.003127434],"category_scores_gemma":[0.009305039,0.0003773437,0.001042682,0.0010080626,0.00027595364,0.0010412883,0.00076741056,0.0016424998,0.0010282006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057488715,0.00041933297,0.010373125,0.00019352592,0.0002561231,0.00015181246,0.00007949372,0.7705136,0.0013302179,0.001571752,0.009544229,0.20499182],"study_design_scores_gemma":[0.000016259586,0.00004584843,0.0005403788,0.000012371186,0.0000149950265,0.000020445481,0.0000067981823,0.99831533,0.00025437959,0.00044568203,0.0003199462,0.000007658761],"about_ca_topic_score_codex":0.0111784525,"about_ca_topic_score_gemma":0.0054928814,"teacher_disagreement_score":0.0111784525,"about_ca_system_score_codex":0.0007933657,"about_ca_system_score_gemma":0.0010110259,"threshold_uncertainty_score":0.02222681},"labels":[],"label_agreement":null},{"id":"W4403830843","doi":"10.1681/asn.2024ndq472kr","title":"Perspectives of Patients and Care Partners on Prognostic Discussions in CKD: A Qualitative Study","year":2024,"lang":"en","type":"article","venue":"Journal of the American Society of Nephrology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Qualitative research; Medicine; Internal medicine; Intensive care medicine; Family medicine; Sociology","score_opus":0.10352559324565917,"score_gpt":0.5221771496756316,"score_spread":0.41865155642997237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403830843","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98564327,0.0012969798,0.0018269132,0.004437082,0.00012458721,0.0002884475,0.00022705349,0.000025074773,0.0061305617],"genre_scores_gemma":[0.9946473,0.0009818603,0.0007693697,0.0014781404,0.000036475907,0.00030435968,0.00008286071,0.000025590978,0.0016739345],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9771847,0.017532265,0.000525671,0.0008315662,0.0011051488,0.0028205572],"domain_scores_gemma":[0.95763403,0.031338003,0.0021937555,0.000596961,0.0025209403,0.005716254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018727072,0.0008875558,0.0012081382,0.0017372402,0.01575064,0.006540879,0.0024638835,0.0029314137,0.0045562866],"category_scores_gemma":[0.032632265,0.0010197223,0.0006601045,0.0021813284,0.012350826,0.0062618977,0.009708335,0.0050368994,0.0004080116],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026583619,0.000023656317,0.001083986,0.00006864952,0.0000027845886,0.00041143212,0.99663925,0.000013474197,0.00014622344,0.00029107637,0.0002095511,0.0010832233],"study_design_scores_gemma":[0.0000036692652,0.000025203404,0.0004374951,0.00007910975,0.0000022393735,0.00012408248,0.99676955,0.000025869631,0.000053023763,0.000085608706,0.0023862687,0.000007970296],"about_ca_topic_score_codex":0.0219704,"about_ca_topic_score_gemma":0.027943479,"teacher_disagreement_score":0.0219704,"about_ca_system_score_codex":0.0076376153,"about_ca_system_score_gemma":0.008675666,"threshold_uncertainty_score":0.099039435},"labels":[],"label_agreement":null},{"id":"W4403834508","doi":"10.1681/asn.2024t4nw31f9","title":"Can-SOLVE CKD: Capturing Our IDEA Journey as a Patient-Oriented Kidney Research Network","year":2024,"lang":"en","type":"article","venue":"Journal of the American Society of Nephrology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Island Health; Kidney Foundation of Canada; University of Toronto; Kativik Regional Government; Canadian Association of Nurses in Oncology; University of Calgary; McGill University","funders":"","keywords":"Kidney disease; Computer science; Medicine; Intensive care medicine; Urology; Internal medicine","score_opus":0.14436509877955606,"score_gpt":0.49045504599662487,"score_spread":0.3460899472170688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403834508","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.695089,0.0061755073,0.06856241,0.18082915,0.0024882844,0.0033193866,0.0005697521,0.00039251387,0.042573895],"genre_scores_gemma":[0.9081864,0.0038669258,0.06345601,0.014667199,0.0003109427,0.0025191153,0.00031195345,0.00023643543,0.0064451317],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9420038,0.049571782,0.0010003549,0.0017751926,0.0025662393,0.0030825958],"domain_scores_gemma":[0.94480693,0.026733603,0.0033706184,0.0027888818,0.004790722,0.017509233],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.057179976,0.00072986976,0.00056389434,0.0020030567,0.019437838,0.015617419,0.003498874,0.0035253745,0.00584013],"category_scores_gemma":[0.053568535,0.0009183966,0.0009832414,0.0014976956,0.015904242,0.015982961,0.024923133,0.009597696,0.0011680657],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004328599,0.00016182948,0.004930844,0.0004245251,0.000024525743,0.00076847884,0.9493219,0.00015890568,0.0004969574,0.008650415,0.008774765,0.026243482],"study_design_scores_gemma":[0.000018107141,0.00015831368,0.0016395751,0.0006427457,0.000020398655,0.0006772613,0.89637595,0.0004249187,0.00027999925,0.009000266,0.09070816,0.000054317567],"about_ca_topic_score_codex":0.004021863,"about_ca_topic_score_gemma":0.009246138,"teacher_disagreement_score":0.9959781,"about_ca_system_score_codex":0.00830527,"about_ca_system_score_gemma":0.031367417,"threshold_uncertainty_score":0.30240023},"labels":[],"label_agreement":null},{"id":"W4403841510","doi":"10.1681/asn.2024xgy74hfd","title":"Development and Validation of Machine-Learning Model to Predict the Risk of Major Cardiovascular Events and Death for Patients with Kidney Failure Having Noncardiac Surgery","year":2024,"lang":"en","type":"article","venue":"Journal of the American Society of Nephrology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary; Seven Oaks General Hospital; University of Manitoba","funders":"","keywords":"Medicine; Intensive care medicine; Heart failure; Cardiology; Internal medicine","score_opus":0.04479558061283299,"score_gpt":0.3468616063106476,"score_spread":0.3020660256978146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403841510","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9313134,0.0007407483,0.061826963,0.00063975697,0.00008435599,0.00054407195,0.0020077717,0.0009175791,0.0019253463],"genre_scores_gemma":[0.96424705,0.00013925096,0.031415574,0.00010091246,0.000017390648,0.00023339104,0.0030547967,0.000030482443,0.00076123595],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898654,0.0003983317,0.00008943129,0.00022081875,0.00016366594,0.00014123034],"domain_scores_gemma":[0.9950808,0.0026233152,0.00025788823,0.00020182549,0.0016740117,0.00016218495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006626643,0.0012223196,0.00084185146,0.0013400888,0.00065450574,0.001060311,0.0014149083,0.0009799363,0.0009626582],"category_scores_gemma":[0.007595781,0.0003760943,0.0010982419,0.00069105596,0.00032925815,0.0004590422,0.00080560404,0.0014076936,0.0004538854],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004225348,0.0008851625,0.18108039,0.000113686016,0.00042817788,0.00031475717,0.00016735146,0.74915916,0.0017334428,0.00048241206,0.003490145,0.061722767],"study_design_scores_gemma":[0.000033338933,0.00013945777,0.01157676,0.000029639905,0.00004342274,0.000034776476,0.00003760919,0.9866666,0.0008207614,0.0002243522,0.0003811958,0.000011970717],"about_ca_topic_score_codex":0.07966912,"about_ca_topic_score_gemma":0.04476206,"teacher_disagreement_score":0.07966912,"about_ca_system_score_codex":0.0022988687,"about_ca_system_score_gemma":0.004525943,"threshold_uncertainty_score":0.15841079},"labels":[],"label_agreement":null},{"id":"W4403863443","doi":"10.1109/access.2024.3487851","title":"A Data-Centric Approach to Investigate the Feasibility of Utilizing Animal Medical Data as a Solution for Human Medical Data Scarcity","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Scarcity; Data modeling; Biological data; Data science; Bioinformatics; Software engineering","score_opus":0.7973398171529654,"score_gpt":0.6412788324650521,"score_spread":0.1560609846879133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403863443","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24809788,0.0026172248,0.73342484,0.002128042,0.00037381603,0.00043144976,0.002770339,0.0035562967,0.006600089],"genre_scores_gemma":[0.7110794,0.00061581994,0.2765926,0.0009293541,0.00017775873,0.00031516826,0.0061478247,0.00010641754,0.0040356545],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9992198,0.00020333093,0.00005257308,0.0002556858,0.00020825543,0.000060483955],"domain_scores_gemma":[0.99863404,0.0004445127,0.00011769408,0.000295591,0.00044095799,0.00006709314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015840507,0.0008454319,0.00054398587,0.0008670267,0.00024367016,0.00093335024,0.0011900981,0.0012007063,0.0010512182],"category_scores_gemma":[0.0034985642,0.0002096223,0.00063956983,0.0007047629,0.00035054804,0.0013264865,0.00078624184,0.0010797889,0.0005633109],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008640417,0.0012454632,0.02483657,0.0007445928,0.0007397099,0.0004472644,0.00027556345,0.28136992,0.08207013,0.005840356,0.013731992,0.5878343],"study_design_scores_gemma":[0.000021300786,0.0003775793,0.0050826757,0.00004315032,0.00008134537,0.0001620765,0.00009170668,0.9581814,0.025816174,0.003072454,0.0070493924,0.000020694471],"about_ca_topic_score_codex":0.0024265826,"about_ca_topic_score_gemma":0.0038589563,"teacher_disagreement_score":0.0024265826,"about_ca_system_score_codex":0.000604334,"about_ca_system_score_gemma":0.0009131691,"threshold_uncertainty_score":0.008377373},"labels":[],"label_agreement":null},{"id":"W4403865337","doi":"10.1101/2024.10.28.24316275","title":"Early detection of non-small cell lung cancer using electronic health record data","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Merck Canada Inc. (Canada)","funders":"","keywords":"Electronic health record; Health records; Cancer; Lung cancer; Computer science; Medicine; Oncology; Political science; Internal medicine; Health care","score_opus":0.20525260998161485,"score_gpt":0.4917588365814746,"score_spread":0.2865062265998598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403865337","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9395681,0.0018922763,0.046016887,0.0014383157,0.00008996373,0.00025412207,0.006618704,0.00040101595,0.0037206288],"genre_scores_gemma":[0.98500085,0.0003929949,0.011827749,0.00010840082,0.000042077907,0.000030660798,0.0022991202,0.0000071129543,0.00029110635],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99829584,0.0008440501,0.00014869029,0.00027394376,0.00035126906,0.00008617705],"domain_scores_gemma":[0.9918439,0.0046977815,0.001398283,0.0007558531,0.0011401314,0.00016402343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033696652,0.00043332652,0.00040653528,0.0018113522,0.00016090213,0.0011222695,0.00048679035,0.00043466716,0.00087412616],"category_scores_gemma":[0.013672523,0.00016839341,0.0005628705,0.0016132625,0.00011645559,0.000852639,0.0005263316,0.0005851996,0.00032219835],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013328057,0.00019746301,0.92442256,0.00011831663,0.00021324695,0.0000814584,0.00005768729,0.006783832,0.001053949,0.00026635363,0.0011289255,0.06554297],"study_design_scores_gemma":[0.000041620624,0.00042513042,0.72228736,0.0002891125,0.00041421907,0.00041481145,0.00028274077,0.26345143,0.0062557296,0.001802194,0.0042918473,0.00004372604],"about_ca_topic_score_codex":0.005192225,"about_ca_topic_score_gemma":0.007441885,"teacher_disagreement_score":0.005192225,"about_ca_system_score_codex":0.0003903163,"about_ca_system_score_gemma":0.0007089684,"threshold_uncertainty_score":0.017820656},"labels":[],"label_agreement":null},{"id":"W4403889664","doi":"10.1007/978-3-031-73741-1_15","title":"Model Driven Development for AI-Based Healthcare Systems: A Review","year":2024,"lang":"en","type":"review","venue":"Lecture notes in computer science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"University of Limerick; Science Foundation Ireland","keywords":"Computer science; Health care; Healthcare system; Development (topology); Artificial intelligence; Software engineering","score_opus":0.3259531644663474,"score_gpt":0.5411854786226167,"score_spread":0.21523231415626926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403889664","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011870038,0.996567,0.0015834924,0.00031952607,0.00011786845,0.00002246493,0.000022527123,0.000017654615,0.0012308072],"genre_scores_gemma":[0.0016677908,0.9957995,0.0019419987,0.00019308657,0.00006613688,0.00003320656,0.000048344387,0.000008274978,0.00024166018],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99834204,0.0004799015,0.00028570325,0.00019511086,0.00062553,0.000071673785],"domain_scores_gemma":[0.99306786,0.00546355,0.00037311972,0.00015734242,0.00084737,0.00009078507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028958127,0.0010558099,0.0014466096,0.0037763226,0.00035128655,0.0019533136,0.0015367944,0.0017605367,0.0031997368],"category_scores_gemma":[0.006348152,0.0006655196,0.0012210028,0.0051961867,0.0008483289,0.0019363969,0.0011400996,0.0016258268,0.0014978203],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043989286,0.00008414079,0.00027456414,0.06994424,0.00024732592,0.00017943872,0.00027301474,0.0025081534,0.00070009276,0.01904781,0.015921135,0.8907761],"study_design_scores_gemma":[0.000026891226,0.00011937003,0.0007012548,0.041328095,0.0003250026,0.0008636455,0.00019045228,0.0010352697,0.00076057325,0.008944802,0.9456529,0.000051732022],"about_ca_topic_score_codex":0.0031588927,"about_ca_topic_score_gemma":0.0022833245,"teacher_disagreement_score":0.0037763226,"about_ca_system_score_codex":0.001584808,"about_ca_system_score_gemma":0.0039436887,"threshold_uncertainty_score":0.015314698},"labels":[],"label_agreement":null},{"id":"W4403905382","doi":"10.59934/jaiea.v4i1.601","title":"Application of the K-Nearest Neighbor Method for Classification of Hypertension Diseases (Case Study: Stabat Health Center)","year":2024,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"k-nearest neighbors algorithm; Center (category theory); Pattern recognition (psychology); Computer science; Artificial intelligence; Crystallography; Chemistry","score_opus":0.17948055968129076,"score_gpt":0.46284147134178744,"score_spread":0.2833609116604967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403905382","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9526635,0.0008620392,0.03533277,0.0006726433,0.00019419397,0.00042808423,0.0015878251,0.00017234684,0.008086494],"genre_scores_gemma":[0.9463422,0.0002292312,0.04995853,0.00007543472,0.00002907663,0.00014972127,0.0009733977,0.000011523979,0.002230833],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9980451,0.00077038875,0.00015549247,0.00030656924,0.00059867796,0.00012373966],"domain_scores_gemma":[0.99787843,0.0011005958,0.00014792435,0.00018071342,0.0005998523,0.00009239732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020752314,0.00034461144,0.00031846223,0.0013254825,0.00073847116,0.00068235066,0.0008472552,0.0010062912,0.001514348],"category_scores_gemma":[0.0038352131,0.00014056278,0.0004760085,0.0012187614,0.0004778409,0.0005299402,0.00054195273,0.00041456442,0.0003016867],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020244794,0.004140319,0.33491683,0.0013745547,0.00039680174,0.0068514594,0.002976178,0.14556418,0.010974573,0.0083688665,0.026600916,0.45581082],"study_design_scores_gemma":[0.00021262317,0.0020473222,0.13055633,0.00019197675,0.00015487455,0.004306687,0.005849357,0.82100993,0.01580778,0.005076253,0.014636794,0.00015009339],"about_ca_topic_score_codex":0.019306539,"about_ca_topic_score_gemma":0.019735951,"teacher_disagreement_score":0.019306539,"about_ca_system_score_codex":0.0011234885,"about_ca_system_score_gemma":0.0006475865,"threshold_uncertainty_score":0.038388312},"labels":[],"label_agreement":null},{"id":"W4403973616","doi":"10.1101/2024.10.28.24316280","title":"GraftIQ: A Hybrid Multi-Class Neural Network Integrating Clinical Insight for Multi-Outcome Prediction in Liver Transplant Recipients","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Vancouver General Hospital; University of Ottawa; York University","funders":"","keywords":"Outcome (game theory); Class (philosophy); Artificial neural network; Computer science; Liver transplantation; Artificial intelligence; Medicine; Internal medicine; Transplantation; Mathematics; Mathematical economics","score_opus":0.4042312851592235,"score_gpt":0.5234755922846018,"score_spread":0.11924430712537831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403973616","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69762474,0.0023140023,0.28875345,0.0016885649,0.0003086259,0.0003345387,0.0020385147,0.003221358,0.0037162267],"genre_scores_gemma":[0.97014385,0.00024339452,0.02642463,0.00034593596,0.00008610068,0.00014227789,0.0012621928,0.000035250927,0.0013164323],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946624,0.00020092019,0.000028675244,0.00013849018,0.00009763227,0.000068082496],"domain_scores_gemma":[0.99914,0.00046655763,0.00007909675,0.00005668764,0.0001764124,0.00008125878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023514726,0.0010152875,0.0007181499,0.00084485573,0.0002243109,0.00083260733,0.0010036344,0.00089339796,0.0013405195],"category_scores_gemma":[0.0029121258,0.0002607877,0.0008053554,0.00040899665,0.00024555344,0.00062437775,0.0012371948,0.0011495793,0.0003051609],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014650169,0.0010923049,0.06628315,0.00016102412,0.00072484324,0.0002994153,0.0000982253,0.60325867,0.00393477,0.0009701324,0.006520591,0.31519175],"study_design_scores_gemma":[0.000021030433,0.00013857707,0.0026186404,0.000010764819,0.000033571203,0.000023085518,0.000010067193,0.9957983,0.0005131449,0.0006115765,0.00021001403,0.000011195007],"about_ca_topic_score_codex":0.007086852,"about_ca_topic_score_gemma":0.006878987,"teacher_disagreement_score":0.007086852,"about_ca_system_score_codex":0.0009015653,"about_ca_system_score_gemma":0.0009113316,"threshold_uncertainty_score":0.014091194},"labels":[],"label_agreement":null},{"id":"W4404015886","doi":"10.21203/rs.3.rs-5363467/v1","title":"Synthetic Data for Accessible Learning in Healthcare: Improving Mortality Prediction with Longitudinal Data","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cambridge Memorial Hospital; McGill University Health Centre; Université de Sherbrooke","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Longitudinal data; Health care; Computer science; Data science; Artificial intelligence; Machine learning; Data mining; Economics; Economic growth","score_opus":0.653082182088013,"score_gpt":0.6384292035500618,"score_spread":0.014652978537951222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404015886","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31268427,0.002663117,0.64500815,0.009125113,0.0016172582,0.00023424391,0.022366457,0.003115669,0.003185776],"genre_scores_gemma":[0.8639667,0.00081390294,0.101756826,0.000491098,0.0005144268,0.00027884447,0.030225944,0.00021403065,0.0017382035],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962838,0.0026618943,0.00016097422,0.00037026528,0.00042847724,0.00009465966],"domain_scores_gemma":[0.963051,0.027688485,0.0009948582,0.005330603,0.002261065,0.0006738491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009637233,0.0007789596,0.00078782206,0.0015850887,0.00045329155,0.0017239322,0.001270009,0.0015520717,0.0040528057],"category_scores_gemma":[0.063444585,0.00050413527,0.0010346654,0.0015584574,0.0006939986,0.0022467524,0.0018593018,0.0024010283,0.00096087914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024722582,0.0016218049,0.07465917,0.00068921247,0.00075714866,0.00030790907,0.00039973843,0.50175536,0.0027991815,0.021645302,0.064824626,0.32806838],"study_design_scores_gemma":[0.00008259394,0.00013422697,0.0032024235,0.000051790823,0.00003473104,0.00004800157,0.00007192549,0.96985,0.0009665314,0.022565383,0.0029720142,0.000020368085],"about_ca_topic_score_codex":0.0028652984,"about_ca_topic_score_gemma":0.002475691,"teacher_disagreement_score":0.009637233,"about_ca_system_score_codex":0.00054805074,"about_ca_system_score_gemma":0.0010726653,"threshold_uncertainty_score":0.050967216},"labels":[],"label_agreement":null},{"id":"W4404041404","doi":"10.1097/01.pcc.0001084780.98260.01","title":"PP036 Topic: AS04–Emerging Sciences, Methodologies, Big Data and Technology: DIRECTED ACYCLIC GRAPHS, AN EPIDEMIOLOGICAL METHOD TO IMPROVE STUDY DESIGN IN PEDIATRIC CRITICAL CARE RESEARCH","year":2024,"lang":"en","type":"article","venue":"Pediatric Critical Care Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Medicine; Big data; Data science; Epidemiology; Intensive care medicine; Data mining; Computer science; Pathology","score_opus":0.7090013874790618,"score_gpt":0.6762076239326252,"score_spread":0.032793763546436594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404041404","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038991005,0.0075287865,0.9401647,0.019365078,0.004447794,0.0023746882,0.0066237943,0.0020925854,0.013503515],"genre_scores_gemma":[0.04693517,0.007276338,0.92309374,0.005251186,0.0020779702,0.0072724745,0.0034259656,0.0007473237,0.003919868],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93758273,0.055636484,0.0019759329,0.0018974389,0.0027115482,0.00019593371],"domain_scores_gemma":[0.70633346,0.25878915,0.008385153,0.0122845685,0.012785625,0.0014221092],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.058057856,0.0009388286,0.001038131,0.004617363,0.0014085211,0.0061709858,0.0015711316,0.0021795232,0.020147974],"category_scores_gemma":[0.1809822,0.0007422581,0.0020272965,0.008291492,0.002455115,0.0038022487,0.003349855,0.0032760717,0.003604377],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002483255,0.00020130706,0.0111410385,0.008248748,0.00090417895,0.00017449085,0.0019824717,0.012580474,0.00069196604,0.34331065,0.18574563,0.43477067],"study_design_scores_gemma":[0.00021407446,0.00024282618,0.0052543376,0.005191756,0.00037727822,0.00028870843,0.00136166,0.055296786,0.00075620436,0.6093721,0.32153925,0.00010505572],"about_ca_topic_score_codex":0.002689099,"about_ca_topic_score_gemma":0.003343738,"teacher_disagreement_score":0.94194216,"about_ca_system_score_codex":0.0026240104,"about_ca_system_score_gemma":0.008849341,"threshold_uncertainty_score":0.30704296},"labels":[],"label_agreement":null},{"id":"W4404149122","doi":"10.3849/cndcgs.2024.194","title":"Improvement in the Field of CBRN Prevention, Preparedness and Protection in the Czech Republic","year":2024,"lang":"en","type":"article","venue":"Challenges to national defence in a contemporary geopolitical situation","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Czech; Preparedness; Field (mathematics); Political science; Law","score_opus":0.2793732495327794,"score_gpt":0.4959472357202395,"score_spread":0.2165739861874601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404149122","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34150618,0.07750452,0.05100956,0.083238125,0.00501431,0.00072530814,0.00082063104,0.0011291492,0.43905222],"genre_scores_gemma":[0.9398007,0.017853234,0.01362784,0.0037148357,0.00021140915,0.000080543316,0.00027064947,0.00010842144,0.024332441],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974371,0.000616254,0.00033459903,0.0003071408,0.00077582925,0.0005290565],"domain_scores_gemma":[0.9972573,0.0006327316,0.0004357448,0.00022895989,0.00097446743,0.0004708834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004495069,0.000310195,0.00033187767,0.0017957097,0.0020195923,0.004807998,0.00092144596,0.0009420656,0.0037727884],"category_scores_gemma":[0.0047906246,0.00025624209,0.0006618892,0.00126332,0.0023487783,0.0019857027,0.0028885414,0.0017177173,0.0005735671],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000376516,0.00044412725,0.027018145,0.00470638,0.0001281944,0.0023852526,0.006402343,0.012967528,0.0084072985,0.3267864,0.03951374,0.57086414],"study_design_scores_gemma":[0.00007471769,0.00035066882,0.089961715,0.0032640232,0.00011423551,0.0019342701,0.0082906475,0.0043479037,0.006988113,0.02750289,0.8568878,0.00028300672],"about_ca_topic_score_codex":0.044307183,"about_ca_topic_score_gemma":0.032853253,"teacher_disagreement_score":0.044307183,"about_ca_system_score_codex":0.006939821,"about_ca_system_score_gemma":0.026145091,"threshold_uncertainty_score":0.088098526},"labels":[],"label_agreement":null},{"id":"W4404239794","doi":"10.3390/electronics13224405","title":"Health Risk Assessment Using Machine Learning: Systematic Review","year":2024,"lang":"en","type":"article","venue":"Electronics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Canada First Research Excellence Fund","keywords":"Computer science; Risk assessment; Systematic review; Artificial intelligence; Machine learning; Risk analysis (engineering); Engineering; Medicine; MEDLINE; Political science; Computer security","score_opus":0.12368082301634693,"score_gpt":0.5284848871635844,"score_spread":0.4048040641472375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404239794","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00051766355,0.99657744,0.00095560757,0.0005790407,0.00012370804,0.00047034858,0.0004646623,0.000027248076,0.00028437263],"genre_scores_gemma":[0.015801704,0.9792956,0.0026266568,0.0007483102,0.000146235,0.00092887273,0.00033315876,0.000012325706,0.00010701658],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9837051,0.0075734397,0.0044261576,0.0010367823,0.0029883632,0.00027029414],"domain_scores_gemma":[0.8922264,0.094113305,0.007900982,0.0012780118,0.0041479436,0.0003334656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01910155,0.0018763482,0.007062993,0.011697363,0.0006249772,0.0030776863,0.0023408048,0.002016335,0.0060596666],"category_scores_gemma":[0.105358176,0.0010348733,0.010835787,0.010381566,0.0009567236,0.0032503742,0.0017673454,0.0017332871,0.00053413125],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012468624,0.000025142856,0.000985266,0.9113443,0.010643642,0.00005761413,0.00011317938,0.00053082826,0.000045279678,0.00045294815,0.0025537119,0.07312348],"study_design_scores_gemma":[0.00015221437,0.00011628584,0.0022310747,0.94394606,0.036136363,0.00017660779,0.00011675822,0.00053213374,0.00012380454,0.00107752,0.015343775,0.000047341073],"about_ca_topic_score_codex":0.008381583,"about_ca_topic_score_gemma":0.018037327,"teacher_disagreement_score":0.01910155,"about_ca_system_score_codex":0.0046905745,"about_ca_system_score_gemma":0.01332743,"threshold_uncertainty_score":0.10101986},"labels":[],"label_agreement":null},{"id":"W4404565208","doi":"10.1016/j.jveb.2024.11.003","title":"Big data studies, small detailed studies, and survey studies: How they can all help","year":2024,"lang":"en","type":"article","venue":"Journal of Veterinary Behavior","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Big data; Data science; Psychology; Computer science; Data mining","score_opus":0.8264265157939573,"score_gpt":0.5954674425266742,"score_spread":0.23095907326728315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404565208","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01926055,0.34075457,0.15240492,0.4333145,0.028494433,0.0050661354,0.0057294522,0.0014139242,0.01356158],"genre_scores_gemma":[0.26372856,0.084200054,0.4020918,0.20835082,0.02176414,0.013437611,0.002231883,0.00079897034,0.0033962312],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.619865,0.3236057,0.02590893,0.010416797,0.017399589,0.002804067],"domain_scores_gemma":[0.05223192,0.8688764,0.016550444,0.037343595,0.021706676,0.003290928],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4677179,0.007373649,0.016772486,0.018377366,0.006146024,0.018416462,0.008933441,0.016012738,0.013603715],"category_scores_gemma":[0.6929195,0.006462038,0.0102165975,0.017686358,0.019720972,0.040883638,0.017600507,0.015538818,0.002013929],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004092569,0.0016053263,0.17412105,0.060657676,0.05240419,0.00096473965,0.018724173,0.0047700317,0.0010838525,0.067327306,0.1902081,0.4240411],"study_design_scores_gemma":[0.0035209232,0.001848108,0.06211342,0.08042175,0.017659232,0.00072698836,0.027704151,0.0067938548,0.0009590519,0.62706167,0.1696139,0.0015770543],"about_ca_topic_score_codex":0.02404476,"about_ca_topic_score_gemma":0.05956323,"teacher_disagreement_score":0.5322821,"about_ca_system_score_codex":0.007399707,"about_ca_system_score_gemma":0.024922077,"threshold_uncertainty_score":0.65639865},"labels":[],"label_agreement":null},{"id":"W4404609376","doi":"10.23919/eusipco63174.2024.10715254","title":"FH-TabNet: Multi-Class Familial Hypercholesterolemia Detection via a Multi-Stage Tabular Deep Learning Network","year":2024,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Familial hypercholesterolemia; Class (philosophy); Computer science; Stage (stratigraphy); Deep learning; Artificial intelligence; Medicine; Internal medicine; Cholesterol; Biology","score_opus":0.15867463247828498,"score_gpt":0.4578268254051282,"score_spread":0.29915219292684325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404609376","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41631344,0.002352333,0.54768914,0.003061751,0.0006358702,0.00030733162,0.0071651745,0.008619687,0.013855278],"genre_scores_gemma":[0.89213383,0.00040647396,0.087870464,0.0010113638,0.00009490131,0.00017398383,0.0067589977,0.00009424265,0.011455726],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998173,0.000039631363,0.00000989296,0.000052523163,0.000036636073,0.000044025506],"domain_scores_gemma":[0.9996407,0.0001389271,0.000035063687,0.000032572643,0.000109478715,0.000043240554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058585784,0.0007193376,0.00047095367,0.0006500101,0.0003445545,0.0006283569,0.0012911765,0.0010251137,0.0028863295],"category_scores_gemma":[0.0016661255,0.00025003843,0.00046558728,0.00036222851,0.00031631053,0.0005629722,0.0008999569,0.00075447897,0.00060818635],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012133736,0.0006901539,0.031390607,0.00024104514,0.00031073455,0.0007548305,0.00020825653,0.35984975,0.009888445,0.005898556,0.03732709,0.5522272],"study_design_scores_gemma":[0.00002013288,0.00009132809,0.0012176272,0.000019912943,0.000022674509,0.00007368088,0.000019538746,0.9933711,0.0015962839,0.002328994,0.0012279081,0.000010742739],"about_ca_topic_score_codex":0.012073135,"about_ca_topic_score_gemma":0.018447516,"teacher_disagreement_score":0.012073135,"about_ca_system_score_codex":0.0010534348,"about_ca_system_score_gemma":0.00092712254,"threshold_uncertainty_score":0.024005711},"labels":[],"label_agreement":null},{"id":"W4404786572","doi":"10.2196/69136","title":"Correction: A Comprehensive Youth Diabetes Epidemiological Data Set and Web Portal: Resource Development and Case Studies","year":2024,"lang":"en","type":"erratum","venue":"JMIR Public Health and Surveillance","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Diabetes and Digestive and Kidney Diseases","keywords":"Epidemiology; Resource (disambiguation); Computer science; Set (abstract data type); Data science; Data set; World Wide Web; Information retrieval; Medicine; Pathology","score_opus":0.4047017682396793,"score_gpt":0.4985772301797914,"score_spread":0.09387546194011209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404786572","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018573606,0.0005546044,0.0011187067,0.11773283,0.87329906,0.0000722346,0.004238368,0.00060921075,0.0021892197],"genre_scores_gemma":[0.01661405,0.00856969,0.01435941,0.3054907,0.49380538,0.0009926786,0.008160887,0.0034298527,0.14857729],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98616797,0.0027331822,0.0031122994,0.0013973449,0.005669483,0.00091970264],"domain_scores_gemma":[0.89152366,0.038173553,0.0046264995,0.0046939547,0.057210583,0.003771821],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010878423,0.0027298399,0.0021873333,0.0057990286,0.0042181346,0.0054800464,0.0045020967,0.0091162985,0.054058526],"category_scores_gemma":[0.17689252,0.0018928193,0.0023920175,0.0045376993,0.0033647285,0.0028868814,0.0031515125,0.015558612,0.02622276],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021946391,0.000005744052,0.000070031616,0.00009054187,0.000011155915,0.0001747177,0.000032827793,0.00002208947,0.0000147822875,0.00035135014,0.9968778,0.0023271267],"study_design_scores_gemma":[0.00009842806,0.000026445789,0.0009861669,0.0011514196,0.000085117266,0.0007741915,0.00022480056,0.00037969084,0.00023188496,0.0015765207,0.9943932,0.00007207293],"about_ca_topic_score_codex":0.06427817,"about_ca_topic_score_gemma":0.07347807,"teacher_disagreement_score":0.06427817,"about_ca_system_score_codex":0.006292615,"about_ca_system_score_gemma":0.01463269,"threshold_uncertainty_score":0.18084377},"labels":[],"label_agreement":null},{"id":"W4404849295","doi":"10.1109/gdigihealth.kee62309.2024.10761936","title":"Predicting Diabetes Status Using Deep Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint John Regional Hospital","funders":"","keywords":"Computer science; Deep learning; Artificial intelligence; Machine learning; Diabetes mellitus; Medicine","score_opus":0.17951884797918727,"score_gpt":0.5039455256757206,"score_spread":0.3244266776965333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404849295","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8718555,0.0029574605,0.10658532,0.0025708305,0.00040684786,0.00012274849,0.0061254883,0.0013220718,0.008053807],"genre_scores_gemma":[0.98329526,0.00051050953,0.011380189,0.0002099095,0.00007202082,0.000028987972,0.0029255447,0.000011878828,0.0015656813],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99973553,0.000061701496,0.000021239603,0.000058277907,0.000042984546,0.000080260616],"domain_scores_gemma":[0.9994085,0.00030417988,0.00006694779,0.000036348752,0.00012409614,0.00005993965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007351594,0.0005419357,0.00035041256,0.0012423759,0.00019238537,0.000750486,0.00042978453,0.0006305601,0.0018438472],"category_scores_gemma":[0.0022082857,0.00015460142,0.0005660278,0.0006918718,0.000117651885,0.00044180913,0.00055814255,0.001030923,0.0005094747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011009625,0.0012592095,0.24029788,0.00018262975,0.000290429,0.0005242932,0.00014110489,0.2529325,0.004250651,0.0011914431,0.01155525,0.48627368],"study_design_scores_gemma":[0.000014861732,0.00009674288,0.021482939,0.000049816445,0.000034105156,0.000060653183,0.00006052266,0.9741374,0.0011638333,0.0019280452,0.00095529656,0.000015837939],"about_ca_topic_score_codex":0.012203263,"about_ca_topic_score_gemma":0.010240783,"teacher_disagreement_score":0.012203263,"about_ca_system_score_codex":0.0005932568,"about_ca_system_score_gemma":0.00054657046,"threshold_uncertainty_score":0.024264514},"labels":[],"label_agreement":null},{"id":"W4404869222","doi":"10.1038/s41598-024-80900-6","title":"Predicting early mortality in hemodialysis patients: a deep learning approach using a nationwide prospective cohort in South Korea","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Korean Society of Nephrology; Seoul National University Hospital; Ministry of Science and ICT, South Korea; Korea Health Industry Development Institute; Institute for Information and Communications Technology Promotion; Ewha Womans University; Seoul National University","keywords":"Hemodialysis; Prospective cohort study; Medicine; Cohort; Cohort study; Intensive care medicine; Internal medicine; Pediatrics","score_opus":0.08245882553795787,"score_gpt":0.40892047000942644,"score_spread":0.3264616444714686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404869222","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9990858,0.000065036045,0.00033319753,0.000037215796,0.0000025542317,0.000009027074,0.00041557962,0.0000027036167,0.000048992442],"genre_scores_gemma":[0.9984603,0.00008161288,0.00043746826,0.000025055613,0.000004097185,0.00001739603,0.0008726819,0.0000020610119,0.00009932726],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99978465,0.000056425528,0.000031349726,0.00007383938,0.000019229132,0.000034553206],"domain_scores_gemma":[0.999556,0.000073772026,0.00010943989,0.000068072055,0.000100462654,0.00009229483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082729163,0.0003755827,0.00028984123,0.0007874828,0.0002813892,0.0005299298,0.00041789282,0.0002885616,0.0004980376],"category_scores_gemma":[0.0011425692,0.0003016545,0.0006151473,0.0006242489,0.00014102341,0.0004524204,0.00070310186,0.0006044527,0.00013068217],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009010265,0.00005892666,0.9951566,0.000012661794,0.00006537707,0.00011067289,0.000109295295,0.00039817058,0.00029765183,0.000024223107,0.00014231214,0.0035339952],"study_design_scores_gemma":[0.000017063778,0.00015159212,0.9878109,0.000025829797,0.00010808548,0.00026692622,0.0007011902,0.010287203,0.00017915228,0.00009377473,0.00034160673,0.000016577389],"about_ca_topic_score_codex":0.015154131,"about_ca_topic_score_gemma":0.020679748,"teacher_disagreement_score":0.015154131,"about_ca_system_score_codex":0.0004321235,"about_ca_system_score_gemma":0.0005612682,"threshold_uncertainty_score":0.030131817},"labels":[],"label_agreement":null},{"id":"W4405022032","doi":"10.26599/bdma.2024.9020077","title":"Editorial: Special Section on Challenges and Opportunities in Biomedical Big Data Analysis: From Large Language Models to Clinical Applications","year":2024,"lang":"en","type":"editorial","venue":"Big Data Mining and Analytics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Data science; Big data; Computer science; Personalized medicine; Process (computing); Health records; Health care; Electronic health record; Biometrics; Artificial intelligence; Data mining; Bioinformatics; Political science; Biology","score_opus":0.6244440855857011,"score_gpt":0.5336140947913186,"score_spread":0.09082999079438248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405022032","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022497052,0.002931755,0.00014617467,0.04929578,0.946561,0.000019154408,0.000042138112,0.00005386797,0.0009276389],"genre_scores_gemma":[0.00017566179,0.0020531607,0.0000972388,0.018675594,0.97566915,0.000017828714,0.000019059535,0.000033468743,0.0032588567],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99326754,0.0011611979,0.0008313999,0.00090992096,0.0034300976,0.00039976448],"domain_scores_gemma":[0.9636134,0.01632932,0.0017283802,0.0008589619,0.012445227,0.0050248513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009116471,0.004023137,0.0045334,0.003983049,0.0045730434,0.011535841,0.004498901,0.021277182,0.013711605],"category_scores_gemma":[0.032220595,0.0013912282,0.0035113152,0.0019451141,0.003999036,0.0073735206,0.0021889908,0.031968202,0.014618081],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001698705,0.000010019932,0.000021691758,0.00009134408,0.00001064334,0.00008383868,0.000011126958,0.000019662317,0.000026970996,0.00021092345,0.99684614,0.0026506262],"study_design_scores_gemma":[0.000062162544,0.00002613999,0.00021817537,0.0005201893,0.000048240097,0.00033583288,0.000066755325,0.00025399847,0.0001084857,0.0019719368,0.9963567,0.000031361917],"about_ca_topic_score_codex":0.002115502,"about_ca_topic_score_gemma":0.005893099,"teacher_disagreement_score":0.021277182,"about_ca_system_score_codex":0.0033234514,"about_ca_system_score_gemma":0.004573947,"threshold_uncertainty_score":0.048213065},"labels":[],"label_agreement":null},{"id":"W4405224300","doi":"10.2196/68825","title":"Correction: Cloud-Based Machine Learning Platform to Predict Clinical Outcomes at Home for Patients With Cardiovascular Conditions Discharged From Hospital: Clinical Trial","year":2024,"lang":"en","type":"article","venue":"JMIR Cardio","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cloud computing; Medicine; Clinical trial; Computer science; Internal medicine; Operating system","score_opus":0.13511681623837307,"score_gpt":0.4812911539682763,"score_spread":0.34617433772990325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405224300","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033001605,0.0012855007,0.0009009545,0.13154079,0.859499,0.00008433264,0.004264358,0.0007452067,0.001349839],"genre_scores_gemma":[0.029827558,0.009754244,0.0073366477,0.31921232,0.5365135,0.0009882236,0.005659026,0.0022636717,0.08844475],"study_design_codex":"not_applicable","study_design_gemma":"randomized_trial","domain_scores_codex":[0.99083203,0.001777288,0.0020177376,0.0012326686,0.0031393848,0.0010007677],"domain_scores_gemma":[0.9319193,0.022900408,0.0035435928,0.0032892283,0.03546978,0.0028777313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0087164715,0.0028587407,0.0036703236,0.0029289662,0.0029008042,0.004879067,0.0045280578,0.01358385,0.062134974],"category_scores_gemma":[0.15479079,0.0013834381,0.0039042928,0.0024204692,0.0033458332,0.0025186075,0.0021392177,0.013171795,0.02426337],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016587152,0.000010467518,0.00018673427,0.0005118654,0.000077084325,0.00033260422,0.000048194037,0.00006694137,0.000058608053,0.0006065182,0.9935901,0.004344914],"study_design_scores_gemma":[0.0012742499,0.00020066934,0.0045812554,0.0036296526,0.00073825615,0.0023188016,0.00037911403,0.0018405607,0.0010961996,0.00634876,0.9773132,0.00027934273],"about_ca_topic_score_codex":0.021004843,"about_ca_topic_score_gemma":0.020688187,"teacher_disagreement_score":0.062134974,"about_ca_system_score_codex":0.0047003864,"about_ca_system_score_gemma":0.010150902,"threshold_uncertainty_score":0.2078622},"labels":[],"label_agreement":null},{"id":"W4405335764","doi":"10.7717/peerj-cs.2437","title":"Synthetic data analysis for early detection of Alzheimer progression through machine learning algorithms","year":2024,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Janssen Alzheimer Immunotherapy Research And Development; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; DoD Alzheimer's Disease Neuroimaging Initiative; H. Lundbeck A/S; Pfizer; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; Eli Lilly and Company; Biogen; Servier; BioClinica; Eisai; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association","keywords":"Computer science; Artificial intelligence; Machine learning; Algorithm","score_opus":0.27976249038513523,"score_gpt":0.5203675896024703,"score_spread":0.24060509921733508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405335764","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.078915544,0.0010546191,0.91524076,0.00043164825,0.00016645619,0.00023052546,0.0013897984,0.0014013401,0.001169367],"genre_scores_gemma":[0.70519865,0.00046436206,0.28868654,0.00009123058,0.00008709882,0.00052164117,0.0039743227,0.000091657894,0.0008845664],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985922,0.00069456047,0.00014775062,0.0002361512,0.00025262436,0.000076676944],"domain_scores_gemma":[0.9912374,0.0065204403,0.00049762335,0.00048612754,0.001138296,0.00012017855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005222699,0.001040097,0.0008926211,0.0021314279,0.00039309938,0.0010519004,0.0009248983,0.00083855056,0.0014168972],"category_scores_gemma":[0.015783679,0.0002879224,0.0012335888,0.0011594533,0.00045362982,0.0007861014,0.000691496,0.0012995568,0.0003014978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018870777,0.00012906484,0.0068286727,0.00016474366,0.00012602769,0.00007980977,0.000073277726,0.89673865,0.0010563638,0.0057387757,0.0018036347,0.087072276],"study_design_scores_gemma":[0.0000022957129,0.000020308391,0.0003938308,0.000006341781,0.0000036477636,0.000008585888,0.000009934181,0.9976562,0.00026804025,0.0013985868,0.00022839471,0.000003722321],"about_ca_topic_score_codex":0.004841245,"about_ca_topic_score_gemma":0.0023370662,"teacher_disagreement_score":0.005222699,"about_ca_system_score_codex":0.00078379683,"about_ca_system_score_gemma":0.0008834132,"threshold_uncertainty_score":0.027620554},"labels":[],"label_agreement":null},{"id":"W4405355207","doi":"10.48550/arxiv.2412.09376","title":"A comprehensive interpretable machine learning framework for Mild Cognitive Impairment and Alzheimer's disease diagnosis","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Cognitive impairment; Disease; Alzheimer's disease; Machine learning; Cognition; Artificial intelligence; Psychology; Cognitive psychology; Computer science; Medicine; Neuroscience; Internal medicine","score_opus":0.25369243475154263,"score_gpt":0.3715121947726608,"score_spread":0.11781976002111816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405355207","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007448305,0.0011225302,0.98789084,0.001237857,0.000067412635,0.00007729184,0.00040612317,0.0004521843,0.0012974042],"genre_scores_gemma":[0.4210187,0.0012435972,0.5713973,0.00064432435,0.00052090304,0.00036963224,0.0020210252,0.00009757129,0.0026869825],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972397,0.0013558854,0.0002120905,0.0005047151,0.00053640356,0.00015118186],"domain_scores_gemma":[0.99596125,0.0026375146,0.00040993557,0.00033170314,0.00051397586,0.00014556247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00558644,0.0013389305,0.0010509599,0.0030358385,0.0007034393,0.0024987212,0.0018555059,0.0013345407,0.0017048481],"category_scores_gemma":[0.01212644,0.0003260806,0.0017128289,0.0015615007,0.001217336,0.0013649507,0.0018015389,0.0023286617,0.00042358405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027744603,0.00032281748,0.012015365,0.00043216397,0.00047948142,0.0010802528,0.0007387245,0.40306175,0.004002896,0.19124237,0.007988436,0.37835833],"study_design_scores_gemma":[0.000017575521,0.000081681435,0.0019677437,0.00009043648,0.00006886674,0.0001990452,0.00006154629,0.8502491,0.00081587984,0.14168686,0.0047315746,0.000029711022],"about_ca_topic_score_codex":0.007269082,"about_ca_topic_score_gemma":0.0076989434,"teacher_disagreement_score":0.007269082,"about_ca_system_score_codex":0.0015487971,"about_ca_system_score_gemma":0.0022212574,"threshold_uncertainty_score":0.029544294},"labels":[],"label_agreement":null},{"id":"W4405356698","doi":"10.4271/j3248_202412","title":"Worldwide On-Board Diagnostic Requirements Overview","year":2024,"lang":"en","type":"standard","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.30523371352987166,"score_gpt":0.5515955339948775,"score_spread":0.24636182046500582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405356698","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035684898,0.002718269,0.074977964,0.013825397,0.002442536,0.002490086,0.010442683,0.009993775,0.8795408],"genre_scores_gemma":[0.036427893,0.006127136,0.055908274,0.008094336,0.0011043733,0.0018256425,0.046603385,0.0044510593,0.8394578],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9886049,0.0018206484,0.0009386098,0.000540354,0.0071687847,0.00092685985],"domain_scores_gemma":[0.98176897,0.0016590228,0.00086656533,0.0016206101,0.013150241,0.0009345905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011295053,0.0010322256,0.00045525076,0.0041658287,0.0013950797,0.006494054,0.0030490565,0.004296866,0.114730105],"category_scores_gemma":[0.015024215,0.00060078746,0.00080679636,0.0023733939,0.0006907419,0.0038451492,0.0025952465,0.002326206,0.15224008],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056895286,0.0001450369,0.00073669665,0.0004645211,0.000006754147,0.00027929482,0.00024849587,0.0015606966,0.0056074783,0.02489862,0.7784635,0.187532],"study_design_scores_gemma":[0.000008090786,0.000023694889,0.00055416714,0.0001932312,0.0000032838275,0.00015301409,0.000114087765,0.0005539528,0.0013512786,0.0012313451,0.9958015,0.000012440117],"about_ca_topic_score_codex":0.011784699,"about_ca_topic_score_gemma":0.010147252,"teacher_disagreement_score":0.114730105,"about_ca_system_score_codex":0.003342837,"about_ca_system_score_gemma":0.010197901,"threshold_uncertainty_score":0.38381046},"labels":[],"label_agreement":null},{"id":"W4405490158","doi":"10.1109/embc53108.2024.10782432","title":"Predicting Diabetes in Canadian Adults Using Machine Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"","keywords":"Computer science; Diabetes mellitus; Machine learning; Artificial intelligence; Medicine","score_opus":0.11977408419846856,"score_gpt":0.4618688578838736,"score_spread":0.34209477368540503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405490158","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9565678,0.0014024923,0.0047026444,0.00293026,0.0000841111,0.00015501709,0.025094228,0.00033835927,0.008724974],"genre_scores_gemma":[0.98021907,0.0008284929,0.007165983,0.00028212016,0.000024235662,0.000037995484,0.009851201,0.000012086916,0.0015789394],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99946934,0.000069303336,0.000033817523,0.0000952583,0.00022145071,0.00011074832],"domain_scores_gemma":[0.9982687,0.00036270445,0.00016122035,0.000058692396,0.0009811515,0.00016742072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012407611,0.0005568622,0.00029753067,0.0015797482,0.0009210062,0.00084789697,0.000858809,0.00037834185,0.002013673],"category_scores_gemma":[0.0051545813,0.00016778195,0.00060357904,0.0021151216,0.00019763902,0.00030186854,0.00041230276,0.00057715335,0.0004530229],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016729567,0.00013838804,0.90234977,0.00012423031,0.00014778961,0.00009559002,0.00021390832,0.016619073,0.0003063061,0.0006448528,0.012518067,0.06667471],"study_design_scores_gemma":[0.000055131106,0.00010711811,0.7210711,0.0001481069,0.00014620408,0.0001409367,0.0007964841,0.26611295,0.0009593493,0.0006984372,0.009708005,0.000056190707],"about_ca_topic_score_codex":0.9873653,"about_ca_topic_score_gemma":0.987288,"teacher_disagreement_score":0.012998522,"about_ca_system_score_codex":0.012998522,"about_ca_system_score_gemma":0.017817695,"threshold_uncertainty_score":0.0943113},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"split"},{"id":"W4405750254","doi":"10.18280/isi.290618","title":"Advanced Disease Detection via Transfer Learning and Convolutional Neural","year":2024,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Transfer of learning; Convolutional neural network; Computer science; Artificial intelligence","score_opus":0.038699556327493854,"score_gpt":0.36381959160149796,"score_spread":0.3251200352740041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405750254","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11906161,0.0024054868,0.8702428,0.00079952786,0.00020568636,0.00010764134,0.00055780757,0.0029878896,0.0036316088],"genre_scores_gemma":[0.8674376,0.00088176207,0.118200034,0.0002805701,0.00017782507,0.00009854536,0.0012085723,0.00007727578,0.011637817],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997507,0.00004350094,0.000012630385,0.00006944341,0.000059894624,0.00006382466],"domain_scores_gemma":[0.9994535,0.00023528954,0.000054222855,0.00007273986,0.00014815063,0.000036181475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095465936,0.00070024986,0.00074780633,0.0011066403,0.00028463514,0.00072187436,0.00113613,0.0009814341,0.0024142622],"category_scores_gemma":[0.0016554791,0.00029327552,0.0006561227,0.00085589004,0.00036853168,0.00092363724,0.0010692033,0.0010776032,0.0010723288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042941858,0.00044566597,0.00532542,0.00014438007,0.00020791704,0.00021317796,0.00006594523,0.16019872,0.020372704,0.005045198,0.0065772887,0.80097425],"study_design_scores_gemma":[0.0000081603675,0.00004121325,0.0009866351,0.000007490088,0.000017712839,0.00004747988,0.0000070698516,0.9909995,0.00393884,0.0033166583,0.0006222309,0.0000069355874],"about_ca_topic_score_codex":0.0069159027,"about_ca_topic_score_gemma":0.0068156705,"teacher_disagreement_score":0.0069159027,"about_ca_system_score_codex":0.00061432034,"about_ca_system_score_gemma":0.0007908032,"threshold_uncertainty_score":0.013751268},"labels":[],"label_agreement":null},{"id":"W4405750350","doi":"10.1016/j.jval.2024.10.2421","title":"MSR187 Automated Data Extraction in Systematic Literature Reviews (SLRs): Assessing the Accuracy and Reliability of a Large Language Model (LLM)","year":2024,"lang":"en","type":"article","venue":"Value in Health","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thermo Fisher Scientific (Canada)","funders":"","keywords":"Computer science; Data extraction; Reliability (semiconductor); Natural language processing; Artificial intelligence; Data mining; MEDLINE; Chemistry","score_opus":0.27148360576928654,"score_gpt":0.5738235770727436,"score_spread":0.302339971303457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405750350","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15091899,0.2047813,0.33055818,0.013828946,0.0023659526,0.105211236,0.16717792,0.01607943,0.009078021],"genre_scores_gemma":[0.2836557,0.014420696,0.58546644,0.0024703944,0.00047703393,0.08288481,0.028590241,0.0010341933,0.0010005799],"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.5209242,0.26683068,0.16978821,0.016934307,0.024317732,0.0012048193],"domain_scores_gemma":[0.1504925,0.74233,0.054551665,0.032175403,0.019111931,0.0013385412],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2975529,0.002834897,0.010154933,0.04166402,0.0030323092,0.008327347,0.0049123424,0.0036204143,0.008248477],"category_scores_gemma":[0.70542246,0.003580704,0.026976263,0.02134186,0.0030636746,0.008192613,0.010026526,0.0026581187,0.0020149453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00733305,0.0003631473,0.04547852,0.5419404,0.114469044,0.0006817752,0.005784465,0.006705114,0.0036419649,0.0061548892,0.021433843,0.24601382],"study_design_scores_gemma":[0.01738989,0.006573766,0.08017766,0.22283106,0.4239161,0.002491613,0.0043623517,0.06618527,0.009789945,0.032363135,0.13139574,0.002523492],"about_ca_topic_score_codex":0.005099252,"about_ca_topic_score_gemma":0.019416384,"teacher_disagreement_score":0.70244706,"about_ca_system_score_codex":0.0047927257,"about_ca_system_score_gemma":0.027375333,"threshold_uncertainty_score":0.8662423},"labels":[],"label_agreement":null},{"id":"W4405901227","doi":"10.1016/j.dajour.2024.100539","title":"An investigation of ensemble learning techniques for obesity risk prediction using lifestyle data","year":2024,"lang":"en","type":"article","venue":"Decision Analytics Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Ensemble learning; Obesity; Computer science; Artificial intelligence; Machine learning; Medicine; Internal medicine","score_opus":0.291383933299753,"score_gpt":0.5328043474961597,"score_spread":0.2414204141964067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405901227","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18084097,0.0031755401,0.80964625,0.0012593663,0.0003439183,0.00016834016,0.0005311668,0.0014465555,0.0025879731],"genre_scores_gemma":[0.8199803,0.0013309319,0.17571013,0.00025166303,0.00019351975,0.000122344,0.0010589894,0.000053722244,0.001298277],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877256,0.00055328856,0.00009359468,0.0002151386,0.00025774,0.00010761347],"domain_scores_gemma":[0.9965668,0.0017256575,0.00019059618,0.00040828533,0.0010098098,0.00009891281],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047012493,0.00094903214,0.0013236369,0.0017227797,0.00046118165,0.0009593525,0.0010099708,0.00071737904,0.0006822827],"category_scores_gemma":[0.006768917,0.00024416088,0.0014037229,0.0014118542,0.00017064631,0.0012885623,0.0006554461,0.0012433372,0.00028948745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030744553,0.00037535976,0.032711968,0.00013302195,0.0006502685,0.00021510063,0.0002161403,0.4012838,0.0030208658,0.0030586342,0.0033859755,0.55464137],"study_design_scores_gemma":[0.0000065895065,0.00007833315,0.00222342,0.000019978506,0.000057374178,0.00003794329,0.00003089372,0.9951108,0.00062019035,0.0011793762,0.0006246709,0.0000103393995],"about_ca_topic_score_codex":0.006031052,"about_ca_topic_score_gemma":0.0054069976,"teacher_disagreement_score":0.006031052,"about_ca_system_score_codex":0.0003794697,"about_ca_system_score_gemma":0.000736986,"threshold_uncertainty_score":0.024862826},"labels":[],"label_agreement":null},{"id":"W4405920746","doi":"10.1007/978-3-031-77299-3_4","title":"Predicting Patient Length of Stay Using Machine Learning Models","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes on data engineering and communications technologies","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence","score_opus":0.2255652909921222,"score_gpt":0.3977211098361476,"score_spread":0.17215581884402542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405920746","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6027791,0.0036012412,0.37038532,0.0033371309,0.00056859077,0.00009673594,0.0054378337,0.0019103907,0.011883722],"genre_scores_gemma":[0.9402687,0.0011006464,0.045072254,0.00015814874,0.00025033447,0.000078798585,0.004488355,0.000094107316,0.008488662],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99979776,0.00005077059,0.000018824809,0.00005264836,0.00004994144,0.000030038698],"domain_scores_gemma":[0.99788934,0.0017004617,0.00014569481,0.00004460768,0.0001623975,0.000057500805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006527991,0.0006270025,0.00054060924,0.0010378462,0.00019043112,0.00090277346,0.00059861917,0.000620679,0.0028285566],"category_scores_gemma":[0.003386135,0.0002480841,0.0007029545,0.0010241425,0.00011543598,0.0006576558,0.00025293248,0.001031253,0.0011198919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003606306,0.00049490546,0.105845034,0.00008631901,0.00021510785,0.00015553314,0.00006927142,0.57860625,0.0011311355,0.0017846058,0.013473059,0.2977782],"study_design_scores_gemma":[0.000005412944,0.00004209356,0.006654027,0.000010310023,0.000014183327,0.000029902652,0.000019251558,0.99108803,0.00023383451,0.0015114282,0.00038453724,0.0000069325765],"about_ca_topic_score_codex":0.009266958,"about_ca_topic_score_gemma":0.011459005,"teacher_disagreement_score":0.009266958,"about_ca_system_score_codex":0.000617899,"about_ca_system_score_gemma":0.0004942997,"threshold_uncertainty_score":0.01842606},"labels":[],"label_agreement":null},{"id":"W4405944176","doi":"10.1007/979-8-8688-1061-9_13","title":"Continuously Learn with AI","year":2024,"lang":"en","type":"book-chapter","venue":"Design Thinking","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science","score_opus":0.16784175676827867,"score_gpt":0.42641768806287017,"score_spread":0.2585759312945915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405944176","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017064286,0.016703948,0.03535202,0.017840728,0.0017164641,0.000058655245,0.00009923795,0.00047246693,0.92605],"genre_scores_gemma":[0.057344534,0.02095232,0.04491028,0.009230775,0.0015550334,0.00028153963,0.0003264531,0.00047903197,0.86491996],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992785,0.00023395917,0.000020949086,0.000116652445,0.0002922396,0.000057799713],"domain_scores_gemma":[0.99902415,0.0005658375,0.000026828453,0.0001380054,0.00012704283,0.00011813192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010573248,0.0007160908,0.0003145975,0.00069788843,0.0017492308,0.006449236,0.0010048121,0.0020079901,0.028379664],"category_scores_gemma":[0.0022116557,0.0003434478,0.00057250075,0.0005376621,0.005091437,0.008559869,0.0030436274,0.0052351826,0.011004807],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000114384575,0.000038176695,0.00013514796,0.0001971809,0.000008298506,0.000058430982,0.0025276416,0.0007629706,0.0005060082,0.79246753,0.112869054,0.0904181],"study_design_scores_gemma":[0.0000028218628,0.000014060835,0.000075237294,0.00017304604,0.000003419176,0.00008614645,0.00038931702,0.00049173116,0.00023739318,0.18129103,0.81722933,0.0000065460335],"about_ca_topic_score_codex":0.0013619914,"about_ca_topic_score_gemma":0.0022665844,"teacher_disagreement_score":0.028379664,"about_ca_system_score_codex":0.0022873515,"about_ca_system_score_gemma":0.0019449013,"threshold_uncertainty_score":0.09493941},"labels":[],"label_agreement":null},{"id":"W4406033721","doi":"10.1145/3704522.3704550","title":"Short Paper: Dementia Patient Health, Prescriptions ML Dataset: LightGBM Classification of XAI-based LIME and SHAP for Dementia Detection","year":2024,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Dementia; Medical prescription; Computer science; Artificial intelligence; Medicine; Internal medicine; Disease; Nursing","score_opus":0.1807604099235828,"score_gpt":0.46500150733124884,"score_spread":0.284241097407666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406033721","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025807029,0.0011669013,0.0015472234,0.0017506991,0.0010284481,0.00024639833,0.96189076,0.0034826375,0.0030799275],"genre_scores_gemma":[0.020198131,0.00023896179,0.0038256824,0.00048362513,0.00019230714,0.00016851973,0.97127706,0.00011650866,0.0034993454],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931085,0.00009954583,0.000084326166,0.0001713222,0.00018308304,0.00015079619],"domain_scores_gemma":[0.9987715,0.00021281815,0.00009396163,0.0002497539,0.00044080612,0.00023122065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008735857,0.0019593383,0.0011382245,0.002305601,0.0008079307,0.0014238803,0.002026549,0.002766188,0.015001277],"category_scores_gemma":[0.0042218138,0.000416879,0.0015688782,0.0018674922,0.0003620226,0.0008209305,0.0011747775,0.0012907499,0.019741815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074331864,0.00038106434,0.017010873,0.00059609825,0.00017645367,0.00022180256,0.0000525484,0.0011906513,0.0018506707,0.00021888464,0.94041085,0.037146695],"study_design_scores_gemma":[0.001862626,0.00085506635,0.18143004,0.0011884924,0.00070934324,0.0013718533,0.0012446435,0.039371546,0.013739482,0.0036674081,0.75423634,0.00032315185],"about_ca_topic_score_codex":0.043549992,"about_ca_topic_score_gemma":0.083208136,"teacher_disagreement_score":0.043549992,"about_ca_system_score_codex":0.0012833017,"about_ca_system_score_gemma":0.002154524,"threshold_uncertainty_score":0.08659297},"labels":[],"label_agreement":null},{"id":"W4406093730","doi":"10.18280/isi.570623","title":"Development of Stroke Prediction System Using Neural Network with Sigmoid Activation Function","year":2024,"lang":"en","type":"article","venue":"Journal Européen des Systèmes Automatisés","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Covenant University Centre for Research, Innovation and Discovery; Covenant University","keywords":"Sigmoid function; Artificial neural network; Activation function; Stroke (engine); Computer science; Function (biology); Artificial intelligence; Engineering; Biology","score_opus":0.09983424378720142,"score_gpt":0.3760222241121086,"score_spread":0.2761879803249072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406093730","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19794042,0.0013118465,0.7763623,0.00067356153,0.000593558,0.00051676517,0.0014098495,0.011703137,0.009488496],"genre_scores_gemma":[0.82772124,0.0009137077,0.15181464,0.00023612974,0.00012350004,0.00036927554,0.0019297526,0.000101573634,0.016790166],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999037,0.000008673226,0.000010623103,0.00003751437,0.00002670049,0.0000128659985],"domain_scores_gemma":[0.9998543,0.000023205826,0.00000794154,0.000009149762,0.00009551071,0.000009838212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028824373,0.0004452093,0.0004587607,0.0005070589,0.00035390776,0.00040150608,0.00063065713,0.00046442926,0.0024192848],"category_scores_gemma":[0.00042482003,0.00025224398,0.0003326756,0.00029896377,0.0000741187,0.0004400543,0.00029021036,0.00034062786,0.0009276749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058681634,0.0004126094,0.022704715,0.0002806564,0.00020680396,0.00085575815,0.00009977542,0.11082527,0.037925925,0.0010308828,0.015335089,0.80973566],"study_design_scores_gemma":[0.00003805811,0.00015351146,0.0082532,0.000029188293,0.00011680028,0.00023995822,0.000034437835,0.96357363,0.023551907,0.0005554239,0.0034256647,0.000028203038],"about_ca_topic_score_codex":0.008769185,"about_ca_topic_score_gemma":0.008329987,"teacher_disagreement_score":0.008769185,"about_ca_system_score_codex":0.0002867406,"about_ca_system_score_gemma":0.0006498552,"threshold_uncertainty_score":0.017436266},"labels":[],"label_agreement":null},{"id":"W4406147622","doi":"10.1017/s0266462324003076","title":"PD45 A Rapid Evidence Synthesis Method For Cancer Screening Recommendations In A Hospital Setting","year":2024,"lang":"en","type":"article","venue":"International Journal of Technology Assessment in Health Care","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Cancer; Intensive care medicine; Family medicine; Internal medicine","score_opus":0.11822197695798897,"score_gpt":0.5917564095914983,"score_spread":0.47353443263350936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406147622","genre_codex":"protocol","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003395521,0.019712444,0.2946704,0.00786142,0.004989558,0.50671035,0.1266323,0.009992034,0.026035972],"genre_scores_gemma":[0.008362777,0.0027775918,0.49818367,0.00063473894,0.00016474235,0.48252216,0.0052844975,0.00032545932,0.0017444098],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.6500433,0.20926404,0.09714795,0.014640144,0.026666416,0.0022381546],"domain_scores_gemma":[0.4434078,0.43719715,0.030101877,0.025452502,0.061445046,0.002395609],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21531147,0.006269635,0.014891274,0.042889662,0.0030149866,0.011468754,0.006938264,0.0064702146,0.12605858],"category_scores_gemma":[0.5683359,0.0057897964,0.026351511,0.035743132,0.0030291004,0.00650033,0.012415175,0.007081473,0.013779253],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022278705,0.0001866575,0.001100715,0.656207,0.012758559,0.00032648098,0.0035023512,0.0029463319,0.0009832403,0.016048422,0.08523584,0.21847652],"study_design_scores_gemma":[0.01695048,0.0012301629,0.005879053,0.35431466,0.035017245,0.00064269936,0.00357676,0.012446059,0.0043099676,0.07052655,0.49413106,0.00097535853],"about_ca_topic_score_codex":0.0054627038,"about_ca_topic_score_gemma":0.0064629815,"teacher_disagreement_score":0.21531147,"about_ca_system_score_codex":0.011611418,"about_ca_system_score_gemma":0.04300865,"threshold_uncertainty_score":0.96766067},"labels":[],"label_agreement":null},{"id":"W4406218705","doi":"10.18280/ts.410602","title":"An Effective Prediction Model of Myocardial Infarction Using Convolution Kernel Weight Based Convolutional Neural Network","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Kernel (algebra); Convolution (computer science); Computer science; Artificial intelligence; Pattern recognition (psychology); Artificial neural network; Mathematics","score_opus":0.08915799044625757,"score_gpt":0.40144213055842853,"score_spread":0.312284140112171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406218705","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21040033,0.002708251,0.7802505,0.0008553571,0.00031329328,0.00006692247,0.0005736448,0.0010673482,0.0037643933],"genre_scores_gemma":[0.9633097,0.0007681663,0.029446322,0.00008919213,0.000080930404,0.0000726397,0.00049026235,0.00003090999,0.0057118447],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99986315,0.000015378822,0.000009157403,0.000051054074,0.00003184868,0.000029341049],"domain_scores_gemma":[0.99982834,0.0000564499,0.000015780732,0.000008602252,0.000080924234,0.000009880812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004022775,0.00053734734,0.00066098745,0.00048558658,0.0002862836,0.0005928385,0.0009246199,0.0006851935,0.0010474584],"category_scores_gemma":[0.0007372188,0.0002686298,0.00048013972,0.0004124262,0.00018458469,0.0006687167,0.0003921498,0.00059270515,0.00029003833],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026399022,0.00021457303,0.0075454875,0.0000970826,0.0001498127,0.00025693863,0.000047020727,0.8006548,0.0064329314,0.004406079,0.0033402795,0.17659098],"study_design_scores_gemma":[0.000002265683,0.0000075813737,0.00041518756,0.0000016885143,0.000011563842,0.000011581942,0.0000012452318,0.998979,0.00022006298,0.000269873,0.00007745496,0.0000025519282],"about_ca_topic_score_codex":0.0260055,"about_ca_topic_score_gemma":0.021604897,"teacher_disagreement_score":0.0260055,"about_ca_system_score_codex":0.0006332473,"about_ca_system_score_gemma":0.0010243249,"threshold_uncertainty_score":0.05170828},"labels":[],"label_agreement":null},{"id":"W4406223044","doi":"10.1002/alz.093796","title":"Development and Validation of Natural Language Processing (NLP)‐Based Risk Prediction Model for Cognitive Impairment in Geriatric Patients","year":2024,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Language impairment; Cognitive impairment; Natural language processing; Artificial intelligence; Cognition; Computer science; Psychology; Developmental psychology; Neuroscience","score_opus":0.07355722728517951,"score_gpt":0.4125980395598922,"score_spread":0.3390408122747127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406223044","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7411227,0.0008017562,0.24688542,0.0014743783,0.00021324644,0.00061088876,0.0031242666,0.0032485204,0.0025187596],"genre_scores_gemma":[0.95568484,0.00013652055,0.040694892,0.0001643948,0.00003916209,0.0002809741,0.0021237843,0.000024342049,0.00085108355],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99950874,0.00014258352,0.000057994046,0.00017263372,0.000060932776,0.00005713055],"domain_scores_gemma":[0.9985098,0.00094053545,0.000078064564,0.000052329415,0.00036935965,0.000049843155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019806272,0.0009441256,0.00064643123,0.0011473672,0.00036519047,0.00086951576,0.0008134999,0.0007685184,0.0016750953],"category_scores_gemma":[0.00397595,0.0002763557,0.00096959446,0.0004308223,0.00020326566,0.0005274143,0.0005962012,0.0011415184,0.00060272054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008490866,0.0015915927,0.123004004,0.00018923887,0.00051889266,0.00093116175,0.00025850424,0.59901166,0.0043960097,0.0008483739,0.007338305,0.26106316],"study_design_scores_gemma":[0.000010187854,0.000045384426,0.0027122514,0.000009732059,0.00002216193,0.00002648596,0.000015511056,0.9964414,0.00035289163,0.00024515664,0.00011407326,0.0000047566164],"about_ca_topic_score_codex":0.018578006,"about_ca_topic_score_gemma":0.00985999,"teacher_disagreement_score":0.018578006,"about_ca_system_score_codex":0.0010813134,"about_ca_system_score_gemma":0.001553108,"threshold_uncertainty_score":0.03693974},"labels":[],"label_agreement":null},{"id":"W4406223688","doi":"10.1002/alz.095754","title":"Performance of plasma biomarkers for diagnosis and prediction of dementia in a Brazilian cohort","year":2024,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Dementia; Cohort; Medicine; Internal medicine; Psychology; Disease","score_opus":0.09265502694105483,"score_gpt":0.4039613728262567,"score_spread":0.3113063458852019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406223688","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99830997,0.0004027999,0.00020145977,0.00007262013,0.000009196155,0.000036169902,0.0003401552,0.000005675981,0.0006220688],"genre_scores_gemma":[0.99914956,0.00020274855,0.00021160264,0.00002850227,0.0000051599304,0.00002708958,0.0002680337,0.000002243188,0.00010500515],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99943084,0.00016493484,0.0000527445,0.00017311749,0.000089949484,0.00008838663],"domain_scores_gemma":[0.9982704,0.0002381346,0.00047383588,0.00028782318,0.00051492633,0.00021479678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001893761,0.00066891016,0.00046066276,0.0013120403,0.00065265165,0.00092728646,0.00047807893,0.00054684666,0.00074688543],"category_scores_gemma":[0.0050384365,0.0005232615,0.0008416112,0.0008020286,0.00039236798,0.00024358259,0.00066041446,0.00044368688,0.000280285],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015396473,0.000049761486,0.9960109,0.000016446053,0.000097402895,0.0001135477,0.00042162224,0.00003055104,0.00056597154,0.000028374285,0.000113838716,0.0023975123],"study_design_scores_gemma":[0.000034178713,0.00015544241,0.99752206,0.000031406806,0.0001154629,0.0003996388,0.0005001961,0.0004287846,0.00015845458,0.00009141858,0.00055170484,0.000011169216],"about_ca_topic_score_codex":0.059905443,"about_ca_topic_score_gemma":0.036464393,"teacher_disagreement_score":0.059905443,"about_ca_system_score_codex":0.00074863486,"about_ca_system_score_gemma":0.0007831055,"threshold_uncertainty_score":0.119113505},"labels":[],"label_agreement":null},{"id":"W4406223742","doi":"10.1002/alz.094096","title":"Performance of an AI‐based prediction model versus stratified thresholds using plasma biomarkers for biological staging of AD","year":2024,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"","keywords":"Artificial intelligence; Computer science","score_opus":0.30182369474885745,"score_gpt":0.4714628494883583,"score_spread":0.16963915473950086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406223742","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8633536,0.0012406829,0.13069363,0.0007010006,0.00016664315,0.00016954058,0.00072872586,0.0011478651,0.0017982938],"genre_scores_gemma":[0.9864503,0.000086972344,0.012227548,0.000068106776,0.000028636843,0.00006912034,0.0005050441,0.000018008212,0.000546079],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990978,0.0003458357,0.000073261355,0.00027053722,0.000098381344,0.000114214185],"domain_scores_gemma":[0.99745756,0.0015839298,0.00017300485,0.00011538245,0.00053300813,0.00013708253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042214748,0.0014743796,0.00114404,0.0012144541,0.00042958872,0.0013108591,0.0009877806,0.0011178608,0.0013776658],"category_scores_gemma":[0.0064258035,0.00027955082,0.0011875327,0.000578974,0.00031742526,0.00073901075,0.0007001631,0.0012660163,0.00052813825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016679065,0.00077408744,0.071432084,0.00013202982,0.0005614347,0.0002361578,0.00016838948,0.78485286,0.0050905747,0.00072980294,0.0024489963,0.13190566],"study_design_scores_gemma":[0.000011373695,0.00010999164,0.0023513888,0.000010259835,0.00004276693,0.000019474908,0.000011572598,0.9966606,0.00046548725,0.00024376217,0.000065550856,0.000007817227],"about_ca_topic_score_codex":0.009069669,"about_ca_topic_score_gemma":0.003302499,"teacher_disagreement_score":0.009069669,"about_ca_system_score_codex":0.0009377117,"about_ca_system_score_gemma":0.0012637868,"threshold_uncertainty_score":0.022325516},"labels":[],"label_agreement":null},{"id":"W4406224415","doi":"10.1002/alz.088942","title":"Development and Validation of Natural Language Processing (NLP)‐Based Risk Prediction Model for Cognitive Impairment in Geriatric Patients","year":2024,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cognitive impairment; Artificial intelligence; Natural language processing; Language impairment; Computer science; Cognition; Psychology; Developmental psychology; Neuroscience","score_opus":0.07355722728517951,"score_gpt":0.4125980395598922,"score_spread":0.3390408122747127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406224415","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7411227,0.0008017562,0.24688542,0.0014743783,0.00021324644,0.00061088876,0.0031242666,0.0032485204,0.0025187596],"genre_scores_gemma":[0.95568484,0.00013652055,0.040694892,0.0001643948,0.00003916209,0.0002809741,0.0021237843,0.000024342049,0.00085108355],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99950874,0.00014258352,0.000057994046,0.00017263372,0.000060932776,0.00005713055],"domain_scores_gemma":[0.9985098,0.00094053545,0.000078064564,0.000052329415,0.00036935965,0.000049843155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019806272,0.0009441256,0.00064643123,0.0011473672,0.00036519047,0.00086951576,0.0008134999,0.0007685184,0.0016750953],"category_scores_gemma":[0.00397595,0.0002763557,0.00096959446,0.0004308223,0.00020326566,0.0005274143,0.0005962012,0.0011415184,0.00060272054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008490866,0.0015915927,0.123004004,0.00018923887,0.00051889266,0.00093116175,0.00025850424,0.59901166,0.0043960097,0.0008483739,0.007338305,0.26106316],"study_design_scores_gemma":[0.000010187854,0.000045384426,0.0027122514,0.000009732059,0.00002216193,0.00002648596,0.000015511056,0.9964414,0.00035289163,0.00024515664,0.00011407326,0.0000047566164],"about_ca_topic_score_codex":0.018578006,"about_ca_topic_score_gemma":0.00985999,"teacher_disagreement_score":0.018578006,"about_ca_system_score_codex":0.0010813134,"about_ca_system_score_gemma":0.001553108,"threshold_uncertainty_score":0.03693974},"labels":[],"label_agreement":null},{"id":"W4406505896","doi":"10.1016/s0967-0653(98)85466-5","title":"10.1016/s0967-0653(98)85466-5","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Java; Computer science; Programming language","score_opus":0.06373969397693514,"score_gpt":0.35833981613474286,"score_spread":0.29460012215780773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406505896","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00043847816,0.0004554873,0.0009071089,0.0004188303,0.00033497476,0.00012557351,0.0008390138,0.0012944121,0.99518615],"genre_scores_gemma":[0.0005118487,0.00020661544,0.00044122984,0.00023799375,0.00006863587,0.0000638819,0.0004030097,0.00021562977,0.99785125],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99908566,0.000064836444,0.00008115732,0.00033297954,0.00024439796,0.00019098773],"domain_scores_gemma":[0.99659544,0.0009368223,0.00021468334,0.00046929537,0.0007312147,0.0010525687],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0014181519,0.0032541782,0.0022069677,0.0033803054,0.0027839257,0.004884369,0.0038444828,0.0061923712,0.98998123],"category_scores_gemma":[0.002508214,0.001201735,0.0017907984,0.0032507356,0.0023082276,0.0072890087,0.0043203067,0.0034909805,0.9941801],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035316934,0.00021804808,0.0008387255,0.00057871593,0.000043226726,0.00024370206,0.00012500866,0.00046951737,0.0017950606,0.0046905284,0.42077738,0.56986696],"study_design_scores_gemma":[0.000055555243,0.0001221236,0.0006532755,0.00037740907,0.000017053595,0.00030711657,0.00012758741,0.0002634981,0.00031771147,0.0006163484,0.99711204,0.000030268677],"about_ca_topic_score_codex":0.004740756,"about_ca_topic_score_gemma":0.0039408766,"teacher_disagreement_score":0.010018766,"about_ca_system_score_codex":0.0011574797,"about_ca_system_score_gemma":0.0011601495,"threshold_uncertainty_score":0.014290571},"labels":[],"label_agreement":null},{"id":"W4406574754","doi":"10.1016/s1558-0164(10)70383-7","title":"10.1016/s1558-0164(10)70383-7","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Intensive care medicine","score_opus":0.07375465048131295,"score_gpt":0.37940886827918036,"score_spread":0.3056542177978674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406574754","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00031491986,0.00037472625,0.0009077959,0.00036919225,0.0002755874,0.000082119004,0.000771978,0.0012068468,0.9956968],"genre_scores_gemma":[0.00045658124,0.00016505113,0.00038143172,0.00018113772,0.00006256079,0.00004285755,0.0004060608,0.00018510359,0.9981193],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99919766,0.0000590723,0.00006576185,0.00027022004,0.00024471994,0.00016252889],"domain_scores_gemma":[0.99742174,0.00069140026,0.00016563866,0.0003547299,0.0005218814,0.00084461336],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012265642,0.002794899,0.001718842,0.0030569665,0.0025207119,0.0046733445,0.0033267997,0.005949975,0.9895328],"category_scores_gemma":[0.0021041639,0.0010019729,0.0014397969,0.0029580393,0.0018765089,0.0062240222,0.003939959,0.0028183963,0.99365306],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002521579,0.00017800093,0.0006818442,0.00045664943,0.000031386477,0.0002082625,0.000094848496,0.0004318667,0.0017115,0.0053045796,0.41285193,0.57779694],"study_design_scores_gemma":[0.00003827519,0.000075595824,0.0004776118,0.0002483135,0.000010827409,0.00021308319,0.00008767547,0.00022281955,0.000310275,0.00064043887,0.9976539,0.000021166392],"about_ca_topic_score_codex":0.0043493393,"about_ca_topic_score_gemma":0.0039834525,"teacher_disagreement_score":0.010467172,"about_ca_system_score_codex":0.0012291975,"about_ca_system_score_gemma":0.0013158089,"threshold_uncertainty_score":0.014930069},"labels":[],"label_agreement":null},{"id":"W4406724834","doi":"10.2196/57874","title":"AI Machine Learning–Based Diabetes Prediction in Older Adults in South Korea: Cross-Sectional Analysis","year":2025,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Medicine; Diabetes mellitus; Machine learning; Anxiety; Gradient boosting; Internal medicine; Random forest; Algorithm; Endocrinology; Mathematics; Computer science","score_opus":0.11338743137608263,"score_gpt":0.5449026758086878,"score_spread":0.43151524443260514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406724834","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99862874,0.00021208919,0.0002360261,0.000043943408,0.0000074298123,0.00002293713,0.0007023493,0.000004129906,0.00014252131],"genre_scores_gemma":[0.9982864,0.000107044216,0.00031143372,0.00004239715,0.0000067103338,0.00003414868,0.0010821073,0.000002376182,0.00012729467],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992901,0.00021439434,0.00014145984,0.0001915577,0.000090826856,0.00007172317],"domain_scores_gemma":[0.9980732,0.00039536794,0.0006014629,0.00025671523,0.00046389413,0.0002093872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020793255,0.00047030655,0.0003896644,0.0009896844,0.0003745979,0.000636688,0.00047935228,0.00043338252,0.0012114294],"category_scores_gemma":[0.003096279,0.00041934938,0.0010149934,0.0011991725,0.00016621525,0.00060484285,0.0006559513,0.0007526191,0.00028767297],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000085598745,0.00006166599,0.9985145,0.00001394858,0.000104606675,0.000022496148,0.00003920619,0.00007514236,0.00004050164,0.0000067830747,0.0000845144,0.0009511472],"study_design_scores_gemma":[0.00001798669,0.0001716157,0.9969054,0.000019293864,0.00015183992,0.00012018311,0.00031128922,0.0020019547,0.000057062993,0.00002795963,0.00020925753,0.0000062652284],"about_ca_topic_score_codex":0.0072922804,"about_ca_topic_score_gemma":0.008405177,"teacher_disagreement_score":0.0072922804,"about_ca_system_score_codex":0.00040288194,"about_ca_system_score_gemma":0.0004515359,"threshold_uncertainty_score":0.014499664},"labels":[],"label_agreement":null},{"id":"W4406782139","doi":"10.54254/2755-2721/2025.20609","title":"Application of Supervised Learning Algorithms in Data Prediction","year":2025,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ste. Anne's Hospital","funders":"","keywords":"Machine learning; Computer science; Artificial intelligence; Semi-supervised learning; Online machine learning; Supervised learning; Instance-based learning; Context (archaeology); Unsupervised learning; Algorithm; Quality (philosophy); Artificial neural network","score_opus":0.0576021101109556,"score_gpt":0.38887511029541705,"score_spread":0.33127300018446143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406782139","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011496304,0.0014174475,0.98371845,0.00054877606,0.0001075639,0.00011029527,0.00012220432,0.0005920067,0.0018869243],"genre_scores_gemma":[0.40085587,0.0022206593,0.5933486,0.00035514793,0.00042205118,0.00034449293,0.0007497553,0.00012904646,0.0015743627],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9908771,0.004837646,0.00068922713,0.0011998819,0.0022272386,0.00016890236],"domain_scores_gemma":[0.9664411,0.02535841,0.001787337,0.0021072293,0.004082554,0.00022345305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009860391,0.0010053867,0.0015059393,0.003101414,0.0007048317,0.0021110575,0.0014316399,0.0012914767,0.0009778356],"category_scores_gemma":[0.032458905,0.00047871988,0.0010357759,0.0028471234,0.0011814096,0.0022858437,0.0011943078,0.0020152577,0.0005939722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018275535,0.0003905157,0.014976824,0.00051622954,0.00051445386,0.00017963535,0.00036245916,0.44754988,0.0016916903,0.031795096,0.004725475,0.49711502],"study_design_scores_gemma":[0.000011925601,0.000049625505,0.0008110317,0.000053354353,0.000025479936,0.00005858941,0.000041678497,0.97066003,0.0014578801,0.024735315,0.002077288,0.000017810915],"about_ca_topic_score_codex":0.0033002633,"about_ca_topic_score_gemma":0.002530849,"teacher_disagreement_score":0.009860391,"about_ca_system_score_codex":0.0010012711,"about_ca_system_score_gemma":0.002116645,"threshold_uncertainty_score":0.05214739},"labels":[],"label_agreement":null},{"id":"W4406811075","doi":"10.18280/isi.300122","title":"Prediction of Depression Levels in Girl Students Using Machine Learning Algorithms","year":2025,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Girl; Depression (economics); Algorithm; Computer science; Machine learning; Artificial intelligence; Psychology; Developmental psychology","score_opus":0.12201078787410694,"score_gpt":0.4268366810287675,"score_spread":0.3048258931546606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406811075","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.967866,0.00057061325,0.02447042,0.00074754545,0.00011718506,0.0001675224,0.0038981717,0.00032753564,0.0018349455],"genre_scores_gemma":[0.9839454,0.00024993668,0.01032925,0.000074037576,0.000056627512,0.00010599367,0.0039459905,0.000012984157,0.001279791],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99972934,0.0000584151,0.00003452116,0.00007586255,0.00004733839,0.00005448906],"domain_scores_gemma":[0.9989427,0.00052502716,0.00018512188,0.000054775024,0.00018486449,0.00010757905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006710162,0.0007518754,0.0006788549,0.0016633398,0.00029004054,0.0007933711,0.00056783337,0.00075081433,0.002211032],"category_scores_gemma":[0.0026344364,0.00020674059,0.00086051883,0.0007250586,0.00014768066,0.00043406244,0.0004573434,0.0009657126,0.0009852641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010033484,0.0012386729,0.83530456,0.00008798458,0.00025651642,0.00031149393,0.00011066079,0.05125404,0.001737035,0.00031109434,0.0047690035,0.10361554],"study_design_scores_gemma":[0.00004903052,0.0004960167,0.15793292,0.000054562246,0.00006373762,0.00019302184,0.0002806446,0.837495,0.0013766361,0.0009551261,0.0010809586,0.000022366521],"about_ca_topic_score_codex":0.0047322013,"about_ca_topic_score_gemma":0.0034534154,"teacher_disagreement_score":0.0047322013,"about_ca_system_score_codex":0.00043763153,"about_ca_system_score_gemma":0.0003080936,"threshold_uncertainty_score":0.009409308},"labels":[],"label_agreement":null},{"id":"W4406823617","doi":"10.1038/s41598-025-87767-1","title":"Efficient diagnosis of diabetes mellitus using an improved ensemble method","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"King Saud University","keywords":"Diabetes mellitus; Computer science; Medicine; Bioinformatics; Internal medicine; Endocrinology; Biology","score_opus":0.12401138056733556,"score_gpt":0.4831311725368786,"score_spread":0.359119791969543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406823617","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08604877,0.0017565594,0.9038593,0.0005129367,0.0003569579,0.000102859965,0.0007231614,0.0029193074,0.0037201138],"genre_scores_gemma":[0.721538,0.001075335,0.26996702,0.0003638045,0.0005005099,0.00012815736,0.0023082604,0.00011739246,0.004001564],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937266,0.00012849917,0.000055016488,0.00018350445,0.00017350556,0.00008683742],"domain_scores_gemma":[0.99888164,0.00038815904,0.000088737695,0.00012844717,0.0004585819,0.000054426353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012834724,0.0007834493,0.0014903509,0.0018844985,0.0004041758,0.00095134386,0.00095422426,0.0008119162,0.0012414302],"category_scores_gemma":[0.0026623392,0.00029655846,0.0013564954,0.0011930895,0.00012506293,0.0007432724,0.00067873555,0.0009585877,0.0008648443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046191053,0.00035043582,0.021434296,0.00011189723,0.00041669293,0.00039122082,0.00011101901,0.1490206,0.012500139,0.0013505372,0.008845808,0.80500543],"study_design_scores_gemma":[0.000010923991,0.00006234328,0.0024045436,0.000013254928,0.00007654603,0.00012383232,0.00001595474,0.99321485,0.0020979983,0.00090083445,0.001063787,0.000015206868],"about_ca_topic_score_codex":0.00482727,"about_ca_topic_score_gemma":0.004458794,"teacher_disagreement_score":0.00482727,"about_ca_system_score_codex":0.0003156902,"about_ca_system_score_gemma":0.00063944585,"threshold_uncertainty_score":0.009598315},"labels":[],"label_agreement":null},{"id":"W4406837799","doi":"10.11591/ijeecs.v38.i1.pp689-698","title":"An ensemble approach for detection of diabetes using SVM and DT","year":2025,"lang":"en","type":"article","venue":"Indonesian Journal of Electrical Engineering and Computer Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bow Valley College","funders":"","keywords":"Support vector machine; Computer science; Diabetes mellitus; Machine learning; Artificial intelligence; Pattern recognition (psychology); Data mining; Medicine; Endocrinology","score_opus":0.04185749220679263,"score_gpt":0.3682601325866487,"score_spread":0.32640264037985606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406837799","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21021509,0.0023179355,0.776902,0.00059781596,0.00056532543,0.00017257655,0.0015413137,0.0033262018,0.0043617277],"genre_scores_gemma":[0.79844546,0.0007448588,0.19215727,0.00022540403,0.00019654054,0.00010363321,0.002733541,0.000065412285,0.005327852],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914813,0.00013334269,0.000100670586,0.00024509296,0.00024289382,0.00012997388],"domain_scores_gemma":[0.99903107,0.00025883105,0.000077729695,0.000097190015,0.00046239523,0.00007273804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010879677,0.00071584986,0.0011397494,0.0023792903,0.0003941854,0.0008935142,0.0008007902,0.00084372895,0.0012364073],"category_scores_gemma":[0.001968417,0.00027217588,0.0012629252,0.0015012723,0.000104808394,0.0009792383,0.00061456946,0.0008447035,0.0007542206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005049009,0.00034782087,0.019241234,0.000077359306,0.00024313267,0.0002368369,0.00007857791,0.06550611,0.014414273,0.0010213937,0.006230708,0.8920977],"study_design_scores_gemma":[0.000007818121,0.00011020425,0.0051668133,0.000011879674,0.000056415534,0.00014774776,0.000034040106,0.98883563,0.0036013816,0.0007159815,0.001293062,0.000019061528],"about_ca_topic_score_codex":0.0073013674,"about_ca_topic_score_gemma":0.0057032728,"teacher_disagreement_score":0.0073013674,"about_ca_system_score_codex":0.00053373456,"about_ca_system_score_gemma":0.0005615432,"threshold_uncertainty_score":0.0145177245},"labels":[],"label_agreement":null},{"id":"W4406844238","doi":"10.1016/j.ekir.2024.11.1219","title":"WCN25-2787 X SPACES : TOPNOTCH PLATFORM FOR VOICE OF NEPHROLOGY COMMUNITY","year":2025,"lang":"en","type":"article","venue":"Kidney International Reports","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; Toronto Western Hospital","funders":"","keywords":"Medicine; Nephrology; Internal medicine","score_opus":0.13164577404746974,"score_gpt":0.4923500866730232,"score_spread":0.36070431262555347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406844238","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010192512,0.0016171534,0.016529491,0.015132951,0.016268523,0.0013747666,0.018372592,0.042311918,0.8782001],"genre_scores_gemma":[0.02424163,0.00059518276,0.0071904957,0.0039681233,0.0023046986,0.00085314113,0.015909184,0.006887074,0.93805057],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99863666,0.00024522762,0.000049418508,0.00018416636,0.0004735371,0.00041098267],"domain_scores_gemma":[0.9920936,0.00076179224,0.000200927,0.000529568,0.001705007,0.0047089774],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0023879078,0.0007884815,0.00056669395,0.0014018473,0.0034284927,0.0061649587,0.0012938615,0.0022392974,0.42973095],"category_scores_gemma":[0.0068822163,0.0003631391,0.0004214463,0.0009427358,0.00079213816,0.005023521,0.008047034,0.0023778984,0.25642487],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002684405,0.000065735636,0.00035928382,0.000086585955,0.0000037433165,0.00009798243,0.00032175324,0.00003646081,0.0017421141,0.0037283243,0.94968754,0.04360199],"study_design_scores_gemma":[0.00004222444,0.00004154493,0.0007499798,0.00005433196,0.0000033599297,0.00003752498,0.00029558077,0.00038330493,0.00055094226,0.0008719076,0.99694294,0.000026315598],"about_ca_topic_score_codex":0.007210037,"about_ca_topic_score_gemma":0.020946573,"teacher_disagreement_score":0.42973095,"about_ca_system_score_codex":0.001277562,"about_ca_system_score_gemma":0.0032958165,"threshold_uncertainty_score":0.8134196},"labels":[],"label_agreement":null},{"id":"W4407025409","doi":"10.1016/b978-0-443-15728-8.00003-3","title":"Artificial intelligence and public health","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Psychology; Artificial intelligence","score_opus":0.2258120130737525,"score_gpt":0.44393146601968075,"score_spread":0.21811945294592824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407025409","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020850248,0.041972376,0.0015836639,0.0050096223,0.001353289,0.000022738664,0.00012237339,0.0000920197,0.9496355],"genre_scores_gemma":[0.0040511047,0.030072365,0.0016514617,0.0023475047,0.001023627,0.000052628642,0.00018111856,0.00008720515,0.9605331],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996099,0.00009796651,0.000018142664,0.000056875764,0.00018796687,0.000029242365],"domain_scores_gemma":[0.9995104,0.00029647653,0.000022950815,0.00005898843,0.000070402704,0.000040674444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006260474,0.0011194017,0.00080270215,0.0025452552,0.0011861551,0.006283274,0.00063266366,0.00272565,0.13279793],"category_scores_gemma":[0.0015382994,0.0005166321,0.0003490379,0.0034911544,0.0020926273,0.004395676,0.002090174,0.0031695627,0.052670937],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000080496275,0.00004040382,0.00010492453,0.00036928718,0.000009537552,0.000053676442,0.00040064548,0.0005113716,0.00019801554,0.22920196,0.51084185,0.25826025],"study_design_scores_gemma":[0.0000028186905,0.000004420417,0.00013702789,0.00032290648,0.0000027621643,0.000045065943,0.000099195255,0.00017386644,0.000029599283,0.05583545,0.9433432,0.0000035435041],"about_ca_topic_score_codex":0.0047144787,"about_ca_topic_score_gemma":0.01034074,"teacher_disagreement_score":0.13279793,"about_ca_system_score_codex":0.0022366662,"about_ca_system_score_gemma":0.0018582181,"threshold_uncertainty_score":0.44425333},"labels":[],"label_agreement":null},{"id":"W4407057415","doi":"10.1007/978-3-658-45877-5_6","title":"Towards Improving Prediction Accuracy and User-Level Explainability using Deep Learning and Knowledge Graphs: A Study on Cassava Disease","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Artificial intelligence; Computer science; Deep learning; Machine learning; Disease; Medicine; Internal medicine","score_opus":0.22119494424921546,"score_gpt":0.47829692560818887,"score_spread":0.25710198135897344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407057415","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7722934,0.004055964,0.20223589,0.0035894117,0.00016544537,0.00010113849,0.003064744,0.0026577548,0.011836258],"genre_scores_gemma":[0.92905205,0.0009999567,0.06032393,0.00022559443,0.000043855805,0.000032119056,0.0031669235,0.0001612143,0.005994436],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996201,0.00015045908,0.000018766152,0.00010700481,0.00007517069,0.0000285685],"domain_scores_gemma":[0.9904377,0.0084599545,0.0001886351,0.0004711128,0.00036019617,0.00008230976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001120474,0.0005222248,0.00030053844,0.0007363661,0.0002969738,0.0010872149,0.0006697496,0.0006744418,0.0019288044],"category_scores_gemma":[0.008011501,0.00016271933,0.0005362104,0.00086085516,0.0002947508,0.0023372176,0.0005055047,0.0014642061,0.00043447784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075664703,0.00094073213,0.08985143,0.00047367314,0.0003175436,0.00056697143,0.0014275684,0.14087792,0.007096392,0.017824903,0.023788994,0.71607727],"study_design_scores_gemma":[0.000024405594,0.00018169046,0.01756158,0.00006270437,0.00013317654,0.00014580303,0.0003856269,0.9379762,0.0045864084,0.031145956,0.0077659376,0.000030429703],"about_ca_topic_score_codex":0.012772919,"about_ca_topic_score_gemma":0.014962946,"teacher_disagreement_score":0.012772919,"about_ca_system_score_codex":0.0006954955,"about_ca_system_score_gemma":0.00059278734,"threshold_uncertainty_score":0.025397122},"labels":[],"label_agreement":null},{"id":"W4407102905","doi":"10.1038/s41581-025-00933-6","title":"Artificial intelligence approaches to enable early detection of CKD","year":2025,"lang":"en","type":"review","venue":"Nature Reviews Nephrology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Seven Oaks General Hospital","funders":"","keywords":"Medicine","score_opus":0.44127383962337713,"score_gpt":0.5160307842774396,"score_spread":0.07475694465406252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407102905","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007665969,0.998459,0.00026159905,0.0003973953,0.00018522097,0.000006167982,0.000018595736,0.000006495382,0.00058888516],"genre_scores_gemma":[0.0010845842,0.9975802,0.0004942728,0.00036130004,0.00025481824,0.000008141634,0.000029097588,0.0000012129027,0.00018650689],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995703,0.000105371255,0.00005993541,0.0000706395,0.00016143809,0.00003229935],"domain_scores_gemma":[0.998293,0.0012285167,0.00013783628,0.000028251989,0.00026583136,0.000046625835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001317323,0.00095471303,0.0019979647,0.002112397,0.00020924908,0.0014027414,0.0009813131,0.0013981562,0.0034126153],"category_scores_gemma":[0.0030717286,0.0002866031,0.0013287764,0.0013639065,0.000538464,0.001096509,0.00081376045,0.0022720776,0.0009733003],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006518454,0.000085333864,0.0003383894,0.019450398,0.00034739386,0.000084196006,0.000028256753,0.00044726397,0.0003786586,0.0035199148,0.012309676,0.96294546],"study_design_scores_gemma":[0.00014205906,0.00040751597,0.0058171405,0.042377427,0.0021303992,0.001406596,0.00013705232,0.0013607432,0.0011058692,0.016035339,0.9289642,0.00011560758],"about_ca_topic_score_codex":0.0024887081,"about_ca_topic_score_gemma":0.003944232,"teacher_disagreement_score":0.0034126153,"about_ca_system_score_codex":0.0007440552,"about_ca_system_score_gemma":0.00147332,"threshold_uncertainty_score":0.011416316},"labels":[],"label_agreement":null},{"id":"W4407164896","doi":"10.1016/j.mex.2025.103210","title":"MapReduce based big data framework using associative Kruskal poly Kernel classifier for diabetic disease prediction","year":2025,"lang":"en","type":"article","venue":"MethodsX","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Associative property; Kernel (algebra); Big data; Classifier (UML); Pattern recognition (psychology); Machine learning; Data mining; Mathematics","score_opus":0.553412797937658,"score_gpt":0.5924231524663424,"score_spread":0.0390103545286844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407164896","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11366422,0.00080145,0.8685024,0.0009250101,0.00028825382,0.00032322423,0.0015737714,0.008246503,0.0056751724],"genre_scores_gemma":[0.7932579,0.0005027097,0.19893098,0.00014218212,0.0001388596,0.00025561926,0.002415552,0.00012703512,0.0042292173],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996561,0.00004572727,0.00002370167,0.00008336744,0.00012843781,0.00006270362],"domain_scores_gemma":[0.9997718,0.00003566176,0.00001699734,0.000041080264,0.00009564829,0.000038713686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039260017,0.000482175,0.0006344362,0.00080977246,0.00049480953,0.00093051593,0.001277655,0.00028943448,0.0015604411],"category_scores_gemma":[0.0008134604,0.00020184439,0.0007243997,0.00081930455,0.00020207278,0.00089044386,0.00076307665,0.0004427951,0.000645568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011734267,0.0011814442,0.025738722,0.00031763164,0.00034067297,0.0010053453,0.00037696905,0.24967697,0.018857628,0.01746735,0.034754317,0.6491094],"study_design_scores_gemma":[0.000031400516,0.00006459289,0.0016523509,0.00000474541,0.000027069093,0.00010712263,0.000105281164,0.98452514,0.0035217674,0.0065816613,0.0033593278,0.000019555458],"about_ca_topic_score_codex":0.010608559,"about_ca_topic_score_gemma":0.010378608,"teacher_disagreement_score":0.010608559,"about_ca_system_score_codex":0.00056884886,"about_ca_system_score_gemma":0.0019247449,"threshold_uncertainty_score":0.021093607},"labels":[],"label_agreement":null},{"id":"W4407247880","doi":"10.1109/aibthings63359.2024.10863685","title":"Alzheimer’s Disease Stage Classification using Blood Data","year":2024,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Lakehead University","funders":"","keywords":"Computer science; Disease; Stage (stratigraphy); Artificial intelligence; Pattern recognition (psychology); Medicine; Internal medicine; Biology","score_opus":0.7257174218579381,"score_gpt":0.6078478438089233,"score_spread":0.11786957804901477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407247880","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9638435,0.0016312874,0.027884446,0.00024759505,0.00019162228,0.00015481193,0.0034989368,0.00067707995,0.0018705959],"genre_scores_gemma":[0.97108793,0.00046027356,0.02087668,0.00010801441,0.00011022519,0.00008702516,0.0063855476,0.000019022797,0.00086527836],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991647,0.00029862073,0.000089496214,0.00016295124,0.00018936956,0.00009486659],"domain_scores_gemma":[0.9981729,0.0008941186,0.000197026,0.0001996689,0.00043421172,0.00010205094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015683747,0.001080116,0.00087040477,0.0022709374,0.0002539033,0.0007441981,0.00046394163,0.00080835854,0.00073326216],"category_scores_gemma":[0.004752709,0.00011675801,0.0005570931,0.0011472502,0.0001575486,0.00049521343,0.00033329212,0.00045725793,0.0006351265],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0045091496,0.002182209,0.5058198,0.00051294727,0.000734487,0.0010058673,0.00021944584,0.040295683,0.04087309,0.0005339951,0.0067639053,0.39654937],"study_design_scores_gemma":[0.00021041642,0.0021434636,0.34438452,0.00013417295,0.00051654904,0.001703079,0.00038343054,0.5784064,0.063279085,0.0019551276,0.0067197676,0.00016398003],"about_ca_topic_score_codex":0.0039163805,"about_ca_topic_score_gemma":0.0043587447,"teacher_disagreement_score":0.0039163805,"about_ca_system_score_codex":0.00028072813,"about_ca_system_score_gemma":0.00035162427,"threshold_uncertainty_score":0.008294463},"labels":[],"label_agreement":null},{"id":"W4407287420","doi":"10.37648/ijrmst.v18i01.010","title":"Employability Of Data Mining &amp; Big Data Analytics Tools And Techniques In Various Sectors Of Healthcare","year":2024,"lang":"en","type":"article","venue":"International Journal of Research in Medical Sciences & Technology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Employability; Big data; Data science; Analytics; Health care; Healthcare industry; Data analysis; Computer science; Business; Data mining; Economics","score_opus":0.7230837861088641,"score_gpt":0.6644765567925899,"score_spread":0.05860722931627427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407287420","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08249963,0.54921526,0.07648563,0.19244297,0.0024905126,0.00051336776,0.0028102763,0.00039915481,0.09314323],"genre_scores_gemma":[0.5570126,0.3112959,0.106527746,0.016477704,0.0030293418,0.00043883512,0.0017085553,0.00016032376,0.0033489955],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9750787,0.012643425,0.001926001,0.0017800014,0.007954012,0.000617998],"domain_scores_gemma":[0.8921655,0.080979556,0.0067836507,0.006576094,0.012223317,0.001272003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029118074,0.0006011652,0.00062932965,0.009165135,0.0011551348,0.010995941,0.0013934418,0.0020558722,0.0027931426],"category_scores_gemma":[0.052021585,0.0005277779,0.0013437477,0.014462817,0.003555557,0.01118005,0.0038763555,0.002758433,0.0008914245],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015587671,0.00015830802,0.052924357,0.010709645,0.00049071317,0.00046114065,0.0036061404,0.002222984,0.0038675952,0.08260349,0.015432379,0.8273674],"study_design_scores_gemma":[0.00004679691,0.00047426744,0.06746069,0.031325363,0.00059543276,0.002906116,0.020976827,0.009181134,0.008887064,0.1288924,0.7289766,0.0002773203],"about_ca_topic_score_codex":0.002823848,"about_ca_topic_score_gemma":0.004481359,"teacher_disagreement_score":0.029118074,"about_ca_system_score_codex":0.0026243562,"about_ca_system_score_gemma":0.005635863,"threshold_uncertainty_score":0.15399295},"labels":[],"label_agreement":null},{"id":"W4407297613","doi":"10.17975/sfj-2025-001","title":"Harnessing AI and Open Data Analytics to Combat Social Inequities Among Adolescents: 2024-25 High School Big Data and AI Challenge","year":2025,"lang":"en","type":"article","venue":"STEM Fellowship Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Big data; Data science; Analytics; Computer science; Psychology; Data mining","score_opus":0.4197191321681569,"score_gpt":0.5108702853309419,"score_spread":0.09115115316278499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407297613","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5465064,0.0021807977,0.022424286,0.3038603,0.010190481,0.0024844299,0.0046973564,0.0018143668,0.1058415],"genre_scores_gemma":[0.66046834,0.0033435808,0.07353605,0.046467174,0.0023866661,0.0027058246,0.007708905,0.00089342304,0.20249003],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99734193,0.00064057234,0.000070289425,0.00021942408,0.00067029917,0.0010574753],"domain_scores_gemma":[0.9876074,0.0004930813,0.00021179451,0.0002909163,0.0017855649,0.009611277],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.009639919,0.00073914597,0.0005361918,0.00086083997,0.0048545604,0.0075952737,0.002146754,0.0026847736,0.01289376],"category_scores_gemma":[0.006349328,0.00051210925,0.0010491087,0.0005759831,0.0018604641,0.0030320957,0.009568347,0.0054118056,0.0041160467],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024423763,0.0047241705,0.07530406,0.00052277435,0.00009300225,0.0014545529,0.024402235,0.0017246793,0.0041555497,0.032937504,0.601172,0.2532652],"study_design_scores_gemma":[0.000111455505,0.0021018882,0.05555882,0.0009507161,0.000049368307,0.0004919195,0.06825544,0.005886518,0.005561082,0.038359668,0.8225241,0.00014907027],"about_ca_topic_score_codex":0.0069155814,"about_ca_topic_score_gemma":0.028709019,"teacher_disagreement_score":0.9978532,"about_ca_system_score_codex":0.0028479658,"about_ca_system_score_gemma":0.017245363,"threshold_uncertainty_score":0.050981402},"labels":[],"label_agreement":null},{"id":"W4407304103","doi":"10.1109/cins63881.2024.10862988","title":"A Study to Evaluate Various Machine Learning Approaches for Early Prediction of Neurodegenerative Diseases","year":2024,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence","score_opus":0.3482298650596749,"score_gpt":0.49361535491224207,"score_spread":0.14538548985256716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407304103","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95041853,0.007977512,0.034185015,0.0003713797,0.00027483568,0.0018160325,0.001557296,0.00025323083,0.0031461122],"genre_scores_gemma":[0.9614197,0.0015765039,0.033039927,0.00021658237,0.00011177012,0.0008979843,0.0016871112,0.000021971742,0.0010284984],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99305844,0.0043715904,0.00068935123,0.00079070433,0.0009342666,0.00015563783],"domain_scores_gemma":[0.96842897,0.023852115,0.0013757349,0.0017481754,0.00420695,0.00038804853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017383115,0.0010203909,0.0007909743,0.0014692135,0.00037480207,0.0011535167,0.0006151587,0.0013153057,0.0006680507],"category_scores_gemma":[0.026558667,0.00024602542,0.001509596,0.00080767943,0.00044099393,0.0015937035,0.000597746,0.0008588622,0.000456135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.022274667,0.017415186,0.2892336,0.0032561151,0.004174934,0.00033399864,0.0006144852,0.12629332,0.018956926,0.002784832,0.0036224232,0.5110395],"study_design_scores_gemma":[0.0027839846,0.1118016,0.19234492,0.000923709,0.0034429643,0.0009646847,0.0009625609,0.63331765,0.037872512,0.0031661093,0.01219246,0.00022682114],"about_ca_topic_score_codex":0.0017476261,"about_ca_topic_score_gemma":0.0012575508,"teacher_disagreement_score":0.017383115,"about_ca_system_score_codex":0.00055262167,"about_ca_system_score_gemma":0.0007877597,"threshold_uncertainty_score":0.09193176},"labels":[],"label_agreement":null},{"id":"W4407432934","doi":"10.2196/62978","title":"Large-Scale Evaluation and Liver Disease Risk Prediction in Finland’s National Electronic Health Record System: Feasibility Study Using Real-World Data","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprint; Electronic health record; Scale (ratio); Health records; Medicine; Environmental health; Computer science; Health care; Geography; World Wide Web; Cartography","score_opus":0.20746736927862416,"score_gpt":0.5357997906149901,"score_spread":0.32833242133636587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407432934","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98847616,0.00014393916,0.0023215811,0.00045828833,0.000034805355,0.00062943774,0.007237313,0.00017966368,0.0005188533],"genre_scores_gemma":[0.9678187,0.00013798279,0.012565671,0.00018029538,0.000050251725,0.00077076827,0.018186009,0.000017427486,0.00027291817],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9893166,0.0048263003,0.0013062439,0.0016616249,0.0022403214,0.00064893207],"domain_scores_gemma":[0.956504,0.027091393,0.0034321486,0.005377759,0.0055896705,0.0020049945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015613477,0.0006421427,0.0006766962,0.0020157536,0.0009835811,0.0017675152,0.0020755266,0.0015993835,0.0012871576],"category_scores_gemma":[0.042994685,0.00036441092,0.0010492876,0.002480138,0.00095205434,0.0023384332,0.0019492361,0.0009167075,0.0007236845],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028466587,0.0072874706,0.8582438,0.0014625653,0.0008092415,0.0021384817,0.003262007,0.02179535,0.0030283893,0.0013572397,0.010571034,0.08719777],"study_design_scores_gemma":[0.0009606484,0.004492509,0.8257894,0.0003803885,0.0005102367,0.0013978293,0.0067811096,0.14233233,0.0062790094,0.0013227001,0.009529282,0.00022463404],"about_ca_topic_score_codex":0.024132341,"about_ca_topic_score_gemma":0.017177949,"teacher_disagreement_score":0.024132341,"about_ca_system_score_codex":0.0029774932,"about_ca_system_score_gemma":0.0034553194,"threshold_uncertainty_score":0.082573},"labels":[],"label_agreement":null},{"id":"W4407571990","doi":"10.52041/iase2023.614","title":"Enhanced graduate training in health data visualization and analytics","year":2024,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; University of British Columbia; University of Manitoba","funders":"","keywords":"Computer science; Visualization; Data visualization; Analytics; Training (meteorology); Data science; Visual analytics; Data analysis; Data mining","score_opus":0.6483573764178129,"score_gpt":0.6175958392385196,"score_spread":0.030761537179293308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407571990","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47308403,0.0030738777,0.13905299,0.13007846,0.008810495,0.0022810453,0.003852149,0.009950796,0.22981618],"genre_scores_gemma":[0.589664,0.0032075066,0.14014356,0.026917001,0.0022964994,0.0011688068,0.004799043,0.0010508227,0.23075277],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952761,0.001239244,0.00021441959,0.0007403168,0.0014876382,0.0010423685],"domain_scores_gemma":[0.95568204,0.0047851927,0.0026562712,0.0039264183,0.011558592,0.021391423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009362602,0.0008995947,0.0007323449,0.002169733,0.0013088544,0.004970075,0.0024127294,0.0017866445,0.06281686],"category_scores_gemma":[0.018454196,0.00063984055,0.00075921,0.0009308378,0.000864483,0.0027910594,0.009050444,0.0036689097,0.021834986],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005425065,0.01024246,0.041512422,0.00084864197,0.000075154436,0.00043958332,0.0059844335,0.002931303,0.012083702,0.011870635,0.2257887,0.6876805],"study_design_scores_gemma":[0.00044777384,0.0058923713,0.1642691,0.0028209558,0.00013889933,0.0037084317,0.0111541925,0.019585853,0.016695194,0.05804259,0.7169734,0.00027123032],"about_ca_topic_score_codex":0.0012132637,"about_ca_topic_score_gemma":0.0032414137,"teacher_disagreement_score":0.06281686,"about_ca_system_score_codex":0.0014659781,"about_ca_system_score_gemma":0.009565311,"threshold_uncertainty_score":0.21014333},"labels":[],"label_agreement":null},{"id":"W4407671823","doi":"10.1016/j.bspc.2025.107672","title":"Artificial intelligence-based multiclass diabetes risk stratification for big data embedded with explainability: From machine learning to attention models","year":2025,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of Toronto","funders":"","keywords":"Computer science; Stratification (seeds); Artificial intelligence; Machine learning; Big data; Risk stratification; Diabetes mellitus; Data mining; Medicine","score_opus":0.1430680811182665,"score_gpt":0.4103109041049205,"score_spread":0.267242822986654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407671823","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36904374,0.0022264463,0.62149763,0.0041417032,0.00015191293,0.00006922378,0.000425336,0.0005917132,0.0018523292],"genre_scores_gemma":[0.97920394,0.0002835377,0.019185683,0.00016646653,0.00010929726,0.000020864045,0.0002597064,0.000021563696,0.0007489033],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994479,0.00024186277,0.000029236036,0.00014669957,0.000059104113,0.000075228665],"domain_scores_gemma":[0.9944423,0.004351974,0.00045510495,0.00030378517,0.00027084845,0.00017596027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002374799,0.00073529244,0.0009121525,0.0012249069,0.0003031193,0.0012606172,0.0009643615,0.0008309329,0.0011627526],"category_scores_gemma":[0.009552918,0.00029202193,0.0007843964,0.0006501665,0.00052989396,0.0016542912,0.0011426677,0.0017266169,0.00014916497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009947284,0.0008829786,0.0793318,0.00023871513,0.0011757717,0.0003759191,0.0004120645,0.49577528,0.0042712986,0.02551916,0.004202204,0.38682002],"study_design_scores_gemma":[0.000010055984,0.000045981313,0.0052949614,0.000014890267,0.00004689447,0.000018181217,0.000020719868,0.9776838,0.00030129368,0.016399138,0.00015351827,0.00001067245],"about_ca_topic_score_codex":0.006420427,"about_ca_topic_score_gemma":0.004815992,"teacher_disagreement_score":0.006420427,"about_ca_system_score_codex":0.000710033,"about_ca_system_score_gemma":0.0006787831,"threshold_uncertainty_score":0.012766123},"labels":[],"label_agreement":null},{"id":"W4407729374","doi":"10.2139/ssrn.5138371","title":"Enhancing Diabetes Risk Prediction: A Comparative Evaluation of Bagging, Boosting, and Ensemble Classifiers with Smote Oversampling","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Oversampling; Boosting (machine learning); Artificial intelligence; Machine learning; Computer science; Random subspace method; Ensemble learning; Pattern recognition (psychology); Support vector machine; Bandwidth (computing)","score_opus":0.12425961016401174,"score_gpt":0.44801314050162266,"score_spread":0.3237535303376109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407729374","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74630827,0.020609805,0.21883059,0.0014891294,0.0009378274,0.00028623434,0.0011712535,0.0037020831,0.0066648847],"genre_scores_gemma":[0.8916652,0.0028257084,0.10144216,0.000377149,0.0003027219,0.00007078902,0.001661183,0.000113979906,0.0015410756],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980794,0.00087154075,0.000109314395,0.0003062607,0.00047630092,0.00015714004],"domain_scores_gemma":[0.99342793,0.00445129,0.00018154358,0.0005263295,0.0012087721,0.00020404936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008412337,0.001462346,0.0024389313,0.0017546086,0.00049623195,0.0013099457,0.0012702165,0.0012889833,0.00087043754],"category_scores_gemma":[0.00943892,0.0003857599,0.001131586,0.0012471201,0.0002938445,0.001769854,0.0011522218,0.0015071307,0.00043433747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040299622,0.0020275733,0.03743576,0.00038758776,0.0015341095,0.0000663402,0.00015842186,0.14069894,0.0036459272,0.0010035875,0.006304318,0.8027075],"study_design_scores_gemma":[0.00013447674,0.001147097,0.008723014,0.00007481981,0.00066383823,0.00007535818,0.00006797715,0.9829517,0.0030856966,0.0014993825,0.0015478722,0.000028924169],"about_ca_topic_score_codex":0.0066002687,"about_ca_topic_score_gemma":0.0056317444,"teacher_disagreement_score":0.008412337,"about_ca_system_score_codex":0.00050344644,"about_ca_system_score_gemma":0.0011568861,"threshold_uncertainty_score":0.044489205},"labels":[],"label_agreement":null},{"id":"W4407753181","doi":"10.3233/shti250029","title":"Optimizing Hypertension Care Through Telementoring Education Platform in Jonglei State, South Sudan: A Framework of Extension of Community Healthcare Outcome-ECHO Project","year":2025,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Health care; Medicine; Business; Population; Psychological intervention; Stroke (engine); Telemedicine; Medical emergency; Economic growth; Nursing; Environmental health; Economics; Engineering","score_opus":0.2777008535053485,"score_gpt":0.537196254463495,"score_spread":0.25949540095814644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407753181","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92246336,0.00086026575,0.011072103,0.013513162,0.00012724736,0.00097288593,0.00048011227,0.00012332037,0.050387587],"genre_scores_gemma":[0.98580027,0.0005529911,0.0099213,0.00039974888,0.000020192523,0.00026105973,0.00014582956,0.000008431058,0.0028900413],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99898356,0.0005914495,0.000030608164,0.000054599834,0.00006957991,0.00027022758],"domain_scores_gemma":[0.9993389,0.00016420387,0.00006758641,0.00003343776,0.00011785828,0.0002780729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023971538,0.00019231495,0.000103491,0.00056529563,0.0013635345,0.0021141316,0.0004936854,0.0004660959,0.002254394],"category_scores_gemma":[0.0014174458,0.00006766938,0.00024007935,0.0004967033,0.0006127245,0.00095382927,0.0027826645,0.0004941492,0.00019170182],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008069094,0.0050833584,0.22556722,0.001893718,0.00018445756,0.0077806762,0.024288084,0.024103852,0.018043328,0.19267136,0.024020698,0.47555637],"study_design_scores_gemma":[0.00046774335,0.0028300793,0.34728938,0.0029566486,0.00044700576,0.0019038672,0.16350754,0.11784716,0.010970048,0.053140864,0.2983498,0.0002898946],"about_ca_topic_score_codex":0.016311895,"about_ca_topic_score_gemma":0.022244778,"teacher_disagreement_score":0.016311895,"about_ca_system_score_codex":0.0025514537,"about_ca_system_score_gemma":0.009078558,"threshold_uncertainty_score":0.032433867},"labels":[],"label_agreement":null},{"id":"W4407822129","doi":"10.3233/978-1-61499-742-9-161","title":"Better Data Quality for Better Healthcare Research Results &amp;ndash; A Case Study","year":2017,"lang":"en","type":"book-chapter","venue":"Studies in health technology and informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Health care; Quality (philosophy); Computer science; Data quality; Data science; Business; Economics; Marketing","score_opus":0.8197584975719893,"score_gpt":0.6837877803803742,"score_spread":0.13597071719161502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407822129","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40119252,0.018734068,0.047564857,0.16372526,0.0017649849,0.0025744552,0.0010880365,0.0005864305,0.36276948],"genre_scores_gemma":[0.80113196,0.009066195,0.0969674,0.009244308,0.00035593516,0.0007250268,0.00046720757,0.00021999056,0.081822],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9846577,0.010495339,0.00069168827,0.00038949065,0.0030915148,0.0006741547],"domain_scores_gemma":[0.9755857,0.01727344,0.0008957852,0.0019196481,0.0025081765,0.0018172837],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026681084,0.00033181853,0.00037442974,0.00123852,0.004721039,0.007647184,0.0016827526,0.0021615843,0.004859619],"category_scores_gemma":[0.021796037,0.00034271582,0.0006506556,0.003181936,0.0036658973,0.004181656,0.0044159293,0.0026160008,0.0009092587],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033068992,0.0024279337,0.031291604,0.0021934763,0.00008810169,0.020207858,0.11686033,0.0018532651,0.0034098418,0.19682083,0.16970976,0.45480633],"study_design_scores_gemma":[0.00013218977,0.00073372055,0.018316187,0.0017957648,0.000094278446,0.014818735,0.0925775,0.0040589394,0.007297732,0.028554818,0.8314755,0.00014463151],"about_ca_topic_score_codex":0.022809582,"about_ca_topic_score_gemma":0.05345922,"teacher_disagreement_score":0.97331893,"about_ca_system_score_codex":0.009831982,"about_ca_system_score_gemma":0.010631003,"threshold_uncertainty_score":0.1411047},"labels":[],"label_agreement":null},{"id":"W4407872939","doi":"10.2196/68066","title":"Machine Learning Model for Predicting Coronary Heart Disease Risk: Development and Validation Using Insights From a Japanese Population–Based Study","year":2025,"lang":"en","type":"article","venue":"JMIR Cardio","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprint; Medicine; Computer science; World Wide Web","score_opus":0.13656240661843277,"score_gpt":0.45044719276044654,"score_spread":0.31388478614201376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407872939","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97135735,0.00035127575,0.027147943,0.00013742439,0.00002518806,0.00018780571,0.0002760239,0.000058068526,0.00045888807],"genre_scores_gemma":[0.9848252,0.00016977315,0.013976644,0.000035159715,0.00001747621,0.00020415781,0.00059418724,0.000008975125,0.0001685058],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99816316,0.0012244914,0.00013001799,0.00023496516,0.00016735704,0.00007999176],"domain_scores_gemma":[0.9937184,0.004153053,0.0002879922,0.00043430782,0.0012449365,0.000161333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011888677,0.00089384714,0.001007235,0.0015976796,0.00056853227,0.00070338737,0.0009968617,0.0006275552,0.0008059922],"category_scores_gemma":[0.015603249,0.00024015603,0.0012487562,0.0009314775,0.00038982488,0.00057991786,0.0006884299,0.00071523414,0.00020328251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008400028,0.0010759785,0.8261211,0.00015958103,0.00096824166,0.00055989344,0.0010842566,0.09361785,0.0009563107,0.00079341454,0.0016474917,0.072175875],"study_design_scores_gemma":[0.0001418357,0.0006478442,0.17522748,0.000056731493,0.00049492257,0.00022118416,0.0005209257,0.8208814,0.00040498452,0.0007475966,0.00061578193,0.000039227598],"about_ca_topic_score_codex":0.018853227,"about_ca_topic_score_gemma":0.008476483,"teacher_disagreement_score":0.018853227,"about_ca_system_score_codex":0.00066139165,"about_ca_system_score_gemma":0.001305197,"threshold_uncertainty_score":0.06287414},"labels":[],"label_agreement":null},{"id":"W4408008751","doi":"10.18280/i2m.240104","title":"Machine Learning Algorithms for Real-Time Analysis of Multimedia Data from IoT-Based Health Instruments for Diabetes Management","year":2025,"lang":"en","type":"article","venue":"Instrumentation Mesure Métrologie","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Internet of Things; Multimedia; Machine learning; Artificial intelligence; Human–computer interaction; Data science; World Wide Web","score_opus":0.18205688326776834,"score_gpt":0.49652181344917706,"score_spread":0.31446493018140875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408008751","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027373768,0.0012074464,0.968474,0.00025385132,0.00013754868,0.00007201548,0.00020142633,0.0013796019,0.0009002572],"genre_scores_gemma":[0.51061153,0.0012531242,0.4823869,0.00022199354,0.000190207,0.00037919285,0.0010361465,0.00013675935,0.003784156],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99950206,0.00009408561,0.00007196848,0.00013525608,0.00014131064,0.0000553143],"domain_scores_gemma":[0.9988304,0.0007017499,0.00011723458,0.00006666276,0.00025749032,0.000026397649],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010324774,0.00083694165,0.00078103296,0.0013833987,0.0004038777,0.000913287,0.0009444733,0.0010108987,0.0017647528],"category_scores_gemma":[0.0038760556,0.00025692192,0.00087038026,0.0013035006,0.0002590219,0.0008705068,0.00059953786,0.0012172862,0.000932831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027816792,0.00037459316,0.003028835,0.00015466035,0.00013868847,0.0001124086,0.0000651421,0.15789375,0.0135141555,0.0027262138,0.0034176908,0.8182957],"study_design_scores_gemma":[0.000007641238,0.000034320812,0.00076622976,0.000011072974,0.0000136877925,0.000036648813,0.000014612633,0.99473155,0.0022536784,0.0015456473,0.0005780687,0.0000068350096],"about_ca_topic_score_codex":0.0033680592,"about_ca_topic_score_gemma":0.0028299154,"teacher_disagreement_score":0.0033680592,"about_ca_system_score_codex":0.0005056635,"about_ca_system_score_gemma":0.0006860949,"threshold_uncertainty_score":0.00669688},"labels":[],"label_agreement":null},{"id":"W4408012425","doi":"10.1007/978-981-97-8355-7_39","title":"Analysis of Survey, Preventative Measures, and Insulin Therapy in Mellitus Prescribing Utilization in Newly Diagnosed Diabetes Patients","year":2025,"lang":"en","type":"book-chapter","venue":"Smart innovation, systems and technologies","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Medicine; Diabetes mellitus; Insulin; Intensive care medicine; Internal medicine; Endocrinology","score_opus":0.19032561452565885,"score_gpt":0.3967449150134605,"score_spread":0.20641930048780163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408012425","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9951733,0.0010495702,0.00019861376,0.00012614526,0.000013113735,0.000012799087,0.0021761665,0.00000661599,0.0012436118],"genre_scores_gemma":[0.996092,0.000717893,0.00029645328,0.00007585219,0.000017319686,0.000021330656,0.0016820573,0.0000040551013,0.0010929948],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993748,0.00029790212,0.00008475502,0.00007355179,0.000101235906,0.00006774177],"domain_scores_gemma":[0.99706846,0.0019112707,0.0005743338,0.000069194844,0.00019132494,0.00018534389],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088043505,0.00014568506,0.00029555417,0.0009466774,0.00024359698,0.00047439148,0.00031178715,0.00036079652,0.0028059152],"category_scores_gemma":[0.0036125497,0.00020548402,0.0013427639,0.0021616686,0.00013421472,0.00040508344,0.00039722447,0.00053888606,0.00028915948],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011159461,0.000034881064,0.9972435,0.00001336087,0.0000638383,0.000017544167,0.000051669984,0.000094818366,0.000021688651,0.00003235171,0.00014766508,0.0021671194],"study_design_scores_gemma":[0.0000029569248,0.00008558786,0.99884367,0.000010602827,0.000046287536,0.000046989157,0.00025501958,0.00049537036,0.000023921522,0.000022838682,0.00016382273,0.000002854205],"about_ca_topic_score_codex":0.023928137,"about_ca_topic_score_gemma":0.039194264,"teacher_disagreement_score":0.023928137,"about_ca_system_score_codex":0.0006164393,"about_ca_system_score_gemma":0.00073617836,"threshold_uncertainty_score":0.04757774},"labels":[],"label_agreement":null},{"id":"W4408017532","doi":"10.1109/icmsci62561.2025.10894078","title":"A Novel AI-Assisted e-Consult Platform Integrating Deep Learning for Enhanced Healthcare Access and Diagnostic Precision","year":2025,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Computer science; Health care; Deep learning; Artificial intelligence","score_opus":0.1592579346506533,"score_gpt":0.5141817423615357,"score_spread":0.3549238077108824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408017532","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12014314,0.0012027136,0.81291765,0.0041934676,0.000518032,0.0006037409,0.0019611053,0.036962118,0.021498019],"genre_scores_gemma":[0.6575587,0.00038341613,0.31822205,0.002425572,0.00015682018,0.00035206124,0.0023772782,0.0003291956,0.018194918],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995135,0.000119963785,0.0000277804,0.000098739765,0.0001727434,0.00006727305],"domain_scores_gemma":[0.9992878,0.00029144046,0.000052165415,0.00008986648,0.0001420404,0.00013674177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073763623,0.0004800901,0.00038363997,0.0006039563,0.00039300308,0.0007322601,0.0012352566,0.0010417125,0.0055363798],"category_scores_gemma":[0.0021761607,0.00022505643,0.0003106558,0.00042281993,0.0002869345,0.0011778942,0.0020476426,0.00095070415,0.0018037853],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002260435,0.001605627,0.008802701,0.0005837833,0.00016232766,0.001917777,0.0006732621,0.048395954,0.0612028,0.011386963,0.07863941,0.78436905],"study_design_scores_gemma":[0.00017065312,0.0004265423,0.00384818,0.00006644564,0.000052388026,0.00083963486,0.0001429576,0.9282951,0.020365775,0.011774346,0.033923414,0.000094569245],"about_ca_topic_score_codex":0.0023930555,"about_ca_topic_score_gemma":0.0041302773,"teacher_disagreement_score":0.0055363798,"about_ca_system_score_codex":0.00066551834,"about_ca_system_score_gemma":0.0013294384,"threshold_uncertainty_score":0.01852101},"labels":[],"label_agreement":null},{"id":"W4408092107","doi":"10.1109/ddp64453.2024.00011","title":"Deep Learning-Based Genetic Detection and Pathogenesis of Diabetes","year":2024,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Pathogenesis; Computer science; Diabetes mellitus; Deep learning; Artificial intelligence; Computational biology; Machine learning; Medicine; Biology; Internal medicine; Endocrinology","score_opus":0.06442818679180806,"score_gpt":0.4077214261964004,"score_spread":0.34329323940459233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408092107","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40280432,0.043361496,0.5187792,0.013948408,0.0008087778,0.000121206,0.0031352784,0.0012802461,0.015761029],"genre_scores_gemma":[0.94661975,0.009765195,0.037639752,0.0010354721,0.00014465106,0.000051564824,0.0010188695,0.000032691154,0.0036920668],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99982494,0.00004739324,0.000010436501,0.000047726247,0.000035955436,0.000033523742],"domain_scores_gemma":[0.9997969,0.00006967974,0.000041256644,0.000014269027,0.000049263253,0.000028631164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056083396,0.00034995668,0.00030133,0.0010350188,0.00017983002,0.000773852,0.00045588115,0.0006712126,0.0011011867],"category_scores_gemma":[0.0010938643,0.0001809991,0.00053504005,0.0006525596,0.0004018172,0.0006864131,0.00050538307,0.001160198,0.0002889886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006096136,0.0005452485,0.15701127,0.0006968523,0.0005836495,0.0010866314,0.00038901242,0.11298448,0.056473006,0.06328496,0.01628809,0.5900473],"study_design_scores_gemma":[0.000053490945,0.00017424006,0.06263269,0.0002890935,0.00024476153,0.0011218549,0.0001829468,0.8095471,0.014894126,0.09623773,0.014535967,0.00008604755],"about_ca_topic_score_codex":0.0051225238,"about_ca_topic_score_gemma":0.003699738,"teacher_disagreement_score":0.0051225238,"about_ca_system_score_codex":0.00088059914,"about_ca_system_score_gemma":0.0006789957,"threshold_uncertainty_score":0.0101854205},"labels":[],"label_agreement":null},{"id":"W4408099082","doi":"10.2196/63186","title":"The Construction and Application of a Clinical Decision Support System for Cardiovascular Diseases: Multimodal Data-Driven Development and Validation Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Decision support system; Clinical decision support system; Computer science; Medicine; Data science; Data mining","score_opus":0.11541814825640388,"score_gpt":0.5123957442605926,"score_spread":0.39697759600418875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408099082","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83374935,0.00017109576,0.1600367,0.00032474851,0.00005088855,0.0010797447,0.0010881287,0.0016195414,0.0018798838],"genre_scores_gemma":[0.832522,0.00006955144,0.16435954,0.00006679862,0.000009155535,0.0004969994,0.0017018215,0.000046665784,0.0007274512],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980051,0.00091728184,0.00017675194,0.0003181526,0.00046605166,0.000116723444],"domain_scores_gemma":[0.99237096,0.0039553144,0.0003199855,0.0006320547,0.0025059856,0.00021566993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00567751,0.0005556121,0.00035287565,0.0009944338,0.0003571875,0.00089344685,0.0009026096,0.00061766524,0.0013643464],"category_scores_gemma":[0.0138495425,0.0002563303,0.0006008072,0.00054206536,0.00042528458,0.00072632835,0.000829187,0.0005808273,0.00028217607],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017103076,0.0040249936,0.13353784,0.0009079581,0.00050884084,0.0012164227,0.0021406834,0.3025412,0.047432825,0.0066461693,0.007440373,0.4918924],"study_design_scores_gemma":[0.00010267659,0.00065503747,0.012057386,0.000048057318,0.00007106105,0.00009094837,0.00023281827,0.96466786,0.019208416,0.00068354775,0.0021615117,0.000020715748],"about_ca_topic_score_codex":0.0067734746,"about_ca_topic_score_gemma":0.0041893,"teacher_disagreement_score":0.0067734746,"about_ca_system_score_codex":0.0013640085,"about_ca_system_score_gemma":0.0019456577,"threshold_uncertainty_score":0.0300259},"labels":[],"label_agreement":null},{"id":"W4408120221","doi":"10.1145/3704137.3704162","title":"Detecting Cardiovascular Morbidity using MIMIC-III Database: Assessing Three Data Imbalance Handling Techniques","year":2024,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Database; Data mining","score_opus":0.4575825066308866,"score_gpt":0.5420083350118211,"score_spread":0.08442582838093449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408120221","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96033525,0.0014053343,0.016264305,0.00058862247,0.00025905666,0.00036917542,0.0171324,0.001591748,0.0020541723],"genre_scores_gemma":[0.92885333,0.00065805495,0.032185134,0.00023102172,0.0002046128,0.00019843919,0.036745507,0.00005527895,0.0008685315],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984479,0.00021613477,0.00028694025,0.0003926709,0.0005165132,0.00013972555],"domain_scores_gemma":[0.99758685,0.0007947158,0.00033787175,0.00033842513,0.00072649965,0.00021568492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023944913,0.00089786196,0.0011864642,0.003643701,0.00043542898,0.0015262107,0.0010649668,0.0009164027,0.000704002],"category_scores_gemma":[0.006202015,0.00018145201,0.0008602951,0.0018779722,0.00017365074,0.0008972992,0.0009646069,0.0004812656,0.0004477207],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032627198,0.0011636942,0.76727915,0.00036473948,0.0010318804,0.00037660086,0.00015167109,0.009821128,0.009008125,0.0003166694,0.010352609,0.19687097],"study_design_scores_gemma":[0.00033880828,0.0019109044,0.7075276,0.00012718343,0.0013055406,0.0014412012,0.0009717107,0.26221848,0.0142132025,0.0012522747,0.008589256,0.00010383815],"about_ca_topic_score_codex":0.0046258806,"about_ca_topic_score_gemma":0.005269976,"teacher_disagreement_score":0.0046258806,"about_ca_system_score_codex":0.00037466452,"about_ca_system_score_gemma":0.00079556997,"threshold_uncertainty_score":0.012663484},"labels":[],"label_agreement":null},{"id":"W4408121597","doi":"10.6000/1929-6029.2025.14.11","title":"Chronic kidney Disease Classification through Hybrid Feature Selection and Ensemble Deep Learning","year":2025,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Feature selection; Ensemble learning; Computer science; Feature (linguistics); Kidney disease; Pattern recognition (psychology); Selection (genetic algorithm); Machine learning; Medicine; Internal medicine","score_opus":0.15498784566678234,"score_gpt":0.5754985133114356,"score_spread":0.4205106676446533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408121597","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29537153,0.0016192069,0.6986564,0.0005016834,0.00014415338,0.00011694868,0.00051463407,0.0019568137,0.0011186071],"genre_scores_gemma":[0.92928576,0.00031183104,0.06796352,0.00018170528,0.00007241522,0.00010980069,0.0009542474,0.00003214773,0.0010884699],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931264,0.00016101352,0.000049938157,0.00016639149,0.00017477585,0.0001353321],"domain_scores_gemma":[0.99930346,0.000249411,0.000058258054,0.000076778764,0.00026730858,0.000044800247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015019687,0.0009429627,0.0016122628,0.0014001156,0.00039961174,0.00067132484,0.0009734667,0.0006763425,0.0004573789],"category_scores_gemma":[0.0017980635,0.00032109534,0.00123831,0.0009869034,0.00018602735,0.0010209491,0.00081091066,0.00087180664,0.00018834094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051278406,0.0005681648,0.025252985,0.00005969898,0.0005149486,0.0002459139,0.00010289876,0.30208156,0.0071170377,0.0008290971,0.0048236423,0.6578912],"study_design_scores_gemma":[0.000009726183,0.0000732552,0.0017107907,0.000005794386,0.000041093543,0.00004237984,0.0000098662695,0.99610656,0.0011073671,0.00067166745,0.00021227563,0.000009176014],"about_ca_topic_score_codex":0.0094529465,"about_ca_topic_score_gemma":0.009997879,"teacher_disagreement_score":0.0094529465,"about_ca_system_score_codex":0.00056590966,"about_ca_system_score_gemma":0.00082514074,"threshold_uncertainty_score":0.018795848},"labels":[],"label_agreement":null},{"id":"W4408185936","doi":"10.2196/64349","title":"The Role of AI in Cardiovascular Event Monitoring and Early Detection: Scoping Literature Review","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Event (particle physics); Computer science; Medicine; Data science","score_opus":0.0362529481417266,"score_gpt":0.4516073148730462,"score_spread":0.4153543667313196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408185936","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002445347,0.998049,0.00033388467,0.0005054603,0.00012673438,0.00013044599,0.00020034447,0.000008158342,0.00040149895],"genre_scores_gemma":[0.0033250656,0.99494284,0.00072306173,0.0003880112,0.00011592622,0.00027997606,0.00015354903,0.000004776234,0.000066709435],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.9906785,0.0028235607,0.003802703,0.0008060216,0.0016324515,0.0002566788],"domain_scores_gemma":[0.90404594,0.079693176,0.008033713,0.0009786829,0.0067767524,0.00047165513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014140516,0.0016603826,0.005305779,0.01716599,0.0009021677,0.004716621,0.0025097881,0.0030198153,0.0057829353],"category_scores_gemma":[0.08606523,0.0011459652,0.0070906994,0.0148605,0.0012035988,0.0035315193,0.0022527934,0.0020409254,0.00079982704],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000119348486,0.000033593584,0.0007580654,0.8268363,0.0028046765,0.00012309651,0.00031718065,0.0003084587,0.00013098845,0.0011531921,0.0035097764,0.16390549],"study_design_scores_gemma":[0.000033856304,0.00007155237,0.0011950511,0.9537257,0.0119405715,0.0002420078,0.00022518828,0.00013156267,0.000118743665,0.0007823409,0.03150726,0.000026146461],"about_ca_topic_score_codex":0.007899436,"about_ca_topic_score_gemma":0.015293445,"teacher_disagreement_score":0.01716599,"about_ca_system_score_codex":0.003641427,"about_ca_system_score_gemma":0.020164572,"threshold_uncertainty_score":0.07478309},"labels":[],"label_agreement":null},{"id":"W4408324807","doi":"10.32628/cseit25112419","title":"Predictive Analytics and Machine Learning in Healthcare: A Comprehensive Framework for Clinical Implementation","year":2025,"lang":"en","type":"article","venue":"International Journal of Scientific Research in Computer Science Engineering and Information Technology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Tekna Plasma Systems (Canada)","funders":"","keywords":"Predictive analytics; Health care; Analytics; Computer science; Data science; Artificial intelligence; Machine learning; Political science","score_opus":0.19560298730202147,"score_gpt":0.5664706018549168,"score_spread":0.37086761455289535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408324807","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00093258766,0.004259985,0.94793814,0.031567477,0.00021289666,0.00038622235,0.000091691814,0.0005623885,0.0140486285],"genre_scores_gemma":[0.07207619,0.0063725533,0.9146671,0.0027188172,0.00053689,0.0010477421,0.00023562598,0.00012050413,0.0022245545],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9853292,0.009227893,0.0010706637,0.0008544419,0.0030762271,0.0004416949],"domain_scores_gemma":[0.9878691,0.007891861,0.0007056013,0.0012806176,0.001581093,0.00067173474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025294663,0.00154811,0.0010930877,0.003761627,0.0016689951,0.010396882,0.0039713513,0.004967192,0.0028594339],"category_scores_gemma":[0.024675027,0.0010016256,0.0013718297,0.0030240703,0.00990378,0.008512116,0.0077933385,0.007393496,0.0012054128],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018670515,0.00007987298,0.0007439768,0.00028369547,0.000035442918,0.00016254744,0.000571711,0.012865136,0.00029559646,0.91799307,0.005111059,0.06183922],"study_design_scores_gemma":[0.00002643468,0.00009103667,0.00036208105,0.0013125443,0.000033394426,0.0002224528,0.00052756537,0.063171074,0.00052433676,0.85865766,0.075017594,0.00005389924],"about_ca_topic_score_codex":0.0066953753,"about_ca_topic_score_gemma":0.004253668,"teacher_disagreement_score":0.025294663,"about_ca_system_score_codex":0.004226886,"about_ca_system_score_gemma":0.013523259,"threshold_uncertainty_score":0.13377255},"labels":[],"label_agreement":null},{"id":"W4408335193","doi":"10.21203/rs.3.rs-6195549/v1","title":"A Multilingual Predictive System for Type 2 Diabetes using the CATBoost Machine Learning Algorithm","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Type (biology); Algorithm","score_opus":0.37648318690941324,"score_gpt":0.5993380618965096,"score_spread":0.22285487498709639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408335193","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.114613734,0.0020967154,0.84014565,0.000841136,0.0012608669,0.0003166584,0.0030164856,0.03011422,0.0075945463],"genre_scores_gemma":[0.5829147,0.00067137385,0.39591998,0.0004999286,0.0004270447,0.00042666736,0.0066602374,0.0007519517,0.011728151],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99945134,0.00008392017,0.00004669454,0.00021536919,0.00012857388,0.00007414658],"domain_scores_gemma":[0.99910396,0.00028482344,0.000038964157,0.00006713746,0.00044880013,0.000056273166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011227059,0.0008601139,0.0010791565,0.0017376009,0.0011754485,0.0011606424,0.0011241875,0.0009282531,0.0055575306],"category_scores_gemma":[0.002368909,0.0003421662,0.0008310035,0.0013796543,0.00023339718,0.0011596074,0.001196775,0.0011477848,0.0032164904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015092158,0.0009144594,0.007500598,0.00024045132,0.00024149647,0.00042573584,0.00011036131,0.0503177,0.016352694,0.0015272308,0.024356665,0.8965034],"study_design_scores_gemma":[0.00008236769,0.00011299192,0.0020262732,0.000028972543,0.00014324467,0.00016000029,0.000056889694,0.9808965,0.008813324,0.0023429224,0.0052952236,0.00004132546],"about_ca_topic_score_codex":0.02461998,"about_ca_topic_score_gemma":0.023881704,"teacher_disagreement_score":0.02461998,"about_ca_system_score_codex":0.00081903016,"about_ca_system_score_gemma":0.0017846548,"threshold_uncertainty_score":0.048953354},"labels":[],"label_agreement":null},{"id":"W4408358245","doi":"10.1109/icses63760.2024.10910546","title":"Revolutioning Healthcare: A Superficial Learning Approach to Predict Heart Diseases by Using Artificial Intelligence (AI) Logic","year":2024,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Health care; Machine learning","score_opus":0.20995103149804853,"score_gpt":0.47567835653219803,"score_spread":0.26572732503414953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408358245","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015790794,0.00055056653,0.9742484,0.0026694094,0.00009083954,0.00010418759,0.00013345355,0.00063792267,0.005774377],"genre_scores_gemma":[0.4295685,0.0009932157,0.5633749,0.0013366643,0.00018894074,0.0001857686,0.00024599806,0.00006058048,0.0040454217],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993352,0.00026038985,0.000056211687,0.00012350595,0.00017879308,0.000045771572],"domain_scores_gemma":[0.99841225,0.0010132835,0.00010705566,0.00020305194,0.0002017042,0.0000626645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016689625,0.0006369833,0.00042303483,0.0011106202,0.0004519786,0.0015488126,0.0012561255,0.0008800086,0.0023067335],"category_scores_gemma":[0.0048950263,0.00031436005,0.0007756412,0.00063112885,0.0016197645,0.002483049,0.0015805388,0.0018934392,0.00051495363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002296516,0.00035853268,0.009897494,0.00039372648,0.00019117004,0.0003851604,0.00085024524,0.27295575,0.0058489772,0.20113526,0.0068582855,0.5008957],"study_design_scores_gemma":[0.000017447288,0.00008268838,0.00060430897,0.00006917014,0.000035739504,0.000077384044,0.00006747458,0.8332954,0.0016853019,0.15965284,0.004388721,0.00002346406],"about_ca_topic_score_codex":0.004359761,"about_ca_topic_score_gemma":0.0047276956,"teacher_disagreement_score":0.004359761,"about_ca_system_score_codex":0.00095546286,"about_ca_system_score_gemma":0.0013152625,"threshold_uncertainty_score":0.008826435},"labels":[],"label_agreement":null},{"id":"W4408365403","doi":"10.1007/978-3-031-84397-6_11","title":"Validation of a Chronic Kidney Disease Prediction System Using Machine Learning Techniques","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Kidney disease; Artificial intelligence; Machine learning; Medicine; Internal medicine","score_opus":0.12936651129847596,"score_gpt":0.4429384271498686,"score_spread":0.31357191585139266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408365403","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8895739,0.00028809765,0.09946052,0.00045214163,0.00026884762,0.0003477999,0.0023908918,0.00207516,0.0051427213],"genre_scores_gemma":[0.9626482,0.000079875914,0.029618073,0.00011326205,0.00003048558,0.0001485507,0.0029445752,0.000038925406,0.004378019],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995671,0.00014132833,0.00005009141,0.000090085974,0.00011871237,0.000032792403],"domain_scores_gemma":[0.9982784,0.0009339662,0.000045954985,0.00011906138,0.0005847477,0.000037827038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016467567,0.00047175612,0.00037024153,0.00049871457,0.00038702297,0.0005560107,0.00063223817,0.0007848252,0.002191956],"category_scores_gemma":[0.002578963,0.00013335819,0.0003246577,0.00025132284,0.0001685788,0.0003009292,0.00034258384,0.00031198162,0.0011106271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002754185,0.0018269264,0.13799302,0.00037217158,0.00050658354,0.000968963,0.00038251042,0.23651108,0.089423865,0.001367627,0.016341338,0.5115518],"study_design_scores_gemma":[0.00009287767,0.00066256046,0.04416019,0.00003089323,0.000116600175,0.00019196622,0.00010551453,0.92153156,0.030618874,0.00035615521,0.002107859,0.000024863875],"about_ca_topic_score_codex":0.009825494,"about_ca_topic_score_gemma":0.0065091923,"teacher_disagreement_score":0.009825494,"about_ca_system_score_codex":0.00040279,"about_ca_system_score_gemma":0.00056978734,"threshold_uncertainty_score":0.019536614},"labels":[],"label_agreement":null},{"id":"W4408400028","doi":"10.1109/idciot64235.2025.10915067","title":"Advanced Block Chain of Electronics Health Care Medical Record Systems Wearable Device Industry 5.0","year":2025,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Wearable computer; Electronics; Wearable technology; Electronic health record; Health care; Block (permutation group theory); Computer science; Electronic medical record; Medical record; Embedded system; Engineering; Electrical engineering; Internet privacy; Medicine","score_opus":0.07325459872239527,"score_gpt":0.4854574990364229,"score_spread":0.4122029003140276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408400028","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04160334,0.008330828,0.55756974,0.0044303928,0.0036460087,0.0023919365,0.0047855387,0.03212245,0.34511977],"genre_scores_gemma":[0.32674998,0.0055663944,0.20871924,0.003980694,0.00097455224,0.0010483665,0.006071211,0.00155496,0.44533473],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99847406,0.00027871595,0.00014265045,0.00021891232,0.000732195,0.00015356894],"domain_scores_gemma":[0.9978504,0.0003543935,0.00016782843,0.0004714394,0.0010130785,0.00014282152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001523697,0.00067173416,0.0005207912,0.0015810482,0.00043293988,0.0020415918,0.0013335592,0.0013032033,0.10247677],"category_scores_gemma":[0.0026220095,0.00041928363,0.00047542993,0.0010784842,0.00024959492,0.0018190457,0.0016299008,0.0008345959,0.06650363],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00115835,0.00029333544,0.0042945137,0.0012711434,0.000089766756,0.00077540806,0.00035112374,0.0015724394,0.0947851,0.04107865,0.13816506,0.7161652],"study_design_scores_gemma":[0.00018869223,0.0015704294,0.008113123,0.0006349906,0.00013303202,0.0028408112,0.00014758694,0.023526067,0.08036011,0.006685075,0.87566143,0.00013857702],"about_ca_topic_score_codex":0.0006783886,"about_ca_topic_score_gemma":0.0005847842,"teacher_disagreement_score":0.10247677,"about_ca_system_score_codex":0.00051241636,"about_ca_system_score_gemma":0.00067866826,"threshold_uncertainty_score":0.34281898},"labels":[],"label_agreement":null},{"id":"W4408521389","doi":"10.1109/bhi62660.2024.10913597","title":"Advanced Receiver Operating Characteristic Curve Analysis to Identify Outliers in Binary Machine Learning Classifications for Precision Medicine","year":2024,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"","keywords":"Receiver operating characteristic; Outlier; Binary number; Computer science; Learning curve; Artificial intelligence; Binary classification; Machine learning; Support vector machine; Mathematics; Operating system","score_opus":0.18521320994813228,"score_gpt":0.550265358878529,"score_spread":0.3650521489303967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408521389","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013922927,0.0037861457,0.97107744,0.00075633556,0.00020460693,0.0002833029,0.001462234,0.006943687,0.0015633214],"genre_scores_gemma":[0.2681427,0.0026925167,0.7211427,0.0006756065,0.0005279883,0.0008617746,0.0031918033,0.0015545189,0.0012103454],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98146915,0.008319128,0.0021578155,0.0023821872,0.0052865655,0.0003851659],"domain_scores_gemma":[0.89855,0.06516244,0.012443095,0.009781155,0.013232842,0.00083050615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026680812,0.0020713334,0.0021541805,0.01171516,0.0007272727,0.004814315,0.00188492,0.0020668486,0.0033049956],"category_scores_gemma":[0.12603399,0.00069392944,0.002275235,0.008398479,0.0011330999,0.0026528614,0.002444718,0.003993484,0.0027836068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088706956,0.00038133416,0.062087692,0.0022152823,0.0014439952,0.00047860818,0.0009202107,0.072087616,0.0121187875,0.02061629,0.03230424,0.79445887],"study_design_scores_gemma":[0.00016902787,0.0011346993,0.041228715,0.0010722845,0.0006965863,0.0024823283,0.00049189845,0.79731655,0.026740178,0.063137986,0.06505355,0.00047622813],"about_ca_topic_score_codex":0.0018306621,"about_ca_topic_score_gemma":0.0018072391,"teacher_disagreement_score":0.026680812,"about_ca_system_score_codex":0.0014250001,"about_ca_system_score_gemma":0.0021763172,"threshold_uncertainty_score":0.14110333},"labels":[],"label_agreement":null},{"id":"W4408605202","doi":"10.1101/2025.03.18.642594","title":"The Global Wheat Full Semantic Organ Segmentation (GWFSS) Dataset","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"HORIZON EUROPE Framework Programme; Horizon 2020 Framework Programme; Grain Research and Development Corporation","keywords":"Segmentation; Computer science; Artificial intelligence; Natural language processing","score_opus":0.05863755236345791,"score_gpt":0.3868905507780852,"score_spread":0.3282529984146273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408605202","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1245427,0.0046835816,0.014733363,0.0007571865,0.0006845593,0.00050916657,0.81409425,0.028186468,0.011808727],"genre_scores_gemma":[0.040943194,0.00031842486,0.010996042,0.00018161879,0.000033610966,0.00015404777,0.9447914,0.00039378915,0.0021878155],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99921453,0.00007250475,0.00005792712,0.00035895538,0.00016846832,0.00012772591],"domain_scores_gemma":[0.9995828,0.000078275705,0.00003092313,0.00013192414,0.00012719427,0.000048900834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070676615,0.0033957877,0.0013337974,0.0024606485,0.0008066469,0.0016279139,0.0022143668,0.0023259681,0.00596967],"category_scores_gemma":[0.0011312842,0.0005392997,0.002162039,0.0022213198,0.0006170457,0.00094599754,0.0014175397,0.0011104944,0.00824377],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015725056,0.0007910758,0.01222325,0.0038778395,0.0007843031,0.0013021657,0.00028284322,0.022245407,0.043842535,0.0019363079,0.75860155,0.15254013],"study_design_scores_gemma":[0.0010975037,0.0010348595,0.09863659,0.0009106876,0.00076658593,0.0036205293,0.0011606201,0.18859412,0.07865878,0.008131658,0.61694396,0.00044416141],"about_ca_topic_score_codex":0.015971452,"about_ca_topic_score_gemma":0.034550823,"teacher_disagreement_score":0.015971452,"about_ca_system_score_codex":0.0011424593,"about_ca_system_score_gemma":0.0010442925,"threshold_uncertainty_score":0.031756997},"labels":[],"label_agreement":null},{"id":"W4408674283","doi":"10.14447/jnmes.v28i1.a02","title":"A Novel Framework for Deep Convolutional Neural Network-Based Heart Failure Disease Prediction Using an Optimized Efficient net-B0 Model","year":2025,"lang":"en","type":"article","venue":"Journal of New Materials for Electrochemical Systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Computer science; Artificial neural network; Artificial intelligence; Heart failure; Net (polyhedron); Internal medicine; Medicine; Mathematics","score_opus":0.09656857025575132,"score_gpt":0.4245398796477215,"score_spread":0.32797130939197017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408674283","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018115075,0.0006139883,0.9774122,0.000260502,0.000059212973,0.000063748616,0.00022369472,0.0011386501,0.0021128324],"genre_scores_gemma":[0.6603353,0.0010309067,0.3238206,0.0005195504,0.00013647576,0.00046087065,0.0014719084,0.00027877878,0.011945557],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99978536,0.000037417503,0.000012959168,0.00006171133,0.00006102595,0.000041525847],"domain_scores_gemma":[0.9997687,0.00007634426,0.000025616864,0.00001709975,0.00008421568,0.000028016251],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082593766,0.0010977022,0.0007620081,0.00059834024,0.00033837438,0.0007457031,0.0019373844,0.0009885267,0.0018412758],"category_scores_gemma":[0.0010528734,0.0005031015,0.0007428391,0.0004687651,0.0005036581,0.0008632302,0.0010489803,0.0010868178,0.0005733026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074931595,0.00006928163,0.0008794842,0.0000512118,0.000053869182,0.00007985972,0.00002392287,0.91970426,0.0026348017,0.010375025,0.0025302419,0.063523024],"study_design_scores_gemma":[0.0000025562736,0.0000063025623,0.00003553032,0.0000017634728,0.000002655294,0.0000045864053,8.573687e-7,0.99886656,0.00016702406,0.0007456028,0.00016505785,0.0000015660245],"about_ca_topic_score_codex":0.027239583,"about_ca_topic_score_gemma":0.024844224,"teacher_disagreement_score":0.027239583,"about_ca_system_score_codex":0.0014546653,"about_ca_system_score_gemma":0.002283306,"threshold_uncertainty_score":0.054162085},"labels":[],"label_agreement":null},{"id":"W4408793880","doi":"10.1109/icccit62592.2025.10928062","title":"Leveraging Machine Learning for Early Detection of Cardiovascular Diseases","year":2025,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning","score_opus":0.09915718095050015,"score_gpt":0.435280998413229,"score_spread":0.33612381746272885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408793880","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36745226,0.010091106,0.60615146,0.005012636,0.00060238113,0.00016679571,0.00074747374,0.001686202,0.008089698],"genre_scores_gemma":[0.9085966,0.0014851772,0.08803346,0.0003418982,0.00018599821,0.00002678342,0.0003802521,0.00002769604,0.0009221473],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998845,0.0005676126,0.000052492356,0.00015501927,0.00027799828,0.000101817415],"domain_scores_gemma":[0.9963192,0.0025275971,0.00035815052,0.00027556144,0.0004146103,0.000104986866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023992963,0.00052418123,0.00072193594,0.00168892,0.00021901981,0.0009317789,0.00043316174,0.0007001144,0.00080923794],"category_scores_gemma":[0.008065187,0.00019414595,0.0005712765,0.0008370792,0.00019086922,0.0010966971,0.0005295572,0.0009809867,0.00056828064],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003362027,0.00070788607,0.14186215,0.00022193877,0.00031359933,0.0002143836,0.00015813416,0.15277877,0.0066599734,0.0031976444,0.0051606153,0.68838865],"study_design_scores_gemma":[0.000017765376,0.00034896686,0.032492418,0.00010570689,0.00011937219,0.0002447437,0.000089938425,0.94891435,0.0048249783,0.009571052,0.0032188124,0.000051842017],"about_ca_topic_score_codex":0.002098935,"about_ca_topic_score_gemma":0.003267519,"teacher_disagreement_score":0.0023992963,"about_ca_system_score_codex":0.0002879474,"about_ca_system_score_gemma":0.0006579561,"threshold_uncertainty_score":0.012688816},"labels":[],"label_agreement":null},{"id":"W4408881096","doi":"10.1007/979-8-8688-1221-7_3","title":"Creating a Basic ChatGPT Client in JavaScript","year":2025,"lang":"en","type":"book-chapter","venue":"Apress eBooks","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"JavaScript; Unobtrusive JavaScript; Computer science; Programming language; World Wide Web; Rich Internet application","score_opus":0.15674719186570404,"score_gpt":0.4394982388737318,"score_spread":0.2827510470080278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408881096","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041064695,0.0013923341,0.6162111,0.00077808055,0.0012375995,0.0013428753,0.0040221284,0.14546633,0.2254431],"genre_scores_gemma":[0.016622147,0.0018489981,0.52624434,0.0014644177,0.00027395814,0.0015826822,0.012263793,0.059658833,0.3800409],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991049,0.000083452054,0.000051137915,0.00014604197,0.00052349496,0.000090959365],"domain_scores_gemma":[0.999137,0.00027267393,0.000024283609,0.0001315021,0.00031020975,0.0001244675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075561047,0.0008377886,0.000797854,0.0009465294,0.001008233,0.0025467628,0.0016186961,0.0014047052,0.101623535],"category_scores_gemma":[0.0027729361,0.0012032602,0.000799181,0.0010988222,0.0004398079,0.0031401631,0.00251303,0.002974071,0.089865595],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017139262,0.00020757642,0.0004927536,0.0012116784,0.000022469687,0.00089268095,0.001616173,0.0011192121,0.022817502,0.026887668,0.46396464,0.48059615],"study_design_scores_gemma":[0.000037832524,0.00003111437,0.00038135276,0.00020817618,0.00001091785,0.000982437,0.000109771885,0.0035707832,0.009558117,0.004852878,0.9802014,0.00005524074],"about_ca_topic_score_codex":0.0017942623,"about_ca_topic_score_gemma":0.0027427254,"teacher_disagreement_score":0.101623535,"about_ca_system_score_codex":0.00070283655,"about_ca_system_score_gemma":0.0013359409,"threshold_uncertainty_score":0.33996457},"labels":[],"label_agreement":null},{"id":"W4408885571","doi":"10.1007/978-3-031-86323-3","title":"International Conference on Biomedical and Health Informatics 2024","year":2025,"lang":"en","type":"book","venue":"World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Taipei Veterans General Hospital; Ngee Ann Polytechnic; National Cheng Kung University; National Taiwan University; Universidade de Coimbra; University of Tokyo; Università degli Studi di Firenze; Universidad Autónoma Metropolitana; Aristotle University of Thessaloniki; České Vysoké Učení Technické v Praze; Chinese Academy of Sciences; University of South Australia; Universidad de Concepción; I-Shou University; Sveučilište u Zagrebu; Universidad Politécnica de Madrid; University of Ottawa; National Tsing Hua University; Boston Scientific Corporation; University of Washington; Universitatea Tehnică din Cluj-Napoca; Chung Yuan Christian University","keywords":"Health informatics; Informatics; Library science; Political science; Computer science; Data science; Health care","score_opus":0.06362215344118852,"score_gpt":0.3997997850356428,"score_spread":0.33617763159445424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408885571","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028696288,0.05225086,0.07435865,0.024920953,0.078546315,0.00037290333,0.0033190202,0.0048053074,0.75855637],"genre_scores_gemma":[0.0094540175,0.023404865,0.02049042,0.003990508,0.007166207,0.00015277383,0.0066322987,0.00052764907,0.92818135],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99888974,0.00020153986,0.00007346143,0.00014748644,0.00056116877,0.00012652244],"domain_scores_gemma":[0.9981616,0.0002740496,0.0000470391,0.00018610978,0.0008604242,0.00047079826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002247197,0.0009993084,0.0010213801,0.0023390015,0.000887208,0.0053505846,0.0011899383,0.0016119059,0.15044743],"category_scores_gemma":[0.0020564427,0.0003464126,0.00073757407,0.002076638,0.0007579514,0.0032226618,0.0029714182,0.0026815392,0.112748995],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036730053,0.000050084476,0.00015136856,0.00019153513,0.00001382176,0.00005454639,0.000044624547,0.00016844131,0.0011465086,0.009824739,0.80856127,0.17975645],"study_design_scores_gemma":[0.0000030488916,0.000012380663,0.00022705483,0.00010029145,0.0000083852965,0.0000903782,0.000029352479,0.00064033834,0.00032887343,0.0026094092,0.99594456,0.000006032599],"about_ca_topic_score_codex":0.0023554338,"about_ca_topic_score_gemma":0.0031304907,"teacher_disagreement_score":0.15044743,"about_ca_system_score_codex":0.00094684603,"about_ca_system_score_gemma":0.0026094315,"threshold_uncertainty_score":0.5032968},"labels":[],"label_agreement":null},{"id":"W4408920006","doi":"10.21203/rs.3.rs-6297944/v1","title":"Can ensemble methods improve predictive performance of existing models estimating chronic kidney disease among patients with diabetes?","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Kidney disease; Diabetes mellitus; Computer science; Disease; Medicine; Econometrics; Artificial intelligence; Machine learning; Internal medicine; Mathematics; Endocrinology","score_opus":0.21976096692371258,"score_gpt":0.5458424374408194,"score_spread":0.3260814705171068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408920006","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61902285,0.0107006,0.34081745,0.011694704,0.0025241368,0.00017335145,0.005541993,0.002041519,0.007483371],"genre_scores_gemma":[0.94059396,0.0025736657,0.04753033,0.0011457865,0.0013554047,0.00008110683,0.0044166213,0.00015948577,0.0021436692],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978002,0.0012489813,0.00014439503,0.0004199729,0.00022051633,0.00016595247],"domain_scores_gemma":[0.9843924,0.010614198,0.00051141623,0.002278563,0.0019030718,0.00030040208],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009668663,0.0015715925,0.0020892413,0.001400789,0.00056435406,0.001697261,0.0014312426,0.0014933029,0.0033319122],"category_scores_gemma":[0.03293653,0.0005914572,0.0023617416,0.0012608771,0.00028054405,0.003765727,0.00123282,0.0029951434,0.0013320924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015260353,0.0008161068,0.23783167,0.00026696635,0.0050793095,0.0001807634,0.0003159661,0.22634465,0.0013072953,0.0021683597,0.019153908,0.50500906],"study_design_scores_gemma":[0.00009952831,0.00044012265,0.03285752,0.00015346086,0.0010078929,0.00013625382,0.00017832356,0.9522426,0.0009208275,0.009538157,0.002368962,0.000056294557],"about_ca_topic_score_codex":0.007680957,"about_ca_topic_score_gemma":0.008633556,"teacher_disagreement_score":0.009668663,"about_ca_system_score_codex":0.00038992582,"about_ca_system_score_gemma":0.0006947579,"threshold_uncertainty_score":0.051133394},"labels":[],"label_agreement":null},{"id":"W4408944579","doi":"10.3390/a18040190","title":"A Data-Driven Intelligent Methodology for Developing Explainable Diagnostic Model for Febrile Diseases","year":2025,"lang":"en","type":"article","venue":"Algorithms","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Royal University","funders":"","keywords":"Computer science; Intensive care medicine; Medicine; Data science","score_opus":0.5297542341434482,"score_gpt":0.5696175165723699,"score_spread":0.039863282428921676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408944579","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007774823,0.0001376183,0.9900816,0.00041312762,0.000020308165,0.00009861001,0.0002840433,0.0006885887,0.0005011776],"genre_scores_gemma":[0.32273164,0.00028296377,0.6731795,0.00034301187,0.000072432944,0.000630665,0.0013410741,0.00011072231,0.0013079128],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989802,0.0004545584,0.0000828152,0.00025681496,0.00016003744,0.000065497225],"domain_scores_gemma":[0.99489814,0.004107467,0.00033095555,0.00019193698,0.0004073223,0.00006424561],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026199066,0.0011245217,0.00059885223,0.0014854989,0.00039144835,0.0011745229,0.0015456341,0.0010093263,0.002539689],"category_scores_gemma":[0.009877952,0.000500021,0.0016318022,0.00083487306,0.00056016375,0.0011531289,0.0012260211,0.0016993062,0.00037141467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000118221185,0.00014775437,0.005409754,0.0003359423,0.00018433311,0.00041332055,0.000419552,0.8300563,0.0027642916,0.028267052,0.002492832,0.12939067],"study_design_scores_gemma":[0.000008362514,0.000019561621,0.00017907009,0.000014566037,0.000014954968,0.000023963814,0.0000161909,0.98925495,0.00046494222,0.009358754,0.0006385163,0.000006116331],"about_ca_topic_score_codex":0.0071459482,"about_ca_topic_score_gemma":0.007685422,"teacher_disagreement_score":0.0071459482,"about_ca_system_score_codex":0.0013258304,"about_ca_system_score_gemma":0.0016506433,"threshold_uncertainty_score":0.014208674},"labels":[],"label_agreement":null},{"id":"W4409045336","doi":"10.61838/jaiai.1.1.6","title":"Intelligent Prediction of Cardiovascular Disease Mortality Using Machine Learning Techniques","year":2024,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Applications and Innovations","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"York University; Iran National Science Foundation; University of Washington; Johns Hopkins University; National Heart, Lung, and Blood Institute; University of California, Davis; University of Minnesota; Case Western Reserve University; National Science Foundation","keywords":"Disease; Computer science; Artificial intelligence; Machine learning; Medicine; Internal medicine","score_opus":0.2123137007033037,"score_gpt":0.46729660303863624,"score_spread":0.25498290233533255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409045336","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32326332,0.0078045847,0.6545649,0.0021780396,0.00041418694,0.00021462374,0.002067538,0.0030792477,0.0064134724],"genre_scores_gemma":[0.88574094,0.0016211496,0.10870041,0.00025729186,0.0002694396,0.000109394,0.0017747909,0.000035545523,0.001491028],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994049,0.00023018236,0.00005805896,0.00012438279,0.00013254238,0.000049937767],"domain_scores_gemma":[0.99847466,0.0009635015,0.0002061932,0.000075969205,0.00023971467,0.00004003727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016566283,0.0007509567,0.0007745181,0.002277178,0.0002546898,0.0009285056,0.0006484477,0.000600395,0.00075941323],"category_scores_gemma":[0.004373518,0.00019510144,0.0008155859,0.0010635093,0.00014595287,0.0006061829,0.00044608055,0.000850464,0.0006221525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034446354,0.00054091506,0.1453334,0.00025668496,0.0004201174,0.00028647974,0.00010246342,0.322286,0.005438852,0.002231827,0.0060192416,0.51673955],"study_design_scores_gemma":[0.000012163282,0.000116988485,0.012879348,0.000053146236,0.000043666652,0.00010442727,0.000027810474,0.98206145,0.0013453175,0.002245503,0.0010895559,0.00002060651],"about_ca_topic_score_codex":0.0030922838,"about_ca_topic_score_gemma":0.0032069327,"teacher_disagreement_score":0.0030922838,"about_ca_system_score_codex":0.0003501916,"about_ca_system_score_gemma":0.00059190096,"threshold_uncertainty_score":0.0087611675},"labels":[],"label_agreement":null},{"id":"W4409075384","doi":"10.1101/2025.04.01.25325021","title":"Targeted Serum Metabolomic Profiling and Machine Learning Approach in Alzheimer’s Disease using the Alzheimer’s Disease Diagnostics Clinical Study (ADDIA) Cohort","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Center for Diagnosis and Research on Alzheimer's Disease","funders":"","keywords":"Profiling (computer programming); Disease; Cohort; Medicine; Alzheimer's disease; Oncology; Internal medicine; Computer science","score_opus":0.3149919226942582,"score_gpt":0.4993276624632043,"score_spread":0.18433573976894613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409075384","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9953117,0.0003673461,0.0023124258,0.00009456234,0.0000129074315,0.0000514102,0.0013339708,0.000058779915,0.0004569196],"genre_scores_gemma":[0.99367684,0.00015549862,0.003783629,0.000070040405,0.000019066894,0.000067174384,0.0018959182,0.000008304747,0.00032346326],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9995844,0.0001444682,0.000047414385,0.00013493827,0.00005776356,0.000031006246],"domain_scores_gemma":[0.9995347,0.00008860588,0.00012977529,0.00009437006,0.00008934726,0.000063171414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012892644,0.00058930286,0.00045324815,0.0012426346,0.00034626582,0.00075171527,0.00033840342,0.00031851747,0.0008190981],"category_scores_gemma":[0.0017411313,0.00016985669,0.0006435191,0.00054318586,0.00012320811,0.00019703298,0.0006123605,0.00045443067,0.00026095012],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016890641,0.0002716128,0.9650008,0.00004362976,0.00057687785,0.00033833046,0.00010663883,0.0019395017,0.007270018,0.00010199848,0.0008316449,0.021829886],"study_design_scores_gemma":[0.00010384544,0.00084214227,0.97357315,0.000035223336,0.00051338365,0.0011429151,0.00015190853,0.016140446,0.00553368,0.00045760509,0.0014763469,0.00002936622],"about_ca_topic_score_codex":0.0022474548,"about_ca_topic_score_gemma":0.0035571693,"teacher_disagreement_score":0.0022474548,"about_ca_system_score_codex":0.0002865108,"about_ca_system_score_gemma":0.00031498045,"threshold_uncertainty_score":0.006818354},"labels":[],"label_agreement":null},{"id":"W4409185257","doi":"10.53759/7669/jmc202505098","title":"Advancing Health Diagnostics: AI-Powered CVD-REF Framework for Precise and Early Risk Assessment","year":2025,"lang":"en","type":"article","venue":"Journal of Machine and Computing","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Risk assessment; Risk analysis (engineering); Computer science; Medicine; Systems engineering; Engineering; Computer security","score_opus":0.03797665696017907,"score_gpt":0.4986130230387605,"score_spread":0.4606363660785814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409185257","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009484078,0.001208168,0.97843665,0.001222004,0.00013635331,0.00013720694,0.0014841056,0.0023750262,0.005516322],"genre_scores_gemma":[0.5036991,0.0017263526,0.48003137,0.0008971219,0.00043919,0.00054156466,0.004155198,0.0002220526,0.00828801],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995579,0.00013291369,0.000024608355,0.00009022229,0.00014025783,0.000054048538],"domain_scores_gemma":[0.9994005,0.00022585715,0.00005183841,0.000047699254,0.00021767023,0.00005648777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013608056,0.00078418717,0.00076602877,0.0013840556,0.00035235734,0.0011605578,0.0016428751,0.0009073413,0.003813849],"category_scores_gemma":[0.003186755,0.00026055085,0.0008295358,0.0007647426,0.00025866157,0.00081807195,0.0011072767,0.0009748872,0.0012082136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020898464,0.00029416423,0.02096426,0.0003670596,0.00028617698,0.00052018237,0.00016082225,0.49773124,0.0021412785,0.046890363,0.026098456,0.40433705],"study_design_scores_gemma":[0.000012246892,0.000029828185,0.0007222391,0.00003386965,0.000032140808,0.000079289995,0.000016769394,0.9769399,0.00039056854,0.016326185,0.005402967,0.000013866659],"about_ca_topic_score_codex":0.012297283,"about_ca_topic_score_gemma":0.017137166,"teacher_disagreement_score":0.012297283,"about_ca_system_score_codex":0.0006528265,"about_ca_system_score_gemma":0.0021145993,"threshold_uncertainty_score":0.024451375},"labels":[],"label_agreement":null},{"id":"W4409229190","doi":"10.1016/j.bspc.2025.107824","title":"Attention-based hybrid deep learning models and its scientific validation for cardiovascular disease risk stratification","year":2025,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of Toronto","funders":"","keywords":"Risk stratification; Stratification (seeds); Computer science; Artificial intelligence; Disease; Machine learning; Deep learning; Medicine; Cardiology; Internal medicine","score_opus":0.07233119977492414,"score_gpt":0.38125356706075064,"score_spread":0.3089223672858265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409229190","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3858982,0.005468908,0.5959546,0.0030814789,0.0004842415,0.00010035631,0.0012346292,0.0014793432,0.006298206],"genre_scores_gemma":[0.97281116,0.0003706905,0.023678275,0.00026014162,0.00011232343,0.0000457834,0.0007497386,0.000041030817,0.0019308206],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929464,0.00028913366,0.000039604718,0.0001614142,0.00013666814,0.00007864914],"domain_scores_gemma":[0.9956955,0.0023792924,0.00025871454,0.0003742836,0.0011406954,0.00015150111],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004678404,0.0006550908,0.00061924173,0.0011560445,0.00040536316,0.0010898717,0.0012230951,0.001490209,0.0015145866],"category_scores_gemma":[0.011971437,0.00024180088,0.00073268067,0.00059316144,0.0004527809,0.0012496427,0.0013229708,0.0014559557,0.00035940774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009755358,0.000650044,0.03131166,0.0002938915,0.00078985246,0.00021926123,0.00018830845,0.5482763,0.010392061,0.01566843,0.010849474,0.3803852],"study_design_scores_gemma":[0.000009743522,0.000037225993,0.0016906654,0.000017870085,0.000041502422,0.000016464059,0.000008297082,0.9930976,0.00094611757,0.003818081,0.00030886178,0.0000075189996],"about_ca_topic_score_codex":0.007567172,"about_ca_topic_score_gemma":0.004961692,"teacher_disagreement_score":0.007567172,"about_ca_system_score_codex":0.00073777226,"about_ca_system_score_gemma":0.0011957131,"threshold_uncertainty_score":0.024742007},"labels":[],"label_agreement":null},{"id":"W4409251331","doi":"10.1055/s-0044-1800720","title":"Telehealth and Precision Prevention: Bridging the Gap for Individualised Health Strategies","year":2024,"lang":"en","type":"review","venue":"Yearbook of Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Telehealth; Enabling; Public health; Digital health; Wearable computer; Medicine; Popularity; Telemedicine; Health care; Bridging (networking); Computer science; Nursing; Psychology; Political science; Computer security","score_opus":0.38268647522078414,"score_gpt":0.591922317036551,"score_spread":0.20923584181576682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409251331","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005927204,0.9965193,0.00022862034,0.0019000147,0.0002329441,0.000008163056,0.000008884022,0.000005850844,0.0010369478],"genre_scores_gemma":[0.0010170137,0.99681723,0.0005355045,0.0009726937,0.0003320183,0.000020192476,0.000014554431,0.0000019833697,0.0002888272],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99872965,0.0005123445,0.0001448201,0.0001335166,0.00038167133,0.00009795654],"domain_scores_gemma":[0.9937925,0.005058275,0.0003413681,0.00013313333,0.0005207229,0.00015418661],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003434704,0.0008687281,0.0016296696,0.00246535,0.0003795468,0.002186221,0.0013605354,0.003009635,0.007962616],"category_scores_gemma":[0.005557457,0.00033683443,0.0012022434,0.0022256032,0.0012429417,0.0032447434,0.0017516313,0.003450689,0.0017711864],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049290014,0.00007459076,0.00012366327,0.026600711,0.00014232074,0.00007808015,0.00015961772,0.000272939,0.00019106765,0.016161233,0.018115222,0.93803126],"study_design_scores_gemma":[0.000046671594,0.00016456877,0.0014365817,0.06789599,0.00024907792,0.000816059,0.00036631225,0.00021284458,0.00023512186,0.016841099,0.9116983,0.00003745236],"about_ca_topic_score_codex":0.0021782399,"about_ca_topic_score_gemma":0.0025743577,"teacher_disagreement_score":0.007962616,"about_ca_system_score_codex":0.0016071728,"about_ca_system_score_gemma":0.0039038998,"threshold_uncertainty_score":0.026637614},"labels":[],"label_agreement":null},{"id":"W4409303104","doi":"10.3389/fmolb.2025.1567199","title":"Identification of metabolomics-based biomarker discovery in individuals with down syndrome utilizing kernel-tree model-enhanced explainable artificial intelligence methodology","year":2025,"lang":"en","type":"article","venue":"Frontiers in Molecular Biosciences","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton; Lakehead University","funders":"King Saud University","keywords":"Identification (biology); Metabolomics; Biomarker; Computer science; Tree (set theory); Kernel (algebra); Computational biology; Biomarker discovery; Machine learning; Artificial intelligence; Biology; Bioinformatics; Mathematics; Proteomics; Genetics; Gene; Ecology","score_opus":0.10167969139405625,"score_gpt":0.42594109775451666,"score_spread":0.3242614063604604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409303104","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40300512,0.00086943817,0.5940524,0.00038331037,0.000036157144,0.000068575995,0.00026846732,0.0004939997,0.0008225303],"genre_scores_gemma":[0.9489834,0.00023438687,0.04973801,0.00004889864,0.000018303987,0.00006149235,0.00028279252,0.000016601029,0.0006160496],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997559,0.00009254839,0.0000124917815,0.000062244006,0.000050014463,0.000026691023],"domain_scores_gemma":[0.9997192,0.00013162906,0.000065790475,0.000020143052,0.000052149528,0.000011008823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010175888,0.00049886625,0.0004376086,0.00067096093,0.00017336867,0.0006419136,0.00038397807,0.0003997567,0.00042932548],"category_scores_gemma":[0.0014364573,0.00013244298,0.00073794357,0.0003493773,0.00019835168,0.0004394618,0.00035435645,0.0003763357,0.00013174693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044600232,0.00031143686,0.086803004,0.00023761769,0.00058110396,0.00026735713,0.00013321564,0.6830614,0.021794174,0.0041150087,0.001054844,0.20119493],"study_design_scores_gemma":[0.000005299438,0.000055738492,0.004646474,0.000004865923,0.000019269726,0.000025843028,0.000008275272,0.99333644,0.000973063,0.0007497838,0.00017006081,0.0000048756588],"about_ca_topic_score_codex":0.0023612946,"about_ca_topic_score_gemma":0.0018390986,"teacher_disagreement_score":0.0023612946,"about_ca_system_score_codex":0.0003987905,"about_ca_system_score_gemma":0.0005237824,"threshold_uncertainty_score":0.005381584},"labels":[],"label_agreement":null},{"id":"W4409336976","doi":"10.5334/ijic.icic24459","title":"Feasibility of mHealth Integration into Integrated Youth Services: A Secondary Data Analytics Approach","year":2025,"lang":"en","type":"article","venue":"International Journal of Integrated Care","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"mHealth; Analytics; Integrated care; Computer science; Data science; Process management; Knowledge management; Business; Health care; Medicine; Psychological intervention; Nursing; Political science","score_opus":0.20435229170946267,"score_gpt":0.4907672050241074,"score_spread":0.28641491331464475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409336976","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7398279,0.00043414757,0.043497883,0.0019384449,0.00016298088,0.13744392,0.051848754,0.00087806705,0.023967883],"genre_scores_gemma":[0.7259458,0.00028713405,0.11586534,0.00071596756,0.00010185325,0.13884862,0.016063403,0.00015684494,0.002015192],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9717971,0.013747358,0.0049133054,0.0023389885,0.00539281,0.0018103989],"domain_scores_gemma":[0.9436271,0.026885962,0.004919446,0.004061236,0.018832106,0.0016740885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.052339572,0.0007440768,0.0014102397,0.00778248,0.0017289708,0.004635974,0.0016721913,0.0010689201,0.007041976],"category_scores_gemma":[0.0921306,0.0007267808,0.002855809,0.008138781,0.0011915789,0.0034108253,0.0053564073,0.0018874228,0.0016859937],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0045685023,0.008635029,0.52882755,0.010244805,0.0014546653,0.00045953717,0.06816036,0.0036096124,0.0035207486,0.007846683,0.012974889,0.34969768],"study_design_scores_gemma":[0.0021579727,0.012047872,0.7679531,0.004863386,0.0017300171,0.00025980826,0.10765121,0.03326297,0.0063975817,0.005944618,0.057415605,0.00031586128],"about_ca_topic_score_codex":0.018586967,"about_ca_topic_score_gemma":0.01819212,"teacher_disagreement_score":0.052339572,"about_ca_system_score_codex":0.0040096003,"about_ca_system_score_gemma":0.012839108,"threshold_uncertainty_score":0.2768014},"labels":[],"label_agreement":null},{"id":"W4409337609","doi":"10.5334/ijic.icic24185","title":"Feasibility of mHealth Integration into Integrated Youth Services: A Secondary Data Analytics Approach","year":2025,"lang":"en","type":"article","venue":"International Journal of Integrated Care","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"mHealth; Analytics; Integrated care; Computer science; Data science; Data analysis; Knowledge management; Health care; Medicine; Psychological intervention; Nursing; Data mining","score_opus":0.20435229170946267,"score_gpt":0.4907672050241074,"score_spread":0.28641491331464475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409337609","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7398279,0.00043414757,0.043497883,0.0019384449,0.00016298088,0.13744392,0.051848754,0.00087806705,0.023967883],"genre_scores_gemma":[0.7259458,0.00028713405,0.11586534,0.00071596756,0.00010185325,0.13884862,0.016063403,0.00015684494,0.002015192],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9717971,0.013747358,0.0049133054,0.0023389885,0.00539281,0.0018103989],"domain_scores_gemma":[0.9436271,0.026885962,0.004919446,0.004061236,0.018832106,0.0016740885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.052339572,0.0007440768,0.0014102397,0.00778248,0.0017289708,0.004635974,0.0016721913,0.0010689201,0.007041976],"category_scores_gemma":[0.0921306,0.0007267808,0.002855809,0.008138781,0.0011915789,0.0034108253,0.0053564073,0.0018874228,0.0016859937],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0045685023,0.008635029,0.52882755,0.010244805,0.0014546653,0.00045953717,0.06816036,0.0036096124,0.0035207486,0.007846683,0.012974889,0.34969768],"study_design_scores_gemma":[0.0021579727,0.012047872,0.7679531,0.004863386,0.0017300171,0.00025980826,0.10765121,0.03326297,0.0063975817,0.005944618,0.057415605,0.00031586128],"about_ca_topic_score_codex":0.018586967,"about_ca_topic_score_gemma":0.01819212,"teacher_disagreement_score":0.052339572,"about_ca_system_score_codex":0.0040096003,"about_ca_system_score_gemma":0.012839108,"threshold_uncertainty_score":0.2768014},"labels":[],"label_agreement":null},{"id":"W4409360221","doi":"10.2196/66068","title":"Optimizing Cardiovascular Risk Management in Primary Care Using a Personalized eCoach Solution Enhanced by an Artificial Intelligence–Driven Clinical Prediction Model: Protocol from the Coronary Artery Disease Risk Estimation and Early Detection Consortium","year":2025,"lang":"en","type":"article","venue":"JMIR Research Protocols","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Preprint; Protocol (science); Medicine; Primary care; Computer science; Alternative medicine; Family medicine; World Wide Web","score_opus":0.323034366139187,"score_gpt":0.5771029175393015,"score_spread":0.25406855140011453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409360221","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016904926,0.00035011087,0.037287384,0.001164993,0.00016835672,0.9334307,0.004365024,0.0002481757,0.006080367],"genre_scores_gemma":[0.013517091,0.0004896663,0.05011365,0.00040079257,0.000052800457,0.9327105,0.0017544449,0.000029536146,0.0009314987],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9889874,0.008148464,0.0011128298,0.0005480382,0.0007872533,0.00041607747],"domain_scores_gemma":[0.98998976,0.004029189,0.0007784035,0.0015752113,0.0027070837,0.00092035177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022225138,0.0013443007,0.0015357038,0.00082809734,0.0015685264,0.0011785164,0.0022228432,0.0018411339,0.018695813],"category_scores_gemma":[0.025896428,0.00096115377,0.0020186852,0.0011013,0.0009457146,0.0007811945,0.0019870508,0.0030062473,0.003156871],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.117688805,0.04997274,0.016335055,0.031085046,0.002816708,0.0019153869,0.0059052194,0.07928396,0.012777338,0.011421554,0.113267355,0.55753094],"study_design_scores_gemma":[0.24991249,0.094232194,0.056908008,0.023264928,0.003943904,0.0011918857,0.0034764423,0.08396455,0.022235336,0.021035383,0.43877676,0.0010580827],"about_ca_topic_score_codex":0.0031860403,"about_ca_topic_score_gemma":0.0048768613,"teacher_disagreement_score":0.022225138,"about_ca_system_score_codex":0.0025604896,"about_ca_system_score_gemma":0.011558766,"threshold_uncertainty_score":0.11753917},"labels":[],"label_agreement":null},{"id":"W4409369952","doi":"10.1016/j.aej.2025.03.025","title":"Identification and diagnosis of chronic heart disease: A deep learning-based hybrid approach","year":2025,"lang":"en","type":"article","venue":"Alexandria Engineering Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Identification (biology); Artificial intelligence; Chronic disease; Computer science; Medicine; Machine learning; Internal medicine; Biology","score_opus":0.0320022044177868,"score_gpt":0.36660413468732256,"score_spread":0.3346019302695358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409369952","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14475717,0.006118205,0.8394922,0.0017079944,0.00023780265,0.00015414227,0.0012052947,0.0021318085,0.0041954033],"genre_scores_gemma":[0.8859665,0.0014793584,0.10538868,0.00093869906,0.0002171391,0.00014651856,0.0019567152,0.000049035658,0.0038574205],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996549,0.00005219802,0.000028969682,0.00012069734,0.00006549765,0.0000777195],"domain_scores_gemma":[0.99972266,0.00009646363,0.000029402298,0.000023789009,0.00008941146,0.000038238853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059387734,0.00096149277,0.00092575786,0.0012822761,0.00030045217,0.0007610295,0.0010617529,0.0012883898,0.001134451],"category_scores_gemma":[0.0010019477,0.00033175395,0.00078574836,0.0007902763,0.0002504469,0.00080196926,0.0011715329,0.0010523349,0.000396713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063772587,0.0007945631,0.020192489,0.00033527185,0.00048208432,0.0005901685,0.00015197345,0.21723817,0.018431585,0.0029002542,0.008533353,0.72971237],"study_design_scores_gemma":[0.000015835412,0.00008272756,0.0019032647,0.000024291767,0.0000488392,0.000096284486,0.000027689946,0.99383825,0.0014328223,0.0018440064,0.0006731462,0.000012805502],"about_ca_topic_score_codex":0.008269045,"about_ca_topic_score_gemma":0.009824886,"teacher_disagreement_score":0.008269045,"about_ca_system_score_codex":0.0005864654,"about_ca_system_score_gemma":0.00077691907,"threshold_uncertainty_score":0.016441822},"labels":[],"label_agreement":null},{"id":"W4409602113","doi":"10.61091/jcmcc127b-057","title":"Decision Tree-Based Modeling in Mental Health Early Warning System for Higher Education Students","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mental health; Decision tree; Warning system; Psychology; Mental model; Tree (set theory); Computer science; Decision tree learning; Medical education; Artificial intelligence; Medicine; Psychiatry; Mathematics; Cognitive science","score_opus":0.08145641225157758,"score_gpt":0.44945875141959435,"score_spread":0.3680023391680168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409602113","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21120684,0.00043842767,0.7818835,0.0010083677,0.00010791481,0.00021295385,0.00058153726,0.0010328722,0.0035276995],"genre_scores_gemma":[0.9157158,0.00027072156,0.08106985,0.00011556251,0.000034008477,0.00024903083,0.00049085525,0.000026942975,0.0020271477],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994728,0.00021829383,0.000042655425,0.00010929155,0.000084153995,0.0000728288],"domain_scores_gemma":[0.9988152,0.00072495785,0.0000908108,0.000027799724,0.00028277352,0.00005847812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011848898,0.0005783574,0.0007221981,0.0009821764,0.0006440231,0.0010908409,0.0007254854,0.0007695983,0.0026384764],"category_scores_gemma":[0.0027624392,0.00036360617,0.0009004437,0.00066513283,0.00023183227,0.0009720868,0.00052517117,0.0007671363,0.00033195614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016488461,0.00013427516,0.006987326,0.000081972576,0.000069172536,0.00011460654,0.00017602666,0.94818383,0.0010023563,0.003953662,0.0011391977,0.037992783],"study_design_scores_gemma":[0.00000413036,0.000015474081,0.0002796267,0.000003630993,0.000006883268,0.000004693623,0.000010597801,0.9985348,0.00008662869,0.0009371213,0.000113497765,0.000002936102],"about_ca_topic_score_codex":0.021295737,"about_ca_topic_score_gemma":0.0145953,"teacher_disagreement_score":0.021295737,"about_ca_system_score_codex":0.001006296,"about_ca_system_score_gemma":0.0012754065,"threshold_uncertainty_score":0.042343557},"labels":[],"label_agreement":null},{"id":"W4409603802","doi":"10.61091/jcmcc127b-246","title":"Automatic classification and storage method of electronic medical records based on improved genetic algorithm","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Genetic algorithm; Medical record; Data mining; Algorithm; Artificial intelligence; Machine learning; Medicine","score_opus":0.04035452829009979,"score_gpt":0.4124235677798684,"score_spread":0.3720690394897686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409603802","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05103398,0.00026137216,0.94382477,0.00028589618,0.00007499808,0.00014072255,0.00018887053,0.0021487065,0.0020407136],"genre_scores_gemma":[0.37438762,0.00027124814,0.62040585,0.00019040695,0.00007835307,0.00020136853,0.0007218575,0.00013508816,0.0036082305],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99845386,0.00026595942,0.00016020852,0.0004218506,0.0005371186,0.00016094328],"domain_scores_gemma":[0.99870014,0.00034469692,0.00018778881,0.00020864677,0.00051348965,0.000045276876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093285815,0.0005033181,0.0010277223,0.0032283969,0.00073231803,0.0015872937,0.0015163824,0.0008729272,0.0014848977],"category_scores_gemma":[0.0039396877,0.00028066497,0.0009565267,0.002477774,0.0004796981,0.0015254747,0.00082565745,0.0005939145,0.00059068145],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016510919,0.000155201,0.0057182754,0.00011068532,0.00008404554,0.0001666214,0.00031068752,0.09813947,0.009881782,0.010103462,0.004529155,0.8706355],"study_design_scores_gemma":[0.000028251401,0.00008186008,0.0019556424,0.000022497123,0.00006940376,0.000215672,0.00009826471,0.98118275,0.00726374,0.006218576,0.0028334332,0.00003001329],"about_ca_topic_score_codex":0.009067527,"about_ca_topic_score_gemma":0.004809246,"teacher_disagreement_score":0.009067527,"about_ca_system_score_codex":0.00093434815,"about_ca_system_score_gemma":0.0017783196,"threshold_uncertainty_score":0.018029511},"labels":[],"label_agreement":null},{"id":"W4409655931","doi":"10.1016/j.aej.2025.03.010","title":"An improved and decentralized/distributed healthcare framework for disabled people through AI models","year":2025,"lang":"en","type":"article","venue":"Alexandria Engineering Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"King Salman Center for Disability Research","keywords":"Health care; Computer science; Business; Economics; Economic growth","score_opus":0.06417228811154463,"score_gpt":0.4504045270024908,"score_spread":0.38623223889094616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409655931","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017962184,0.00033836195,0.967577,0.0016142298,0.000098121054,0.0001493335,0.00018096136,0.0015936107,0.010486228],"genre_scores_gemma":[0.5697416,0.0005434207,0.41522092,0.00042070987,0.000106352025,0.00033064027,0.00039421563,0.00014001859,0.013102086],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99958056,0.0001236427,0.00002940681,0.00010763912,0.00009942544,0.00005937711],"domain_scores_gemma":[0.99969375,0.000087289256,0.000023490335,0.000043825832,0.00008648038,0.00006515977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007521714,0.00036818226,0.0004263452,0.00043925885,0.000940571,0.001656432,0.001260341,0.0009334338,0.0044854265],"category_scores_gemma":[0.0012189106,0.00021202661,0.00074714277,0.00036146562,0.0006684147,0.0017547073,0.0022730809,0.0009621543,0.0008709913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041863744,0.0004878728,0.0034056527,0.00027249378,0.0001175889,0.0010202533,0.001851457,0.4918112,0.015179573,0.27414614,0.014772281,0.19651683],"study_design_scores_gemma":[0.00003410085,0.000049685004,0.00027917037,0.000023186352,0.000024042829,0.00012246972,0.00014512727,0.9414713,0.0013229587,0.04123738,0.015267928,0.000022728607],"about_ca_topic_score_codex":0.0101369545,"about_ca_topic_score_gemma":0.011210718,"teacher_disagreement_score":0.0101369545,"about_ca_system_score_codex":0.001178909,"about_ca_system_score_gemma":0.0026441338,"threshold_uncertainty_score":0.020155907},"labels":[],"label_agreement":null},{"id":"W4409656024","doi":"10.2196/75690","title":"Correction: Machine Learning Models for Frailty Classification of Older Adults in Northern Thailand: Model Development and Validation Study","year":2025,"lang":"en","type":"erratum","venue":"JMIR Aging","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Gerontology; Medicine","score_opus":0.16487347900251334,"score_gpt":0.4464352724442534,"score_spread":0.28156179344174004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409656024","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024147148,0.0012805699,0.008745926,0.05853212,0.89531946,0.00028110435,0.027166683,0.0022742727,0.0039851572],"genre_scores_gemma":[0.14573388,0.005764195,0.05914068,0.13759126,0.20551851,0.0028335804,0.04043011,0.010716428,0.39227137],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98986185,0.0028675927,0.002733136,0.0011951921,0.00280832,0.0005339037],"domain_scores_gemma":[0.84403634,0.05126591,0.0040099137,0.009382201,0.08923912,0.002066564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012799999,0.0024772626,0.002147695,0.0035540438,0.002568298,0.0032061355,0.0043827984,0.004347345,0.115502596],"category_scores_gemma":[0.24830768,0.0010387745,0.002303185,0.0037405167,0.0014651205,0.0029278663,0.002535321,0.0061224797,0.038775705],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017109039,0.00001903397,0.0007172855,0.0003718516,0.000072695526,0.00021611172,0.000059094167,0.00018595753,0.000054122203,0.00043098512,0.9880881,0.009613672],"study_design_scores_gemma":[0.0011584086,0.0002524943,0.012830713,0.0035097662,0.0010413558,0.0019277405,0.00083255605,0.009607144,0.0029912852,0.011039089,0.9545213,0.00028822338],"about_ca_topic_score_codex":0.04508247,"about_ca_topic_score_gemma":0.047863323,"teacher_disagreement_score":0.115502596,"about_ca_system_score_codex":0.0029719833,"about_ca_system_score_gemma":0.009220737,"threshold_uncertainty_score":0.38639468},"labels":[],"label_agreement":null},{"id":"W4409787725","doi":"10.61091/jcmcc127a-523","title":"Machine Learning-Based Injury Risk Prediction Models for Athletes in Rehabilitation","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Athletes; Rehabilitation; Physical medicine and rehabilitation; Computer science; Machine learning; Artificial intelligence; Physical therapy; Medicine","score_opus":0.040603996086540466,"score_gpt":0.3848132848663795,"score_spread":0.34420928877983903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409787725","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.862354,0.0015235167,0.12847595,0.002146104,0.00020644657,0.00017672832,0.0020599992,0.0005363305,0.0025210206],"genre_scores_gemma":[0.98669446,0.0002936567,0.009470378,0.00007999185,0.00005674945,0.000091284935,0.0015602676,0.00001948206,0.0017337176],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995016,0.00014885867,0.00004881672,0.000131674,0.00006292442,0.00010616751],"domain_scores_gemma":[0.99704784,0.0019872466,0.00024986916,0.00008450462,0.0004817664,0.00014881391],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023968962,0.0008402754,0.0012070868,0.0019643744,0.0005283404,0.0014668133,0.0013723869,0.0013647337,0.0031890266],"category_scores_gemma":[0.006877974,0.00036767544,0.0013602932,0.0010193135,0.0002733378,0.0009599248,0.00077055127,0.0016032349,0.00069816416],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008733306,0.0011207537,0.15827401,0.0000989339,0.00032326704,0.00018524844,0.00010532795,0.7270462,0.00040355235,0.0018262402,0.0043231063,0.10542004],"study_design_scores_gemma":[0.000007528111,0.000051571697,0.005866258,0.000016668493,0.00002819462,0.000018187799,0.00003263713,0.9927907,0.00008035907,0.0010082506,0.000093310206,0.000006233362],"about_ca_topic_score_codex":0.023783898,"about_ca_topic_score_gemma":0.017287137,"teacher_disagreement_score":0.023783898,"about_ca_system_score_codex":0.0011932327,"about_ca_system_score_gemma":0.001506919,"threshold_uncertainty_score":0.04729092},"labels":[],"label_agreement":null},{"id":"W4409829731","doi":"10.53555/sfs.v7i3.3558","title":"Personalized Health Care Decisions Powered By Big Data And Generative Artificial Intelligence In Genomic Diagnostics","year":2021,"lang":"en","type":"article","venue":"Journal of Survey in Fisheries Sciences","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Big data; Generative grammar; Data science; Health care; Personalized medicine; Computer science; Artificial intelligence; Biology; Bioinformatics; Data mining; Political science","score_opus":0.62857217120748,"score_gpt":0.49140699321043413,"score_spread":0.13716517799704586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409829731","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029279267,0.041856047,0.80382204,0.08945755,0.0019510085,0.00030347786,0.0018413472,0.0009618447,0.030527497],"genre_scores_gemma":[0.6398682,0.02977276,0.30639344,0.01276136,0.003236283,0.0006060221,0.0018147905,0.00027512,0.005272032],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9945088,0.003214604,0.00027120364,0.0008614281,0.0009286474,0.0002153445],"domain_scores_gemma":[0.97644913,0.02015869,0.0007381579,0.0015946918,0.0006181823,0.00044121224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007446247,0.00076030067,0.0013673792,0.0020840752,0.001121787,0.006001311,0.0018675703,0.0034605858,0.0030832218],"category_scores_gemma":[0.023294626,0.0007997017,0.0015006514,0.002428002,0.0069228355,0.0070006624,0.0040714387,0.0067621474,0.00074688223],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000204161,0.00018651827,0.0066483007,0.0013933887,0.0004561312,0.0007018842,0.0013465428,0.10710123,0.001242491,0.7037835,0.02106325,0.15587264],"study_design_scores_gemma":[0.000025503718,0.000027456565,0.0009687185,0.00021714308,0.000054020624,0.00012396333,0.0002079772,0.08007871,0.00035778107,0.9006845,0.017193796,0.0000603702],"about_ca_topic_score_codex":0.0031314893,"about_ca_topic_score_gemma":0.0029599948,"teacher_disagreement_score":0.007446247,"about_ca_system_score_codex":0.0026153566,"about_ca_system_score_gemma":0.0022056838,"threshold_uncertainty_score":0.039379954},"labels":[],"label_agreement":null},{"id":"W4409902518","doi":"10.22214/ijraset.2025.69526","title":"AI-Based Healthcare Chatbot System","year":2025,"lang":"en","type":"article","venue":"International Journal for Research in Applied Science and Engineering Technology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity College","funders":"","keywords":"Chatbot; Healthcare system; Health care; Computer science; World Wide Web; Political science","score_opus":0.19320046260366597,"score_gpt":0.5724545242797762,"score_spread":0.3792540616761102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409902518","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15018694,0.00494446,0.40608674,0.0057122908,0.0030185254,0.0026451556,0.012010665,0.31047776,0.10491745],"genre_scores_gemma":[0.6604915,0.0011957565,0.18793258,0.004806905,0.0006999393,0.0021022637,0.019838301,0.002297733,0.12063499],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995221,0.00013381001,0.00004911856,0.00013377708,0.000113405935,0.000047806254],"domain_scores_gemma":[0.998615,0.0006640708,0.000069660055,0.00010060766,0.00027975344,0.0002708636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083172275,0.0007364349,0.00049633696,0.00084614876,0.0007520879,0.0009416811,0.0015890949,0.0011742349,0.020116067],"category_scores_gemma":[0.0026270521,0.0002591948,0.00035888387,0.00031521564,0.00031473098,0.0009831238,0.0012718763,0.0008083667,0.008263841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005044602,0.0018822465,0.0062051616,0.0037357386,0.0003252041,0.0054765893,0.0030818041,0.014039108,0.12728232,0.015879275,0.3664613,0.45058656],"study_design_scores_gemma":[0.0009975614,0.0012990321,0.01126157,0.00041819352,0.00030648752,0.0041156854,0.0014221949,0.48138124,0.050458923,0.023253633,0.42470664,0.00037886677],"about_ca_topic_score_codex":0.003306163,"about_ca_topic_score_gemma":0.0024231214,"teacher_disagreement_score":0.020116067,"about_ca_system_score_codex":0.0007013942,"about_ca_system_score_gemma":0.000886078,"threshold_uncertainty_score":0.067294955},"labels":[],"label_agreement":null},{"id":"W4410061591","doi":"10.53555/sfs.v9i3.3568","title":"Integrating Machine Learning and Big Data Analytics to Transform Patient Outcomes in Chronic Disease Management","year":2022,"lang":"en","type":"article","venue":"Journal of Survey in Fisheries Sciences","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Big data; Data science; Analytics; Computer science; Disease; Chronic disease; Medicine; Artificial intelligence; Psychology; Machine learning; Knowledge management; Intensive care medicine; Data mining; Internal medicine","score_opus":0.4999394559518861,"score_gpt":0.46634134664946236,"score_spread":0.03359810930242374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410061591","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054862402,0.3707043,0.37347358,0.1561157,0.0027087107,0.0019534947,0.004888725,0.0012556124,0.034037497],"genre_scores_gemma":[0.47614184,0.1495069,0.35530207,0.012266369,0.0018622736,0.001423626,0.0022619774,0.00012463244,0.0011102754],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98105997,0.014049247,0.0014390126,0.0010418458,0.0020394896,0.0003705319],"domain_scores_gemma":[0.9408775,0.04723627,0.0038265602,0.0030587153,0.0041782246,0.0008226867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025866585,0.0008107573,0.0011068986,0.0068251053,0.00067487126,0.0055867904,0.00133317,0.0010807347,0.0014886701],"category_scores_gemma":[0.053650677,0.00035745505,0.0019912499,0.007263183,0.0019804442,0.0067835487,0.00370293,0.0026734308,0.00040230894],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019406693,0.00031378577,0.032352068,0.020713778,0.0015806032,0.00019240433,0.0025754909,0.011040494,0.001257895,0.11638256,0.010968825,0.802428],"study_design_scores_gemma":[0.0002536665,0.0012623833,0.047432143,0.06960265,0.0035744596,0.0004994583,0.008693333,0.059442293,0.00718889,0.5311175,0.27052608,0.00040720415],"about_ca_topic_score_codex":0.0037364191,"about_ca_topic_score_gemma":0.006938655,"teacher_disagreement_score":0.025866585,"about_ca_system_score_codex":0.003090347,"about_ca_system_score_gemma":0.010789752,"threshold_uncertainty_score":0.13679719},"labels":[],"label_agreement":null},{"id":"W4410071166","doi":"10.3390/a18050265","title":"Forecasting Cancer Incidence in Canada by Age, Sex, and Region Until 2026 Using Machine Learning Techniques","year":2025,"lang":"en","type":"article","venue":"Algorithms","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Laurentian University","funders":"","keywords":"Incidence (geometry); Cancer incidence; Cancer; Computer science; Artificial intelligence; Demography; Medicine; Machine learning; Mathematics; Internal medicine","score_opus":0.12916660872842856,"score_gpt":0.4414684905899365,"score_spread":0.3123018818615079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410071166","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89024854,0.0032401066,0.01683769,0.005579864,0.00016239437,0.00011858364,0.06858896,0.00092339684,0.014300494],"genre_scores_gemma":[0.96550757,0.0013360373,0.0077643017,0.00018814007,0.000026784337,0.000025922911,0.020595478,0.000031420914,0.0045242216],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997743,0.00002255428,0.000010760368,0.000037881553,0.00008611107,0.00006843226],"domain_scores_gemma":[0.99916625,0.00010121073,0.000067825946,0.0000237911,0.0005657331,0.00007522132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052671146,0.0003841529,0.00023340431,0.0017082107,0.0006407336,0.0007750386,0.00071364944,0.0003012682,0.0012970782],"category_scores_gemma":[0.0022324773,0.00014633092,0.00065404736,0.0026615455,0.00017432097,0.00028480426,0.00032549634,0.0004894249,0.00038496125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021688562,0.00008550325,0.59285945,0.00017944185,0.00018252891,0.00020154218,0.0002457928,0.2812464,0.00053410744,0.002864111,0.025244242,0.09614001],"study_design_scores_gemma":[0.000022980445,0.00004599134,0.30833894,0.0001094422,0.000086030705,0.000066744666,0.0006104675,0.67082125,0.00075901893,0.0012649477,0.017834624,0.000039530954],"about_ca_topic_score_codex":0.9926783,"about_ca_topic_score_gemma":0.9922454,"teacher_disagreement_score":0.016176123,"about_ca_system_score_codex":0.016176123,"about_ca_system_score_gemma":0.020963242,"threshold_uncertainty_score":0.11736649},"labels":[],"label_agreement":null},{"id":"W4410100528","doi":"10.47392/irjaeh.2025.0129","title":"AI- Based Heart Disease Detection Using Machine Learning","year":2025,"lang":"en","type":"article","venue":"International Research Journal on Advanced Engineering Hub (IRJAEH)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning","score_opus":0.1513779749869514,"score_gpt":0.553785817858072,"score_spread":0.40240784287112064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410100528","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13111617,0.0015868038,0.8493134,0.0026519015,0.00027738255,0.00032417045,0.001052597,0.0053958558,0.008281734],"genre_scores_gemma":[0.8218338,0.00049401895,0.17350888,0.00046500316,0.0001470968,0.00015193241,0.0008725099,0.00004926003,0.002477465],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992508,0.00024363685,0.00006104045,0.00014394576,0.00024191104,0.00005859481],"domain_scores_gemma":[0.9972066,0.0017513064,0.0002195291,0.00019181517,0.00053552043,0.000095114185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013639189,0.00058232446,0.0006005018,0.0019865118,0.00039994903,0.0014097254,0.0008891281,0.0007940075,0.0016201137],"category_scores_gemma":[0.0064903875,0.00019678478,0.0005297041,0.0010652939,0.00032078323,0.0009944158,0.00069692306,0.0009330026,0.00080343144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045438213,0.0008256755,0.03361193,0.00023736112,0.00022750164,0.0003486265,0.0002626912,0.21464667,0.012105665,0.008544931,0.009474433,0.7192601],"study_design_scores_gemma":[0.000015670292,0.000071953735,0.0029217498,0.000020062496,0.000018307363,0.00007770866,0.000042660176,0.9842465,0.003438625,0.007889237,0.0012401856,0.000017279523],"about_ca_topic_score_codex":0.0046858415,"about_ca_topic_score_gemma":0.004260532,"teacher_disagreement_score":0.0046858415,"about_ca_system_score_codex":0.0007799582,"about_ca_system_score_gemma":0.0007749873,"threshold_uncertainty_score":0.00931716},"labels":[],"label_agreement":null},{"id":"W4410168140","doi":"10.1016/b978-0-443-23979-3.00019-1","title":"Data analytics and cognitive computing for digital health: A generic approach and a review of emerging technologies, challenges, and research directions","year":2025,"lang":"en","type":"review","venue":"Elsevier eBooks","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Data science; Analytics; Cognitive computing; Computer science; Cognition; Psychology; Neuroscience","score_opus":0.585672525355511,"score_gpt":0.5758419921448784,"score_spread":0.009830533210632542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410168140","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000077912104,0.9970483,0.00066530023,0.0010269353,0.00019426446,0.000008688926,0.000014282565,0.000007436173,0.0009568016],"genre_scores_gemma":[0.00067687425,0.99737144,0.0010037615,0.00046130008,0.0002470206,0.000011109987,0.000015844795,0.0000019011568,0.00021074315],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99911326,0.00022858543,0.00013009398,0.00012668502,0.00033889286,0.00006253911],"domain_scores_gemma":[0.996479,0.0025847447,0.00021047067,0.000077143326,0.0005138917,0.00013482381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023299926,0.0011448081,0.0020014988,0.0064285896,0.00053362694,0.0033601327,0.0012520219,0.002044601,0.0026554174],"category_scores_gemma":[0.0031796456,0.00041762678,0.00096344406,0.007373409,0.0019449032,0.0044441284,0.0017933864,0.0033419095,0.0010503463],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004399235,0.0000859233,0.0004170647,0.029547717,0.00014505305,0.00015308459,0.00025213495,0.000622264,0.00073041976,0.038708158,0.02173186,0.90756226],"study_design_scores_gemma":[0.000018969611,0.00011228554,0.0015573992,0.032674666,0.00023868986,0.0011628476,0.0005317311,0.000656936,0.0004273527,0.032560803,0.9299812,0.00007712828],"about_ca_topic_score_codex":0.0036490436,"about_ca_topic_score_gemma":0.005983931,"teacher_disagreement_score":0.0064285896,"about_ca_system_score_codex":0.0019647381,"about_ca_system_score_gemma":0.0051516574,"threshold_uncertainty_score":0.014255226},"labels":[],"label_agreement":null},{"id":"W4410168835","doi":"10.1002/cdt3.70007","title":"Protocol for an Integrative Meta‐Analysis of the Application of Machine Learning Algorithms in the Prediction of Chronic Disease Risks and Outcomes","year":2025,"lang":"en","type":"article","venue":"Chronic Diseases and Translational Medicine","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Medicine; Protocol (science); Disease; Meta-analysis; Machine learning; Algorithm; Artificial intelligence; Alternative medicine; Computer science; Internal medicine; Pathology","score_opus":0.19495001430582395,"score_gpt":0.5247377087847794,"score_spread":0.3297876944789555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410168835","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00083466416,0.0034256526,0.011691115,0.0014859743,0.0015311964,0.95216763,0.025995795,0.00072433316,0.0021436287],"genre_scores_gemma":[0.0011651866,0.0004913672,0.0063214456,0.00045982323,0.000066426874,0.989267,0.0015324045,0.000051825642,0.0006444358],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.95196456,0.023540178,0.013642726,0.005399614,0.0041928897,0.0012600821],"domain_scores_gemma":[0.9056266,0.043460317,0.013924457,0.019253327,0.01596842,0.0017669],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06792982,0.0064715142,0.013849112,0.008168092,0.0029371574,0.005902193,0.004489499,0.009087621,0.1039397],"category_scores_gemma":[0.18900596,0.004015521,0.029001355,0.0072455355,0.0024676742,0.005298084,0.003370711,0.009811031,0.012417684],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.039692983,0.0005984511,0.002321154,0.6583086,0.05179488,0.00093048887,0.0015661017,0.005401479,0.003110869,0.016469045,0.15670724,0.063098826],"study_design_scores_gemma":[0.11753504,0.003018055,0.012397181,0.3561831,0.0798423,0.00074209995,0.000728553,0.007667588,0.0043706135,0.0597906,0.35682443,0.00090047496],"about_ca_topic_score_codex":0.005074379,"about_ca_topic_score_gemma":0.007613781,"teacher_disagreement_score":0.1039397,"about_ca_system_score_codex":0.009943622,"about_ca_system_score_gemma":0.023170121,"threshold_uncertainty_score":0.3592515},"labels":[],"label_agreement":null},{"id":"W4410187365","doi":"10.63278/1426","title":"A Robust MI-Based Hybrid Diagnostic Model for Early Detection of Heart Diseases","year":2025,"lang":"en","type":"article","venue":"Metallurgical and Materials Engineering","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Materials science; Cardiology; Internal medicine; Medicine","score_opus":0.07590066273951229,"score_gpt":0.36058508389246247,"score_spread":0.2846844211529502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410187365","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08921558,0.0017885935,0.90079117,0.00070863444,0.00021934556,0.00012583876,0.00053033844,0.002132933,0.0044875364],"genre_scores_gemma":[0.9123303,0.0005646243,0.07956222,0.00028541425,0.00015086,0.00018908807,0.0006546195,0.000055386197,0.006207476],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99972254,0.000047804442,0.000021393033,0.000094414885,0.000070709706,0.000043158725],"domain_scores_gemma":[0.99960655,0.00015636109,0.00004433874,0.000026591613,0.00014580642,0.00002032168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084835436,0.00060728187,0.0009184753,0.000987132,0.00035672841,0.0008987379,0.0013487192,0.0008490324,0.0017526386],"category_scores_gemma":[0.0015041478,0.00029787948,0.00080224033,0.000535203,0.00020008709,0.0005789271,0.0005762884,0.0008466818,0.00082904124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006771971,0.00035759178,0.01367458,0.0001354154,0.00038644654,0.00033701197,0.00012737245,0.56993186,0.018975785,0.004582056,0.0053120516,0.3855026],"study_design_scores_gemma":[0.000003714458,0.000053096985,0.000809681,0.0000047411604,0.000029230552,0.00005087976,0.0000039127767,0.997459,0.0007765654,0.00044601076,0.00035518344,0.000008058366],"about_ca_topic_score_codex":0.006690658,"about_ca_topic_score_gemma":0.0062957914,"teacher_disagreement_score":0.006690658,"about_ca_system_score_codex":0.00063983415,"about_ca_system_score_gemma":0.00056538155,"threshold_uncertainty_score":0.013303399},"labels":[],"label_agreement":null},{"id":"W4410213089","doi":"10.34172/hpp.025.43105","title":"Artificial intelligence survival models for identifying relevant risk factors for incident diabetes in Azar cohort population","year":2025,"lang":"en","type":"article","venue":"Health Promotion Perspectives","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"University of Tabriz; Tabriz University of Medical Sciences","keywords":"Medicine; Lasso (programming language); Proportional hazards model; Body mass index; Population; Waist; Cohort; Concordance; Internal medicine; Diabetes mellitus; Random forest; Statistics; Artificial intelligence; Environmental health; Computer science; Mathematics; Endocrinology","score_opus":0.2598115529163273,"score_gpt":0.5115856487618774,"score_spread":0.2517740958455501,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410213089","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82601804,0.0030829024,0.16215062,0.0025197288,0.00024336175,0.00018137463,0.0030727042,0.0005255406,0.0022057614],"genre_scores_gemma":[0.97461617,0.0007554617,0.0212395,0.00017287156,0.00014235429,0.00017190735,0.0019947328,0.000022793263,0.00088424224],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99939764,0.00036231126,0.00003053704,0.00008180979,0.00006306633,0.0000647733],"domain_scores_gemma":[0.99757856,0.0017423796,0.00027353558,0.00010253456,0.0002315695,0.00007154777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045433417,0.0007512132,0.0005417015,0.0014235392,0.0003343608,0.0007436476,0.000725456,0.00044154451,0.0014197459],"category_scores_gemma":[0.0054238867,0.00017645855,0.0011701143,0.00074809964,0.00021159786,0.000309587,0.00043313243,0.001095164,0.00029082582],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004962391,0.00032365072,0.32503766,0.00018431921,0.0010209314,0.00028277104,0.00020816512,0.59721,0.00060354493,0.0032880583,0.0061269137,0.06521777],"study_design_scores_gemma":[0.000025584231,0.00012966045,0.018531814,0.000046299632,0.00017510648,0.00006545679,0.000065222,0.977792,0.00015781775,0.0022107842,0.0007854632,0.000014669486],"about_ca_topic_score_codex":0.008844178,"about_ca_topic_score_gemma":0.0059728315,"teacher_disagreement_score":0.008844178,"about_ca_system_score_codex":0.0005015243,"about_ca_system_score_gemma":0.0010319002,"threshold_uncertainty_score":0.024027824},"labels":[],"label_agreement":null},{"id":"W4410410429","doi":"10.22541/au.174730399.99371489/v1","title":"Towards Technological Health: Improving Access to Public Healthcare in B.C. by Integrating Virtual Care and Predictive AI","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Health care; Public healthcare; Business; Public health care; Nursing; Public health; Knowledge management; Computer science; Medicine; Health policy; Economic growth; Economics","score_opus":0.1562897012717247,"score_gpt":0.5046101720191685,"score_spread":0.34832047074744377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410410429","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16924301,0.0048382147,0.05636326,0.3679816,0.0013891228,0.00035163396,0.00101129,0.0027596764,0.39606223],"genre_scores_gemma":[0.8165332,0.0058598076,0.08498094,0.01436729,0.00031801045,0.00014916254,0.0010321566,0.00030727655,0.07645213],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99846965,0.00062278035,0.000033114655,0.00015633494,0.00036592086,0.00035222055],"domain_scores_gemma":[0.996947,0.0009296169,0.00016570529,0.00035161804,0.00059495936,0.0010111232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032584218,0.00046392638,0.00024112265,0.0010151342,0.0023291293,0.007962043,0.0010571681,0.001857958,0.014521596],"category_scores_gemma":[0.007427209,0.00024012971,0.00036948605,0.0016446623,0.0031168598,0.0037859448,0.003496414,0.0026397288,0.0029632389],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039105795,0.00047399083,0.034191594,0.00043582747,0.00007509715,0.00040768896,0.004746067,0.0069911587,0.003915272,0.15016156,0.18700553,0.61120504],"study_design_scores_gemma":[0.00020656054,0.0005369963,0.06919549,0.0010132979,0.000118525124,0.0006196793,0.02030832,0.05146412,0.010596727,0.16862017,0.67710555,0.00021460572],"about_ca_topic_score_codex":0.20044245,"about_ca_topic_score_gemma":0.2207836,"teacher_disagreement_score":0.79955757,"about_ca_system_score_codex":0.007816983,"about_ca_system_score_gemma":0.019001337,"threshold_uncertainty_score":0.39855146},"labels":[],"label_agreement":null},{"id":"W4410494511","doi":"10.1007/978-3-031-90341-0_13","title":"Assisting Personal Support Worker’s e-Training with AI Prediction","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Guelph","funders":"","keywords":"Training (meteorology); Computer science; Artificial intelligence; Geography","score_opus":0.20920061779631988,"score_gpt":0.4618421721298551,"score_spread":0.25264155433353525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410494511","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3893339,0.009156533,0.50120986,0.004970448,0.0004879233,0.0003288712,0.005772747,0.014331844,0.07440788],"genre_scores_gemma":[0.8011553,0.0032766578,0.15464658,0.0003393157,0.00015010576,0.0001426414,0.0045155883,0.00021849717,0.03555531],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99979633,0.000059699643,0.000008454605,0.00004077861,0.00007753268,0.000017133163],"domain_scores_gemma":[0.9986432,0.001035235,0.00006887558,0.000071392125,0.00013731906,0.00004400372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078591827,0.0005394562,0.0002725849,0.0008739088,0.00017953414,0.0010900731,0.00068394997,0.0004858752,0.008295802],"category_scores_gemma":[0.002927816,0.0001455143,0.0003264529,0.00086707127,0.00011160657,0.0009309102,0.00054426433,0.00078591343,0.004353721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009410367,0.00022967346,0.022926653,0.00022782398,0.000030007433,0.00008364695,0.000195192,0.0339927,0.0026792958,0.0015999173,0.027742226,0.9101987],"study_design_scores_gemma":[0.000014417609,0.00021454362,0.026622338,0.00035965734,0.000035169047,0.00025293863,0.00036246056,0.91943705,0.008665606,0.009069338,0.034918357,0.000048178466],"about_ca_topic_score_codex":0.0034123636,"about_ca_topic_score_gemma":0.004550134,"teacher_disagreement_score":0.008295802,"about_ca_system_score_codex":0.00035629544,"about_ca_system_score_gemma":0.0004576895,"threshold_uncertainty_score":0.02775222},"labels":[],"label_agreement":null},{"id":"W4410506516","doi":"10.12927/hcpap.2025.27569","title":"Training Data Tell Us a Lot About Whom Health AI Tools Are Likely to Benefit","year":2025,"lang":"en","type":"article","venue":"A Nudge Too Far? A Nudge at All? On Paying People to Be Healthy","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Institute for Work & Health","funders":"","keywords":"Training (meteorology); Computer science; Data science; Geography","score_opus":0.38611120857927017,"score_gpt":0.5145671997662392,"score_spread":0.12845599118696904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410506516","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32402244,0.017044397,0.1783533,0.17849739,0.004534282,0.0018985724,0.2221103,0.002575601,0.07096368],"genre_scores_gemma":[0.7624341,0.004227286,0.0737849,0.03172825,0.0012975599,0.00231609,0.11878969,0.0009869146,0.0044353404],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9688056,0.019813197,0.002670758,0.0035844573,0.003883568,0.0012424041],"domain_scores_gemma":[0.6537673,0.2822862,0.011883044,0.03436155,0.0140601145,0.0036417271],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.053062413,0.0017021674,0.002610176,0.0040311394,0.0022828477,0.007851598,0.0024110004,0.0051971897,0.012630567],"category_scores_gemma":[0.2630853,0.0012238974,0.002826595,0.0036620551,0.0037918105,0.012981319,0.004045074,0.008480912,0.00784104],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037590952,0.0013471618,0.42550948,0.0034899192,0.0026239713,0.000404403,0.0019369746,0.02743422,0.002566401,0.030987373,0.23859489,0.26134613],"study_design_scores_gemma":[0.001366568,0.0015382426,0.2408648,0.009033213,0.0025278607,0.0017064647,0.006156565,0.09959795,0.007687671,0.3374838,0.29128212,0.0007547831],"about_ca_topic_score_codex":0.0038736886,"about_ca_topic_score_gemma":0.0056201485,"teacher_disagreement_score":0.053062413,"about_ca_system_score_codex":0.0023431121,"about_ca_system_score_gemma":0.0037386795,"threshold_uncertainty_score":0.2806242},"labels":[],"label_agreement":null},{"id":"W4410544996","doi":"10.18280/isi.300424","title":"Generative Adversarial Network Based Improved Transfer Learning Models for Chronic Heart Failure Detection","year":2025,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Adversarial system; Generative grammar; Transfer of learning; Generative adversarial network; Computer science; Artificial intelligence; Machine learning; Deep learning","score_opus":0.04913976061440594,"score_gpt":0.34759975492835316,"score_spread":0.2984599943139472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410544996","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08206354,0.0017231727,0.9081437,0.00090502115,0.00016708237,0.00006459495,0.00030871562,0.0013042742,0.0053198473],"genre_scores_gemma":[0.95439714,0.00049809396,0.036464434,0.0003089876,0.00007711228,0.00010245065,0.00047197347,0.00007201926,0.0076077813],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99974865,0.00008270708,0.000011228425,0.00006803948,0.000046271627,0.000043140393],"domain_scores_gemma":[0.9991922,0.0005373377,0.00007398546,0.000040086376,0.00012736095,0.000029124769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000914825,0.00084700587,0.0007067908,0.0004891169,0.00022052268,0.0005737588,0.0009436417,0.00078886445,0.0017864668],"category_scores_gemma":[0.0021981983,0.00034155918,0.00065158424,0.00035334087,0.0005266332,0.0005708971,0.0007734505,0.001600754,0.0004840216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006362479,0.000032821306,0.0010376394,0.000021592547,0.000030403187,0.00004732226,0.00002450434,0.9674618,0.00077575125,0.002954335,0.0009993967,0.026550796],"study_design_scores_gemma":[9.040753e-7,0.0000054501875,0.000068370355,0.0000017265717,0.0000022018712,0.0000040652844,9.2827275e-7,0.9991365,0.000099857716,0.00061100035,0.00006756028,0.0000014208107],"about_ca_topic_score_codex":0.006717483,"about_ca_topic_score_gemma":0.0055087595,"teacher_disagreement_score":0.006717483,"about_ca_system_score_codex":0.00080950704,"about_ca_system_score_gemma":0.00052275945,"threshold_uncertainty_score":0.013356745},"labels":[],"label_agreement":null},{"id":"W4410565760","doi":"10.53555/sfs.v8i3.3605","title":"Machine Learning-Driven Biomarker Discovery in Chronic Kidney Disease for Personalized Therapeutic Strategies","year":2021,"lang":"en","type":"article","venue":"Journal of Survey in Fisheries Sciences","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Biomarker; Biomarker discovery; Kidney disease; Personalized medicine; Disease; Medicine; Computational biology; Bioinformatics; Computer science; Internal medicine; Biology; Proteomics; Gene","score_opus":0.4040859334795851,"score_gpt":0.4624606229309218,"score_spread":0.058374689451336725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410565760","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042245027,0.061977323,0.8449111,0.04185369,0.0010984624,0.00029565813,0.0018965959,0.0011789666,0.0045431154],"genre_scores_gemma":[0.6454099,0.037485186,0.3022685,0.006149188,0.0026902067,0.0006570221,0.0027004858,0.00019034233,0.0024491013],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997696,0.001207831,0.00014921486,0.0003879254,0.0004187661,0.00014018844],"domain_scores_gemma":[0.994044,0.0037318403,0.00059834734,0.00047812265,0.0008906359,0.00025714285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006153132,0.0006828845,0.0018052385,0.0015618168,0.0005024253,0.0027470342,0.001315837,0.0015393953,0.0014671402],"category_scores_gemma":[0.01716221,0.0004679577,0.0010606403,0.0014463713,0.0010794459,0.0022483778,0.0018450506,0.0031770696,0.0006694251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081353774,0.0004929742,0.029559642,0.002451332,0.0008720497,0.00062777376,0.00029906782,0.26646864,0.012571818,0.10184907,0.03390858,0.5500855],"study_design_scores_gemma":[0.00008999775,0.00026713457,0.00437829,0.0005664955,0.0002448804,0.0002902668,0.00010551819,0.6959239,0.0061846063,0.2645496,0.027281439,0.000117748736],"about_ca_topic_score_codex":0.0024187567,"about_ca_topic_score_gemma":0.002512485,"teacher_disagreement_score":0.006153132,"about_ca_system_score_codex":0.0014674627,"about_ca_system_score_gemma":0.00377066,"threshold_uncertainty_score":0.032541275},"labels":[],"label_agreement":null},{"id":"W4410568955","doi":"10.1007/978-3-031-88762-8_17","title":"An Efficient Framework for Multi-level Lung Cancer Prediction Using Support Vector Machine Classifier","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Workplace Health, Safety and Compensation Commission","funders":"","keywords":"Support vector machine; Lung cancer; Classifier (UML); Computer science; Artificial intelligence; Machine learning; Oncology; Medicine","score_opus":0.3569091041819048,"score_gpt":0.5422085270092531,"score_spread":0.18529942282734835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410568955","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004661889,0.0005997561,0.9921321,0.00009555627,0.0000705696,0.00005388215,0.00020300208,0.0014455692,0.00073775864],"genre_scores_gemma":[0.16362357,0.0010272638,0.8245129,0.00017504646,0.00022259529,0.00030311497,0.0017810739,0.00014066906,0.008213771],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99962485,0.000049764512,0.000022779248,0.00007897146,0.0001667075,0.000056977104],"domain_scores_gemma":[0.99975306,0.00005861677,0.000013607696,0.000021905387,0.00013780362,0.000015035938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005315953,0.00061491545,0.0012989097,0.0009488432,0.00045606738,0.00094628474,0.0016951794,0.00093646615,0.0026244235],"category_scores_gemma":[0.0008900576,0.0003302176,0.00085672847,0.0009994416,0.00017152753,0.0009362106,0.00075790734,0.0009268012,0.0015373937],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013935534,0.00019951569,0.0012654057,0.000107271575,0.00010300162,0.00021639797,0.00003820755,0.16330953,0.011716546,0.01061367,0.013394824,0.7988963],"study_design_scores_gemma":[0.0000043915675,0.000022471393,0.00019452686,0.000004444686,0.000012726268,0.000050184066,0.000006250027,0.994534,0.0015175167,0.0021499095,0.0014964415,0.0000070984574],"about_ca_topic_score_codex":0.0120008355,"about_ca_topic_score_gemma":0.012969953,"teacher_disagreement_score":0.0120008355,"about_ca_system_score_codex":0.00045857576,"about_ca_system_score_gemma":0.0013961118,"threshold_uncertainty_score":0.023861945},"labels":[],"label_agreement":null},{"id":"W4410595433","doi":"10.18280/ria.390101","title":"Comparison of Machine Learning Classification Methods for Early Detection of Diabetes","year":2025,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Universitas Sebelas Maret","keywords":"Artificial intelligence; Computer science; Machine learning; Pattern recognition (psychology)","score_opus":0.2524308111262094,"score_gpt":0.5428236255316927,"score_spread":0.2903928144054833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410595433","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5754155,0.11297138,0.26702422,0.004261501,0.0023084125,0.0010050378,0.00453189,0.00265353,0.029828504],"genre_scores_gemma":[0.8417033,0.02057995,0.13063718,0.0003556351,0.0004440562,0.0003402597,0.0029977039,0.000095918556,0.0028458638],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99385345,0.0021516823,0.00062730815,0.00050153286,0.0026163915,0.00024953985],"domain_scores_gemma":[0.98703593,0.009092071,0.00051319844,0.00045201188,0.002718054,0.00018865944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009234871,0.0010459607,0.0013503573,0.006669169,0.00040585725,0.0015766728,0.0009791119,0.0010354513,0.0011416859],"category_scores_gemma":[0.013254528,0.00020504951,0.0012917356,0.0034882228,0.00020670373,0.0012473019,0.0005082679,0.00081262604,0.000522193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024602893,0.0009513413,0.06683135,0.0014585598,0.0013734024,0.00010779979,0.00016492998,0.044739064,0.0019393762,0.0021461903,0.0063404455,0.87148726],"study_design_scores_gemma":[0.00029991908,0.0031997273,0.116207935,0.00083158084,0.0011588251,0.0005407571,0.0007877801,0.8495261,0.008978089,0.0036561987,0.014624822,0.00018830739],"about_ca_topic_score_codex":0.0040520667,"about_ca_topic_score_gemma":0.0028715353,"teacher_disagreement_score":0.009234871,"about_ca_system_score_codex":0.0009148756,"about_ca_system_score_gemma":0.0009232805,"threshold_uncertainty_score":0.04883927},"labels":[],"label_agreement":null},{"id":"W4410737755","doi":"10.2196/preprints.64753","title":"The Value of Remote Vital Signs Monitoring in Detecting Clinical Deterioration in Patients in Hospital at Home Programs or Postacute Medical Patients in the Community: Systematic Review (Preprint)","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Preprint; Vital signs; Medicine; Value (mathematics); Medical emergency; Signs and symptoms; Surgery; Computer science; World Wide Web","score_opus":0.17314109018705667,"score_gpt":0.5016810366754493,"score_spread":0.3285399464883926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410737755","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024894557,0.99447376,0.00017749758,0.00040900375,0.00027019216,0.00092609465,0.0009735345,0.00001731934,0.00026314752],"genre_scores_gemma":[0.04513721,0.9481606,0.0012251036,0.0015093029,0.0003298868,0.0026733342,0.0006852167,0.00001556146,0.00026374136],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9915815,0.0027721557,0.003347018,0.0007384065,0.0013215033,0.00023937288],"domain_scores_gemma":[0.9671788,0.023138551,0.0065041394,0.00043798288,0.0024794,0.00026101],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009255784,0.0012772457,0.009257017,0.0061630514,0.00045869645,0.0030363945,0.0015531724,0.002034271,0.005134625],"category_scores_gemma":[0.052263383,0.0008823079,0.011030641,0.0067155645,0.00074040785,0.0023463303,0.0013644808,0.0012107354,0.00028868846],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037477564,0.000010623722,0.0007545693,0.9672038,0.017677015,0.00003632091,0.000084633364,0.00005745836,0.00009251284,0.000069790076,0.0011638292,0.012474717],"study_design_scores_gemma":[0.00068540394,0.00029073475,0.006634723,0.7921105,0.19150381,0.00021453635,0.00020103934,0.00014177324,0.00022001051,0.00020635576,0.007740498,0.000050629595],"about_ca_topic_score_codex":0.0073251813,"about_ca_topic_score_gemma":0.016057458,"teacher_disagreement_score":0.009257017,"about_ca_system_score_codex":0.0037079537,"about_ca_system_score_gemma":0.007976169,"threshold_uncertainty_score":0.048949838},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4410769795","doi":"10.1101/2025.05.26.25328366","title":"Short-term and long-term outcome prediction for patients with coronary artery disease using machine learning and comprehensive multi-center patient data","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Alberta Health Services; Royal Alexandra Hospital; University of Ottawa; Libin Cardiovascular Institute of Alberta; University of Alberta; University of Calgary","funders":"Canadian Institutes of Health Research; Alberta Innovates","keywords":"Term (time); Outcome (game theory); Coronary artery disease; Center (category theory); Medicine; Disease; Cardiology; Internal medicine; Computer science; Artificial intelligence; Mathematics","score_opus":0.24065346810604066,"score_gpt":0.46187121414565885,"score_spread":0.2212177460396182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410769795","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9795705,0.000418114,0.01581619,0.00041807536,0.000019669471,0.000071103816,0.0031582676,0.00013722257,0.00039083353],"genre_scores_gemma":[0.991508,0.00008533006,0.0045648986,0.000059712114,0.000019099814,0.00004052379,0.003627067,0.000007336591,0.00008790155],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979808,0.0008621072,0.00017217529,0.0005529886,0.00027565192,0.0001563371],"domain_scores_gemma":[0.98456347,0.008978535,0.0025613594,0.0017715921,0.0013435758,0.0007815199],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007817024,0.0008725575,0.0007302396,0.0022333283,0.00039391263,0.0010066389,0.00092931814,0.0006561333,0.00057489245],"category_scores_gemma":[0.01868102,0.0002662892,0.001081636,0.0017017679,0.0005691346,0.00090165035,0.0013393691,0.0010745908,0.00019192642],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003492815,0.00020863175,0.91211444,0.00005552756,0.00049646985,0.00009278343,0.00010384099,0.06545829,0.0002672753,0.0002591561,0.0008337399,0.019760553],"study_design_scores_gemma":[0.00003631791,0.00038853695,0.5598068,0.0000631994,0.00024384356,0.00016356852,0.00016417739,0.4356224,0.00063814246,0.0020869432,0.00072980503,0.000056300305],"about_ca_topic_score_codex":0.02160965,"about_ca_topic_score_gemma":0.028979072,"teacher_disagreement_score":0.02160965,"about_ca_system_score_codex":0.0014217483,"about_ca_system_score_gemma":0.0018443473,"threshold_uncertainty_score":0.042967737},"labels":[],"label_agreement":null},{"id":"W4410949402","doi":"10.1101/2025.06.01.25328752","title":"Barriers and Facilitators to the Implementation of Artificial Intelligence Enabled Diabetes Interventions in Lower-Middle-Income Countries: A Systematic Review Protocol","year":2025,"lang":"en","type":"review","venue":"medRxiv","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children’s Health Research Institute; Lawson Health Research Institute; London Health Sciences Centre; Western University","funders":"","keywords":"Low and middle income countries; Psychological intervention; Protocol (science); Psychology; Computer science; Medicine; Developing country; Economics; Economic growth; Nursing; Alternative medicine","score_opus":0.1533877343419988,"score_gpt":0.5264238326082814,"score_spread":0.3730360982662826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410949402","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013320663,0.015665404,0.0017189821,0.00066312554,0.00024781746,0.9749487,0.004700681,0.00009300992,0.00063009746],"genre_scores_gemma":[0.0017034885,0.008027027,0.0030925146,0.00049925887,0.000032162032,0.9855474,0.000665582,0.000011194963,0.00042138953],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.95596945,0.014846733,0.018634655,0.0032120547,0.0055293078,0.0018077493],"domain_scores_gemma":[0.9438124,0.026173351,0.013450964,0.0032658488,0.011566493,0.0017309958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08029422,0.005405808,0.024849826,0.021613972,0.0044527343,0.008197949,0.00655132,0.008110323,0.04383971],"category_scores_gemma":[0.108091846,0.0055053434,0.018172652,0.015875498,0.0050878585,0.010170334,0.0062571396,0.0039225216,0.0044766176],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011305519,0.00008477114,0.0005164834,0.9761736,0.0022076305,0.0002460901,0.0010963848,0.0002181373,0.0003198116,0.0011662482,0.003876809,0.01296345],"study_design_scores_gemma":[0.006422996,0.0010328859,0.0031171746,0.91451615,0.022304717,0.00035678598,0.0021580057,0.0004748337,0.0009249576,0.0023484407,0.046101972,0.00024106582],"about_ca_topic_score_codex":0.008768244,"about_ca_topic_score_gemma":0.018723577,"teacher_disagreement_score":0.08029422,"about_ca_system_score_codex":0.018539734,"about_ca_system_score_gemma":0.076260865,"threshold_uncertainty_score":0.4246415},"labels":[],"label_agreement":null},{"id":"W4410961670","doi":"10.1007/978-981-96-0185-1_34","title":"An Intelligent Prognostication Framework for Lung Cancer Prediction via K-Nearest Neighbors (KNN) Algorithm","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"k-nearest neighbors algorithm; Computer science; Algorithm; Lung cancer; Artificial intelligence; Pattern recognition (psychology); Medicine; Internal medicine","score_opus":0.05609471179615581,"score_gpt":0.4186059555185654,"score_spread":0.36251124372240956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410961670","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008107745,0.00092467613,0.98848385,0.00018427776,0.000093645416,0.000039256967,0.00013336662,0.0007766829,0.0012564752],"genre_scores_gemma":[0.43859234,0.0013654557,0.54976887,0.00030787967,0.00028904446,0.00023288777,0.00086914445,0.00010585696,0.008468606],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99967563,0.00004905106,0.000024899318,0.00010106011,0.00010808048,0.00004131298],"domain_scores_gemma":[0.9998099,0.000055596178,0.000012733575,0.00001174123,0.00009955947,0.0000105440495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060268,0.00052266207,0.0012495696,0.0006201383,0.0005526464,0.0006958287,0.0014930051,0.00089789444,0.0019186576],"category_scores_gemma":[0.0008585799,0.00028247756,0.0007093178,0.0006532858,0.00023889563,0.0007972342,0.0007044889,0.0006771574,0.0007432912],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014057884,0.00013568612,0.00139531,0.00008648068,0.000094440584,0.00013063075,0.000056108245,0.46302104,0.0036511885,0.0071260645,0.0065211253,0.51764137],"study_design_scores_gemma":[0.0000036810754,0.00001611017,0.0001389966,0.0000043908676,0.000012599877,0.000023051656,0.0000052948476,0.9966988,0.0003943405,0.002007063,0.00069016154,0.0000054819934],"about_ca_topic_score_codex":0.017621946,"about_ca_topic_score_gemma":0.015642121,"teacher_disagreement_score":0.017621946,"about_ca_system_score_codex":0.00055364997,"about_ca_system_score_gemma":0.0010276306,"threshold_uncertainty_score":0.03503871},"labels":[],"label_agreement":null},{"id":"W4410984428","doi":"10.22541/au.174897559.99564896/v1","title":"A Comparative Analysis of Artificial Intelligence Search Tools for Evidence Synthesis","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Agency for Drugs and Technologies in Health","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.6558632414450133,"score_gpt":0.6182259202497302,"score_spread":0.03763732119528307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410984428","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10691664,0.53038013,0.29846114,0.0074360236,0.0010398016,0.007450447,0.007094826,0.0020283612,0.03919265],"genre_scores_gemma":[0.612086,0.058824964,0.31604475,0.0011037285,0.0006372889,0.00484776,0.0035659184,0.00059067766,0.0022989633],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.69198084,0.24921016,0.025826052,0.0044249785,0.027308632,0.0012493139],"domain_scores_gemma":[0.11361606,0.8594415,0.00828733,0.008256083,0.009697222,0.00070183136],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.15558869,0.002797248,0.0061828466,0.03452684,0.001202019,0.011300976,0.002606431,0.0032731798,0.02184149],"category_scores_gemma":[0.5776654,0.0012038901,0.009081642,0.02301861,0.002761676,0.009183271,0.0059134425,0.0022518644,0.0013300868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.021294186,0.00087241025,0.01700547,0.05999257,0.02572242,0.00038091742,0.0025957802,0.021764167,0.0011849303,0.055771295,0.0055640955,0.78785163],"study_design_scores_gemma":[0.018952735,0.022054736,0.0784246,0.071744666,0.12409234,0.004997509,0.006457707,0.2921957,0.009510176,0.29537964,0.07459795,0.0015922328],"about_ca_topic_score_codex":0.0030055917,"about_ca_topic_score_gemma":0.003750028,"teacher_disagreement_score":0.8444113,"about_ca_system_score_codex":0.006711536,"about_ca_system_score_gemma":0.007731282,"threshold_uncertainty_score":0.82284147},"labels":[],"label_agreement":null},{"id":"W4411025259","doi":"10.1097/01.hjh.0001118500.85100.a2","title":"Artificial Intelligence vs. Human Expertise in Diagnosing Acute Coronary Syndromes: A Meta-Analysis Focusing on 12-Lead Electrocardiogram Model","year":2025,"lang":"en","type":"article","venue":"Journal of Hypertension","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Lead (geology); Meta-analysis; Acute coronary syndrome; Cardiology; Intensive care medicine; Internal medicine; Myocardial infarction","score_opus":0.4015879954020386,"score_gpt":0.4865997492666987,"score_spread":0.08501175386466009,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411025259","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010473188,0.987092,0.0012112259,0.00035154098,0.00016946769,0.00012556101,0.0002714711,0.000021006117,0.0002845169],"genre_scores_gemma":[0.5218972,0.46980992,0.0042091473,0.0013443778,0.00070497714,0.00063043286,0.000945249,0.00006378289,0.00039495714],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9811398,0.011277582,0.0038682984,0.0018735756,0.0014757846,0.00036494905],"domain_scores_gemma":[0.91147184,0.07769161,0.006015022,0.001884273,0.0023492058,0.00058809004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031190746,0.0028981254,0.0148456795,0.005638205,0.00067149126,0.0044739856,0.0024989294,0.0032430615,0.003044856],"category_scores_gemma":[0.056732573,0.0012299458,0.054500822,0.006525918,0.0008747273,0.002571587,0.0014353271,0.0028261717,0.0002566996],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00439337,0.000040053787,0.016015803,0.08666614,0.8816312,0.00010811997,0.000076698736,0.0007373215,0.00014530966,0.00014712871,0.0002653841,0.009773449],"study_design_scores_gemma":[0.0004232147,0.00024903627,0.004234115,0.005717195,0.9880469,0.000057139543,0.000028808086,0.00039327034,0.000060805236,0.0001921207,0.00058166916,0.000015731563],"about_ca_topic_score_codex":0.0047979555,"about_ca_topic_score_gemma":0.0078107356,"teacher_disagreement_score":0.031190746,"about_ca_system_score_codex":0.0016847237,"about_ca_system_score_gemma":0.0021403641,"threshold_uncertainty_score":0.16495436},"labels":[],"label_agreement":null},{"id":"W4411183658","doi":"10.1007/s00198-025-07541-x","title":"Machine learning is changing osteoporosis detection: an integrative review","year":2025,"lang":"en","type":"review","venue":"Osteoporosis International","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nexen (Canada)","funders":"National Natural Science Foundation of China","keywords":"Medicine; Osteoporosis; Rheumatology; Orthopedic surgery; Medical physics; Physical therapy; Internal medicine; Artificial intelligence; Surgery; Computer science","score_opus":0.11939338207148328,"score_gpt":0.4954077746510967,"score_spread":0.37601439257961344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411183658","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000034472774,0.9994485,0.000044173805,0.00025408316,0.0000857308,0.000003992375,0.000015260237,0.0000020535938,0.00011172791],"genre_scores_gemma":[0.00036127385,0.9989868,0.00013455725,0.0003238594,0.00011664175,0.0000063610155,0.000017685454,9.635687e-7,0.000051899697],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993861,0.00016496898,0.00015364151,0.000099630546,0.00016385948,0.00003177767],"domain_scores_gemma":[0.9957885,0.0030708278,0.00042190618,0.000055566652,0.0005650452,0.00009811226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023081265,0.000869645,0.00323301,0.0031557262,0.00029668826,0.0016602221,0.0014685917,0.00174185,0.004271184],"category_scores_gemma":[0.0052533913,0.00045817724,0.0017783324,0.0031820813,0.0006094897,0.0017637333,0.0010472958,0.0018828176,0.000932843],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014038324,0.000084981424,0.0004498594,0.12606682,0.0011683687,0.00008823179,0.00008447293,0.0002738406,0.0003085598,0.0018400908,0.020915156,0.84857935],"study_design_scores_gemma":[0.00024495012,0.00039563442,0.0043539773,0.16585387,0.008953668,0.0010031429,0.0002806335,0.00042209314,0.0003488316,0.004762623,0.81327665,0.0001039419],"about_ca_topic_score_codex":0.002950549,"about_ca_topic_score_gemma":0.008436228,"teacher_disagreement_score":0.004271184,"about_ca_system_score_codex":0.0008977674,"about_ca_system_score_gemma":0.0028363112,"threshold_uncertainty_score":0.014288545},"labels":[],"label_agreement":null},{"id":"W4411339293","doi":"10.2196/74415","title":"Machine Learning–Based Analysis of Lifestyle Risk Factors for Atherosclerotic Cardiovascular Disease: Retrospective Case-Control Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprint; Medicine; Atherosclerotic cardiovascular disease; Disease; Computer science; Internal medicine; World Wide Web","score_opus":0.049997501908884655,"score_gpt":0.41709860928533643,"score_spread":0.3671011073764518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411339293","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9976605,0.00061514234,0.00085081364,0.000043150783,0.000015621146,0.00007431623,0.00046518884,0.0000073242422,0.00026795396],"genre_scores_gemma":[0.9982218,0.00020513963,0.00060003356,0.000051974377,0.000034278906,0.00009817199,0.00069263787,0.0000038327285,0.00009206596],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982253,0.00047465725,0.00022981488,0.000598571,0.00031496142,0.00015675256],"domain_scores_gemma":[0.9981499,0.0003022046,0.00066845975,0.00046996237,0.00024018741,0.00016923487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020012693,0.000480676,0.00080443383,0.0010172079,0.000754277,0.00073777797,0.0005731204,0.00081148616,0.0010179194],"category_scores_gemma":[0.0029659236,0.000787714,0.0008382565,0.0018689559,0.0004458616,0.00063498,0.0004086465,0.0009014373,0.0002260752],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028853034,0.0001441625,0.9977927,0.000023658955,0.00021490971,0.00011872199,0.000029469975,0.0000766477,0.00024213326,0.00004518055,0.00013156462,0.0008923621],"study_design_scores_gemma":[0.00010788795,0.0003089428,0.99656624,0.00001547768,0.00026825548,0.0007395355,0.00007885381,0.0013046024,0.00009486591,0.000090993046,0.00041199935,0.000012306647],"about_ca_topic_score_codex":0.0028254704,"about_ca_topic_score_gemma":0.0027627766,"teacher_disagreement_score":0.0028254704,"about_ca_system_score_codex":0.0004838477,"about_ca_system_score_gemma":0.00062919315,"threshold_uncertainty_score":0.010583878},"labels":[],"label_agreement":null},{"id":"W4411386977","doi":"10.1016/j.imu.2025.101661","title":"Enhancing diabetes risk prediction: A comparative evaluation of bagging, boosting, and ensemble classifiers with SMOTE oversampling","year":2025,"lang":"en","type":"article","venue":"Informatics in Medicine Unlocked","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cistel Technology (Canada); Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Boosting (machine learning); Oversampling; Random subspace method; Machine learning; Artificial intelligence; Computer science; Ensemble learning; Pattern recognition (psychology); Support vector machine; Bandwidth (computing)","score_opus":0.15669711350098092,"score_gpt":0.47702231412376417,"score_spread":0.32032520062278325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411386977","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7089196,0.0151237445,0.26304486,0.0015052984,0.00085446186,0.00038596452,0.0008306787,0.0021084477,0.007226863],"genre_scores_gemma":[0.922463,0.0019789294,0.07305664,0.00035222573,0.00020401386,0.000082942795,0.0009553524,0.000053713313,0.00085321843],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983889,0.00074065843,0.00010815446,0.00022229238,0.00040584366,0.00013419817],"domain_scores_gemma":[0.9943506,0.003701109,0.00023711292,0.0004179327,0.0011109418,0.00018235782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007389795,0.0012904971,0.0019325734,0.001704225,0.0004940173,0.0010137719,0.0010337648,0.00098775,0.0004913428],"category_scores_gemma":[0.00960918,0.00029194594,0.001109298,0.0011084593,0.00028009663,0.0015187394,0.00091423426,0.0013320069,0.00023367997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023367251,0.0012683516,0.047232818,0.00031271717,0.00086393853,0.00009720787,0.00020721013,0.3860642,0.0023779122,0.0016406833,0.005125598,0.5524727],"study_design_scores_gemma":[0.00004273845,0.000564326,0.00478152,0.000043579643,0.00015406641,0.00003915439,0.00005467859,0.99149334,0.0011225423,0.0009105288,0.00077570963,0.000017904982],"about_ca_topic_score_codex":0.006881245,"about_ca_topic_score_gemma":0.0054179095,"teacher_disagreement_score":0.007389795,"about_ca_system_score_codex":0.00054304453,"about_ca_system_score_gemma":0.0010948157,"threshold_uncertainty_score":0.039081454},"labels":[],"label_agreement":null},{"id":"W4411400787","doi":"10.51244/ijrsi.2025.120500158","title":"Research Capabilities and Engagement of Nurses from Training Hospitals in Tacloban City","year":2025,"lang":"en","type":"article","venue":"International journal of research and scientific innovation","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Workload; Quarter (Canadian coin); Psychology; Medical education; Descriptive research; Work engagement; Research design; Professional development; Work (physics); Medicine; Sociology; Management; Engineering","score_opus":0.45395353888299955,"score_gpt":0.6203896804346671,"score_spread":0.16643614155166758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411400787","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9989078,0.000064753905,0.000028466828,0.00021621204,0.0000025346233,0.0000098013315,0.000041728836,8.4294487e-7,0.0007278787],"genre_scores_gemma":[0.9988005,0.00019674664,0.00015124126,0.00014387429,0.000004973507,0.000038583123,0.000090028734,8.6303294e-7,0.0005731726],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99827266,0.0007142545,0.00020243619,0.00012197426,0.00029778024,0.00039089035],"domain_scores_gemma":[0.99232036,0.0020180675,0.0023432206,0.00021987782,0.0012962659,0.0018022202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024215542,0.00009392799,0.0002236811,0.00093656295,0.001538865,0.0012363608,0.0004056221,0.0003155533,0.0016943404],"category_scores_gemma":[0.0066315634,0.00014664578,0.00015674617,0.00093430805,0.0005820931,0.0007167052,0.0018735228,0.000537678,0.0002739397],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000108604945,0.00018175784,0.92299473,0.00016903332,0.000020134798,0.00048463396,0.05311443,0.00013589973,0.00066271564,0.00021321913,0.0009485529,0.020966327],"study_design_scores_gemma":[0.0000065232307,0.0002358789,0.8860126,0.0001407215,0.00000868397,0.00024821097,0.11021862,0.00023676554,0.0001507976,0.00009419472,0.0026256314,0.000021368951],"about_ca_topic_score_codex":0.017560685,"about_ca_topic_score_gemma":0.056007206,"teacher_disagreement_score":0.017560685,"about_ca_system_score_codex":0.0020260988,"about_ca_system_score_gemma":0.004028089,"threshold_uncertainty_score":0.034916937},"labels":[],"label_agreement":null},{"id":"W4411464911","doi":"10.21776/ub.mnj.2025.011.01.21","title":"UNCONTROLLED DIABETES AS FACTOR AFFECTING COGNITIVE FUNCTION IN TYPE 2 DIABETES MELLITUS","year":2025,"lang":"en","type":"article","venue":"MNJ (Malang Neurology Journal)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Glycated hemoglobin; Logistic regression; Medicine; Cognition; Diabetes mellitus; Montreal Cognitive Assessment; Type 2 Diabetes Mellitus; Type 2 diabetes; Bivariate analysis; Risk factor; Internal medicine; Statistics; Cognitive impairment; Endocrinology; Mathematics; Psychiatry","score_opus":0.05333999501995492,"score_gpt":0.40634870459490996,"score_spread":0.35300870957495506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411464911","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9946577,0.0027267956,0.000108081236,0.00029258514,0.000043238906,0.000015694091,0.00020135123,0.000004465587,0.0019500309],"genre_scores_gemma":[0.9990355,0.0005268142,0.000083018414,0.00004703437,0.000036979396,0.0000051292186,0.00009610488,0.0000010004061,0.00016841486],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994869,0.00011147964,0.00006645532,0.000066274,0.00019067436,0.0000781719],"domain_scores_gemma":[0.9982413,0.0003484732,0.0009361742,0.00005421383,0.00014362777,0.0002761847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060798984,0.00021334007,0.00024199554,0.0007340022,0.00046706793,0.00069593545,0.00030500704,0.00030703298,0.002308021],"category_scores_gemma":[0.002523075,0.00012498174,0.00049101695,0.0013465573,0.00024885687,0.00025527086,0.00028234857,0.0008308653,0.00014094073],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052717107,0.000047664653,0.99788433,0.000021661275,0.000026837895,0.0002383453,0.000038212827,0.000012509045,0.000035971512,0.000015050403,0.00007972581,0.0015470654],"study_design_scores_gemma":[0.0000042661086,0.00009068771,0.9983835,0.000028277951,0.00006075405,0.0009157994,0.00013569674,0.00008135584,0.00003011085,0.000042840904,0.00022335902,0.0000033491167],"about_ca_topic_score_codex":0.004947251,"about_ca_topic_score_gemma":0.004651148,"teacher_disagreement_score":0.004947251,"about_ca_system_score_codex":0.00026470635,"about_ca_system_score_gemma":0.00059045234,"threshold_uncertainty_score":0.009836912},"labels":[],"label_agreement":null},{"id":"W4411658774","doi":"10.51847/cup0zxe","title":"10.51847/cUp0ZXE","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Decision tree; Artificial neural network; Computer science; Artificial intelligence; Machine learning; Decision tree learning; Tree (set theory); Algorithm; Mathematics","score_opus":0.08150564879527511,"score_gpt":0.39688862935745445,"score_spread":0.31538298056217934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411658774","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000826588,0.000493623,0.0020344043,0.0006395576,0.00045611235,0.00012870344,0.0023272724,0.0038136644,0.98928005],"genre_scores_gemma":[0.002052721,0.00031002908,0.0013516664,0.00045288907,0.0000958649,0.000057426347,0.0021247691,0.0006060647,0.9929484],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996153,0.000027363736,0.000025294194,0.0001258805,0.00013198066,0.000074124015],"domain_scores_gemma":[0.99887115,0.00019686171,0.000047231766,0.00022172567,0.00038614552,0.0002767947],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00063803897,0.0018778096,0.0008449418,0.0031247756,0.0016508121,0.0033905278,0.0014996605,0.0034300524,0.9754165],"category_scores_gemma":[0.0015275192,0.00055944803,0.00065693917,0.0031665792,0.00077353936,0.0029964822,0.0028774256,0.0014186915,0.98351675],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016816022,0.00013833272,0.00072719686,0.00026427145,0.000014060303,0.00017687188,0.00006006691,0.00025027114,0.0023502326,0.0039662407,0.47024718,0.5216371],"study_design_scores_gemma":[0.000035324898,0.000033064218,0.0007729119,0.00013845513,0.000010753345,0.00019607517,0.000052418047,0.00031668492,0.000627434,0.0008400207,0.9969593,0.000017598146],"about_ca_topic_score_codex":0.0048831715,"about_ca_topic_score_gemma":0.0038690197,"teacher_disagreement_score":0.024583519,"about_ca_system_score_codex":0.0009761708,"about_ca_system_score_gemma":0.00063777476,"threshold_uncertainty_score":0.035065413},"labels":[],"label_agreement":null},{"id":"W4411713439","doi":"10.55041/ijsrem51058","title":"CardioNet.AI - Heart Disease Predictor Model","year":2025,"lang":"en","type":"article","venue":"INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Cardiology; Disease; Internal medicine; Medicine; Artificial intelligence; Computer science","score_opus":0.15589393779604355,"score_gpt":0.5085537581160609,"score_spread":0.3526598203200173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411713439","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14194758,0.004564,0.39022407,0.008683832,0.0028797444,0.0014123074,0.35166034,0.060378436,0.038249623],"genre_scores_gemma":[0.546762,0.0026217115,0.14140278,0.0027146426,0.0007249216,0.002187014,0.27479863,0.0008409234,0.027947407],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998392,0.000025118587,0.000013210852,0.00007053617,0.000031861615,0.000020110454],"domain_scores_gemma":[0.9997161,0.000118952885,0.000020000858,0.000031452953,0.00008924807,0.000024209006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005206118,0.0010248199,0.00049376854,0.00091458927,0.00030585678,0.0008347287,0.0016336894,0.0007772956,0.0115254605],"category_scores_gemma":[0.0021191793,0.00030872723,0.0006775312,0.00078179396,0.00017511897,0.00068100914,0.00070498255,0.0015084781,0.005538717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012460682,0.00062147423,0.03934027,0.00066821306,0.00047625322,0.00045696684,0.000110858506,0.2852087,0.0022550214,0.009957965,0.3721109,0.28754732],"study_design_scores_gemma":[0.00011286878,0.00009383486,0.003157316,0.00005046543,0.000064744294,0.00011987774,0.000023124643,0.9593606,0.0011478325,0.0064514587,0.029390309,0.000027517688],"about_ca_topic_score_codex":0.016604511,"about_ca_topic_score_gemma":0.019895272,"teacher_disagreement_score":0.016604511,"about_ca_system_score_codex":0.0007485935,"about_ca_system_score_gemma":0.0014483988,"threshold_uncertainty_score":0.038556457},"labels":[],"label_agreement":null},{"id":"W4411753619","doi":"10.1093/humrep/deaf097.410","title":"P-101 The dual AI system including 3D-AI showed high performance for predicting implantation","year":2025,"lang":"en","type":"article","venue":"Human Reproduction","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Dual (grammatical number); Medicine; Computer science; Art","score_opus":0.17178842189813656,"score_gpt":0.4809703321057862,"score_spread":0.3091819102076496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411753619","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9168439,0.006432734,0.05611217,0.00094214414,0.0006216749,0.00029292086,0.0044867713,0.0023176554,0.011950127],"genre_scores_gemma":[0.98347247,0.0004040131,0.011853108,0.00011534748,0.0001284244,0.00009270561,0.0019613057,0.00008373138,0.0018889223],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979772,0.0006025762,0.00021262254,0.00058924145,0.0004857181,0.00013262822],"domain_scores_gemma":[0.9955479,0.002411774,0.00045518312,0.00028638612,0.0010282573,0.0002705395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041205683,0.0012527776,0.0010021161,0.0015618689,0.00037548566,0.0023870661,0.0006483247,0.0010866149,0.0044974512],"category_scores_gemma":[0.01106681,0.0003595165,0.0013566343,0.00068499404,0.000327138,0.0010400331,0.001006203,0.0008696475,0.0021093637],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004591826,0.00040556237,0.61299485,0.00068781816,0.001737148,0.0005044459,0.00018369465,0.016360119,0.02419196,0.00046124248,0.009877349,0.32800388],"study_design_scores_gemma":[0.00023892666,0.004408472,0.46320128,0.00026279854,0.0019305537,0.0038557244,0.0003490158,0.48916623,0.025101947,0.001985456,0.009208387,0.00029122038],"about_ca_topic_score_codex":0.0015422051,"about_ca_topic_score_gemma":0.001304634,"teacher_disagreement_score":0.0044974512,"about_ca_system_score_codex":0.00042285884,"about_ca_system_score_gemma":0.00053093344,"threshold_uncertainty_score":0.021791935},"labels":[],"label_agreement":null},{"id":"W4411792976","doi":"10.18280/ts.420321","title":"A Cloud Edge Based Heart Disease Detection Using DenseNet Convoluted Radial Basis Neural Network for Diabetic Patients","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial neural network; Cloud computing; Computer science; Enhanced Data Rates for GSM Evolution; Basis (linear algebra); Artificial intelligence; Mathematics; Geometry; Operating system","score_opus":0.08927859142605019,"score_gpt":0.3961344554534029,"score_spread":0.30685586402735276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411792976","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8317204,0.0017353685,0.15510689,0.0010454383,0.00025509176,0.00020634271,0.003289122,0.002372884,0.004268357],"genre_scores_gemma":[0.95183325,0.00043960172,0.041582707,0.00020191201,0.000056228193,0.00006306093,0.0031124887,0.00003184804,0.0026789065],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998085,0.000021539017,0.000013382811,0.0000606758,0.000049224276,0.00004680076],"domain_scores_gemma":[0.99980336,0.000042867723,0.000022228984,0.000018847653,0.00008507096,0.000027537597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031963052,0.0006047526,0.0006395619,0.0008953226,0.000284589,0.00056150765,0.0008076875,0.00061108836,0.001332201],"category_scores_gemma":[0.00073215197,0.00022937982,0.0005958331,0.00058731093,0.000120299606,0.00036662695,0.0004927304,0.00053915166,0.00047549087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023184582,0.0020592061,0.12654378,0.00025942715,0.00031024002,0.0017591871,0.00015007163,0.22466855,0.015007725,0.0009057385,0.017352374,0.6086652],"study_design_scores_gemma":[0.000018996896,0.00009391137,0.007653268,0.000010346967,0.000023271044,0.00010461185,0.00002886571,0.9885005,0.0027811264,0.0002690271,0.000504562,0.00001150461],"about_ca_topic_score_codex":0.018007513,"about_ca_topic_score_gemma":0.018631594,"teacher_disagreement_score":0.018007513,"about_ca_system_score_codex":0.00066224445,"about_ca_system_score_gemma":0.0005568017,"threshold_uncertainty_score":0.035805404},"labels":[],"label_agreement":null},{"id":"W4412017252","doi":"10.18280/isi.300505","title":"SMOTE-ENN Resampling to Optimize Diabetes Prediction in Imbalanced Data","year":2025,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Resampling; Computer science; Artificial intelligence; Machine learning; Data mining; Pattern recognition (psychology)","score_opus":0.0928380235529106,"score_gpt":0.39948168302528403,"score_spread":0.30664365947237343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412017252","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3473813,0.0015792712,0.6433078,0.0007486676,0.00033933343,0.00024048318,0.0008731034,0.0029888852,0.002541129],"genre_scores_gemma":[0.78568244,0.00028131373,0.20871802,0.00039769174,0.00008463793,0.00020762565,0.0027590133,0.00016896483,0.0017002918],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921525,0.0003109248,0.00006240084,0.00018115183,0.00012444805,0.000105746185],"domain_scores_gemma":[0.9982108,0.0010085657,0.00013759089,0.00013822207,0.00045077378,0.000054114756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004422945,0.0009577278,0.00085381826,0.0008286798,0.00041295477,0.0006782845,0.0007470061,0.00059173146,0.00073061994],"category_scores_gemma":[0.008235249,0.0003042424,0.0010373549,0.00048894255,0.0003307775,0.00076563214,0.00063238124,0.0012194256,0.0003251096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007662401,0.00040157512,0.029471334,0.00023090096,0.0004625856,0.00015636657,0.00018265698,0.70160466,0.0075911367,0.0024995066,0.0055192104,0.25111383],"study_design_scores_gemma":[0.00001939215,0.00007563541,0.0028839135,0.000018035764,0.000027350756,0.000019847175,0.000034376077,0.99322814,0.002077908,0.0007815048,0.00082564924,0.000008282604],"about_ca_topic_score_codex":0.011860177,"about_ca_topic_score_gemma":0.013939061,"teacher_disagreement_score":0.011860177,"about_ca_system_score_codex":0.00056641636,"about_ca_system_score_gemma":0.0013968705,"threshold_uncertainty_score":0.02358234},"labels":[],"label_agreement":null},{"id":"W4412037924","doi":"10.18280/isi.300501","title":"Detection of Heart Disease Using Binary Classification Machine Learning Model","year":2025,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Binary classification; Computer science; Binary number; Artificial intelligence; Machine learning; Pattern recognition (psychology); Support vector machine; Mathematics","score_opus":0.1051175393826718,"score_gpt":0.40373646196857915,"score_spread":0.29861892258590733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412037924","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3833037,0.002116511,0.5943919,0.0010975164,0.0004506134,0.00054829137,0.005650611,0.0041448153,0.008295949],"genre_scores_gemma":[0.8596149,0.00045451027,0.1319579,0.00019380957,0.000112458314,0.0002822323,0.004982554,0.00004092793,0.0023608296],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987668,0.0003677333,0.0001416064,0.00027991846,0.00030400167,0.0001400879],"domain_scores_gemma":[0.99796754,0.0010489859,0.00022173751,0.00018365828,0.0005235337,0.000054507906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017990087,0.0007581168,0.0008244731,0.0028058405,0.00034336612,0.001291302,0.00080662605,0.0008780625,0.0014150828],"category_scores_gemma":[0.005433593,0.00015536693,0.00078281754,0.00130333,0.00020663496,0.0009583607,0.00048956234,0.00064255594,0.0012449814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008869557,0.0012181497,0.15205507,0.00039983948,0.00032456583,0.00041031317,0.00017595026,0.13232632,0.008848727,0.0036487116,0.015811885,0.6838935],"study_design_scores_gemma":[0.00002574724,0.00019121949,0.018401777,0.00006154557,0.000052778945,0.0002502418,0.00007897597,0.9716612,0.003532755,0.0035563363,0.0021481554,0.00003918676],"about_ca_topic_score_codex":0.006374884,"about_ca_topic_score_gemma":0.0038328,"teacher_disagreement_score":0.006374884,"about_ca_system_score_codex":0.0004919572,"about_ca_system_score_gemma":0.00068555505,"threshold_uncertainty_score":0.012675583},"labels":[],"label_agreement":null},{"id":"W4412042216","doi":"10.1016/j.jtho.2025.04.006","title":"A Response to the Letter to the Editor: “Decision Trees and Random Forests: Nonlinear and Nonparametric Alternatives to Logistic Regression in Biological Data Analysis”","year":2025,"lang":"en","type":"letter","venue":"Journal of Thoracic Oncology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AstraZeneca (Canada)","funders":"","keywords":"Logistic regression; Random forest; Nonparametric statistics; Decision tree; Medicine; Statistics; Nonparametric regression; Econometrics; Machine learning; Mathematics; Computer science","score_opus":0.22447510982785124,"score_gpt":0.5833782056270076,"score_spread":0.35890309579915636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412042216","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000093025774,0.0006397313,0.00015912778,0.9529689,0.045485422,0.000013478359,0.000087297005,0.000021726379,0.0005312661],"genre_scores_gemma":[0.00078784407,0.00055050553,0.00031153316,0.9395909,0.055831935,0.000041736734,0.000031545424,0.000029914838,0.0028241132],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99051803,0.0028048004,0.0017103698,0.0012386405,0.0028081818,0.00092002656],"domain_scores_gemma":[0.9577859,0.02651404,0.0026567623,0.0007447798,0.008850315,0.0034481732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010685694,0.0013448943,0.0028606374,0.001504157,0.0046754293,0.007246009,0.0030236533,0.06222981,0.007194762],"category_scores_gemma":[0.07904882,0.0015303865,0.0025985576,0.0015663778,0.0033504567,0.0046850187,0.001892569,0.06551084,0.008649745],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003286579,0.000016266347,0.0001729104,0.00003501469,0.00001250104,0.0002923873,0.000048858114,0.000038900776,0.000048277343,0.00057898206,0.99595696,0.002766002],"study_design_scores_gemma":[0.00014794519,0.00006714146,0.0013196185,0.0005617283,0.00005572878,0.0010972152,0.00043359504,0.0009972953,0.00022755313,0.0058215866,0.98914707,0.00012358312],"about_ca_topic_score_codex":0.009824673,"about_ca_topic_score_gemma":0.016759492,"teacher_disagreement_score":0.06222981,"about_ca_system_score_codex":0.005346881,"about_ca_system_score_gemma":0.00814653,"threshold_uncertainty_score":0.056512058},"labels":[],"label_agreement":null},{"id":"W4412048689","doi":"10.1016/j.ijcard.2025.133584","title":"Predicting coronary artery disease using machine learning with optimized feature selection","year":2025,"lang":"en","type":"letter","venue":"International Journal of Cardiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill Genome Centre","funders":"Lady Davis Institute for Medical Research; Canadian Institutes of Health Research; Watanabe Foundation; TD Bank; Japan Student Services Organization; Fonds de Recherche du Québec - Santé","keywords":"Medicine; Coronary artery disease; Feature selection; Cardiology; Selection (genetic algorithm); Feature (linguistics); Internal medicine; Artificial intelligence; Disease; Machine learning","score_opus":0.06951126247498594,"score_gpt":0.42305026191478823,"score_spread":0.35353899943980227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412048689","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18413754,0.0054519325,0.06823816,0.7059112,0.014949965,0.0002150089,0.0011237268,0.0007287287,0.019243723],"genre_scores_gemma":[0.75951284,0.0038813634,0.0720743,0.11358516,0.033200566,0.00023914938,0.0010403465,0.00012390601,0.016342374],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994467,0.00022046648,0.0000714403,0.00005438987,0.000146073,0.000060873583],"domain_scores_gemma":[0.99523914,0.0036237563,0.00014521921,0.00015635863,0.0006873832,0.00014810417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013513865,0.00025670326,0.0009181529,0.0005343783,0.00029896008,0.0010093205,0.00058847445,0.0027415988,0.0015126121],"category_scores_gemma":[0.009188293,0.00020165896,0.00059866736,0.00037711914,0.000398118,0.0005822187,0.00023688604,0.0037161433,0.0011347358],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002720793,0.00093014824,0.0730379,0.00016147175,0.0003158173,0.0069649243,0.00021748779,0.008256063,0.009010248,0.0050585205,0.29224455,0.60108215],"study_design_scores_gemma":[0.0021898237,0.0029513803,0.101204686,0.00050923007,0.00072913105,0.030274337,0.0008684455,0.54718643,0.0143327145,0.07860652,0.2207931,0.00035431088],"about_ca_topic_score_codex":0.0014788334,"about_ca_topic_score_gemma":0.0044975984,"teacher_disagreement_score":0.0027415988,"about_ca_system_score_codex":0.000369897,"about_ca_system_score_gemma":0.00048511257,"threshold_uncertainty_score":0.007146895},"labels":[],"label_agreement":null},{"id":"W4412163733","doi":"10.1158/1557-3265.aimachine-a052","title":"Abstract A052: The S-RACE Platform: Empowering Healthcare Real-World Data with Artificial Intelligence (AI) Using a Cloud-Based Approach","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Race (biology); Cloud computing; Computer science; Health care; Artificial intelligence; Data science; Medicine; Biology; Operating system; Political science","score_opus":0.8049209988426096,"score_gpt":0.707454911255144,"score_spread":0.09746608758746556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163733","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06503937,0.001219878,0.47877958,0.008025793,0.0013376878,0.002398119,0.0695431,0.32638356,0.047272902],"genre_scores_gemma":[0.44154727,0.0011955851,0.4231469,0.0030643796,0.0005937523,0.0015095182,0.09232731,0.016959295,0.019656008],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975509,0.0005434086,0.0002402998,0.00057729596,0.0008450563,0.00024308254],"domain_scores_gemma":[0.99354446,0.0015840887,0.00038683877,0.002316582,0.0012781157,0.0008899311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004358428,0.0011483381,0.000757921,0.0014051748,0.0006814058,0.00451497,0.0025843065,0.00077243225,0.020827515],"category_scores_gemma":[0.009474976,0.00057770644,0.001160649,0.0017231021,0.0008987773,0.004312693,0.0041058366,0.001695863,0.009588876],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008072998,0.001084257,0.014970612,0.0013117028,0.00038692504,0.0014682726,0.0014896207,0.03744141,0.03203483,0.088950016,0.59836817,0.21442123],"study_design_scores_gemma":[0.001138606,0.0008742459,0.0095006935,0.0003996742,0.00014166662,0.00059798924,0.0005268263,0.5123794,0.035377663,0.06587073,0.37290552,0.00028700638],"about_ca_topic_score_codex":0.0066341073,"about_ca_topic_score_gemma":0.0043608705,"teacher_disagreement_score":0.020827515,"about_ca_system_score_codex":0.0010460329,"about_ca_system_score_gemma":0.0025578095,"threshold_uncertainty_score":0.06967491},"labels":[],"label_agreement":null},{"id":"W4412163857","doi":"10.1158/1557-3265.aimachine-b012","title":"Abstract B012: Prompting Large Language Models to Predict Adverse Events during Cancer Treatment","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre","funders":"","keywords":"Adverse effect; Cancer; Medicine; Intensive care medicine; Oncology; Internal medicine","score_opus":0.5986622321742983,"score_gpt":0.6997175649584702,"score_spread":0.10105533278417189,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163857","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77315384,0.0016272388,0.17498203,0.005450069,0.000610004,0.0006018365,0.015076464,0.023611153,0.004887444],"genre_scores_gemma":[0.93585134,0.00020716443,0.051991884,0.00060422486,0.00016829955,0.0002325111,0.009001084,0.00017036185,0.0017732139],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99837035,0.00096116855,0.00012614757,0.0003366461,0.000121231315,0.000084474],"domain_scores_gemma":[0.9857555,0.011750119,0.00063181453,0.00056092156,0.0009625572,0.00033901873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005265129,0.0013098969,0.0006336144,0.0010063641,0.00029225476,0.0010662691,0.0011039118,0.001022434,0.0043601976],"category_scores_gemma":[0.017168604,0.0003452532,0.0012150869,0.0004700058,0.00023706727,0.001106214,0.001000768,0.0015431291,0.0014371141],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041768216,0.0015213426,0.11705474,0.0006228626,0.0007051069,0.00045200382,0.00032649192,0.50250274,0.0038306848,0.0013661438,0.028087767,0.33935338],"study_design_scores_gemma":[0.00012281974,0.0004263897,0.004885744,0.000046083635,0.0000812482,0.000046053665,0.00005288989,0.9897432,0.0015614629,0.0017837704,0.0012209683,0.000029323282],"about_ca_topic_score_codex":0.0094769085,"about_ca_topic_score_gemma":0.008180165,"teacher_disagreement_score":0.0094769085,"about_ca_system_score_codex":0.0011024078,"about_ca_system_score_gemma":0.0015460507,"threshold_uncertainty_score":0.027845025},"labels":[],"label_agreement":null},{"id":"W4412163902","doi":"10.1158/1557-3265.aimachine-a057","title":"Abstract A057: Multimodal AI Modeling of Clinical Panel-Based Sequencing for HRD Detection in Ovarian Cancer","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Ovarian cancer; Medicine; Computational biology; DNA sequencing; Cancer; Oncology; Artificial intelligence; Bioinformatics; Computer science; Biology; Internal medicine; Genetics; Gene","score_opus":0.8227929207050889,"score_gpt":0.7389504298564317,"score_spread":0.08384249084865725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163902","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6946086,0.0008082824,0.2967218,0.0012295098,0.000062161955,0.00016805928,0.001960592,0.0015447482,0.002896153],"genre_scores_gemma":[0.9857248,0.00007082649,0.01220334,0.00011179357,0.00002017004,0.00007459248,0.00060879556,0.000025406174,0.0011602181],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99979323,0.000076736884,0.000009300552,0.00006620017,0.000021776208,0.000032693482],"domain_scores_gemma":[0.9993587,0.0004296583,0.000067053195,0.000025131285,0.00007569468,0.00004372745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097047054,0.00083006755,0.000532205,0.00066386187,0.00022009038,0.0007145011,0.0005712547,0.00073193497,0.0020413916],"category_scores_gemma":[0.00225539,0.0002709732,0.00084927847,0.00031614804,0.0003498421,0.0003087296,0.0005626163,0.00088394823,0.00034324714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012839567,0.000059837737,0.00734588,0.000024413515,0.00006077089,0.000067412504,0.00002928401,0.9686743,0.0013017965,0.0003738557,0.0004690628,0.021464866],"study_design_scores_gemma":[0.0000016281326,0.00001358702,0.00051841623,0.0000014506163,0.000003450279,0.0000061293435,0.0000029285125,0.9990397,0.0001197007,0.00024972475,0.000041250136,0.000001948012],"about_ca_topic_score_codex":0.01614747,"about_ca_topic_score_gemma":0.010770043,"teacher_disagreement_score":0.01614747,"about_ca_system_score_codex":0.0008816306,"about_ca_system_score_gemma":0.0006496215,"threshold_uncertainty_score":0.032106936},"labels":[],"label_agreement":null},{"id":"W4412370635","doi":"10.29303/jppipa.v11i6.11081","title":"Analysis of Electronic Medical Records Data Security: Case Study in Citra Husada Sigli Hospital","year":2025,"lang":"en","type":"article","venue":"Jurnal Penelitian Pendidikan IPA","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital","funders":"","keywords":"Medical record; Medical emergency; Medicine; Radiology","score_opus":0.0939730511670279,"score_gpt":0.4969199667257233,"score_spread":0.40294691555869544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412370635","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99023825,0.0007945348,0.0012492159,0.0031581076,0.00003798101,0.00015055615,0.00007387935,0.000011465734,0.004286034],"genre_scores_gemma":[0.9918686,0.0016955443,0.0014799798,0.000758839,0.00003754554,0.00006299422,0.00004941956,0.000012970516,0.004034038],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9943505,0.0031902113,0.0002794059,0.00034836106,0.000994548,0.00083702075],"domain_scores_gemma":[0.9928706,0.0038429322,0.0012272333,0.00020815597,0.0008570853,0.0009939955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033087425,0.00034678364,0.0003300945,0.0016403798,0.005858397,0.0024426465,0.0012096905,0.0021197854,0.0025911087],"category_scores_gemma":[0.00756869,0.00039300026,0.0004669346,0.0018388752,0.0023699282,0.0016857184,0.0024031275,0.0017756984,0.00034591788],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020227802,0.00132973,0.12938876,0.0013676046,0.00007246249,0.17280717,0.6239365,0.00056388625,0.0033057295,0.006922925,0.008317185,0.051785864],"study_design_scores_gemma":[0.000009566374,0.00035608042,0.038003534,0.00043483538,0.000029358962,0.038636483,0.89123076,0.0006649185,0.002079023,0.00067815604,0.02782242,0.00005486106],"about_ca_topic_score_codex":0.0055260565,"about_ca_topic_score_gemma":0.012465938,"teacher_disagreement_score":0.005858397,"about_ca_system_score_codex":0.004461627,"about_ca_system_score_gemma":0.0033161715,"threshold_uncertainty_score":0.03237158},"labels":[],"label_agreement":null},{"id":"W4412468874","doi":"10.3389/fphys.2025.1549306","title":"Prediction of obesity levels based on physical activity and eating habits with a machine learning model integrated with explainable artificial intelligence","year":2025,"lang":"en","type":"article","venue":"Frontiers in Physiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Interpretability; Machine learning; Random forest; Gradient boosting; Decision tree; Artificial intelligence; Computer science; Naive Bayes classifier; Support vector machine; Boosting (machine learning)","score_opus":0.08546961578532303,"score_gpt":0.3738796469523352,"score_spread":0.2884100311670122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412468874","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18385212,0.00025661345,0.81205344,0.00063110824,0.00004816159,0.000096762036,0.0003621372,0.00087573467,0.0018238957],"genre_scores_gemma":[0.8495427,0.00015862312,0.1482447,0.00015224292,0.00004274914,0.00015469734,0.00058270857,0.000044411903,0.0010771817],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99947315,0.00020124241,0.00002910802,0.00014637025,0.000114117596,0.000035998975],"domain_scores_gemma":[0.9979886,0.0013463744,0.00024028606,0.00011099885,0.0002708773,0.00004280334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001687202,0.00080502464,0.0005014132,0.0009565655,0.00023015862,0.001143754,0.0007351611,0.0005002119,0.0010561213],"category_scores_gemma":[0.005815709,0.00029367677,0.00096329994,0.00044251618,0.00029937507,0.000858112,0.00070008734,0.0011727521,0.00031728728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020914017,0.00034525542,0.052165948,0.00020134923,0.0003618577,0.00018437469,0.00026428187,0.7992075,0.0040290686,0.006739671,0.0012373261,0.1350542],"study_design_scores_gemma":[0.0000049852333,0.00004127265,0.0024669683,0.000014376249,0.000026316911,0.00001924821,0.00001340148,0.9943975,0.00046875412,0.0022706445,0.00026943532,0.0000072121884],"about_ca_topic_score_codex":0.0040686633,"about_ca_topic_score_gemma":0.0039788727,"teacher_disagreement_score":0.0040686633,"about_ca_system_score_codex":0.0007186486,"about_ca_system_score_gemma":0.0010149475,"threshold_uncertainty_score":0.008922875},"labels":[],"label_agreement":null},{"id":"W4412533309","doi":"10.5267/j.ijdns.2024.8.021","title":"Optimizing diabetes prediction with MLP neural networks and feature selection algorithm","year":2025,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Feature selection; Computer science; Artificial neural network; Artificial intelligence; Selection (genetic algorithm); Machine learning; Pattern recognition (psychology); Feature (linguistics)","score_opus":0.054827769215260794,"score_gpt":0.42633778672268213,"score_spread":0.37151001750742135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412533309","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.120701216,0.0007706154,0.8748193,0.00035878253,0.000097943885,0.000090701804,0.00011928338,0.00088634127,0.0021557852],"genre_scores_gemma":[0.84300953,0.00028295882,0.15474746,0.00010808342,0.0000617253,0.00017429554,0.00019863115,0.000032553326,0.0013848835],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995247,0.00014891123,0.0000431107,0.000105786,0.00011901589,0.0000584631],"domain_scores_gemma":[0.999363,0.0003495663,0.000061702034,0.000027950187,0.00018419701,0.00001364987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015982996,0.0007495746,0.0007931356,0.00097043306,0.00031919387,0.00068827474,0.0005943031,0.0006612829,0.0006390148],"category_scores_gemma":[0.0030851655,0.00037664952,0.0006170439,0.0009210185,0.00020906262,0.00066139887,0.0004410374,0.0005663003,0.00019766069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015671039,0.00010896344,0.0055408413,0.00006842561,0.000102250444,0.000091212605,0.000035766512,0.808049,0.003115367,0.0009437552,0.001025136,0.1807625],"study_design_scores_gemma":[0.000004983556,0.00002386679,0.0005657025,0.000004843666,0.0000094992865,0.000010535006,0.000004401972,0.99825066,0.0006566239,0.00033203154,0.00013336186,0.0000035127857],"about_ca_topic_score_codex":0.0047535393,"about_ca_topic_score_gemma":0.002939777,"teacher_disagreement_score":0.0047535393,"about_ca_system_score_codex":0.0005957323,"about_ca_system_score_gemma":0.0007310842,"threshold_uncertainty_score":0.009451747},"labels":[],"label_agreement":null},{"id":"W4412561906","doi":"10.1016/j.engappai.2025.111741","title":"Neural network-based analysis of clinical and demographic variables for predicting platelet counts and prothrombin time in chronic kidney disease patients","year":2025,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Prothrombin time; Artificial neural network; Kidney disease; Disease; Chronic renal failure; Artificial intelligence; Internal medicine; Medicine","score_opus":0.049963630477827564,"score_gpt":0.4150139630652954,"score_spread":0.3650503325874679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412561906","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9966162,0.0004257891,0.0018368213,0.00016151424,0.00003921309,0.000019805175,0.00034534105,0.000018954799,0.00053636014],"genre_scores_gemma":[0.99832577,0.00016602929,0.00082561775,0.000027040875,0.000018161796,0.000015580512,0.0003792114,0.000001841647,0.00024059175],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996872,0.00012618658,0.00003683786,0.000058851572,0.000050565133,0.000040451876],"domain_scores_gemma":[0.99895835,0.00059241365,0.000129033,0.000035396875,0.00019340817,0.00009131835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010161826,0.0003566145,0.0005256024,0.0008402626,0.0002235813,0.0006100371,0.00040334175,0.00056660915,0.0012163961],"category_scores_gemma":[0.0030634196,0.000113970134,0.00044183523,0.00057855254,0.0001463506,0.0003591601,0.00028225436,0.00055687415,0.00020522045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00318284,0.0008889359,0.93683565,0.00006401983,0.000449135,0.00018611361,0.00006116125,0.012111719,0.0014960498,0.00012864878,0.0007834697,0.043812267],"study_design_scores_gemma":[0.00013419669,0.0009904725,0.66919327,0.00003771351,0.0004531316,0.00030875232,0.00024256224,0.3268036,0.0009870717,0.0004158744,0.00040399868,0.000029322504],"about_ca_topic_score_codex":0.006636151,"about_ca_topic_score_gemma":0.0064750686,"teacher_disagreement_score":0.006636151,"about_ca_system_score_codex":0.0004488713,"about_ca_system_score_gemma":0.0004732174,"threshold_uncertainty_score":0.013195038},"labels":[],"label_agreement":null},{"id":"W4412611645","doi":"10.1038/s41598-025-12310-1","title":"Machine learning driven diabetes care using predictive-prescriptive analytics for personalized medication prescription","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Medical prescription; Predictive analytics; Diabetes mellitus; Analytics; Computer science; Personalized medicine; Machine learning; Data science; Medicine; Artificial intelligence; Bioinformatics; Pharmacology; Endocrinology; Biology","score_opus":0.09928478466856275,"score_gpt":0.4365445165248482,"score_spread":0.33725973185628544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412611645","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09833812,0.0031665864,0.8778995,0.0057832967,0.00016789672,0.0003374395,0.0032416026,0.004860135,0.006205388],"genre_scores_gemma":[0.8106554,0.0010784201,0.18349355,0.0006848373,0.00014875435,0.00017969863,0.0029084804,0.00009138691,0.0007594409],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981098,0.0008534268,0.00017911794,0.000330333,0.00044137173,0.00008595984],"domain_scores_gemma":[0.99117905,0.006686331,0.0006987971,0.00048369332,0.0007707469,0.00018141491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031300322,0.0010211719,0.0007993722,0.0018462491,0.0004547674,0.001731655,0.0011039118,0.0006895527,0.0012391349],"category_scores_gemma":[0.014794801,0.0003714104,0.00073544803,0.0018809688,0.00038311095,0.0015795819,0.0011014511,0.0019411386,0.0004543824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004921478,0.00072868454,0.049481492,0.00037609955,0.00024216958,0.0005407367,0.00047654947,0.6019686,0.002045358,0.014614736,0.009077382,0.319956],"study_design_scores_gemma":[0.000018146988,0.00003647822,0.0011281634,0.000046023906,0.000021550759,0.000047703277,0.000049813232,0.9829641,0.0009004657,0.013170671,0.001599093,0.000017734814],"about_ca_topic_score_codex":0.014178416,"about_ca_topic_score_gemma":0.014733631,"teacher_disagreement_score":0.014178416,"about_ca_system_score_codex":0.0011602837,"about_ca_system_score_gemma":0.0021885233,"threshold_uncertainty_score":0.028191805},"labels":[],"label_agreement":null},{"id":"W4412687694","doi":"10.1007/978-981-96-4722-4_19","title":"Optimizing Early Diabetes Detection Through Machine Learning: A Comparative Analysis of Classification Models","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Heritage College","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence","score_opus":0.314173462385227,"score_gpt":0.46707962390809354,"score_spread":0.15290616152286657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412687694","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12282902,0.034720972,0.82231885,0.0026846726,0.00038235702,0.000082363484,0.00046610498,0.0015870975,0.014928603],"genre_scores_gemma":[0.7052449,0.013325022,0.2692933,0.00050212996,0.00034894093,0.00008883421,0.00086591614,0.00042729898,0.009903556],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991559,0.000432587,0.00004612866,0.000109848865,0.00018640018,0.000069150046],"domain_scores_gemma":[0.9888509,0.009917388,0.00023841223,0.0002761153,0.00066131586,0.00005593175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028662386,0.0010117216,0.0014368464,0.0009377819,0.00026902094,0.0015937255,0.0011271386,0.000969117,0.0019907297],"category_scores_gemma":[0.008801074,0.00034899247,0.0008848816,0.0013246483,0.0003266973,0.0014756317,0.00045253793,0.001095919,0.0004061137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000400472,0.00017255527,0.003872281,0.00019830481,0.00017647925,0.00004500369,0.000050533086,0.58408093,0.0008169335,0.008477252,0.004119041,0.39759022],"study_design_scores_gemma":[0.0000072097596,0.00005205329,0.00073482655,0.000017589653,0.00004056289,0.000019797732,0.000014372079,0.99508035,0.00054629287,0.002912208,0.0005670764,0.000007627881],"about_ca_topic_score_codex":0.011473993,"about_ca_topic_score_gemma":0.008479945,"teacher_disagreement_score":0.011473993,"about_ca_system_score_codex":0.0010808953,"about_ca_system_score_gemma":0.0012490257,"threshold_uncertainty_score":0.022814393},"labels":[],"label_agreement":null},{"id":"W4412718452","doi":"10.1007/978-3-031-98565-2_68","title":"A Novel Intelligent Decision Support System for Acute Coronary Syndrome Classification Using Reinforcement Learning-Enhanced Random Forests","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"North York General Hospital; University of Toronto","funders":"","keywords":"Random forest; Reinforcement learning; Computer science; Acute coronary syndrome; Artificial intelligence; Decision support system; Medicine; Internal medicine","score_opus":0.098684989589488,"score_gpt":0.403858966238248,"score_spread":0.30517397664876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412718452","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0602878,0.0008129664,0.92918587,0.00030930352,0.0002625325,0.0001646205,0.00034194047,0.0064754197,0.0021596395],"genre_scores_gemma":[0.6405535,0.00033038884,0.3545769,0.00030931257,0.0001520549,0.00020249476,0.00064614543,0.00009129199,0.0031380234],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99976844,0.000040999428,0.000019285919,0.000067054076,0.00006172112,0.0000424161],"domain_scores_gemma":[0.9997203,0.00012113906,0.000021624628,0.000018239307,0.00009527367,0.000023486096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066658575,0.0005303364,0.0009185738,0.00054509426,0.0003615587,0.0004970429,0.00089425215,0.00065618486,0.0020862422],"category_scores_gemma":[0.0008080462,0.00024142906,0.0005840921,0.00034149212,0.00010875495,0.00047523604,0.00041643894,0.00050400366,0.0006785173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004627927,0.0005549991,0.0034990693,0.000108442786,0.0001794205,0.00034408696,0.00004786703,0.11386925,0.01623607,0.00093512866,0.0076013096,0.8561614],"study_design_scores_gemma":[0.000037641334,0.0000883283,0.00096751197,0.000008150515,0.00004483472,0.00008636887,0.000006840264,0.99497616,0.0024622711,0.00049330475,0.0008161954,0.000012368625],"about_ca_topic_score_codex":0.0064734886,"about_ca_topic_score_gemma":0.009531818,"teacher_disagreement_score":0.0064734886,"about_ca_system_score_codex":0.0002685302,"about_ca_system_score_gemma":0.0006047794,"threshold_uncertainty_score":0.012871623},"labels":[],"label_agreement":null},{"id":"W4412798192","doi":"10.2196/70621","title":"Optimizing Feature Selection and Machine Learning Algorithms for Early Detection of Prediabetes Risk: Comparative Study","year":2025,"lang":"en","type":"article","venue":"JMIR Bioinformatics and Biotechnology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Prediabetes; Feature selection; Computer science; Selection (genetic algorithm); Artificial intelligence; Machine learning; Feature (linguistics); Pattern recognition (psychology); Medicine; Diabetes mellitus","score_opus":0.06289600529600652,"score_gpt":0.4114418252403894,"score_spread":0.3485458199443829,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412798192","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91207576,0.015310846,0.06974792,0.00043328461,0.00011169102,0.00014650625,0.00038830918,0.00033311802,0.0014526129],"genre_scores_gemma":[0.96772915,0.0018472646,0.02911399,0.00007827929,0.0000713677,0.00009285946,0.000623384,0.000038518898,0.0004051278],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9978816,0.0013912249,0.00011824734,0.00024720517,0.0002450782,0.0001166399],"domain_scores_gemma":[0.993016,0.0056948233,0.00029517163,0.0002497999,0.0006504254,0.000093714814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064374832,0.0008836195,0.0011345705,0.0016265226,0.00020865277,0.00068625517,0.0004441807,0.00057669333,0.00066611415],"category_scores_gemma":[0.009805528,0.00015060115,0.0011422542,0.0013926399,0.0002587045,0.0005743609,0.0003713327,0.0004781172,0.00016052378],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0057469252,0.0015479326,0.12876432,0.0007328643,0.0015827228,0.00024418597,0.00013582794,0.22695108,0.0026243438,0.0011050798,0.0037128283,0.62685186],"study_design_scores_gemma":[0.0002452488,0.0032196394,0.07521966,0.000112976006,0.0006403335,0.0003221144,0.00013038104,0.91324276,0.003415335,0.0014037723,0.0020017629,0.000045944504],"about_ca_topic_score_codex":0.0024799472,"about_ca_topic_score_gemma":0.0010790023,"teacher_disagreement_score":0.0064374832,"about_ca_system_score_codex":0.0005209871,"about_ca_system_score_gemma":0.0005691886,"threshold_uncertainty_score":0.03404504},"labels":[],"label_agreement":null},{"id":"W4413001992","doi":"10.19139/soic-2310-5070-2319","title":"Improving Heart Disease Prediction Accuracy through Machine Learning Algorithms","year":2025,"lang":"en","type":"article","venue":"Statistics Optimization & Information Computing","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Machine learning; Computer science; Artificial intelligence; Algorithm","score_opus":0.04746319776124497,"score_gpt":0.4133984807299549,"score_spread":0.3659352829687099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413001992","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22637069,0.00785447,0.7498149,0.0029921837,0.00038169304,0.00017623261,0.0007370592,0.0040236483,0.0076490664],"genre_scores_gemma":[0.81258756,0.0015572588,0.182034,0.00046594997,0.00028072,0.000094968025,0.0009377139,0.00007517807,0.0019666436],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911267,0.0003737552,0.00007222712,0.0001599421,0.00020892992,0.000072508905],"domain_scores_gemma":[0.9966947,0.002215842,0.0002858944,0.00020828916,0.0005313451,0.000063989566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030963891,0.0010147638,0.00094813114,0.0015910987,0.00028668155,0.0012205307,0.00086730556,0.0008674894,0.0012488537],"category_scores_gemma":[0.008686421,0.00025019582,0.00049820787,0.0010493321,0.00022644494,0.0011572123,0.00066710054,0.0010651179,0.0008975442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030935518,0.00042586957,0.034158643,0.00015313902,0.00021821226,0.00008390517,0.00005567918,0.3486986,0.0022967204,0.0025194176,0.005504084,0.6055764],"study_design_scores_gemma":[0.0000160032,0.000080802856,0.002707352,0.000038834318,0.000027199912,0.000038894177,0.000014777326,0.9926448,0.0012403799,0.0024357513,0.0007449093,0.000010414275],"about_ca_topic_score_codex":0.004052157,"about_ca_topic_score_gemma":0.0036492415,"teacher_disagreement_score":0.004052157,"about_ca_system_score_codex":0.00051294145,"about_ca_system_score_gemma":0.0010949993,"threshold_uncertainty_score":0.016375482},"labels":[],"label_agreement":null},{"id":"W4413050087","doi":"10.3233/shti251211","title":"Clinical Decision Support for Alzheimer’s: Challenges in Generalizable Data-Driven Approach","year":2025,"lang":"en","type":"review","venue":"Studies in health technology and informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Decision support system; Clinical decision support system; Data science; Artificial intelligence; Machine learning","score_opus":0.7621688915304731,"score_gpt":0.6564293893012447,"score_spread":0.10573950222922834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413050087","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010887029,0.9404134,0.030797483,0.023636801,0.0007151882,0.0001338487,0.0006585488,0.00013153075,0.0024244743],"genre_scores_gemma":[0.032215156,0.9078089,0.045640334,0.009541827,0.0025564122,0.00031128927,0.001238695,0.000048999376,0.00063846953],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9936401,0.00336142,0.0007864002,0.0006136547,0.0014694481,0.00012892547],"domain_scores_gemma":[0.95094144,0.04403788,0.0011265863,0.00088995637,0.0026641246,0.0003400277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016246527,0.0010115616,0.0037068003,0.0024555554,0.00034263296,0.003660302,0.0033018072,0.002789166,0.0025113656],"category_scores_gemma":[0.041770864,0.00060795073,0.002116089,0.0027396362,0.0011134556,0.004421561,0.0018967657,0.0052111945,0.0013697911],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010638376,0.00008952373,0.0009133463,0.019071795,0.0007471565,0.00013698523,0.00018376803,0.0067457682,0.00023574017,0.017419936,0.018536394,0.9358132],"study_design_scores_gemma":[0.00025921635,0.0003867355,0.0035548378,0.05067318,0.0015244803,0.001503543,0.00086686254,0.028287375,0.0009909241,0.32198516,0.58978426,0.00018331197],"about_ca_topic_score_codex":0.00267986,"about_ca_topic_score_gemma":0.0031075133,"teacher_disagreement_score":0.016246527,"about_ca_system_score_codex":0.0015966318,"about_ca_system_score_gemma":0.0042488575,"threshold_uncertainty_score":0.08592087},"labels":[],"label_agreement":null},{"id":"W4413157595","doi":"10.1109/icoeca66273.2025.00121","title":"Early Detection of Lung Cancer using DenseNet with AI Support","year":2025,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Lung cancer; Artificial intelligence; Medicine","score_opus":0.11139891972119483,"score_gpt":0.5249210809303554,"score_spread":0.4135221612091606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413157595","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24483503,0.001878473,0.72215694,0.0043221964,0.0005434533,0.00046235532,0.0018276632,0.0050363517,0.01893766],"genre_scores_gemma":[0.8990353,0.0003939254,0.09224168,0.0005183941,0.00011764776,0.00013056307,0.0012848844,0.00006583142,0.006211808],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996935,0.00006918284,0.000019656576,0.00007738111,0.000082258804,0.00005808553],"domain_scores_gemma":[0.99919444,0.0004116923,0.00005492862,0.00006114006,0.0002256715,0.00005207853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008242127,0.00073205144,0.00053969614,0.000917947,0.00033128494,0.0010737978,0.001176997,0.0009220497,0.0030780549],"category_scores_gemma":[0.0027986304,0.00027036495,0.0004997756,0.00045139174,0.0003329853,0.001254426,0.00090185355,0.0007804705,0.0008248],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080857,0.00063338416,0.028375516,0.00043413203,0.00023538069,0.0007688502,0.00033889938,0.43421343,0.009969764,0.0069052977,0.012601497,0.5047153],"study_design_scores_gemma":[0.000011414478,0.00010101289,0.0018624476,0.000033710177,0.000029866016,0.00010694239,0.00006774626,0.98752403,0.00287692,0.005036083,0.0023364727,0.000013406271],"about_ca_topic_score_codex":0.012238888,"about_ca_topic_score_gemma":0.01653302,"teacher_disagreement_score":0.012238888,"about_ca_system_score_codex":0.00088159944,"about_ca_system_score_gemma":0.0010369212,"threshold_uncertainty_score":0.024335325},"labels":[],"label_agreement":null},{"id":"W4413228161","doi":"10.18280/isi.300605","title":"A Novel Hybrid Model Combining Feature Selection and Imbalance Handling for Prediction of Heart Failure Survival","year":2025,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Feature selection; Selection (genetic algorithm); Heart failure; Feature (linguistics); Artificial intelligence; Computer science; Machine learning; Pattern recognition (psychology); Internal medicine; Medicine","score_opus":0.05375026234234497,"score_gpt":0.3600202821796844,"score_spread":0.3062700198373394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413228161","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25487807,0.0024148533,0.73416656,0.0015773635,0.00062491035,0.00016754716,0.001451956,0.0023314245,0.002387318],"genre_scores_gemma":[0.93186295,0.00053902826,0.060890574,0.0003613031,0.00040361396,0.00021121828,0.0015230824,0.00006517523,0.004143054],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99957937,0.000093690935,0.000034848155,0.00012752919,0.00009436391,0.00007020159],"domain_scores_gemma":[0.9993569,0.00031009584,0.00004556034,0.00003298739,0.00021112544,0.000043362597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013877413,0.00078154815,0.0012981262,0.001171683,0.00041719584,0.0009696162,0.0015195698,0.00091050315,0.0013856924],"category_scores_gemma":[0.001496548,0.00030222794,0.0009918946,0.0009297096,0.00018317958,0.0008929031,0.00069425517,0.0007524191,0.00053674786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013340083,0.0011101734,0.033941716,0.00016200636,0.0010856063,0.00038649485,0.000104447856,0.45340747,0.008962764,0.0012864538,0.010436552,0.4877823],"study_design_scores_gemma":[0.000021489328,0.00009178381,0.0019425212,0.0000059679282,0.00007756004,0.000039199087,0.0000066863827,0.9968201,0.0003434175,0.00036069268,0.00028031794,0.000010136241],"about_ca_topic_score_codex":0.007710853,"about_ca_topic_score_gemma":0.007072932,"teacher_disagreement_score":0.007710853,"about_ca_system_score_codex":0.0003900169,"about_ca_system_score_gemma":0.0008927943,"threshold_uncertainty_score":0.015331924},"labels":[],"label_agreement":null},{"id":"W4413420910","doi":"10.1038/s41598-025-16376-9","title":"Machine learning enhanced expert system for detecting heart failure decompensation using patient reported vitals and electronic health records","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto; Public Health Ontario; Ted Rogers Centre for Heart Research; University Health Network","funders":"University Health Network","keywords":"Decompensation; Health records; Computer science; Electronic health record; Heart failure; Artificial intelligence; Medicine; Machine learning; Medical emergency; Internal medicine; Health care","score_opus":0.07177287947946756,"score_gpt":0.43427541605629955,"score_spread":0.36250253657683196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413420910","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6056393,0.00091214525,0.3750643,0.0005970624,0.0001885241,0.0009046098,0.0032059797,0.009303882,0.004184242],"genre_scores_gemma":[0.7720875,0.00018587893,0.22297972,0.0002963584,0.00006203074,0.00023757142,0.0022899832,0.0000409188,0.0018200101],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989912,0.0002855212,0.00012811477,0.00031001843,0.00022372144,0.00006133604],"domain_scores_gemma":[0.99776185,0.001311688,0.00018347654,0.00013750345,0.0005311486,0.00007417706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017583652,0.0005312139,0.0006347374,0.0014096106,0.00023601831,0.00050592126,0.0006234926,0.0006924741,0.0014368539],"category_scores_gemma":[0.005356128,0.00020718537,0.00040401347,0.0005708761,0.00010567052,0.00065176276,0.00038464504,0.0005003301,0.000546447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002007734,0.0022126366,0.0811915,0.00035879476,0.00036443974,0.00085337315,0.00016202977,0.09967329,0.0156183345,0.0008553083,0.008888165,0.78781444],"study_design_scores_gemma":[0.00010206921,0.00046061006,0.014689097,0.000035898443,0.000094249976,0.00031815015,0.00003981243,0.97482306,0.007072873,0.00061199197,0.0017238124,0.000028384036],"about_ca_topic_score_codex":0.004189646,"about_ca_topic_score_gemma":0.0046840115,"teacher_disagreement_score":0.004189646,"about_ca_system_score_codex":0.00045410986,"about_ca_system_score_gemma":0.00062241824,"threshold_uncertainty_score":0.009299219},"labels":[],"label_agreement":null},{"id":"W4413438807","doi":"10.62051/nzr6tw29","title":"Diabetes Risk Prediction Model Using Machine Learning","year":2025,"lang":"en","type":"article","venue":"Transactions on Computer Science and Intelligent Systems Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Diabetes mellitus; Computer science; Machine learning; Artificial intelligence; Medicine","score_opus":0.2681865827769257,"score_gpt":0.5068459250151395,"score_spread":0.23865934223821378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413438807","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27704215,0.0029401977,0.7061652,0.0017984356,0.00036858045,0.0003970141,0.0032281913,0.0032613778,0.004798825],"genre_scores_gemma":[0.8837811,0.0008251696,0.10997464,0.0002064847,0.00014366812,0.0003021875,0.002753215,0.00004657944,0.0019669004],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992995,0.00026635634,0.00006054413,0.00014968649,0.00014452595,0.00007935738],"domain_scores_gemma":[0.99872655,0.000786222,0.00011005967,0.000052353946,0.0002907506,0.00003407705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024760056,0.00067699066,0.0008336953,0.0014368704,0.000272321,0.0009703674,0.00093968597,0.00056178926,0.0012340083],"category_scores_gemma":[0.0045542195,0.00020602685,0.0010191842,0.0009784503,0.00012685274,0.00056482974,0.00041149333,0.0009355507,0.00081994646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052233465,0.0005305212,0.05411518,0.00018491784,0.0003526505,0.00033172427,0.00007492619,0.6569273,0.0015291104,0.002388335,0.007731147,0.27531186],"study_design_scores_gemma":[0.0000121767325,0.000050662027,0.0018099142,0.000019519626,0.00003325391,0.00004852556,0.000011062844,0.995906,0.00031391304,0.0012247474,0.0005605294,0.000009657847],"about_ca_topic_score_codex":0.008123072,"about_ca_topic_score_gemma":0.0041838787,"teacher_disagreement_score":0.008123072,"about_ca_system_score_codex":0.0005416449,"about_ca_system_score_gemma":0.0010763167,"threshold_uncertainty_score":0.016151547},"labels":[],"label_agreement":null},{"id":"W4413463968","doi":"10.23977/jaip.2025.080309","title":"Investigation and Analyses of AI Application among Freshmen","year":2025,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Practice","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Mathematics education","score_opus":0.24444194933653357,"score_gpt":0.5576605167410802,"score_spread":0.3132185674045466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413463968","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9986564,0.000105663865,0.000105198626,0.00017142156,0.000004207961,0.000009636529,0.00003838643,0.0000020291454,0.0009071444],"genre_scores_gemma":[0.99701476,0.0002121189,0.00012424341,0.000098722565,0.000011127376,0.000014278516,0.000055451903,0.0000018060367,0.0024674323],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992938,0.00014272127,0.00005631151,0.00011674282,0.00022461497,0.00016567961],"domain_scores_gemma":[0.99717283,0.0006665351,0.00084204,0.00011203155,0.00069349445,0.0005130066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009809822,0.000113889844,0.00014780056,0.0012552884,0.0010621845,0.0007981848,0.0003063342,0.00029722787,0.0041811876],"category_scores_gemma":[0.0039646723,0.00013585408,0.00019022913,0.0008248837,0.0005135488,0.0006663409,0.0006065091,0.00049632683,0.00048618147],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058519756,0.00024927538,0.9271582,0.00008552269,0.000016763408,0.00030946056,0.027480599,0.000031468582,0.0016165959,0.00044124798,0.00071675214,0.04183554],"study_design_scores_gemma":[0.0000016099702,0.0002087046,0.94447744,0.00003633119,0.000015812848,0.00018843295,0.049127273,0.00013430629,0.0006794505,0.000108289285,0.005012246,0.000010227648],"about_ca_topic_score_codex":0.0056580785,"about_ca_topic_score_gemma":0.010041129,"teacher_disagreement_score":0.0056580785,"about_ca_system_score_codex":0.0007469438,"about_ca_system_score_gemma":0.0010261231,"threshold_uncertainty_score":0.013987422},"labels":[],"label_agreement":null},{"id":"W4413612324","doi":"10.3389/fendo.2025.1601883","title":"Enhanced diabetes prediction using skip-gated recurrent unit with gradient clipping approach","year":2025,"lang":"en","type":"article","venue":"Frontiers in Endocrinology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Princess Nourah Bint Abdulrahman University","keywords":"Diabetes mellitus; Clipping (morphology); Computer science; Unit (ring theory); Internal medicine; Medicine; Computational biology; Cardiology; Biology; Endocrinology; Mathematics","score_opus":0.08430059586835525,"score_gpt":0.40502945049481487,"score_spread":0.3207288546264596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413612324","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20447412,0.0028535696,0.7803872,0.00079454546,0.00040844656,0.00010926537,0.0010106894,0.0042251972,0.0057368907],"genre_scores_gemma":[0.9239726,0.00062126265,0.06825803,0.00044624455,0.00014863649,0.00006536412,0.0015849253,0.00007285012,0.0048299846],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998223,0.00003165914,0.00001112647,0.000045506025,0.00004218239,0.000047295816],"domain_scores_gemma":[0.99973494,0.00010165771,0.000021643555,0.000019917541,0.00009599751,0.000025864498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037977681,0.0008055361,0.0007645706,0.00051122817,0.00023684789,0.0004677432,0.000871945,0.0005621202,0.0016597923],"category_scores_gemma":[0.0010665597,0.00021713556,0.00053680263,0.0003906871,0.0001424047,0.00057810993,0.000449828,0.00089303876,0.00048827165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006181714,0.00045845442,0.0095224995,0.00013181752,0.00018552731,0.00067735306,0.00008874641,0.40952513,0.013162879,0.0026022303,0.011667944,0.55135924],"study_design_scores_gemma":[0.0000050948443,0.000029162307,0.00043947707,0.000003407857,0.000012090963,0.000022619157,0.0000046873774,0.99781775,0.0011160036,0.00033870628,0.00020580106,0.000005148597],"about_ca_topic_score_codex":0.012504946,"about_ca_topic_score_gemma":0.012490463,"teacher_disagreement_score":0.012504946,"about_ca_system_score_codex":0.0003903461,"about_ca_system_score_gemma":0.0006664628,"threshold_uncertainty_score":0.024864316},"labels":[],"label_agreement":null},{"id":"W4413679396","doi":"10.1109/compsac65507.2025.00108","title":"Automatic Diagnosis of Hip and Knee Osteoarthritis from Medical Text Records","year":2025,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Mitacs","keywords":"Osteoarthritis; Medical record; Computer science; Medicine; Artificial intelligence; Radiology; Pathology; Alternative medicine","score_opus":0.07305607767701847,"score_gpt":0.4476300787130124,"score_spread":0.3745740010359939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413679396","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65188485,0.021633746,0.23309357,0.0039051755,0.0015874434,0.0022813426,0.06236596,0.015760545,0.007487343],"genre_scores_gemma":[0.6772617,0.0029940205,0.23298655,0.00067991845,0.0009395993,0.00042299353,0.07978823,0.0001749402,0.0047520585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983607,0.00030953396,0.00034765713,0.00042459546,0.00039337683,0.00016413626],"domain_scores_gemma":[0.99469393,0.0028682556,0.00061578414,0.00024842776,0.0013863615,0.00018716791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015015869,0.001133732,0.0008683164,0.0058411043,0.00060611527,0.0010927452,0.0010618273,0.0014251454,0.0016335191],"category_scores_gemma":[0.0071791755,0.00022723546,0.0012730095,0.0018568283,0.0002893412,0.0011577003,0.0006085531,0.00077457714,0.0026208314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017409842,0.0010546277,0.064404964,0.0038457445,0.00036191172,0.004286772,0.0004979604,0.011940263,0.08706042,0.00095687085,0.04069904,0.78315055],"study_design_scores_gemma":[0.0005077828,0.0012876262,0.12259522,0.0012364666,0.0013712632,0.007908226,0.0018295188,0.68803763,0.1186571,0.0055564824,0.050768316,0.0002443316],"about_ca_topic_score_codex":0.009101682,"about_ca_topic_score_gemma":0.011147435,"teacher_disagreement_score":0.009101682,"about_ca_system_score_codex":0.0004768126,"about_ca_system_score_gemma":0.0016527765,"threshold_uncertainty_score":0.0180974},"labels":[],"label_agreement":null},{"id":"W4413745661","doi":"10.21203/rs.3.rs-6459111/v1","title":"A Sequence-Based Neural Network Model for Obesity Prediction among Adults Aged 18-64 Based on Physical Fitness Variables","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Aging","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Artificial neural network; Sequence (biology); Obesity; Gerontology; Physical fitness; Computer science; Psychology; Artificial intelligence; Medicine; Physical therapy; Biology; Internal medicine; Genetics","score_opus":0.34339943643497256,"score_gpt":0.5444738328520926,"score_spread":0.20107439641712005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413745661","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.932674,0.00080123846,0.06085706,0.0010228463,0.0003167423,0.00007708562,0.0016960349,0.0002523335,0.002302638],"genre_scores_gemma":[0.990101,0.00021398948,0.005997504,0.00007098437,0.000047297068,0.00006574142,0.00092075893,0.0000073374513,0.0025752704],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998572,0.000030841657,0.000010516067,0.00005936976,0.00001572773,0.000026402015],"domain_scores_gemma":[0.99936837,0.00037058775,0.00004747408,0.00002086957,0.00015531333,0.000037369988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008948628,0.00062226463,0.0005745383,0.0007009656,0.00031600668,0.0005308419,0.00084306713,0.00090231595,0.0027808482],"category_scores_gemma":[0.0022832397,0.00032014074,0.00061030954,0.00058423687,0.0001874316,0.0005429708,0.00036044882,0.0010906471,0.0005433003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012068594,0.0011391513,0.07042899,0.00009673601,0.0003876717,0.00025987043,0.000102265425,0.84119016,0.001332553,0.0010838612,0.0023486451,0.080423206],"study_design_scores_gemma":[0.00001387286,0.00005276309,0.0045438064,0.0000071734976,0.000028677741,0.000013842254,0.000008818631,0.99490464,0.00006858162,0.00029861013,0.000054957414,0.000004338164],"about_ca_topic_score_codex":0.030695904,"about_ca_topic_score_gemma":0.023884209,"teacher_disagreement_score":0.030695904,"about_ca_system_score_codex":0.00068382686,"about_ca_system_score_gemma":0.0007320567,"threshold_uncertainty_score":0.0610345},"labels":[],"label_agreement":null},{"id":"W4413775356","doi":"10.23889/ijpds.v10i4.3114","title":"Developing a Health Data Analytic Service to Serve the Private Sector for Public Benefit","year":2025,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University Health Network; University of British Columbia; University of New Brunswick","funders":"","keywords":"Private sector; Public sector; Business; Service (business); Public relations; Marketing; Economics; Economic growth; Political science","score_opus":0.588304350646068,"score_gpt":0.6075084979088123,"score_spread":0.01920414726274433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413775356","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08061509,0.0019642971,0.34413052,0.31758845,0.002826211,0.04020163,0.016472453,0.020965466,0.17523591],"genre_scores_gemma":[0.19448209,0.0016304638,0.70882165,0.027191393,0.000569133,0.0094188815,0.008121507,0.002280276,0.04748461],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9353796,0.026893096,0.0041947374,0.0033417442,0.01990391,0.010286908],"domain_scores_gemma":[0.7571552,0.028640633,0.0083728945,0.021437729,0.123967156,0.0604264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09368853,0.00083605485,0.00071613,0.0059227897,0.0131834345,0.01040913,0.006029277,0.0029185573,0.019538937],"category_scores_gemma":[0.105629325,0.0012757769,0.0011316976,0.008401327,0.0041228933,0.0065726726,0.014506279,0.0041231383,0.0075265607],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003160535,0.00058640895,0.045522213,0.001007204,0.0000772583,0.00086924294,0.045404084,0.0012675026,0.005691099,0.02067573,0.43052995,0.4480533],"study_design_scores_gemma":[0.00018479812,0.00020204447,0.025909837,0.0012200526,0.00004696046,0.0002915509,0.065076195,0.0065139607,0.0022959565,0.008504626,0.88952124,0.00023280692],"about_ca_topic_score_codex":0.7766889,"about_ca_topic_score_gemma":0.808958,"teacher_disagreement_score":0.7766889,"about_ca_system_score_codex":0.052475046,"about_ca_system_score_gemma":0.4068411,"threshold_uncertainty_score":0.4954782},"labels":[],"label_agreement":null},{"id":"W4413848866","doi":"10.1016/j.knosys.2025.114383","title":"Prostate cancer forecasting in small samples based on lightweight neural networks using ensemble learning","year":2025,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nipissing University","funders":"National Natural Science Foundation of China","keywords":"Artificial neural network; Ensemble learning; Prostate cancer; Computer science; Artificial intelligence; Machine learning; Ensemble forecasting; Cancer; Medicine; Internal medicine","score_opus":0.2263426364595368,"score_gpt":0.43593707657967234,"score_spread":0.20959444012013553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413848866","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2828687,0.0010175194,0.71077716,0.0007243077,0.00015849335,0.00005764683,0.00039232965,0.0016218269,0.00238202],"genre_scores_gemma":[0.9516272,0.00028548716,0.045997735,0.00015768579,0.00009495817,0.000043688906,0.00061295694,0.000043721997,0.0011366031],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996829,0.000083669955,0.000021337293,0.00009311467,0.000070788876,0.00004816791],"domain_scores_gemma":[0.9984836,0.0008459489,0.00013813359,0.00019189308,0.00028131963,0.000059126764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013127126,0.00079051504,0.0009452997,0.0005598,0.00033048654,0.0006228431,0.0010062284,0.00055566314,0.00070682005],"category_scores_gemma":[0.004714255,0.00032160024,0.00057504594,0.00057546346,0.00028905284,0.0012207441,0.0007551829,0.0012021438,0.00024053942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010392899,0.00006810358,0.0040740115,0.00002701237,0.00008230403,0.000085075764,0.00003715384,0.91376716,0.001634593,0.0011420884,0.0009487072,0.078029834],"study_design_scores_gemma":[0.0000011053124,0.000006110496,0.00018236665,0.0000013664389,0.0000032735431,0.000002607657,0.000002174627,0.9991203,0.00013499388,0.0004971422,0.000047072826,0.0000015123138],"about_ca_topic_score_codex":0.012671611,"about_ca_topic_score_gemma":0.019210022,"teacher_disagreement_score":0.012671611,"about_ca_system_score_codex":0.00065095985,"about_ca_system_score_gemma":0.0007365177,"threshold_uncertainty_score":0.025195718},"labels":[],"label_agreement":null},{"id":"W4413905035","doi":"10.18103/mra.v13i3.6465","title":"A study to assess the relationship between cognitive impairment and glycemic management in patients with type 2 diabetes using MoCA score","year":2025,"lang":"en","type":"article","venue":"Medical Research Archives","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Glycemic; Medicine; Type 2 diabetes; Montreal Cognitive Assessment; Diabetes mellitus; Cognitive impairment; Cognition; Internal medicine; Gerontology; Endocrinology; Psychiatry","score_opus":0.4165982506234531,"score_gpt":0.5834332512084603,"score_spread":0.16683500058500722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413905035","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9988223,0.00018271992,0.00006571177,0.000036949157,0.000011005997,0.000050006274,0.00034662097,0.0000020106936,0.00048267626],"genre_scores_gemma":[0.99877554,0.000098585224,0.00022242239,0.00006533539,0.00001920335,0.00006900971,0.00043896187,0.0000011318514,0.00030977657],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9995956,0.00010941646,0.000060637543,0.000077390214,0.00009702354,0.000059975577],"domain_scores_gemma":[0.9986517,0.00024053194,0.00048269,0.000051349336,0.00027381416,0.00029993348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081243285,0.00029575458,0.00041177135,0.0011611069,0.0007109237,0.00067267526,0.0002505441,0.00048605455,0.001578434],"category_scores_gemma":[0.002506437,0.00021736465,0.0006116273,0.001476151,0.00016338057,0.0006233622,0.0003196013,0.0006284479,0.0003353153],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014358136,0.00012282851,0.9987337,0.000010848176,0.000038548915,0.000030212323,0.000051719813,0.000007998304,0.000044978766,0.0000059938125,0.00006333478,0.0007462961],"study_design_scores_gemma":[0.00003516791,0.00076948496,0.998326,0.000008556304,0.00004978339,0.00018448978,0.0002802131,0.000103136954,0.00003529582,0.0000136063745,0.00018895094,0.000005214899],"about_ca_topic_score_codex":0.0056392234,"about_ca_topic_score_gemma":0.005731379,"teacher_disagreement_score":0.0056392234,"about_ca_system_score_codex":0.00035952425,"about_ca_system_score_gemma":0.0005943935,"threshold_uncertainty_score":0.011212826},"labels":[],"label_agreement":null},{"id":"W4413977425","doi":"10.2196/82230","title":"Machine Learning-Augmented Traditional Analysis: Lactate versus Lactate-to-Albumin Ratio in Predicting Mortality Risk among Septic Patients — A Large-scale Retrospective Study (Preprint)","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprint; Scale (ratio); Albumin; Retrospective cohort study; Medicine; Internal medicine; Computer science; Geography; World Wide Web; Cartography","score_opus":0.053337162166265335,"score_gpt":0.42398107251305356,"score_spread":0.37064391034678823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413977425","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99616724,0.0006010794,0.0017792087,0.00013383586,0.000043528325,0.000029452764,0.0010050086,0.000024072919,0.0002165247],"genre_scores_gemma":[0.99660206,0.0002545985,0.0014941067,0.000058545535,0.000099286415,0.00004309551,0.0012387696,0.000011760025,0.00019767883],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99891925,0.0005995458,0.00010874604,0.00020617743,0.00011228343,0.00005405982],"domain_scores_gemma":[0.9960901,0.0018905414,0.00069024775,0.0006642642,0.00044217517,0.00022261398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034551963,0.00034219248,0.00046662765,0.000566024,0.00017105749,0.0006182966,0.00039917487,0.0003566854,0.0014125071],"category_scores_gemma":[0.008118824,0.00015927492,0.00091639976,0.00075354305,0.00027177786,0.000495492,0.0004208359,0.0005208503,0.00037720936],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036148827,0.0001766864,0.98065656,0.00009573832,0.0004995638,0.00020308455,0.000082946164,0.00090815243,0.0006456254,0.00013119754,0.0014596556,0.011525846],"study_design_scores_gemma":[0.00022632936,0.0024490578,0.977358,0.00005659815,0.00069242844,0.00062311254,0.00035579587,0.015355386,0.0011230293,0.0004537849,0.0012597457,0.00004673725],"about_ca_topic_score_codex":0.0010090653,"about_ca_topic_score_gemma":0.0006908841,"teacher_disagreement_score":0.0034551963,"about_ca_system_score_codex":0.00016772165,"about_ca_system_score_gemma":0.0003110313,"threshold_uncertainty_score":0.018272996},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4414162834","doi":"10.2196/64979","title":"Interpretable Machine Learning Model for Predicting and Assessing the Risk of Diabetic Nephropathy: Prediction Model Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Interpretability; Missing data; Predictive power; Receiver operating characteristic; Diabetic nephropathy; Medical record; Support vector machine; Diabetes mellitus; Nephropathy","score_opus":0.06761221979112114,"score_gpt":0.4571152846750505,"score_spread":0.3895030648839294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414162834","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7082268,0.0029910516,0.28010756,0.0024844443,0.0002370513,0.00047500926,0.0016714229,0.00055988034,0.003246799],"genre_scores_gemma":[0.97029054,0.00058771495,0.026489835,0.00016037251,0.000085552725,0.00023553839,0.0009492782,0.000020503538,0.001180632],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884075,0.0006062086,0.00006069053,0.00021478282,0.00014588771,0.0001316929],"domain_scores_gemma":[0.9932481,0.0052292687,0.00039882067,0.00022287674,0.00073961896,0.0001612565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005411243,0.001207418,0.001063054,0.0014047995,0.00038282163,0.0010256192,0.0012065185,0.0011944006,0.0018207107],"category_scores_gemma":[0.010412028,0.00027103597,0.0012316956,0.0008402346,0.00034876,0.00072439865,0.0008596248,0.0019268281,0.00030246947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005938452,0.0008131397,0.08041755,0.00017199392,0.0006033706,0.00041561422,0.00013629188,0.85560995,0.00045260458,0.0030882782,0.003185712,0.05451162],"study_design_scores_gemma":[0.0000136528815,0.000068651105,0.0020735802,0.0000157153,0.00003276109,0.00002884747,0.000012347073,0.99672395,0.00007875859,0.0007944124,0.00015118222,0.0000062256036],"about_ca_topic_score_codex":0.014575564,"about_ca_topic_score_gemma":0.0052911476,"teacher_disagreement_score":0.014575564,"about_ca_system_score_codex":0.0009353863,"about_ca_system_score_gemma":0.0013310685,"threshold_uncertainty_score":0.028981447},"labels":[],"label_agreement":null},{"id":"W4414188134","doi":"10.18280/isi.300714","title":"Lung Mass Identification Using Tiny Deep Learning Based on Lightweight MobileNet and Raspberry Pi 5 for Low Source Medical Diagnostic","year":2025,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Deep learning; Convolutional neural network; Raspberry pi; Software deployment; Identification (biology); Deep neural networks","score_opus":0.03075285663789026,"score_gpt":0.3720024701879773,"score_spread":0.34124961355008704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414188134","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41118786,0.0014449296,0.5526464,0.0007614216,0.00030598,0.0002511607,0.0009985506,0.02256349,0.009840253],"genre_scores_gemma":[0.89835304,0.00031248515,0.09416141,0.00044279918,0.000024539535,0.00011862942,0.001020236,0.0001633935,0.0054034707],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99981946,0.000020338399,0.0000074455843,0.000050520146,0.0000673036,0.00003499021],"domain_scores_gemma":[0.99980086,0.000060108727,0.000028724731,0.00004134803,0.00004802983,0.000020981659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026165467,0.00066124165,0.0002747518,0.00044062603,0.00013538155,0.00033213687,0.0010286494,0.00048849394,0.0025479416],"category_scores_gemma":[0.0008861493,0.00023339738,0.00021830866,0.00023644423,0.00023495742,0.0007178259,0.00065170316,0.0004448731,0.0007503987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011584862,0.00037560216,0.014510902,0.0004370456,0.00020213358,0.0010077268,0.00015369068,0.164379,0.12522647,0.0041756527,0.017341383,0.67103195],"study_design_scores_gemma":[0.000041223782,0.0003559015,0.0049726395,0.000052814743,0.000054302276,0.00039245124,0.000050821243,0.9263446,0.057385787,0.0016524137,0.008656312,0.00004068135],"about_ca_topic_score_codex":0.005406197,"about_ca_topic_score_gemma":0.009186859,"teacher_disagreement_score":0.005406197,"about_ca_system_score_codex":0.0005311797,"about_ca_system_score_gemma":0.0005049625,"threshold_uncertainty_score":0.010749459},"labels":[],"label_agreement":null},{"id":"W4414188515","doi":"10.18280/isi.300712","title":"Comparative Evaluation of Machine Learning Models for Diabetes Prediction: A Focus on Ensemble Methods","year":2025,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Focus (optics); Ensemble learning; Key (lock); Feature (linguistics); Interpretability","score_opus":0.2205544225251508,"score_gpt":0.4817434015574827,"score_spread":0.26118897903233185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414188515","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.767082,0.025035355,0.18990768,0.0031861314,0.0009558704,0.00034149585,0.0020659466,0.0020376865,0.009387939],"genre_scores_gemma":[0.94838655,0.003084691,0.04519511,0.00024405417,0.00019556367,0.000094441144,0.0018255042,0.000097174,0.0008768606],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99425465,0.0032562441,0.00052736135,0.00062254496,0.0011006648,0.00023865167],"domain_scores_gemma":[0.9726513,0.020823155,0.0008584533,0.0018012462,0.003463966,0.00040179893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022552293,0.0016742073,0.0019541476,0.0029309022,0.0005719646,0.0016372364,0.001249062,0.001256338,0.000653585],"category_scores_gemma":[0.025995616,0.00025305912,0.001281599,0.001854231,0.00032592018,0.0021559668,0.001058735,0.0014961781,0.0002527413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015384295,0.000650523,0.06955973,0.00049113913,0.0017544451,0.000115221555,0.00015373902,0.6619478,0.0011896659,0.0019546025,0.0049545877,0.25569016],"study_design_scores_gemma":[0.00003074655,0.00065668783,0.008190813,0.00010273638,0.00023883235,0.000059928687,0.00010242294,0.98746186,0.0010984261,0.0011523961,0.0008739407,0.000031174794],"about_ca_topic_score_codex":0.009585792,"about_ca_topic_score_gemma":0.007301716,"teacher_disagreement_score":0.022552293,"about_ca_system_score_codex":0.0008639848,"about_ca_system_score_gemma":0.0011573425,"threshold_uncertainty_score":0.11926937},"labels":[],"label_agreement":null},{"id":"W4414188708","doi":"10.18280/isi.300701","title":"Ensemble Machine Learning for the Classification and Prediction of Mellitus Diabetes","year":2025,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Ensemble learning; Support vector machine; Diabetes mellitus; Type 2 Diabetes Mellitus; Feature (linguistics); Statistical classification","score_opus":0.07277450350793868,"score_gpt":0.3678433838011124,"score_spread":0.29506888029317374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414188708","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29608625,0.01105494,0.6815105,0.0009966996,0.00063780375,0.00015419167,0.0018474474,0.0028763548,0.0048358],"genre_scores_gemma":[0.9016877,0.0016412965,0.09333748,0.00009782593,0.00014419263,0.00007057059,0.0014742052,0.00003146987,0.0015153028],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990575,0.00033111172,0.00008695934,0.00014908129,0.00028692328,0.000088516215],"domain_scores_gemma":[0.9987043,0.00069069146,0.000085291,0.0001441443,0.00033539045,0.000040173512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022483168,0.00065146503,0.0009864024,0.0016865203,0.00034109745,0.0006300843,0.00059167336,0.0004934307,0.00069057767],"category_scores_gemma":[0.0040805247,0.0001849381,0.0007021369,0.0014993307,0.000108912485,0.0006689044,0.00041922092,0.0010039906,0.0003552391],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002835541,0.00027104482,0.019438218,0.00009670826,0.00035619742,0.00012081215,0.00008523428,0.32761666,0.0026468767,0.0016869237,0.0057508107,0.641647],"study_design_scores_gemma":[0.000004914958,0.000055188706,0.0034436788,0.000017518249,0.000033500437,0.00003011598,0.000021038562,0.99279743,0.0010854806,0.00148194,0.0010175768,0.000011662125],"about_ca_topic_score_codex":0.008868424,"about_ca_topic_score_gemma":0.007652664,"teacher_disagreement_score":0.008868424,"about_ca_system_score_codex":0.00047532184,"about_ca_system_score_gemma":0.0006002935,"threshold_uncertainty_score":0.017633617},"labels":[],"label_agreement":null},{"id":"W4414252446","doi":"10.6000/1929-6029.2025.14.52","title":"Heart Disease Prediction using an Ensemble Learning Method: A Study at King Abdullah Hospital in Bisha, Saudi Arabia","year":2025,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"False positive paradox; Logistic regression; Support vector machine; Ensemble learning; Disease; Psychological intervention; Heart disease; Health care","score_opus":0.28159851425152704,"score_gpt":0.6403699487134586,"score_spread":0.3587714344619316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414252446","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9991412,0.0001605687,0.00013115561,0.00020924318,0.000007254393,0.000010648776,0.00011262854,0.0000035613493,0.00022369123],"genre_scores_gemma":[0.99903166,0.00020732536,0.00015352711,0.00010476811,0.000019286415,0.000007989877,0.00025863375,0.0000021526703,0.0002145749],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995316,0.00013609153,0.00004413895,0.0000877755,0.00010604845,0.00009441225],"domain_scores_gemma":[0.997603,0.00059881917,0.00036268577,0.00015355748,0.000888036,0.0003939095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010514115,0.00035200076,0.00034360387,0.0006043919,0.0005071189,0.00053154666,0.00041591146,0.00051623216,0.00078090123],"category_scores_gemma":[0.0029956033,0.00018431667,0.00043846213,0.00065640727,0.00019449538,0.00048331736,0.00047708652,0.00058923516,0.00029098973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018452863,0.0002153077,0.98473215,0.000036910755,0.00007996909,0.00061083335,0.001149757,0.00048141074,0.00028097487,0.000047873473,0.0009810627,0.011199308],"study_design_scores_gemma":[0.000028870734,0.00041816532,0.9849814,0.000044093533,0.000102416656,0.00078245776,0.003808185,0.008324217,0.00030209776,0.00006149681,0.0011187217,0.000027882048],"about_ca_topic_score_codex":0.037066244,"about_ca_topic_score_gemma":0.032332707,"teacher_disagreement_score":0.037066244,"about_ca_system_score_codex":0.0008151862,"about_ca_system_score_gemma":0.0006882676,"threshold_uncertainty_score":0.073701024},"labels":[],"label_agreement":null},{"id":"W4414462776","doi":"10.1109/icscds65426.2025.11167276","title":"Early Disease Prediction using Supervised Machine Learning","year":2025,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Random forest; Artificial neural network; Decision tree; Support vector machine; Supervised learning; Robustness (evolution); Entropy (arrow of time); Reliability (semiconductor); Feature (linguistics)","score_opus":0.1614477180842561,"score_gpt":0.47948260085104394,"score_spread":0.3180348827667878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414462776","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09611543,0.0021521433,0.8917692,0.0011627782,0.0002449769,0.0002201016,0.0013605604,0.0030662878,0.003908477],"genre_scores_gemma":[0.77553755,0.0010545976,0.21634811,0.00037079674,0.00038784527,0.00018043637,0.0034074837,0.00008781347,0.0026254165],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985434,0.000557263,0.00012171795,0.0002832533,0.00038665807,0.00010768393],"domain_scores_gemma":[0.99340665,0.0036872586,0.000776753,0.0007153652,0.0012305136,0.0001834022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025970468,0.0008685775,0.0011839331,0.0031603454,0.00039878217,0.0010312638,0.00090941635,0.00081158243,0.001412951],"category_scores_gemma":[0.008454625,0.00027849097,0.0010195611,0.0013718441,0.00032170847,0.0012397504,0.00076277857,0.0012124538,0.001096106],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005660114,0.0010099129,0.085726924,0.00037822293,0.0004614094,0.00056826277,0.00021011701,0.18734932,0.0063917255,0.0069845407,0.012930466,0.69742316],"study_design_scores_gemma":[0.00002479289,0.00015556351,0.005040453,0.000076634635,0.00005066806,0.00026331694,0.000040470906,0.97373974,0.0039102063,0.014297765,0.0023730537,0.000027356522],"about_ca_topic_score_codex":0.002334564,"about_ca_topic_score_gemma":0.0035161583,"teacher_disagreement_score":0.0031603454,"about_ca_system_score_codex":0.00049648725,"about_ca_system_score_gemma":0.0012492351,"threshold_uncertainty_score":0.013734698},"labels":[],"label_agreement":null},{"id":"W4414463559","doi":"10.1109/conit65521.2025.11167663","title":"Enhanced Diabetes Diagnosis Using Ensemble Classifiers with Explainable AI and Oversampling for Imbalanced Data","year":2025,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Random forest; Ensemble learning; Interpretability; Oversampling; Random subspace method; Preprocessor; Feature selection; Classifier (UML); Decision tree","score_opus":0.22707101836521118,"score_gpt":0.49967059489203264,"score_spread":0.27259957652682143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414463559","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14243954,0.0011090733,0.85264164,0.00061166537,0.00017149746,0.0000773839,0.0003299083,0.0011731712,0.0014460435],"genre_scores_gemma":[0.8825579,0.00040384155,0.11464277,0.00024612734,0.00018259748,0.00007249164,0.0008631923,0.00003930646,0.0009917212],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9991854,0.0002542883,0.000059930844,0.00019300434,0.00020083098,0.00010658722],"domain_scores_gemma":[0.99781054,0.0010872635,0.00021381737,0.0002504847,0.00056371046,0.000074147996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023791704,0.00074552046,0.0011433591,0.001319063,0.0004782838,0.001005174,0.00077246386,0.0006535931,0.00059581746],"category_scores_gemma":[0.005327415,0.00020109331,0.0010672626,0.0008660912,0.0002018469,0.0011951814,0.00081218284,0.0013734238,0.00025837417],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047706277,0.00035621633,0.04533136,0.000092940885,0.00042402546,0.00033862935,0.00032190577,0.31603098,0.0091726305,0.0039051308,0.003847362,0.61970174],"study_design_scores_gemma":[0.000007491252,0.000078102785,0.0026683058,0.000011568195,0.000049746668,0.000058355927,0.000036299283,0.99256855,0.0014867086,0.0023872836,0.0006350463,0.000012518237],"about_ca_topic_score_codex":0.004898723,"about_ca_topic_score_gemma":0.005077225,"teacher_disagreement_score":0.004898723,"about_ca_system_score_codex":0.00042526488,"about_ca_system_score_gemma":0.00075966405,"threshold_uncertainty_score":0.012582362},"labels":[],"label_agreement":null},{"id":"W4414500367","doi":"10.1109/icscsa66339.2025.11170759","title":"An Efficient and User-Friendly Hybrid Approach for Classifying and Predicting Cardiovascular Disease Risks","year":2025,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Disease; Affect (linguistics); Coronary artery disease; Chest pain; Risk assessment; Predictive modelling; Process (computing)","score_opus":0.1621303485545464,"score_gpt":0.4658057667473114,"score_spread":0.303675418192765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414500367","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018400155,0.00027775054,0.9660482,0.00026861165,0.000086597465,0.00013235475,0.0008115622,0.011156034,0.002818728],"genre_scores_gemma":[0.32078356,0.000459508,0.66670203,0.00040491522,0.00009585805,0.00054842007,0.0023796961,0.00035130262,0.008274727],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99956125,0.00008981104,0.000036342073,0.00011693666,0.00016368656,0.00003186482],"domain_scores_gemma":[0.99932945,0.00029069066,0.000037797734,0.000079337275,0.00022676481,0.000035989477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079039007,0.0010059231,0.00081719697,0.0012365569,0.00035163062,0.0014473124,0.0015218491,0.0010892578,0.0064133247],"category_scores_gemma":[0.0023917535,0.0004339071,0.0009295492,0.0009022145,0.00016168835,0.0010708501,0.00106094,0.00073333207,0.0023204265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078258914,0.0004957532,0.009055041,0.00024325882,0.00038189956,0.00058835215,0.00023854763,0.1873522,0.017809302,0.0052943714,0.020357078,0.7574016],"study_design_scores_gemma":[0.00001996632,0.000054582986,0.0009563962,0.000015681955,0.0000437877,0.00015453364,0.000037568723,0.9903197,0.002236472,0.002647397,0.0034868843,0.00002708824],"about_ca_topic_score_codex":0.006163177,"about_ca_topic_score_gemma":0.0076373625,"teacher_disagreement_score":0.0064133247,"about_ca_system_score_codex":0.00036615558,"about_ca_system_score_gemma":0.0006826284,"threshold_uncertainty_score":0.021454632},"labels":[],"label_agreement":null},{"id":"W4414526809","doi":"10.1007/978-3-031-89424-4_9","title":"AI-Based Thyroid Disease Prediction and Binary Classification Models","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ford Motor Company (Canada)","funders":"","keywords":"Thyroid; Thyroid disease; Goiter; Endocrine disease; Disease; Logistic regression; Artificial neural network","score_opus":0.20322653810544858,"score_gpt":0.4449314879544865,"score_spread":0.24170494984903793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414526809","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01431373,0.025369523,0.8485258,0.0051178336,0.0019956238,0.00006333569,0.0011391069,0.0015395889,0.10193538],"genre_scores_gemma":[0.33447716,0.021522319,0.45001316,0.0018017723,0.0022686797,0.00017612374,0.003059314,0.00035010258,0.18633145],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999785,0.000054290267,0.000012248655,0.000046403322,0.00008694568,0.000015035788],"domain_scores_gemma":[0.9989121,0.0008411991,0.000031457468,0.00005969493,0.00013794188,0.00001766719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006787504,0.0005107499,0.00044837414,0.00072036,0.0002589135,0.0013517553,0.0010117125,0.0006161031,0.008512179],"category_scores_gemma":[0.0022595162,0.0002477324,0.00059303484,0.0012199408,0.00044943194,0.0012526709,0.0004747932,0.0012836698,0.003128084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007643028,0.00010438206,0.0019157494,0.0003429774,0.0001041788,0.00013984152,0.00010531025,0.09237555,0.0022448958,0.105315164,0.057551656,0.739724],"study_design_scores_gemma":[0.000007938714,0.000043727476,0.001638133,0.00009722732,0.000041360363,0.00022782743,0.00005257871,0.8096331,0.0017219218,0.14984559,0.036666438,0.000024270346],"about_ca_topic_score_codex":0.0066508246,"about_ca_topic_score_gemma":0.006926144,"teacher_disagreement_score":0.008512179,"about_ca_system_score_codex":0.00072645914,"about_ca_system_score_gemma":0.00039599588,"threshold_uncertainty_score":0.02847606},"labels":[],"label_agreement":null},{"id":"W4414538444","doi":"10.1109/icc52391.2025.11161799","title":"An Integrated Approach to AI-Generated Content in E-Health","year":2025,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Robustness (evolution); Generative grammar; Task (project management); Generative model; Synthetic data; Scarcity","score_opus":0.33282103562780835,"score_gpt":0.5336105856162413,"score_spread":0.20078954998843296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414538444","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012361767,0.0003125902,0.98171866,0.0010235425,0.00011875962,0.000110272784,0.0002797061,0.0014625171,0.0026122073],"genre_scores_gemma":[0.59293526,0.00053745374,0.39291418,0.0012262438,0.0003252177,0.00033672407,0.0014795288,0.00046831506,0.009777148],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99926645,0.00030986083,0.000028401568,0.00019224163,0.00015560289,0.000047564674],"domain_scores_gemma":[0.9975036,0.0015359009,0.00011420825,0.0004487511,0.00029903947,0.000098617544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00161041,0.00057419343,0.00046773112,0.0007208346,0.00030450296,0.0012765998,0.00136328,0.0011215225,0.0032031562],"category_scores_gemma":[0.005940191,0.00029554742,0.0007183265,0.000611843,0.0009868358,0.0018545681,0.0017577402,0.0018523929,0.0011802551],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004758312,0.0005961246,0.004899327,0.00044210663,0.00018875182,0.00049387396,0.000870096,0.37119168,0.042286154,0.078979135,0.013200852,0.48637608],"study_design_scores_gemma":[0.000018481984,0.00009464376,0.0005239914,0.000019399324,0.000019420815,0.00011793624,0.000045349985,0.94803315,0.008066265,0.037677407,0.0053640394,0.000019921106],"about_ca_topic_score_codex":0.0018271348,"about_ca_topic_score_gemma":0.002592112,"teacher_disagreement_score":0.0032031562,"about_ca_system_score_codex":0.00080705853,"about_ca_system_score_gemma":0.0007194047,"threshold_uncertainty_score":0.010715604},"labels":[],"label_agreement":null},{"id":"W4414585619","doi":"10.1158/1538-7445.pancreatic25-b073","title":"Abstract B073: Predicting pancreatic cancer risk from clinical notes using large language models","year":2025,"lang":"en","type":"article","venue":"Cancer Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Sunnybrook Health Science Centre; University Health Network; University of Toronto; North Pacific Marine Science Organization; Princess Margaret Cancer Centre","funders":"","keywords":"Cohort; Pancreatic cancer; Weighting; Cancer; Stage (stratigraphy); Disease; Cohort study; Sampling (signal processing)","score_opus":0.5698433855608535,"score_gpt":0.6805833097340788,"score_spread":0.11073992417322531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414585619","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9332415,0.0005505788,0.046620823,0.0016365584,0.00010283772,0.00024898068,0.012396869,0.0034310003,0.0017708465],"genre_scores_gemma":[0.9585491,0.00012940775,0.02730833,0.00021636035,0.00003957598,0.00011220067,0.0123844445,0.00006167781,0.001198929],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937147,0.00028097213,0.0000452384,0.00018312174,0.000070244445,0.00004892305],"domain_scores_gemma":[0.99578947,0.0029539976,0.00019498856,0.00031106028,0.0005462475,0.00020410768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025716925,0.00091856235,0.00039175505,0.0006969818,0.00036914682,0.00069490285,0.0012110376,0.0006308257,0.0020869193],"category_scores_gemma":[0.0096084215,0.0003302138,0.00079983275,0.00043075354,0.00026824718,0.0005708057,0.00071646925,0.0008701945,0.0006886977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025369278,0.00060142955,0.32756314,0.0004329927,0.0008892503,0.000730438,0.0006866141,0.47077924,0.0065828417,0.0013028545,0.01982535,0.16806889],"study_design_scores_gemma":[0.00011575023,0.00015745332,0.026348323,0.000037997455,0.00009679302,0.00007424543,0.00012403367,0.968793,0.0017837852,0.0010922774,0.0013427229,0.000033605244],"about_ca_topic_score_codex":0.16427548,"about_ca_topic_score_gemma":0.183519,"teacher_disagreement_score":0.16427548,"about_ca_system_score_codex":0.0019583586,"about_ca_system_score_gemma":0.0021455074,"threshold_uncertainty_score":0.32663858},"labels":[],"label_agreement":null},{"id":"W4414605673","doi":"10.1109/icdsns65743.2025.11168562","title":"Automated Liver Tumor Segmentation and Diagnosis Using Self-Guided Deep Clustering Networks","year":2025,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Deep learning; Robustness (evolution); Cluster analysis; Segmentation; Pattern recognition (psychology); Image segmentation; Task (project management); Medical imaging","score_opus":0.12866705557107705,"score_gpt":0.47586989908000416,"score_spread":0.3472028435089271,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414605673","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05732046,0.0003784839,0.93670416,0.00027407715,0.00005133723,0.00008308446,0.00015034684,0.0020582506,0.0029798087],"genre_scores_gemma":[0.68183595,0.00027559986,0.30970025,0.00030015674,0.000059516733,0.000100906895,0.0005675697,0.00016878496,0.00699123],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996799,0.00004665527,0.000015340545,0.000105725165,0.00009586734,0.000056536064],"domain_scores_gemma":[0.99964523,0.00006946384,0.0000551005,0.000059480368,0.00014103131,0.00002981838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049437507,0.0005387207,0.00046494132,0.0010724621,0.00043760778,0.0006904675,0.0011461524,0.0010675981,0.0011696852],"category_scores_gemma":[0.0008590528,0.00037874654,0.00051353266,0.00064184965,0.00036592668,0.0006249907,0.00090392336,0.00054263143,0.00062733755],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003650967,0.00022433508,0.006055277,0.00012278007,0.00013121039,0.0002487778,0.00018335608,0.35363263,0.05384446,0.0071823034,0.0067351414,0.57127464],"study_design_scores_gemma":[0.000004264741,0.000023528642,0.0005968646,0.000006088707,0.000009969279,0.000066718836,0.000010613183,0.9887215,0.008209692,0.001669732,0.0006718196,0.000009269889],"about_ca_topic_score_codex":0.0072684386,"about_ca_topic_score_gemma":0.012666423,"teacher_disagreement_score":0.0072684386,"about_ca_system_score_codex":0.0009854706,"about_ca_system_score_gemma":0.0010977921,"threshold_uncertainty_score":0.014452219},"labels":[],"label_agreement":null},{"id":"W4414650098","doi":"10.63050/jpps.22.03.340","title":"THE USE OF CLOZAPINE IN PAKISTAN: A STUDY BASED ON CLOZARIL PATIENTS MONITORING SYSTEM (CPMS)","year":2025,"lang":"en","type":"article","venue":"Journal of Pakistan Psychiatric Society","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Clozapine; Schizophrenia (object-oriented programming); Drug; Medical record; Antipsychotic; Quarter (Canadian coin)","score_opus":0.10321900186265258,"score_gpt":0.4907556597024502,"score_spread":0.3875366578397976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414650098","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99951386,0.000036403235,0.000015466816,0.000044038723,0.0000023171203,0.000009531684,0.00013999829,5.8617167e-7,0.00023786162],"genre_scores_gemma":[0.9994966,0.00010412085,0.00003010581,0.00006872119,0.0000064234446,0.0000064855717,0.000162436,8.4971646e-7,0.00012426745],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994325,0.00012061342,0.000082580766,0.00008961989,0.00014113152,0.00013350486],"domain_scores_gemma":[0.99805355,0.00038025746,0.0008997819,0.00007071968,0.00025112266,0.00034447995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004469399,0.00026484343,0.00031646373,0.00092664,0.0010931019,0.000675659,0.00028691045,0.00051993266,0.0020078218],"category_scores_gemma":[0.0017663462,0.00046451716,0.0004914857,0.0014941343,0.0005581601,0.000668059,0.00044602194,0.0008258648,0.0003795517],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010271365,0.00015261045,0.99704856,0.000018690424,0.000021088306,0.0004021981,0.00094891415,0.00001494008,0.00014659394,0.000016113057,0.00009310749,0.0010345272],"study_design_scores_gemma":[0.000012750399,0.00043766914,0.9958688,0.000012241783,0.000023461866,0.0008455358,0.0023843485,0.00009637646,0.00006022475,0.000011795746,0.00023767387,0.000009225395],"about_ca_topic_score_codex":0.043051425,"about_ca_topic_score_gemma":0.04257183,"teacher_disagreement_score":0.043051425,"about_ca_system_score_codex":0.0010368308,"about_ca_system_score_gemma":0.0011793666,"threshold_uncertainty_score":0.08560169},"labels":[],"label_agreement":null},{"id":"W4414665438","doi":"10.1007/978-3-031-91643-4_2","title":"Intelligent Healthcare: Progress in Machine Learning and IoT Solutions","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in social networks","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nova Scotia Health Authority; Cape Breton University","funders":"","keywords":"Transformative learning; Internet of Things; Health care; Leverage (statistics); Big data; Analytics; Transparency (behavior); Precision medicine; Psychological intervention","score_opus":0.08618268533902498,"score_gpt":0.42677303667620586,"score_spread":0.34059035133718085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414665438","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024200638,0.626819,0.07908101,0.015304125,0.0060912794,0.000065966284,0.00048304073,0.0010098474,0.26872563],"genre_scores_gemma":[0.033408146,0.6491467,0.07925983,0.00765385,0.008339664,0.00012502822,0.0012257167,0.0005500534,0.2202911],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99951196,0.00006305273,0.000028645694,0.0000831398,0.00027379143,0.000039439255],"domain_scores_gemma":[0.999169,0.00053612207,0.000036375724,0.00006602226,0.00013013485,0.0000624001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080682675,0.0010293385,0.0008012128,0.0015700011,0.00038773424,0.004600405,0.0007729266,0.0018584552,0.016583214],"category_scores_gemma":[0.001168365,0.0004396742,0.0005186867,0.0033011935,0.0011352737,0.005165565,0.0017283156,0.0028479386,0.0083663855],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032371765,0.000095764386,0.00024606774,0.0013871116,0.0000232338,0.00005301053,0.00023504524,0.0014199547,0.0019041272,0.12865995,0.16348559,0.70245785],"study_design_scores_gemma":[0.000005989618,0.000034096895,0.0004593893,0.0006997776,0.000011492802,0.00022930409,0.00010112158,0.0031054874,0.00062462466,0.058425277,0.9362838,0.000019573925],"about_ca_topic_score_codex":0.00083427824,"about_ca_topic_score_gemma":0.0014553145,"teacher_disagreement_score":0.016583214,"about_ca_system_score_codex":0.00075020496,"about_ca_system_score_gemma":0.0010236313,"threshold_uncertainty_score":0.055476367},"labels":[],"label_agreement":null},{"id":"W4414710214","doi":"10.30953/thmt.v10.582","title":"A Systematic Review of Internet of Things Technologies and Their Applications in The Early Detection And Management Of Diabetes Complications.","year":2025,"lang":"en","type":"article","venue":"Telehealth and Medicine Today","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"The Internet; Internet of Things; Randomized controlled trial; Mobile apps; Diabetes management; Clinical trial; MEDLINE; Diabetes mellitus","score_opus":0.047838288430712514,"score_gpt":0.4070514153424363,"score_spread":0.35921312691172375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414710214","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012248736,0.9957632,0.00025450505,0.00036321755,0.0002770034,0.000906803,0.0007266593,0.000010692533,0.00047307176],"genre_scores_gemma":[0.015036096,0.9801855,0.001291897,0.0008995604,0.00012897435,0.001675349,0.00044336414,0.000009162023,0.0003300199],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.98776996,0.004056098,0.0048345802,0.0006502348,0.0024384886,0.00025054615],"domain_scores_gemma":[0.96669614,0.022572815,0.0062974873,0.0005416468,0.0034692762,0.0004226959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0109166205,0.0015192667,0.0076051275,0.01508498,0.0009270616,0.002639075,0.0013172006,0.0016932995,0.005228891],"category_scores_gemma":[0.051492594,0.0009144041,0.007485032,0.014358859,0.0009799056,0.0023883746,0.0013893705,0.0011870175,0.00048673694],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027011134,0.000015120065,0.0005951416,0.96429837,0.008034286,0.00008717293,0.00014585581,0.000059682232,0.00017318146,0.00016403577,0.0015303163,0.02462663],"study_design_scores_gemma":[0.00038914272,0.0002726127,0.0035362458,0.8987774,0.07625033,0.00034479718,0.00021164365,0.000059260972,0.00020094415,0.00029810725,0.019625416,0.000034077573],"about_ca_topic_score_codex":0.008218745,"about_ca_topic_score_gemma":0.02994066,"teacher_disagreement_score":0.01508498,"about_ca_system_score_codex":0.003760755,"about_ca_system_score_gemma":0.017598486,"threshold_uncertainty_score":0.057733297},"labels":[],"label_agreement":null},{"id":"W4414710547","doi":"10.6000/1929-6029.2025.14.56","title":"Comparative Analysis of Machine Learning Models for Early Heart Disease Diagnosis","year":2025,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Categorical variable; Support vector machine; Logistic regression; Random forest; Heart disease; Set (abstract data type); Test set; Data set; Hyperparameter optimization","score_opus":0.42112494453671073,"score_gpt":0.65631888865129,"score_spread":0.23519394411457922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414710547","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7354772,0.029957367,0.2092978,0.005846096,0.0012485028,0.00034655555,0.0038326837,0.0025931604,0.011400639],"genre_scores_gemma":[0.9664345,0.002092835,0.026809126,0.00022314933,0.00020068936,0.00011732316,0.0027245367,0.00014613375,0.001251691],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99432653,0.0037786092,0.00034979382,0.0005123589,0.0007321819,0.00030056023],"domain_scores_gemma":[0.939008,0.054734785,0.001055834,0.0013368736,0.0033795321,0.00048508783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016651176,0.0017674665,0.0015585367,0.0045421557,0.0006295869,0.0018420228,0.0012619735,0.0015233257,0.0021047266],"category_scores_gemma":[0.0351325,0.0004096762,0.0021074945,0.0019043238,0.00042468577,0.0018797098,0.0008325585,0.0015642495,0.00063534564],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018412414,0.00043539787,0.040001083,0.00047047954,0.0009572014,0.00017313722,0.00012583334,0.839378,0.00046057778,0.004421825,0.0062166,0.10551852],"study_design_scores_gemma":[0.000022350938,0.00019319242,0.003856909,0.000039332608,0.00009914448,0.000031055835,0.000053596,0.993317,0.00026628334,0.0016712835,0.00043104365,0.000018804907],"about_ca_topic_score_codex":0.013256225,"about_ca_topic_score_gemma":0.0071694483,"teacher_disagreement_score":0.016651176,"about_ca_system_score_codex":0.0022626205,"about_ca_system_score_gemma":0.001474984,"threshold_uncertainty_score":0.088060856},"labels":[],"label_agreement":null},{"id":"W4414714150","doi":"10.1016/j.cjca.2025.08.089","title":"P123 PREDICTION OF ATRIAL FIBRILLATION FOLLOWING CARDIAC SURGERY USING DEEP LEARNING, CLINICAL MODELS, AND POLYGENIC SCORES","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Cardiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Atrial fibrillation; Cardiac surgery; Complication; Modalities; Cardiac arrhythmia; Polygenic risk score","score_opus":0.20474493322056658,"score_gpt":0.4552934370024608,"score_spread":0.2505485037818942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414714150","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9890322,0.00048239992,0.007196926,0.00057129905,0.00006320455,0.000012095537,0.0016960823,0.00008188564,0.0008640286],"genre_scores_gemma":[0.9974757,0.00011826938,0.0008694649,0.000036681005,0.000037204358,0.0000071101913,0.0010984899,0.000007236487,0.0003498763],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99964607,0.00009279822,0.000038623228,0.00010735666,0.000050166218,0.00006502251],"domain_scores_gemma":[0.9973259,0.0015700958,0.00042543813,0.00017696465,0.00025990076,0.0002416814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009913406,0.0005096491,0.0005383388,0.0007034413,0.00026428624,0.0010755423,0.00043330237,0.00075188186,0.0016049859],"category_scores_gemma":[0.0055406666,0.00018427694,0.0007324559,0.00058136834,0.00024692874,0.00053797074,0.000495857,0.0011675879,0.000418049],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012540001,0.00025783788,0.93954414,0.00004756625,0.00043789775,0.00040253391,0.00003483006,0.014585398,0.0012657441,0.00042504806,0.0018908869,0.039854083],"study_design_scores_gemma":[0.00008633583,0.00040511726,0.57453966,0.000049473783,0.00047652787,0.0008660727,0.00009032261,0.4175823,0.0011710125,0.0039031764,0.0007836195,0.00004630506],"about_ca_topic_score_codex":0.005340231,"about_ca_topic_score_gemma":0.005617548,"teacher_disagreement_score":0.005340231,"about_ca_system_score_codex":0.0002998178,"about_ca_system_score_gemma":0.0005182405,"threshold_uncertainty_score":0.010618269},"labels":[],"label_agreement":null},{"id":"W4415189963","doi":"10.1364/boe.580226","title":"Deep learning optimized dual-analyte detection-based biosensor for monitoring pregnancy stage using a urine sample","year":2025,"lang":"en","type":"article","venue":"Biomedical Optics Express","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sensitivity (control systems); Biosensor; Deep learning; Surface plasmon resonance; Photonic-crystal fiber; Artificial neural network; Optical coherence tomography","score_opus":0.12948680498549242,"score_gpt":0.4601303106966956,"score_spread":0.33064350571120316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415189963","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22652784,0.0005254949,0.76900655,0.00032613325,0.000045923585,0.00004876764,0.0001672379,0.0010248394,0.0023272175],"genre_scores_gemma":[0.8757886,0.00017863102,0.121498354,0.00014635483,0.000011092748,0.000076489756,0.00014244056,0.000032366774,0.0021257624],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99983346,0.00003154795,0.000007767911,0.00004953897,0.000052298536,0.000025366466],"domain_scores_gemma":[0.9998324,0.00006871432,0.000022980506,0.000010544517,0.00005610246,0.000009206129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046315687,0.0005741754,0.0004154419,0.00025323217,0.00015830394,0.00031384468,0.0006553115,0.00066289736,0.00053284806],"category_scores_gemma":[0.0006045685,0.0002891311,0.0004561404,0.00018518973,0.0002455684,0.0005008889,0.00036954242,0.0004819866,0.00018588481],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013994589,0.00022215025,0.003175707,0.00012800242,0.000070367736,0.000088356675,0.00004085775,0.85504484,0.079901256,0.0011860918,0.0005149514,0.059487514],"study_design_scores_gemma":[0.0000020105704,0.000022287793,0.000112418864,0.0000011284175,0.0000036270255,0.0000061240016,0.000001865947,0.99401385,0.0056535094,0.000103498176,0.00007659315,0.0000031396269],"about_ca_topic_score_codex":0.004697692,"about_ca_topic_score_gemma":0.007923928,"teacher_disagreement_score":0.004697692,"about_ca_system_score_codex":0.00087701646,"about_ca_system_score_gemma":0.0008057016,"threshold_uncertainty_score":0.0093407035},"labels":[],"label_agreement":null},{"id":"W4415284538","doi":"10.1109/icmctc62214.2025.11196593","title":"Integrating Machine Learning Models for Accurate Prediction of Diabetes","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Windsor Clinical Research","funders":"","keywords":"Random forest; Predictive modelling; Support vector machine; Deep learning; Diabetes mellitus; Decision tree","score_opus":0.24834499935370608,"score_gpt":0.46709697089667324,"score_spread":0.21875197154296716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415284538","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15361723,0.0047231778,0.83253175,0.002805747,0.00037399362,0.00008254055,0.0006072322,0.0017046042,0.0035537374],"genre_scores_gemma":[0.857665,0.001543777,0.13818745,0.0002811842,0.00017844696,0.00006194135,0.00071685424,0.000052125975,0.0013131811],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993451,0.0002498056,0.000050976116,0.000116572366,0.00017212053,0.00006531153],"domain_scores_gemma":[0.9980452,0.0013284533,0.00012496603,0.00014100404,0.00030563454,0.000054798507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018343829,0.00062594324,0.0006315843,0.00085180055,0.00026925598,0.001037511,0.0005242252,0.0007594194,0.0011069624],"category_scores_gemma":[0.0056918194,0.00031166413,0.0006307872,0.00082224805,0.00016665595,0.0010860333,0.0006318246,0.0014167198,0.00056655105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014317152,0.00022383142,0.016123997,0.00009364237,0.00015823993,0.00012939182,0.00007001847,0.78899926,0.0020481383,0.003070311,0.0024351047,0.18650487],"study_design_scores_gemma":[0.0000031700977,0.000023560424,0.00091280055,0.000014984216,0.00001548011,0.00002011478,0.000007795886,0.9954412,0.000561898,0.0025526767,0.00043815406,0.0000080874115],"about_ca_topic_score_codex":0.008083259,"about_ca_topic_score_gemma":0.009374838,"teacher_disagreement_score":0.008083259,"about_ca_system_score_codex":0.0005358633,"about_ca_system_score_gemma":0.0010031869,"threshold_uncertainty_score":0.016072392},"labels":[],"label_agreement":null},{"id":"W4415446442","doi":"10.1016/j.jacc.2025.09.1487","title":"TCT-1256 Integrating Fractal Analysis with Deep Learning Models for Predicting 30-Day Major Adverse Cardiovascular Events","year":2025,"lang":"en","type":"article","venue":"Journal of the American College of Cardiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; McMaster University; St. Joseph’s Healthcare Hamilton; University of Alberta Hospital; Alberta Hospital Edmonton","funders":"","keywords":"Deep learning; Fractal analysis; Fractal; Artificial neural network; Pattern recognition (psychology)","score_opus":0.040810998378589924,"score_gpt":0.3778107180857032,"score_spread":0.3369997197071133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415446442","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89878225,0.005226406,0.070996985,0.0017522416,0.00067437434,0.00014538727,0.009584897,0.0040206104,0.008816877],"genre_scores_gemma":[0.95512,0.00087180344,0.027895756,0.00039407864,0.0002662258,0.000092436734,0.01010498,0.00012404723,0.00513068],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999894,0.000023832781,0.0000062364047,0.000026731648,0.000029404087,0.00001980767],"domain_scores_gemma":[0.9997645,0.00008732758,0.000018064133,0.000019183597,0.00007803493,0.000032865573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035603193,0.000559263,0.00048638726,0.00058784155,0.00016299482,0.00041464152,0.000420383,0.0006279441,0.0014928657],"category_scores_gemma":[0.0010380938,0.00014739705,0.00050129753,0.00031624569,0.00007757627,0.0002410946,0.0003155548,0.0006200011,0.00059937616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026758332,0.0015023641,0.09780984,0.00024956604,0.00081160624,0.00045663567,0.00005657531,0.23305933,0.018272016,0.0018628886,0.05981665,0.58342665],"study_design_scores_gemma":[0.00011796705,0.00038466544,0.0132739395,0.000023372124,0.000112374335,0.00011620849,0.00001344481,0.97749275,0.0038851206,0.0009838968,0.0035559526,0.00004032722],"about_ca_topic_score_codex":0.008931419,"about_ca_topic_score_gemma":0.011628734,"teacher_disagreement_score":0.008931419,"about_ca_system_score_codex":0.0002788087,"about_ca_system_score_gemma":0.00048016518,"threshold_uncertainty_score":0.017758906},"labels":[],"label_agreement":null},{"id":"W4415446504","doi":"10.1016/j.jacc.2025.09.1077","title":"TCT-894 Development and Internal Validation of an AI-Driven Model for 5-Year Cardiovascular Disease Risk Prediction in the Canadian Longitudinal Study on Aging: Comparative Performance vs. Traditional Risk Scores","year":2025,"lang":"en","type":"article","venue":"Journal of the American College of Cardiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Montreal Heart Institute","funders":"","keywords":"Longitudinal study; Longitudinal data; Disease; Risk assessment; Risk factor","score_opus":0.17144718945278842,"score_gpt":0.423482750785251,"score_spread":0.2520355613324626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415446504","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9318656,0.00044581847,0.053395156,0.0005030401,0.00019397974,0.0006212747,0.0077720056,0.0021649345,0.0030381773],"genre_scores_gemma":[0.9415651,0.00015308488,0.04307895,0.00020168257,0.00004098075,0.00052687136,0.012091138,0.00022871574,0.0021134971],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99842286,0.0006621447,0.00011152824,0.0002799617,0.0004039224,0.00011955094],"domain_scores_gemma":[0.9950937,0.002090657,0.00018214445,0.00028819314,0.002181965,0.00016338179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074761747,0.001042036,0.00066630053,0.0011419675,0.00065669353,0.00108947,0.00162789,0.0006984929,0.0013491156],"category_scores_gemma":[0.013127781,0.00038014827,0.0010106302,0.0007700311,0.00026761775,0.00039211597,0.0007832447,0.0010255465,0.0009098484],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004201509,0.0020899535,0.5240467,0.00021679656,0.002685096,0.00029204538,0.00041405854,0.17358387,0.0072660707,0.0013565811,0.02294783,0.26089945],"study_design_scores_gemma":[0.0004053032,0.0005932599,0.12919046,0.000047624013,0.00054997386,0.00017200154,0.00010094828,0.86030936,0.003929562,0.00080683496,0.003835294,0.00005933396],"about_ca_topic_score_codex":0.12693547,"about_ca_topic_score_gemma":0.103320196,"teacher_disagreement_score":0.8730645,"about_ca_system_score_codex":0.0016901884,"about_ca_system_score_gemma":0.004164798,"threshold_uncertainty_score":0.25239325},"labels":[],"label_agreement":null},{"id":"W4415481727","doi":"10.1101/2025.10.21.25338475","title":"Digital Registrar: A Schema-First Framework for Multi-Cancer Privacy-Preserving Pathology Abstraction via Local LLMs","year":2025,"lang":"","type":"preprint","venue":"medRxiv","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AUG Signals (Canada)","funders":"","keywords":"Reuse; Abstraction; Population; Cancer registry; Completeness (order theory); Cancer","score_opus":0.21644188373134204,"score_gpt":0.4895632775683701,"score_spread":0.27312139383702805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415481727","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030185038,0.00014995276,0.90101284,0.00047549588,0.00006847003,0.00022916694,0.002577597,0.09046505,0.0020029016],"genre_scores_gemma":[0.13381621,0.00040702478,0.82148427,0.0012834595,0.000076312885,0.00057509996,0.019954104,0.017513065,0.004890436],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99630713,0.0009028923,0.00048808803,0.00092254824,0.0011259986,0.00025322544],"domain_scores_gemma":[0.99370676,0.0015051193,0.00034843496,0.0034742015,0.0007083097,0.0002572508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064492174,0.0011499384,0.0008103649,0.00167776,0.00071998016,0.004446583,0.004030737,0.0012744362,0.007931763],"category_scores_gemma":[0.014375273,0.0011722177,0.0038681065,0.0012545461,0.0015223527,0.0058601466,0.008834953,0.002753348,0.0052958606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009672838,0.0003787139,0.019083094,0.0017986132,0.00068591733,0.0014288303,0.0040556462,0.13285144,0.025935326,0.22799794,0.109656,0.47516125],"study_design_scores_gemma":[0.00011650613,0.00013090395,0.0019190387,0.0003263067,0.00018524185,0.0006529873,0.00057728705,0.56607765,0.039690804,0.14689662,0.24325058,0.00017606755],"about_ca_topic_score_codex":0.0070383525,"about_ca_topic_score_gemma":0.008239207,"teacher_disagreement_score":0.007931763,"about_ca_system_score_codex":0.0019188683,"about_ca_system_score_gemma":0.0044713398,"threshold_uncertainty_score":0.03410715},"labels":[],"label_agreement":null},{"id":"W4415483707","doi":"10.1038/s41540-026-00742-y","title":"Supervised machine learning identifies impaired mitochondrial quality control in β cells with development of type 2 diabetes","year":2025,"lang":"en","type":"preprint","venue":"npj Systems Biology and Applications","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Center for Advancing Translational Sciences; National Institutes of Health; Human Islet Research Network; University of Pennsylvania; Alberta Innovates; Canadian Institutes of Health Research; U.S. Department of Veterans Affairs","keywords":"Mitophagy; Mitochondrial biogenesis; Type 2 diabetes; Mitochondrion; Cell type; Cell; Classifier (UML); Gene","score_opus":0.08838169009863828,"score_gpt":0.4363877186486086,"score_spread":0.3480060285499703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415483707","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97597575,0.00010033014,0.023130408,0.000041687512,0.0000063764496,0.000019903093,0.0002625191,0.00012589042,0.0003371016],"genre_scores_gemma":[0.99445146,0.000021500078,0.0050272136,0.000014043075,0.0000034639388,0.000013902903,0.00033819643,0.000006781875,0.00012355638],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9997768,0.00006952036,0.000019459007,0.00007131316,0.000039404396,0.000023520957],"domain_scores_gemma":[0.9993049,0.00027625784,0.00018652616,0.000073703086,0.00010475989,0.000053899912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072968233,0.00026654216,0.000334118,0.00060295925,0.00014617502,0.0004267685,0.00024160337,0.0002841796,0.00052277243],"category_scores_gemma":[0.0014022834,0.00009108659,0.0003200196,0.00026502227,0.00018999819,0.00017817733,0.00035285918,0.00030256927,0.00011098244],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012531613,0.00035955786,0.7274386,0.0001168091,0.0004640245,0.00030440436,0.00016179442,0.07161241,0.08512254,0.0007370406,0.0007685396,0.11166102],"study_design_scores_gemma":[0.000019424733,0.000329265,0.27932987,0.000021646805,0.00007534755,0.000280218,0.00008427177,0.70120955,0.016319308,0.0019147772,0.00039392078,0.000022287162],"about_ca_topic_score_codex":0.00078248786,"about_ca_topic_score_gemma":0.0009896453,"teacher_disagreement_score":0.00078248786,"about_ca_system_score_codex":0.00024560236,"about_ca_system_score_gemma":0.00017660414,"threshold_uncertainty_score":0.0038589835},"labels":[],"label_agreement":null},{"id":"W4415706941","doi":"10.1371/journal.pone.0335442","title":"Predicting hypertension and identifying most important factors among married women in Bangladesh using machine learning approach","year":2025,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Calgary General Hospital; Alberta Health Services","funders":"","keywords":"Prioritization; Psychological intervention; Biometrics; Blood pressure; Random forest; Risk assessment; Theory of planned behavior; Predictive modelling","score_opus":0.21177794016914853,"score_gpt":0.38366222675491485,"score_spread":0.17188428658576632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415706941","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9881606,0.00049660425,0.008225374,0.0005793767,0.000017767601,0.000063263135,0.0013732517,0.000064700165,0.0010190936],"genre_scores_gemma":[0.9940433,0.00017787071,0.004556629,0.00006217004,0.000012682005,0.000030924333,0.00084648316,0.0000042666884,0.00026569417],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995254,0.00023199512,0.000045935973,0.00009603635,0.000050884955,0.000049725124],"domain_scores_gemma":[0.9985946,0.000861899,0.00019954325,0.00006847162,0.00018187742,0.00009368338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017930306,0.00060098385,0.00041070738,0.001136236,0.0003567825,0.00078450894,0.0005050272,0.000448521,0.0015964723],"category_scores_gemma":[0.0044565215,0.00021851152,0.0006656373,0.00068123435,0.00019369514,0.00040965923,0.00057600124,0.00056975253,0.0004174433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018560223,0.00010222576,0.9538236,0.0000657757,0.00014035293,0.00012483035,0.00020613197,0.012891159,0.0006157998,0.00014926364,0.0005332666,0.031162003],"study_design_scores_gemma":[0.000053707085,0.00054314133,0.5318415,0.00023113265,0.0002774813,0.0004009566,0.0018082202,0.4578033,0.0018150047,0.0033859364,0.0017785851,0.000060986444],"about_ca_topic_score_codex":0.015394456,"about_ca_topic_score_gemma":0.014362774,"teacher_disagreement_score":0.015394456,"about_ca_system_score_codex":0.0005775077,"about_ca_system_score_gemma":0.0008349268,"threshold_uncertainty_score":0.030609667},"labels":[],"label_agreement":null},{"id":"W4415956882","doi":"10.1002/ejhf.70076","title":"Unsupervised Machine Learning for Cardiovascular Disease: A Framework for Future Studies","year":2025,"lang":"en","type":"review","venue":"European Journal of Heart Failure","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"Agence Nationale de la Recherche; Université de Lorraine","keywords":"Cluster analysis; Unsupervised learning; Clinical Practice; Risk stratification; Personalized medicine; Predictive modelling; Resource (disambiguation)","score_opus":0.20707486293878818,"score_gpt":0.4894961708952026,"score_spread":0.2824213079564144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415956882","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002817212,0.8753124,0.080442175,0.03647936,0.0020395715,0.0002562431,0.00017107016,0.00014760706,0.004869768],"genre_scores_gemma":[0.014539447,0.8452186,0.12365187,0.007768375,0.004461781,0.0019453561,0.0003249307,0.00008821546,0.0020014534],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9890953,0.0077829333,0.0009014028,0.0007584896,0.0012602846,0.00020153134],"domain_scores_gemma":[0.9650688,0.027714685,0.0013207837,0.0017880908,0.0033884947,0.00071900146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034807935,0.0020932637,0.004692275,0.008518549,0.0013918106,0.0060681426,0.0047333105,0.004782917,0.0043490008],"category_scores_gemma":[0.032980595,0.00086632854,0.0024631876,0.0060411394,0.0074613313,0.008902923,0.00409773,0.00788854,0.0017064153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007574258,0.00015938396,0.0009546012,0.02508361,0.0005379707,0.00034085935,0.0011419476,0.0046011843,0.00034328824,0.5435945,0.03664711,0.38651973],"study_design_scores_gemma":[0.000039076105,0.00013565751,0.00078543735,0.025913356,0.00024299088,0.00034841476,0.0007405335,0.0042757755,0.00015442318,0.6445635,0.32269529,0.00010556367],"about_ca_topic_score_codex":0.0047234953,"about_ca_topic_score_gemma":0.004248559,"teacher_disagreement_score":0.034807935,"about_ca_system_score_codex":0.0047246343,"about_ca_system_score_gemma":0.010741935,"threshold_uncertainty_score":0.18408418},"labels":[],"label_agreement":null},{"id":"W4416257154","doi":"10.2196/70272","title":"Artificial Intelligence–Enhanced Multi-Algorithm R Shiny Application for Predictive Modeling and Analytics: Case Study of Alzheimer Disease Diagnostics","year":2025,"lang":"en","type":"article","venue":"JMIR Aging","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Strong; Tulane University","keywords":"Alzheimer's disease; Artificial neural network; Disease; Pattern recognition (psychology)","score_opus":0.18737896720547195,"score_gpt":0.5135932955376482,"score_spread":0.32621432833217623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416257154","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8273511,0.006321854,0.14258447,0.0064927326,0.00023700082,0.0005030566,0.0019914955,0.0011691316,0.013349196],"genre_scores_gemma":[0.9081991,0.0020927736,0.08499207,0.00041376046,0.00017302601,0.00017759165,0.0010622018,0.00013931382,0.0027502],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874663,0.00053801696,0.00013320676,0.0002000422,0.00029136793,0.00009067398],"domain_scores_gemma":[0.9953903,0.0029385188,0.00038411826,0.00046596103,0.00059097615,0.0002301357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036050964,0.0007781546,0.00067914126,0.0019394894,0.0006340218,0.0015766526,0.0010114074,0.0014880416,0.0023373566],"category_scores_gemma":[0.010522958,0.00029339603,0.0009382595,0.0013901296,0.00078910316,0.000639447,0.0009458051,0.0011927548,0.00090520846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001448102,0.0017162705,0.34852546,0.0013821813,0.0006698954,0.072611995,0.0026223313,0.061932694,0.007528695,0.011119537,0.03528519,0.45515764],"study_design_scores_gemma":[0.00030296788,0.001369332,0.1308617,0.000900564,0.0005141586,0.07497204,0.0023000722,0.69309354,0.017542388,0.030850163,0.047055475,0.00023769065],"about_ca_topic_score_codex":0.0045392076,"about_ca_topic_score_gemma":0.0056136767,"teacher_disagreement_score":0.0045392076,"about_ca_system_score_codex":0.0006572182,"about_ca_system_score_gemma":0.0008979522,"threshold_uncertainty_score":0.019065797},"labels":[],"label_agreement":null},{"id":"W4416343438","doi":"10.18280/isi.300922","title":"Machine Learning with Neural Networks and Random Forest to Predict Nutritional Risk in Children Under 5 Years of Age","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Random forest; Artificial neural network; Deep learning; Feature (linguistics); Statistical learning","score_opus":0.024472665224012098,"score_gpt":0.31457646628487745,"score_spread":0.29010380106086536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416343438","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9889653,0.0017254825,0.00709151,0.00035296113,0.00008609076,0.000025430667,0.0012867864,0.0000681106,0.00039849363],"genre_scores_gemma":[0.99016494,0.00046947005,0.007479878,0.00003485119,0.000038127026,0.000030297606,0.0012409816,0.000009447907,0.00053198816],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999696,0.00014008298,0.000025919739,0.00006057318,0.00003878569,0.000038771566],"domain_scores_gemma":[0.99850583,0.0010783491,0.00013885609,0.000048856487,0.00013732989,0.00009067564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014968565,0.00050174736,0.0005327574,0.0010507617,0.00020386638,0.0005287391,0.00046667276,0.0007012552,0.0007247646],"category_scores_gemma":[0.0041098297,0.00019823335,0.00088657625,0.0005647328,0.00011915122,0.0004627405,0.0003250532,0.0010314431,0.00022191285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021532995,0.0008252918,0.90272576,0.00007316492,0.00057674875,0.00021940656,0.000075341435,0.033578284,0.00047141302,0.00032011114,0.0017871248,0.05719398],"study_design_scores_gemma":[0.0001179327,0.00063219084,0.3687405,0.000079732905,0.0004903302,0.00028423665,0.00025798698,0.62596935,0.0007719588,0.0018916846,0.0007320506,0.00003211384],"about_ca_topic_score_codex":0.01618521,"about_ca_topic_score_gemma":0.014165099,"teacher_disagreement_score":0.01618521,"about_ca_system_score_codex":0.00038715545,"about_ca_system_score_gemma":0.0005212608,"threshold_uncertainty_score":0.032182038},"labels":[],"label_agreement":null},{"id":"W4416799953","doi":"10.1109/icriset64803.2025.11251935","title":"Reliable and Systematic Diabetes Prediction Based on Health Indicators using Machine Learning Algorithm","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada); Horizon College and Seminary","funders":"","keywords":"Decision tree; Preprocessor; Data pre-processing; Normalization (sociology); Classifier (UML); Consistency (knowledge bases); Decision tree learning; Statistical classification","score_opus":0.07078512946654501,"score_gpt":0.41342761234216696,"score_spread":0.34264248287562193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416799953","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24173988,0.004392249,0.74103355,0.0014653034,0.00032728902,0.0004768196,0.0024738845,0.0026685167,0.0054225014],"genre_scores_gemma":[0.7092813,0.001645923,0.28458527,0.00014131067,0.00013119863,0.00022310489,0.002639754,0.000059098988,0.0012930176],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984421,0.0005186292,0.00021767894,0.0003295143,0.0004077263,0.00008428694],"domain_scores_gemma":[0.9953779,0.0025976195,0.0005224212,0.00033919612,0.0010479579,0.0001148482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00271347,0.00069584063,0.0011920558,0.0031109124,0.00040529284,0.0014213916,0.00065153954,0.00061859254,0.0010493216],"category_scores_gemma":[0.009285205,0.00021343,0.0007841233,0.0024524247,0.0001988664,0.0011352872,0.000576418,0.00089844037,0.0005757863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006605858,0.00053440675,0.13507952,0.0005443678,0.0003693062,0.00035661212,0.00023464793,0.18147387,0.003429698,0.0024976654,0.0057376744,0.6690816],"study_design_scores_gemma":[0.00005125023,0.00031801683,0.02503196,0.00023506093,0.00015136825,0.0002561439,0.00019366774,0.9600554,0.0052263197,0.005122285,0.0032941608,0.00006439227],"about_ca_topic_score_codex":0.0057561216,"about_ca_topic_score_gemma":0.0049312585,"teacher_disagreement_score":0.0057561216,"about_ca_system_score_codex":0.00054323685,"about_ca_system_score_gemma":0.0019013563,"threshold_uncertainty_score":0.014350355},"labels":[],"label_agreement":null},{"id":"W4417053426","doi":"10.1109/cises66934.2025.11264882","title":"Transforming Healthcare Ecosystems: Scalable Big Data Management and Analytics for Member, Provider, and Claims Intelligence","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Big data; Analytics; Health care; Scalability; Healthcare industry; Predictive analytics; Data analysis","score_opus":0.34975975267193626,"score_gpt":0.47637440009782533,"score_spread":0.12661464742588907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417053426","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033435576,0.0033543734,0.87844837,0.03468443,0.0011159156,0.0006865714,0.0042913053,0.03149064,0.012492914],"genre_scores_gemma":[0.45462814,0.0029772453,0.5219039,0.0041420152,0.00074211974,0.0004900322,0.010551537,0.0016416057,0.0029235051],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9944448,0.0020972746,0.0005452015,0.00081541337,0.0017037378,0.00039358175],"domain_scores_gemma":[0.9897558,0.0025078482,0.00087822566,0.0040263124,0.0015683839,0.0012634761],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009191397,0.0010669652,0.0008472924,0.0026231022,0.001366289,0.008299515,0.0026587103,0.0015119641,0.0016413991],"category_scores_gemma":[0.01814481,0.0008099809,0.0010694885,0.0030760248,0.0015252343,0.010427354,0.01049886,0.0033055253,0.0012539417],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006124763,0.0006359769,0.042466152,0.00075441913,0.0007696899,0.00135728,0.0024015643,0.08130421,0.011865036,0.18201517,0.18896353,0.4868545],"study_design_scores_gemma":[0.00008142865,0.00013643848,0.0061092256,0.00029091278,0.000107939435,0.0004781851,0.0022896403,0.48581654,0.0068579577,0.35873622,0.13894373,0.00015174344],"about_ca_topic_score_codex":0.0028669706,"about_ca_topic_score_gemma":0.003916222,"teacher_disagreement_score":0.009191397,"about_ca_system_score_codex":0.0014208035,"about_ca_system_score_gemma":0.0039086794,"threshold_uncertainty_score":0.048609316},"labels":[],"label_agreement":null},{"id":"W4417467021","doi":"10.1016/j.cjca.2025.12.024","title":"Comprehensive Machine Learning-Enabled Outcome Prediction for Patients With Coronary Artery Disease Using Multicentre Patient Data","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Cardiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta; Royal Alexandra Hospital; Libin Cardiovascular Institute of Alberta; University of Ottawa; South Health Campus; Alberta Health Services; University of Calgary","funders":"Canadian Institutes of Health Research; Alberta Innovates","keywords":"Coronary artery disease; CAD; Patient data; Feature (linguistics); Real world data; Outcome (game theory)","score_opus":0.13148503066658196,"score_gpt":0.40430676042338903,"score_spread":0.2728217297568071,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417467021","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.943496,0.0019721035,0.016280394,0.0017972226,0.00014569593,0.00011769495,0.034379095,0.00057256676,0.0012391821],"genre_scores_gemma":[0.9526305,0.0002856124,0.010003227,0.00014627274,0.00009871367,0.000058154426,0.03651821,0.000019949106,0.00023936885],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987834,0.00040569904,0.0001610881,0.00033544982,0.00017284635,0.00014145083],"domain_scores_gemma":[0.9960777,0.0017932388,0.0005487033,0.0006771486,0.000549968,0.00035318107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020742656,0.0007566639,0.0013556308,0.0019460651,0.00036620937,0.001287915,0.0007062693,0.0008261529,0.0008529676],"category_scores_gemma":[0.007969215,0.00026938718,0.0011853854,0.001988077,0.00017123537,0.0007996686,0.001204521,0.0013120314,0.00051331025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012073534,0.00067687,0.87025183,0.00024045334,0.0014190937,0.0006918274,0.00017128569,0.027226059,0.0021175975,0.0005377198,0.010954289,0.0845056],"study_design_scores_gemma":[0.00014936448,0.0006904812,0.6615229,0.0001910514,0.000986815,0.0008961477,0.00038267928,0.32094708,0.0026448334,0.004528893,0.0069548837,0.00010487829],"about_ca_topic_score_codex":0.00824248,"about_ca_topic_score_gemma":0.0133640105,"teacher_disagreement_score":0.00824248,"about_ca_system_score_codex":0.00046542267,"about_ca_system_score_gemma":0.001190685,"threshold_uncertainty_score":0.016389012},"labels":[],"label_agreement":null},{"id":"W4417515038","doi":"10.1038/s41598-025-31562-5","title":"Predicting and classifying type 2 diabetes using a transparent ensemble model combining random forest, k-nearest neighbor, and neural networks","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Interpretability; Random forest; Ensemble learning; Artificial neural network; Feature selection; Missing data; Decision tree; Leverage (statistics); Deep learning; Data pre-processing","score_opus":0.14878856841330831,"score_gpt":0.4222256248179109,"score_spread":0.2734370564046026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417515038","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5814494,0.0009458884,0.41403913,0.0005111333,0.0001680744,0.00010657195,0.00035428812,0.00088729325,0.0015382472],"genre_scores_gemma":[0.9450084,0.00013673604,0.05371625,0.00008129692,0.00006362274,0.000049136423,0.0003136071,0.000014394566,0.0006165225],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921286,0.00031234647,0.00006218647,0.0001838333,0.00011966585,0.00010898817],"domain_scores_gemma":[0.99864393,0.00068175374,0.00012309151,0.000115380746,0.0003694466,0.000066430184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003498621,0.0010177924,0.0013350073,0.0014903906,0.0004984133,0.000806638,0.0011623956,0.0007780934,0.00041643574],"category_scores_gemma":[0.0031517565,0.00036621967,0.0013825262,0.00073434436,0.00021291048,0.00080350036,0.0006437816,0.0008709258,0.00021600585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046537357,0.0004839131,0.034951672,0.00004036022,0.00044901838,0.00016157425,0.00009104793,0.7857826,0.0029356596,0.00058576337,0.0011193849,0.17293365],"study_design_scores_gemma":[0.0000028702307,0.000027445129,0.0010520698,0.0000028828965,0.00002390916,0.000009328701,0.0000063227485,0.99846184,0.00019359708,0.00017600521,0.000038480026,0.0000051685342],"about_ca_topic_score_codex":0.01315603,"about_ca_topic_score_gemma":0.012313254,"teacher_disagreement_score":0.01315603,"about_ca_system_score_codex":0.00051197404,"about_ca_system_score_gemma":0.0006947016,"threshold_uncertainty_score":0.026158929},"labels":[],"label_agreement":null},{"id":"W617994174","doi":"","title":"Development of a metabolic syndrome personal health record system.","year":2015,"lang":"en","type":"article","venue":"PubMed","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Metabolic syndrome; Promotion (chess); Medicine; Health promotion; Quarter (Canadian coin); Population; Diabetes mellitus; Family medicine; Gerontology; Environmental health; Public health; Nursing; Geography; Political science","score_opus":0.3344712874987728,"score_gpt":0.43700413189251053,"score_spread":0.10253284439373772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W617994174","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04819619,0.0021686237,0.73166853,0.0069524604,0.0018785432,0.016569674,0.088555574,0.07095863,0.03305182],"genre_scores_gemma":[0.082528815,0.0009811156,0.79198056,0.0018610975,0.00039461494,0.0045896675,0.09296124,0.0015704163,0.02313244],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99443936,0.0013853962,0.0011934858,0.0009128037,0.0018863825,0.00018254847],"domain_scores_gemma":[0.9841196,0.003658765,0.00102668,0.002124944,0.007989713,0.0010802981],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012928996,0.00043791198,0.00074743835,0.002653404,0.00079776434,0.0019157442,0.0014182803,0.000916044,0.008723017],"category_scores_gemma":[0.01836948,0.00047507614,0.0007790984,0.0018157137,0.00024546683,0.0022980692,0.0017431538,0.0014629721,0.009686642],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013931523,0.0007818529,0.031900007,0.0018855821,0.00029775276,0.0008189131,0.0015014738,0.0014332589,0.03789746,0.0058608158,0.12444456,0.7917851],"study_design_scores_gemma":[0.0008090041,0.0016926134,0.0699722,0.001126668,0.0006390305,0.0021369148,0.0008212853,0.021486072,0.0725619,0.0031333752,0.82536215,0.00025874565],"about_ca_topic_score_codex":0.0033249063,"about_ca_topic_score_gemma":0.002785593,"teacher_disagreement_score":0.012928996,"about_ca_system_score_codex":0.0008138795,"about_ca_system_score_gemma":0.0045035845,"threshold_uncertainty_score":0.068375885},"labels":[],"label_agreement":null},{"id":"W6888847735","doi":"10.25316/ir-18894","title":"The Flagstone V.22:No.6 [June 2017]","year":2017,"lang":"en","type":"other","venue":"VIURRSpace (Vancouver Island University)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"The arts; Drama; Gray (unit); Performance art; Temptation; Dream; Desert (philosophy)","score_opus":0.04870347114768616,"score_gpt":0.35015741233708053,"score_spread":0.3014539411893944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6888847735","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010822227,0.0036183903,0.00015882835,0.045225404,0.011681209,0.00011790004,0.0022341346,0.00026948753,0.9356124],"genre_scores_gemma":[0.005623205,0.0011183701,0.0000716102,0.05880609,0.0016822525,0.00018133412,0.0007375048,0.00016460461,0.931615],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987539,0.00009992167,0.000054724576,0.00014501186,0.00041772515,0.0005286224],"domain_scores_gemma":[0.9983779,0.0002349346,0.000058801183,0.00012211014,0.0008314119,0.00037479802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013065801,0.0005755024,0.0004311206,0.00076413434,0.0058719316,0.005581135,0.0013205104,0.0093078315,0.18809676],"category_scores_gemma":[0.0051294784,0.0006369165,0.0006101694,0.00090022624,0.0011481451,0.0032642968,0.0021392473,0.007958259,0.10951057],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000632699,0.000006613508,0.00011653748,0.000018090856,9.209813e-7,0.000040709005,0.00004715141,0.0000054661573,0.0000206976,0.0045907022,0.99146044,0.0036863293],"study_design_scores_gemma":[0.0000046888385,0.000004299365,0.00064535544,0.00008948336,0.0000013086063,0.000023743472,0.00008084734,0.000006753904,0.000021248994,0.0005352867,0.99858105,0.0000059669937],"about_ca_topic_score_codex":0.10034062,"about_ca_topic_score_gemma":0.20683938,"teacher_disagreement_score":0.18809676,"about_ca_system_score_codex":0.004253468,"about_ca_system_score_gemma":0.009481758,"threshold_uncertainty_score":0.62924635},"labels":[],"label_agreement":null},{"id":"W6889216606","doi":"10.25384/sage.c.6611050","title":"From therapeutic nihilism to armamentarium: A meta-analysis of randomized clinical trials assessing safety and efficacy of endovascular therapy for acute large ischemic strokes","year":2023,"lang":"en","type":"other","venue":"Sage Journals Data","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Randomized controlled trial; Modified Rankin Scale; Confidence interval; Stroke (engine); Relative risk; Ambulatory; MEDLINE","score_opus":0.5811557024380697,"score_gpt":0.6229199149116375,"score_spread":0.04176421247356776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6889216606","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023055833,0.97174746,0.0025975846,0.0006076642,0.0005644334,0.0004211733,0.0005165983,0.000072862174,0.0004163657],"genre_scores_gemma":[0.72082514,0.26675242,0.005881505,0.0020188629,0.0010811484,0.0017023366,0.0012146401,0.00011171906,0.00041227185],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.95120096,0.032512214,0.008799518,0.0036904945,0.0030661055,0.0007306058],"domain_scores_gemma":[0.9247881,0.06004644,0.00926269,0.0030265325,0.0021262912,0.0007499818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.052026793,0.004113608,0.022148486,0.0075724847,0.00078476506,0.005713422,0.0028948025,0.00336169,0.0033010994],"category_scores_gemma":[0.07005828,0.0017079031,0.07509595,0.0065602795,0.0014166543,0.0025204062,0.002222157,0.0036238492,0.0003289008],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0048572845,0.000017297985,0.0031360462,0.029837461,0.9590607,0.000049192622,0.000028802206,0.00036485193,0.00011007266,0.00006647731,0.00011030984,0.0023614361],"study_design_scores_gemma":[0.001092566,0.00020042442,0.0018647194,0.0019449166,0.99415827,0.00003178508,0.000016407026,0.00020797914,0.000050191902,0.00017245894,0.00025039152,0.000009906548],"about_ca_topic_score_codex":0.002491733,"about_ca_topic_score_gemma":0.0035408037,"teacher_disagreement_score":0.052026793,"about_ca_system_score_codex":0.0021188406,"about_ca_system_score_gemma":0.0019202341,"threshold_uncertainty_score":0.27514726},"labels":[],"label_agreement":null},{"id":"W6893078250","doi":"10.5281/zenodo.13824490","title":"Harnessing Machine Learning for Diabetes Prediction: Optimizing Classifiers to Tackle Canada's Growing Health Challenge","year":2024,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University Canada West","funders":"","keywords":"Feature (linguistics); Support vector machine; Diabetes mellitus; Key (lock); Interpretability","score_opus":0.45018071940690557,"score_gpt":0.6189054453164629,"score_spread":0.16872472590955728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6893078250","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29961976,0.004939944,0.66886353,0.01079204,0.0005326812,0.00037976642,0.0011312696,0.0021585051,0.011582523],"genre_scores_gemma":[0.877039,0.00094783993,0.117104135,0.0008522318,0.00032572338,0.00011196495,0.0011016736,0.000073216885,0.0024442514],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993475,0.00025495022,0.000038557384,0.00012991305,0.00012233148,0.00010670928],"domain_scores_gemma":[0.99720603,0.0016839658,0.00015880703,0.00011158253,0.00072793366,0.00011172714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019722418,0.0007264367,0.0010572422,0.001103325,0.0005811393,0.0016144111,0.00089387817,0.0011870702,0.0012796755],"category_scores_gemma":[0.008557481,0.00028376945,0.0005253051,0.0011293413,0.00029627953,0.00097209786,0.0005872468,0.001376366,0.00046085665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019311007,0.00033213687,0.025251888,0.000083268074,0.00012533154,0.00009959272,0.00006597074,0.63872606,0.0010330125,0.0027435,0.010061788,0.32128444],"study_design_scores_gemma":[0.000006912365,0.000018296503,0.0006188217,0.000007958222,0.0000115102785,0.000005366173,0.000012319778,0.99767154,0.00015299532,0.001186174,0.00030494758,0.000003114892],"about_ca_topic_score_codex":0.08566979,"about_ca_topic_score_gemma":0.062100638,"teacher_disagreement_score":0.9143302,"about_ca_system_score_codex":0.0019695538,"about_ca_system_score_gemma":0.0036159616,"threshold_uncertainty_score":0.17034227},"labels":[],"label_agreement":null},{"id":"W6901861284","doi":"10.60692/qkrwj-twn94","title":"Prognostic Modeling and Prevention of Diabetes Using Machine Learning Technique","year":2019,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Framingham Risk Score; Hidden Markov model; Receiver operating characteristic; Population; Diabetes mellitus; Risk assessment; Sample (material); Random forest","score_opus":0.14407597353201163,"score_gpt":0.3717321852916397,"score_spread":0.22765621175962808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901861284","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39988157,0.0014698359,0.5906517,0.0017483045,0.0001443022,0.00012902664,0.0010640055,0.0012942194,0.0036170653],"genre_scores_gemma":[0.9572606,0.00033475016,0.04143533,0.00006485405,0.000045078148,0.000035455883,0.00030888722,0.000009395769,0.00050564256],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994067,0.0003195765,0.00004868034,0.00007595286,0.000100392965,0.000048668735],"domain_scores_gemma":[0.9968407,0.0022951888,0.00036722617,0.00016631835,0.00027715295,0.000053484087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024538122,0.00034715614,0.000397401,0.0015519024,0.000258914,0.00070457684,0.00033874557,0.00038190707,0.0012725592],"category_scores_gemma":[0.007940555,0.00015060215,0.0005247601,0.00073222455,0.00020105689,0.0004977349,0.00031714272,0.0005810379,0.00033294788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034918523,0.0003869469,0.35966763,0.00018772809,0.00044732142,0.00028257133,0.0002120463,0.35968548,0.0029094317,0.0054157367,0.0028824105,0.26757345],"study_design_scores_gemma":[0.000014011192,0.000117528725,0.021880308,0.00005048406,0.000058856593,0.00010365159,0.000041014377,0.97219694,0.0009248922,0.003942191,0.00065395527,0.000016157848],"about_ca_topic_score_codex":0.010192291,"about_ca_topic_score_gemma":0.0066014724,"teacher_disagreement_score":0.010192291,"about_ca_system_score_codex":0.00061644905,"about_ca_system_score_gemma":0.0010195121,"threshold_uncertainty_score":0.020265937},"labels":[],"label_agreement":null},{"id":"W6902114434","doi":"10.6084/m9.figshare.19101786","title":"Additional file 1 of The path from big data analytics capabilities to value in hospitals: a scoping review","year":2022,"lang":"en","type":"article","venue":"Open MIND","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Big data; Path (computing); Value (mathematics); Analytics; Data analysis","score_opus":0.39418395641613097,"score_gpt":0.503247005097594,"score_spread":0.10906304868146305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902114434","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012965804,0.00028146495,0.00020518004,0.0004922504,0.000057845933,0.00052512693,0.9968676,0.00007784192,0.0013628935],"genre_scores_gemma":[0.009854342,0.0046800533,0.009749716,0.0031446998,0.0004472837,0.030812897,0.9140008,0.0004684789,0.026841732],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.99703074,0.00063553214,0.0010491681,0.0004077433,0.0006328365,0.00024406372],"domain_scores_gemma":[0.8838223,0.09528411,0.006935519,0.0016297805,0.0113514885,0.0009767894],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0060974956,0.0012198421,0.0018184062,0.008881977,0.00091762684,0.0023348571,0.002043041,0.0018456965,0.82013196],"category_scores_gemma":[0.09506966,0.0007097759,0.0020738137,0.0145012615,0.00045626023,0.003907922,0.001937637,0.0014654456,0.05764778],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044631513,0.000058503505,0.0011821506,0.11215919,0.00017504091,0.00007527906,0.00020352384,0.00032409973,0.0000933815,0.0028229272,0.8668486,0.015610916],"study_design_scores_gemma":[0.004423101,0.00027614392,0.015825758,0.1049033,0.0010851956,0.00035189372,0.0010107011,0.00076662115,0.0004431357,0.01240533,0.85832995,0.00017881214],"about_ca_topic_score_codex":0.010427929,"about_ca_topic_score_gemma":0.017032778,"teacher_disagreement_score":0.82013196,"about_ca_system_score_codex":0.0031199371,"about_ca_system_score_gemma":0.008412461,"threshold_uncertainty_score":0.25655997},"labels":[],"label_agreement":null},{"id":"W6902383090","doi":"10.6084/m9.figshare.28104878.v1","title":"Additional file 1 of Bias in machine learning applications to address non-communicable diseases at a population-level: a scoping review","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trillium Health Centre; Wellesley Institute; Centre for Addiction and Mental Health; Hospital for Sick Children; Institute for Clinical Evaluative Sciences; McGill University; Toronto Metropolitan University; University of Toronto; SickKids Foundation; Western University","funders":"","keywords":"Feature (linguistics); Key (lock); Training set; File format","score_opus":0.4437344140826379,"score_gpt":0.5284800377268163,"score_spread":0.08474562364417837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902383090","genre_codex":"dataset","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016419799,0.0006015632,0.0002702029,0.0003849242,0.00006974489,0.0006176457,0.9965251,0.00013730802,0.0012292737],"genre_scores_gemma":[0.014584676,0.007025692,0.012640765,0.0036690428,0.00051641103,0.03689186,0.8935459,0.0008059271,0.030319821],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.99659353,0.00071742747,0.0013878228,0.00047363696,0.0006094607,0.00021801877],"domain_scores_gemma":[0.8895962,0.09137689,0.0075436356,0.001860508,0.008998207,0.00062456675],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005880966,0.0013932396,0.0024360465,0.008817295,0.00076977146,0.0023385966,0.00196431,0.0019841932,0.80446315],"category_scores_gemma":[0.093842015,0.00075661484,0.0032328914,0.012584001,0.0004126781,0.003330636,0.0016620109,0.0011735813,0.04616127],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081756484,0.000060937688,0.0017043131,0.25366366,0.0006104736,0.00009663334,0.00017891,0.0004325283,0.00015077922,0.002511777,0.7169111,0.022861412],"study_design_scores_gemma":[0.008108122,0.00034581506,0.01985813,0.16964383,0.0037444464,0.0005163397,0.00055439875,0.0010242136,0.0005766814,0.011711175,0.78370404,0.00021293105],"about_ca_topic_score_codex":0.008678144,"about_ca_topic_score_gemma":0.015399401,"teacher_disagreement_score":0.99411905,"about_ca_system_score_codex":0.0029432701,"about_ca_system_score_gemma":0.006682215,"threshold_uncertainty_score":0.2789095},"labels":[],"label_agreement":null},{"id":"W6911528179","doi":"10.5281/zenodo.13926972","title":"Performance Analysis of Diabetes Detection Using Machine Learning Classifiers","year":2024,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University Canada West","funders":"","keywords":"Pattern recognition (psychology); Support vector machine; Feature (linguistics); Training set; Interpretability","score_opus":0.5348770311047472,"score_gpt":0.6573528867679655,"score_spread":0.12247585566321839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6911528179","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94782877,0.008285017,0.025034264,0.0013584406,0.0009314725,0.00013462987,0.005903105,0.0027786077,0.007745711],"genre_scores_gemma":[0.97302926,0.00086551043,0.015757082,0.00016732267,0.00021184955,0.000041594172,0.008527163,0.000042701977,0.0013575148],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9964652,0.00086745084,0.0003816578,0.0006570691,0.0010792852,0.0005492676],"domain_scores_gemma":[0.9901432,0.006433875,0.0006738587,0.00047552297,0.0018822801,0.00039123325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005170956,0.0010883196,0.001383682,0.0038892399,0.00050420687,0.0018125034,0.0008167303,0.001289951,0.00082135614],"category_scores_gemma":[0.012572044,0.00015600942,0.0008974877,0.0018225497,0.00020564946,0.0009435923,0.00054542086,0.0010241107,0.0009856198],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004417233,0.0015513387,0.31338182,0.0005913386,0.0009289595,0.0005255862,0.00016807749,0.16532044,0.005761125,0.0013180602,0.024629103,0.48140693],"study_design_scores_gemma":[0.000058075708,0.0007393807,0.04485475,0.000082472114,0.0001727242,0.00028076442,0.000172672,0.94212186,0.0081807375,0.00077464967,0.0025084352,0.000053420834],"about_ca_topic_score_codex":0.011804923,"about_ca_topic_score_gemma":0.005323275,"teacher_disagreement_score":0.011804923,"about_ca_system_score_codex":0.0009654537,"about_ca_system_score_gemma":0.0008271899,"threshold_uncertainty_score":0.027346969},"labels":[],"label_agreement":null},{"id":"W6911699561","doi":"10.5281/zenodo.13287012","title":"Performance of Machine Learning Classifiers for Diabetes Prediction","year":2024,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Canada West","funders":"","keywords":"C4.5 algorithm; Decision tree; Perceptron; Logistic regression; Stochastic gradient descent; Multilayer perceptron; Receiver operating characteristic; Random forest","score_opus":0.4887422859433318,"score_gpt":0.6460913430871523,"score_spread":0.15734905714382053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6911699561","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5821603,0.02658978,0.35954836,0.0028732452,0.0022703363,0.00056669867,0.0055250595,0.007491328,0.012974918],"genre_scores_gemma":[0.91334647,0.0020643251,0.07890481,0.00035594005,0.00033561912,0.0001423078,0.0034835455,0.000104643485,0.0012623215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99322283,0.0023314862,0.0008452475,0.001124144,0.0019891902,0.00048709146],"domain_scores_gemma":[0.9758169,0.017654018,0.0011980663,0.0012330357,0.003733485,0.00036445304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011791659,0.001991612,0.0022231985,0.004117376,0.0007438542,0.002640127,0.0012962649,0.0020662616,0.0010753179],"category_scores_gemma":[0.031810444,0.00040664774,0.0012123395,0.0026763668,0.00035581732,0.0020397594,0.0007443917,0.0016233858,0.0012538515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018954312,0.0005753179,0.093289874,0.0005252373,0.00087737135,0.0003214725,0.00012501283,0.3117668,0.0035112314,0.0015520975,0.011530344,0.5740298],"study_design_scores_gemma":[0.000026861382,0.00028015304,0.008664394,0.00009085615,0.00010767889,0.00010956166,0.00006615973,0.98420113,0.0036304614,0.0012678439,0.0015170698,0.000037875994],"about_ca_topic_score_codex":0.006481931,"about_ca_topic_score_gemma":0.0028702288,"teacher_disagreement_score":0.011791659,"about_ca_system_score_codex":0.0011079775,"about_ca_system_score_gemma":0.0013261846,"threshold_uncertainty_score":0.062361002},"labels":[],"label_agreement":null},{"id":"W6922038070","doi":"10.1021/jo501299j.s001","title":"Metal-Free Reduction of Secondary\\nand Tertiary &lt;i&gt;N&lt;/i&gt;‑Phenyl Amides by Tris(pentafluorophenyl)boron-Catalyzed Hydrosilylation","year":2016,"lang":"en","type":"article","venue":"Figshare","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Hydrosilylation; Reduction (mathematics); Aryl; Functional group; Chemical reduction; Yield (engineering)","score_opus":0.07128024826926835,"score_gpt":0.3629818275967614,"score_spread":0.2917015793274931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6922038070","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8778181,0.003937299,0.058024216,0.00048325455,0.00028528093,0.00025330353,0.0018733196,0.0009787814,0.056346394],"genre_scores_gemma":[0.9668288,0.0021631,0.013864001,0.00016401982,0.000023460172,0.000066896726,0.0014167542,0.00011248764,0.015360489],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998493,0.000010981701,0.000009502855,0.00003059277,0.000038896957,0.000060722272],"domain_scores_gemma":[0.9999646,0.0000046837154,0.0000073860942,0.0000060687903,0.000008456093,0.000008827949],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017010224,0.00044845385,0.00015439901,0.0001691704,0.00018933702,0.000159474,0.00043989703,0.00025305117,0.0036737202],"category_scores_gemma":[0.00010744347,0.00022856421,0.00022680277,0.00014842267,0.00018657555,0.00025322277,0.00036428348,0.00047836453,0.001660288],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007476053,0.000023374903,0.00004440441,0.00012663568,0.000008939548,0.00009606421,0.00004777146,0.00014643419,0.9921113,0.0006308236,0.0005236976,0.0061657093],"study_design_scores_gemma":[0.000009127287,0.00007342445,0.00024506068,0.0000055797814,0.000005258899,0.00006319758,0.0000094236475,0.0003245678,0.9953211,0.00005895484,0.0038781778,0.000006139422],"about_ca_topic_score_codex":0.0010371192,"about_ca_topic_score_gemma":0.0027524908,"teacher_disagreement_score":0.0036737202,"about_ca_system_score_codex":0.0002801263,"about_ca_system_score_gemma":0.00032271974,"threshold_uncertainty_score":0.012289882},"labels":[],"label_agreement":null},{"id":"W6930739150","doi":"10.5281/zenodo.13287011","title":"Performance of Machine Learning Classifiers for Diabetes Prediction","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Canada West","funders":"","keywords":"C4.5 algorithm; Decision tree; Perceptron; Logistic regression; Stochastic gradient descent; Multilayer perceptron; Receiver operating characteristic; Random forest","score_opus":0.12267801370136858,"score_gpt":0.37768987504451346,"score_spread":0.2550118613431449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930739150","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5821603,0.02658978,0.35954836,0.0028732452,0.0022703363,0.00056669867,0.0055250595,0.007491328,0.012974918],"genre_scores_gemma":[0.91334647,0.0020643251,0.07890481,0.00035594005,0.00033561912,0.0001423078,0.0034835455,0.000104643485,0.0012623215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99322283,0.0023314862,0.0008452475,0.001124144,0.0019891902,0.00048709146],"domain_scores_gemma":[0.9758169,0.017654018,0.0011980663,0.0012330357,0.003733485,0.00036445304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011791659,0.001991612,0.0022231985,0.004117376,0.0007438542,0.002640127,0.0012962649,0.0020662616,0.0010753179],"category_scores_gemma":[0.031810444,0.00040664774,0.0012123395,0.0026763668,0.00035581732,0.0020397594,0.0007443917,0.0016233858,0.0012538515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018954312,0.0005753179,0.093289874,0.0005252373,0.00087737135,0.0003214725,0.00012501283,0.3117668,0.0035112314,0.0015520975,0.011530344,0.5740298],"study_design_scores_gemma":[0.000026861382,0.00028015304,0.008664394,0.00009085615,0.00010767889,0.00010956166,0.00006615973,0.98420113,0.0036304614,0.0012678439,0.0015170698,0.000037875994],"about_ca_topic_score_codex":0.006481931,"about_ca_topic_score_gemma":0.0028702288,"teacher_disagreement_score":0.011791659,"about_ca_system_score_codex":0.0011079775,"about_ca_system_score_gemma":0.0013261846,"threshold_uncertainty_score":0.062361002},"labels":[],"label_agreement":null},{"id":"W6939229599","doi":"10.60692/2hd01-y6t83","title":"Analysis of Dimensionality Reduction Techniques on Big Data","year":2020,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Dimensionality reduction; Random forest; Naive Bayes classifier; Principal component analysis; Linear discriminant analysis; Decision tree; Curse of dimensionality","score_opus":0.4570259056470832,"score_gpt":0.43385519956623186,"score_spread":0.02317070608085131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939229599","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10885647,0.008606697,0.87275475,0.0022755181,0.00038629523,0.00050606125,0.002092498,0.0011413683,0.0033803035],"genre_scores_gemma":[0.5386508,0.0076311394,0.44556418,0.00029323425,0.0004473139,0.0008855574,0.005046813,0.0001466387,0.0013343937],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99445796,0.0019502752,0.00045410972,0.0004860308,0.0024023962,0.0002491189],"domain_scores_gemma":[0.99106336,0.004792695,0.00090382533,0.0012698947,0.0018505797,0.00011961939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00449995,0.0011209265,0.0012657788,0.0038745,0.00083956035,0.001999416,0.00067507615,0.0005286328,0.00064136507],"category_scores_gemma":[0.014971531,0.00031121608,0.0014191929,0.0043360386,0.0006631596,0.001850951,0.0011844791,0.0011872075,0.00032710526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026831726,0.00036995945,0.024796253,0.0016489179,0.00093575066,0.0006329535,0.0008359625,0.17945965,0.009371532,0.0281753,0.012813264,0.74069214],"study_design_scores_gemma":[0.000033196964,0.00025579132,0.026136724,0.0002750245,0.00013618817,0.0004285901,0.00078816473,0.89356834,0.007947784,0.056876566,0.0134588005,0.00009474845],"about_ca_topic_score_codex":0.0017304305,"about_ca_topic_score_gemma":0.0012877948,"teacher_disagreement_score":0.00449995,"about_ca_system_score_codex":0.0007729226,"about_ca_system_score_gemma":0.0010690821,"threshold_uncertainty_score":0.023798347},"labels":[],"label_agreement":null},{"id":"W6939407258","doi":"10.60692/c0m0e-v9q40","title":"Prognostic Modeling and Prevention of Diabetes Using Machine Learning Technique","year":2019,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Framingham Risk Score; Hidden Markov model; Receiver operating characteristic; Population; Diabetes mellitus; Risk assessment; Sample (material); Random forest","score_opus":0.14407597353201163,"score_gpt":0.3717321852916397,"score_spread":0.22765621175962808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939407258","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39988157,0.0014698359,0.5906517,0.0017483045,0.0001443022,0.00012902664,0.0010640055,0.0012942194,0.0036170653],"genre_scores_gemma":[0.9572606,0.00033475016,0.04143533,0.00006485405,0.000045078148,0.000035455883,0.00030888722,0.000009395769,0.00050564256],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994067,0.0003195765,0.00004868034,0.00007595286,0.000100392965,0.000048668735],"domain_scores_gemma":[0.9968407,0.0022951888,0.00036722617,0.00016631835,0.00027715295,0.000053484087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024538122,0.00034715614,0.000397401,0.0015519024,0.000258914,0.00070457684,0.00033874557,0.00038190707,0.0012725592],"category_scores_gemma":[0.007940555,0.00015060215,0.0005247601,0.00073222455,0.00020105689,0.0004977349,0.00031714272,0.0005810379,0.00033294788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034918523,0.0003869469,0.35966763,0.00018772809,0.00044732142,0.00028257133,0.0002120463,0.35968548,0.0029094317,0.0054157367,0.0028824105,0.26757345],"study_design_scores_gemma":[0.000014011192,0.000117528725,0.021880308,0.00005048406,0.000058856593,0.00010365159,0.000041014377,0.97219694,0.0009248922,0.003942191,0.00065395527,0.000016157848],"about_ca_topic_score_codex":0.010192291,"about_ca_topic_score_gemma":0.0066014724,"teacher_disagreement_score":0.010192291,"about_ca_system_score_codex":0.00061644905,"about_ca_system_score_gemma":0.0010195121,"threshold_uncertainty_score":0.020265937},"labels":[],"label_agreement":null},{"id":"W6939461076","doi":"10.6084/m9.figshare.22622996.v1","title":"Additional file 1 of Development of a patients’ satisfaction analysis system using machine learning and lexicon-based methods","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of British Columbia","funders":"","keywords":"Development (topology); Feature (linguistics); Quality (philosophy); Active learning (machine learning); Statistical analysis","score_opus":0.24925888719290204,"score_gpt":0.49070098250377947,"score_spread":0.24144209531087743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939461076","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004907682,0.000018143615,0.0013289384,0.00011128555,0.000044933295,0.00024826726,0.9940513,0.001363412,0.0023429422],"genre_scores_gemma":[0.016671173,0.00013107285,0.018976375,0.0008339013,0.00012479666,0.00435525,0.93819374,0.0028327438,0.017880918],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937695,0.00016155854,0.00013653585,0.00014119086,0.00012577743,0.000057976118],"domain_scores_gemma":[0.9717458,0.023804769,0.0007003111,0.0009963483,0.0023156009,0.00043732827],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015497797,0.00092910253,0.0009856316,0.00230534,0.0005281578,0.0015247836,0.0015648268,0.0010019338,0.892424],"category_scores_gemma":[0.030984048,0.000587468,0.00071462645,0.0024595966,0.0002673143,0.0012169012,0.0010580649,0.00071453076,0.24031125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004947386,0.00017878566,0.002223366,0.0024257766,0.00004942533,0.000111157264,0.00010475952,0.0006413261,0.00022789226,0.00086373556,0.9671236,0.025555275],"study_design_scores_gemma":[0.008641525,0.0007321234,0.039115757,0.0026839355,0.00034651233,0.0010539882,0.0007555735,0.011530006,0.0043389536,0.020535005,0.909922,0.00034459704],"about_ca_topic_score_codex":0.0053705787,"about_ca_topic_score_gemma":0.009846638,"teacher_disagreement_score":0.892424,"about_ca_system_score_codex":0.00091500545,"about_ca_system_score_gemma":0.0014998785,"threshold_uncertainty_score":0.15344405},"labels":[],"label_agreement":null},{"id":"W6949206850","doi":"10.5281/zenodo.13824491","title":"Harnessing Machine Learning for Diabetes Prediction: Optimizing Classifiers to Tackle Canada's Growing Health Challenge","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University Canada West","funders":"","keywords":"Feature (linguistics); Support vector machine; Diabetes mellitus; Key (lock); Interpretability","score_opus":0.12442226309935259,"score_gpt":0.3749856280857431,"score_spread":0.25056336498639054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6949206850","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54447544,0.00784897,0.41212723,0.011851083,0.0008714472,0.00026269417,0.00427371,0.0055534123,0.012735988],"genre_scores_gemma":[0.91766924,0.00081437355,0.072126605,0.00082052517,0.00023597499,0.000059169324,0.0029359139,0.0001593003,0.0051789097],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995353,0.00011730255,0.00002049594,0.000111313995,0.00010670175,0.00010891298],"domain_scores_gemma":[0.9986339,0.0004776391,0.00006636025,0.000075583754,0.00066275406,0.0000838067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014253142,0.00089883135,0.0008942305,0.0009722979,0.0006080919,0.0015606299,0.0009616466,0.0011566734,0.0012006721],"category_scores_gemma":[0.0044164974,0.00029843525,0.0006024066,0.0011421987,0.0003034631,0.0006256027,0.00058075663,0.0011639734,0.0006630939],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003553578,0.0004002773,0.032231607,0.00010613077,0.0002444102,0.00013378763,0.00006716668,0.51919526,0.0038545171,0.001802548,0.028663892,0.41294503],"study_design_scores_gemma":[0.00001646609,0.00002594057,0.0015715741,0.000008596844,0.000039214985,0.00000974399,0.000019498104,0.99512583,0.0011177934,0.0010329173,0.0010268646,0.0000056422878],"about_ca_topic_score_codex":0.316679,"about_ca_topic_score_gemma":0.30729675,"teacher_disagreement_score":0.683321,"about_ca_system_score_codex":0.002647393,"about_ca_system_score_gemma":0.0057187555,"threshold_uncertainty_score":0.62967145},"labels":[],"label_agreement":null},{"id":"W6958607964","doi":"10.6084/m9.figshare.28104878","title":"Additional file 1 of Bias in machine learning applications to address non-communicable diseases at a population-level: a scoping review","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trillium Health Centre; Wellesley Institute; Centre for Addiction and Mental Health; Hospital for Sick Children; Institute for Clinical Evaluative Sciences; McGill University; Toronto Metropolitan University; University of Toronto; SickKids Foundation; Western University","funders":"","keywords":"Feature (linguistics); Key (lock); Training set; File format","score_opus":0.4437344140826379,"score_gpt":0.5284800377268163,"score_spread":0.08474562364417837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958607964","genre_codex":"dataset","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016419799,0.0006015632,0.0002702029,0.0003849242,0.00006974489,0.0006176457,0.9965251,0.00013730802,0.0012292737],"genre_scores_gemma":[0.014584676,0.007025692,0.012640765,0.0036690428,0.00051641103,0.03689186,0.8935459,0.0008059271,0.030319821],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.99659353,0.00071742747,0.0013878228,0.00047363696,0.0006094607,0.00021801877],"domain_scores_gemma":[0.8895962,0.09137689,0.0075436356,0.001860508,0.008998207,0.00062456675],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005880966,0.0013932396,0.0024360465,0.008817295,0.00076977146,0.0023385966,0.00196431,0.0019841932,0.80446315],"category_scores_gemma":[0.093842015,0.00075661484,0.0032328914,0.012584001,0.0004126781,0.003330636,0.0016620109,0.0011735813,0.04616127],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081756484,0.000060937688,0.0017043131,0.25366366,0.0006104736,0.00009663334,0.00017891,0.0004325283,0.00015077922,0.002511777,0.7169111,0.022861412],"study_design_scores_gemma":[0.008108122,0.00034581506,0.01985813,0.16964383,0.0037444464,0.0005163397,0.00055439875,0.0010242136,0.0005766814,0.011711175,0.78370404,0.00021293105],"about_ca_topic_score_codex":0.008678144,"about_ca_topic_score_gemma":0.015399401,"teacher_disagreement_score":0.99411905,"about_ca_system_score_codex":0.0029432701,"about_ca_system_score_gemma":0.006682215,"threshold_uncertainty_score":0.2789095},"labels":[],"label_agreement":null},{"id":"W6977082170","doi":"10.6084/m9.figshare.25223503.v1","title":"Additional file 1 of Characterizing the limitations of using diagnosis codes in the context of machine learning for healthcare","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation","funders":"","keywords":"Context (archaeology); Health care; Key (lock); Training set","score_opus":0.47025314484665703,"score_gpt":0.4764973894160241,"score_spread":0.006244244569367063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977082170","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000368369,0.000033278226,0.0005332722,0.00018687386,0.00003399194,0.00010982113,0.9967339,0.00021900045,0.0017815506],"genre_scores_gemma":[0.025083609,0.00028932554,0.012067435,0.0017103067,0.00022708318,0.0029601417,0.9421224,0.0012828603,0.014256818],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99826777,0.000471147,0.00036226143,0.00039164312,0.00035397903,0.00015307884],"domain_scores_gemma":[0.8198831,0.16120307,0.004036158,0.004640061,0.009322416,0.0009151616],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003227346,0.0008585401,0.00094462535,0.0032734228,0.0008559007,0.0022656398,0.001758829,0.0018026386,0.89148015],"category_scores_gemma":[0.12117595,0.00053131615,0.0010137709,0.003743519,0.00033951164,0.0019695088,0.0012513263,0.00095015444,0.15962568],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039488092,0.00014550539,0.004478638,0.0035856212,0.000074511256,0.0000727927,0.000105713865,0.00056677713,0.00006692338,0.0019775685,0.97377974,0.014751303],"study_design_scores_gemma":[0.005655332,0.00052482577,0.06198664,0.012525258,0.00047985223,0.0014898778,0.0015090604,0.0073536085,0.0014168349,0.044719,0.86206234,0.00027743494],"about_ca_topic_score_codex":0.008864665,"about_ca_topic_score_gemma":0.012903966,"teacher_disagreement_score":0.89148015,"about_ca_system_score_codex":0.0014540823,"about_ca_system_score_gemma":0.0025195505,"threshold_uncertainty_score":0.1547904},"labels":[],"label_agreement":null},{"id":"W7006298744","doi":"","title":"This is America: Black Cis Men Never Held Accountable for Selling Out Black Pain for White Pleasure","year":2018,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"White (mutation); Joke; Pleasure; Happening; Girl; Dance; Value (mathematics)","score_opus":0.041743565918984725,"score_gpt":0.3204341731132476,"score_spread":0.2786906071942629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7006298744","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17198896,0.0052514845,0.0020856436,0.16385354,0.013362364,0.00011240343,0.00030976208,0.00039848578,0.6426374],"genre_scores_gemma":[0.3246454,0.0018860581,0.0006667947,0.05717341,0.00065381767,0.0000775398,0.00010214152,0.0004659877,0.61432886],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983444,0.0003281396,0.000033783417,0.00026977257,0.00043895695,0.000584923],"domain_scores_gemma":[0.9972338,0.00018622303,0.00015342807,0.00013728841,0.0007636888,0.0015254895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014390183,0.00057588564,0.0004919647,0.00065530965,0.028162181,0.009140166,0.00087668607,0.002485721,0.05961406],"category_scores_gemma":[0.003966567,0.000534554,0.0002627902,0.0005638317,0.0062796483,0.005483345,0.006302244,0.011326936,0.0073666936],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012981067,0.00015467482,0.0060260342,0.00018775759,0.00004698109,0.0016166271,0.27437916,0.000037166417,0.0035474792,0.09254632,0.5523503,0.068977684],"study_design_scores_gemma":[0.000007539246,0.000044789125,0.0027507602,0.0002802181,0.000017318442,0.00041140046,0.15578361,0.000046146062,0.00046244528,0.0017052158,0.8384567,0.0000339046],"about_ca_topic_score_codex":0.057874784,"about_ca_topic_score_gemma":0.112925105,"teacher_disagreement_score":0.05961406,"about_ca_system_score_codex":0.00374957,"about_ca_system_score_gemma":0.006035421,"threshold_uncertainty_score":0.19942892},"labels":[],"label_agreement":null},{"id":"W7018552259","doi":"","title":"Economic survey of Canada, 1992","year":2014,"lang":"en","type":"other","venue":"Americanae (AECID Library)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Economic data; Economic analysis; Economic indicator","score_opus":0.05438774349044611,"score_gpt":0.3704160955575094,"score_spread":0.31602835206706326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7018552259","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010143263,0.0035720416,0.00009428899,0.0014521742,0.00014792124,0.00013655165,0.9621272,0.00012426068,0.022202311],"genre_scores_gemma":[0.07173521,0.017477911,0.001061575,0.0013658187,0.00015438416,0.00064667745,0.70675904,0.00017254989,0.20062684],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973252,0.000089517875,0.0002491329,0.0001789005,0.0015257588,0.00063161954],"domain_scores_gemma":[0.99156463,0.00024693232,0.00050514494,0.00011607564,0.0068144356,0.00075270835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011339627,0.0011906747,0.0010617397,0.015176715,0.0023862284,0.0029938733,0.002165287,0.00089123624,0.017433465],"category_scores_gemma":[0.0067644473,0.0009906003,0.0011036335,0.03679376,0.00046742495,0.0011151045,0.001118272,0.0013563489,0.006329507],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019988425,0.00011253842,0.08759148,0.00077670586,0.0001420099,0.000104098595,0.00026060155,0.0005567715,0.00004357573,0.0018987918,0.8814293,0.026884163],"study_design_scores_gemma":[0.00007438695,0.000023065837,0.608093,0.0005394816,0.000091730275,0.00009835704,0.0008161142,0.00045934215,0.0001332658,0.00020977473,0.38941374,0.000047733443],"about_ca_topic_score_codex":0.9958086,"about_ca_topic_score_gemma":0.9972011,"teacher_disagreement_score":0.047896005,"about_ca_system_score_codex":0.047896005,"about_ca_system_score_gemma":0.1147471,"threshold_uncertainty_score":0.34751147},"labels":[],"label_agreement":null},{"id":"W7033494961","doi":"","title":"Prevalence and clinical features of hypoadrenocorticism in Great Pyrenees dogs in a referred population: 11 cases","year":2017,"lang":"en","type":"article","venue":"PubMed Central","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Confidence interval; Population; Cachexia; Retrospective cohort study; Epidemiology","score_opus":0.23223930906849247,"score_gpt":0.4854199624257,"score_spread":0.2531806533572075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7033494961","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99947995,0.00016223869,0.000040763996,0.000009849742,0.0000017341896,0.000008257922,0.000028643495,0.0000021552514,0.00026627057],"genre_scores_gemma":[0.9996433,0.00015024692,0.000061103114,0.00001059153,0.0000050848575,0.000003950352,0.00007456782,6.9001527e-7,0.00005039721],"study_design_codex":"observational","study_design_gemma":"case_report","domain_scores_codex":[0.99948514,0.00009476417,0.00006240615,0.00012811471,0.00012784582,0.000101658086],"domain_scores_gemma":[0.9995122,0.00008297569,0.00020143922,0.000038351125,0.00006064706,0.00010430258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037532425,0.0003157164,0.00027163408,0.0012597302,0.0006575694,0.0006359699,0.00034714918,0.0004975226,0.00094178424],"category_scores_gemma":[0.0011107113,0.0004038425,0.00020923131,0.0007631079,0.0008395987,0.000481534,0.00057083805,0.00020458706,0.00017827147],"study_design_candidate":"case_report","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004439647,0.000049131915,0.99084854,0.000018381486,0.000010852052,0.00596847,0.00047505437,0.000024664258,0.00088145863,0.00002030656,0.000062126215,0.0015966422],"study_design_scores_gemma":[0.0000071128516,0.00018577256,0.9732299,0.000015960613,0.000016169493,0.024928857,0.000971662,0.00009992447,0.00015450311,0.000025557143,0.00035850322,0.0000061866813],"about_ca_topic_score_codex":0.0041393917,"about_ca_topic_score_gemma":0.005137417,"teacher_disagreement_score":0.0041393917,"about_ca_system_score_codex":0.0005930103,"about_ca_system_score_gemma":0.0003015027,"threshold_uncertainty_score":0.008230627},"labels":[],"label_agreement":null},{"id":"W7035247260","doi":"","title":"جيل التمكين | ولاية غرب إفريقية","year":2022,"lang":"ar","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Brother; Islam; State (computer science); Supporter; Spanish Civil War","score_opus":0.028956886175500865,"score_gpt":0.2965363175860013,"score_spread":0.26757943141050045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7035247260","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003238716,0.002537102,0.0043335524,0.006797386,0.011150232,0.00025805883,0.0017816804,0.0019710471,0.9679322],"genre_scores_gemma":[0.012096939,0.0032772233,0.0038613488,0.0018315292,0.0021020223,0.00027926193,0.001590736,0.0021450906,0.9728159],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99861157,0.00019699009,0.00010843918,0.00016025567,0.0007249193,0.00019777993],"domain_scores_gemma":[0.99714017,0.00045088376,0.0001588373,0.0003369683,0.0014976976,0.0004154738],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016081639,0.0007889445,0.0005729967,0.0016026283,0.0023199222,0.0077502034,0.0007883782,0.0012429648,0.6640541],"category_scores_gemma":[0.006109031,0.0005203444,0.0006238216,0.0018822226,0.0019256228,0.0029452285,0.0025089823,0.0037051241,0.63551986],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018653662,0.0000712871,0.00053550344,0.00068565126,0.000013953734,0.0004581797,0.0017123889,0.00009399097,0.0036898497,0.026083492,0.73267317,0.23379605],"study_design_scores_gemma":[0.0000070390834,0.000011589516,0.00048344786,0.00013179723,0.000002962221,0.00015813118,0.00052725134,0.00002031916,0.0005003847,0.00072318345,0.99742484,0.000009146483],"about_ca_topic_score_codex":0.0024908087,"about_ca_topic_score_gemma":0.0033951164,"teacher_disagreement_score":0.3359459,"about_ca_system_score_codex":0.0015736771,"about_ca_system_score_gemma":0.0024052877,"threshold_uncertainty_score":0.47918606},"labels":[],"label_agreement":null},{"id":"W7035656584","doi":"","title":"Age structure of Thuja plicata in the tree layer of old-growth stands near Vancouver, British Columbia","year":2008,"lang":"en","type":"article","venue":"Research Exchange (Washington State University)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Thuja; Age structure; Layer (electronics); Forest structure; Tree (set theory)","score_opus":0.183615894476271,"score_gpt":0.4101683629546574,"score_spread":0.22655246847838642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7035656584","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99340266,0.0005934223,0.00011560788,0.000031001044,0.0000071998766,0.000021020654,0.0010187473,0.000013823083,0.004796525],"genre_scores_gemma":[0.99587977,0.00025923943,0.00020277267,0.000024129677,0.0000023787397,0.000011852417,0.00071207806,0.000007290789,0.0029005709],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9996518,0.000021687623,0.0000148899,0.00008179876,0.00008432389,0.00014546675],"domain_scores_gemma":[0.99845076,0.00009436584,0.00016152818,0.00003632677,0.0009390203,0.00031806252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026352133,0.0003419024,0.0004170028,0.004647922,0.0029533808,0.0016060736,0.0011302017,0.0003192532,0.0022603052],"category_scores_gemma":[0.0005974273,0.00036397483,0.00022558942,0.0043559563,0.00089433615,0.00030386497,0.0008322642,0.00045670583,0.00069223985],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032242158,0.000048446353,0.9557034,0.00008341454,0.000088419794,0.00053971517,0.008512969,0.0002563301,0.0068706763,0.0003131509,0.0014610306,0.025799995],"study_design_scores_gemma":[0.000001990496,0.000007585555,0.9952259,0.000019913285,0.000011640777,0.000064343854,0.0032984738,0.00010715313,0.000106649095,0.000017972046,0.0011323126,0.0000061282476],"about_ca_topic_score_codex":0.92256147,"about_ca_topic_score_gemma":0.98586845,"teacher_disagreement_score":0.07743853,"about_ca_system_score_codex":0.005945408,"about_ca_system_score_gemma":0.0024901489,"threshold_uncertainty_score":0.15578914},"labels":[],"label_agreement":null},{"id":"W7037894712","doi":"","title":"Feb 26 2024- Bell MTS To Drop Axe In Brandon- On Canada Day","year":2024,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sight; Work (physics); Sketch; Front (military)","score_opus":0.02147279917563518,"score_gpt":0.2993880253088765,"score_spread":0.2779152261332413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7037894712","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008218613,0.0020105862,0.00040461108,0.05418975,0.014066043,0.000295899,0.009247065,0.0013628596,0.9102045],"genre_scores_gemma":[0.004911885,0.00020153048,0.00009539765,0.0053207856,0.00022222816,0.000020977759,0.0009564854,0.00015909126,0.9881115],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999186,0.000018895642,0.000011585138,0.00006487091,0.0003522058,0.00036652258],"domain_scores_gemma":[0.99901795,0.000015754355,0.000015405969,0.000019840109,0.00042288267,0.00050819974],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00058070826,0.00051596604,0.00035786047,0.00048422997,0.010305402,0.0055655898,0.00082152715,0.0039482615,0.38260308],"category_scores_gemma":[0.0013440747,0.00037563033,0.00042315785,0.0004468907,0.00068858085,0.0012009152,0.0020090826,0.0038583535,0.12126205],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019404295,0.0000121896455,0.0004541364,0.000011735956,0.0000014076332,0.00009918332,0.00008442679,0.000010523685,0.000112553,0.0011972165,0.994605,0.0033922216],"study_design_scores_gemma":[0.000005896433,0.00001249604,0.002433721,0.000027291102,0.0000015452838,0.000022552586,0.00050899986,0.000021852566,0.000069858026,0.00012247177,0.9967661,0.0000071328805],"about_ca_topic_score_codex":0.6397538,"about_ca_topic_score_gemma":0.9334793,"teacher_disagreement_score":0.38260308,"about_ca_system_score_codex":0.00949688,"about_ca_system_score_gemma":0.013223724,"threshold_uncertainty_score":0.88064176},"labels":[],"label_agreement":null},{"id":"W7098854937","doi":"","title":"Par","year":2013,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nova scotia; Context (archaeology); Vetting","score_opus":0.2491426563945901,"score_gpt":0.5342167757641826,"score_spread":0.2850741193695925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7098854937","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019071334,0.0036264483,0.006455306,0.0114113595,0.0097447485,0.0003405906,0.004844059,0.0034617377,0.9582087],"genre_scores_gemma":[0.010634244,0.0019455977,0.0036160322,0.0049165795,0.0010404325,0.00025337443,0.0032839726,0.0013392615,0.9729706],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964849,0.00065145805,0.00022609689,0.00094989705,0.0012522144,0.0004355541],"domain_scores_gemma":[0.996693,0.00041392338,0.0001932847,0.0007597933,0.0013490797,0.00059091335],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020346553,0.0013332042,0.00090171304,0.001986107,0.0037903714,0.010904436,0.0022358373,0.0043723225,0.65901715],"category_scores_gemma":[0.0074464343,0.00062875374,0.001019957,0.0017304643,0.001442892,0.0067272573,0.006656043,0.004173844,0.5451055],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014465686,0.00007760926,0.0008989919,0.00044956966,0.000021793647,0.00035723875,0.000944192,0.000108707194,0.0011192639,0.03995454,0.78905,0.16687348],"study_design_scores_gemma":[0.0000063559805,0.000011024029,0.00024380084,0.000079930636,0.0000031039265,0.00013675871,0.00017066869,0.000050158418,0.00016200819,0.0015196165,0.9976089,0.000007685282],"about_ca_topic_score_codex":0.005808857,"about_ca_topic_score_gemma":0.008300484,"teacher_disagreement_score":0.34098285,"about_ca_system_score_codex":0.0026484278,"about_ca_system_score_gemma":0.0041244873,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W7104180403","doi":"10.1007/978-3-032-03558-5_30","title":"IoT-Based Smart Healthcare Framework Using Fuzzy Decision Making","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Health care; Fuzzy logic; Robustness (evolution); Reliability (semiconductor); Wearable computer; Transformative learning; Artificial neural network; Healthcare system","score_opus":0.10335699346171306,"score_gpt":0.43138208937199396,"score_spread":0.3280250959102809,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7104180403","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01066149,0.00034102795,0.9751961,0.00028141477,0.00011811738,0.00010437321,0.00023477546,0.0012399432,0.011822676],"genre_scores_gemma":[0.51366204,0.00062399573,0.47403637,0.0002253529,0.00008785679,0.00023355708,0.0006898044,0.00010627845,0.010334725],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99971443,0.000046863704,0.000028867653,0.000061943334,0.00010861207,0.000039337323],"domain_scores_gemma":[0.9998921,0.000033444052,0.000007775763,0.00001278166,0.000035007943,0.000018809964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044514838,0.000414786,0.0005925196,0.00045403343,0.00051917764,0.001468168,0.0010731994,0.00077690167,0.0044367635],"category_scores_gemma":[0.00041099332,0.00021978817,0.00078398467,0.00045150385,0.00032547183,0.0010971308,0.0011073406,0.0005964146,0.00076313264],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004911509,0.00040534543,0.0019943658,0.00032778198,0.00023389938,0.0011900013,0.00036269048,0.38104355,0.034615748,0.17884111,0.0148448385,0.38564947],"study_design_scores_gemma":[0.00002317601,0.0000500451,0.0003207286,0.000040931598,0.000041344083,0.0001488872,0.000059447873,0.94046277,0.0056843734,0.037425112,0.01571637,0.000026786698],"about_ca_topic_score_codex":0.0031517702,"about_ca_topic_score_gemma":0.0031576979,"teacher_disagreement_score":0.0044367635,"about_ca_system_score_codex":0.0004813424,"about_ca_system_score_gemma":0.00076434517,"threshold_uncertainty_score":0.014842451},"labels":[],"label_agreement":null},{"id":"W7108342711","doi":"10.63332/joph.v5i12.3723","title":"Early Prognosis of Diabetes Harnessing Physiological Data and Artificial Intelligence","year":2025,"lang":"","type":"article","venue":"Journal of Posthumanism","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Diabetes mellitus; Biomedicine; Disease; Artificial neural network; Artificial pancreas; Projection (relational algebra)","score_opus":0.29846496548116097,"score_gpt":0.4743263335523127,"score_spread":0.1758613680711517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7108342711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7822567,0.007010591,0.18698028,0.004422102,0.00085060904,0.00019333877,0.00460449,0.0015089719,0.012172891],"genre_scores_gemma":[0.9741994,0.0019335393,0.020569902,0.00026346033,0.00022842879,0.000033403445,0.0015973878,0.000014332472,0.0011601296],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99972564,0.00005705109,0.000034834644,0.00006631961,0.00007988168,0.000036359594],"domain_scores_gemma":[0.9994036,0.000225518,0.00010409093,0.000060624974,0.00015317908,0.000052915624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006386498,0.00059273763,0.0004765922,0.0016342135,0.00023735268,0.0011401772,0.00037941078,0.0006012193,0.00073241536],"category_scores_gemma":[0.001953801,0.00013127479,0.00038610096,0.0007543758,0.00019673862,0.000691675,0.0006051224,0.0008179087,0.00038107968],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00090319564,0.00087580894,0.31114998,0.00034147987,0.0002687728,0.0010476884,0.00024959922,0.05433392,0.017825888,0.0018842904,0.0076530906,0.6034663],"study_design_scores_gemma":[0.000050630446,0.0007752249,0.2371309,0.00029835635,0.00028590971,0.0010200071,0.000555543,0.7215858,0.019216422,0.01025318,0.008669035,0.00015904548],"about_ca_topic_score_codex":0.0032349913,"about_ca_topic_score_gemma":0.0041722925,"teacher_disagreement_score":0.0032349913,"about_ca_system_score_codex":0.00031661044,"about_ca_system_score_gemma":0.0003757177,"threshold_uncertainty_score":0.006432295},"labels":[],"label_agreement":null},{"id":"W7115068870","doi":"10.2196/78648","title":"Machine Learning for the Analysis of Healthy Lifestyle Data: Scoping Review and Guidelines","year":2025,"lang":"en","type":"article","venue":"JMIR Human Factors","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Data collection; Multidisciplinary approach; Representativeness heuristic; Checklist; Workflow; Random forest; Process (computing); Transparency (behavior)","score_opus":0.43115680881261775,"score_gpt":0.6123100713303227,"score_spread":0.18115326251770492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115068870","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022139784,0.9754415,0.005295297,0.008347205,0.0016956943,0.0052132895,0.0015597902,0.00013736697,0.0020884546],"genre_scores_gemma":[0.0032020693,0.95132273,0.025163095,0.004220778,0.0008048835,0.012884258,0.0016927206,0.0000695164,0.0006399324],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.91199684,0.027337035,0.04717468,0.0025076058,0.010081347,0.0009025087],"domain_scores_gemma":[0.6839541,0.23889332,0.029884042,0.007023303,0.03829822,0.0019470634],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.092403054,0.0031969382,0.009595902,0.036349814,0.002382438,0.0077535706,0.008151713,0.009701772,0.009944096],"category_scores_gemma":[0.28141853,0.002343731,0.012660114,0.02274977,0.0035776088,0.009178391,0.006358917,0.006224757,0.0032225824],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012413232,0.0000439225,0.00045589168,0.8098287,0.001955494,0.0002019757,0.00068819703,0.0004336732,0.00022170592,0.003352676,0.027446888,0.1552468],"study_design_scores_gemma":[0.0000514608,0.000028451488,0.0002674811,0.9432013,0.0025293324,0.000107328415,0.00015404422,0.00015295393,0.000100479774,0.002276919,0.0510991,0.00003118687],"about_ca_topic_score_codex":0.0132113965,"about_ca_topic_score_gemma":0.020600159,"teacher_disagreement_score":0.90759695,"about_ca_system_score_codex":0.0088703325,"about_ca_system_score_gemma":0.054861043,"threshold_uncertainty_score":0.4886799},"labels":[],"label_agreement":null},{"id":"W7116406781","doi":"10.2196/82462","title":"Explainable Logistic Regression for Heart Disease Risk Prediction in Community and Clinical Populations: Development and External Validation Study (Preprint)","year":2025,"lang":"en","type":"article","venue":"JMIR Cardio","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Logistic regression; Heart disease; Disease; Risk assessment; Regression analysis; MEDLINE","score_opus":0.3183562680799437,"score_gpt":0.5600324116557923,"score_spread":0.2416761435758486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116406781","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8808914,0.0009765965,0.09961817,0.00081157614,0.0003310577,0.0022126634,0.009672026,0.0028423301,0.0026441684],"genre_scores_gemma":[0.878908,0.00033182462,0.08351688,0.00043605443,0.00013263064,0.0016368573,0.03302945,0.00028877315,0.0017195719],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99449366,0.003658525,0.00024772104,0.0008245258,0.00061962544,0.00015580197],"domain_scores_gemma":[0.9786663,0.010833699,0.00079071004,0.0043302984,0.0047667455,0.00061213557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029966794,0.0013669892,0.00075053883,0.0009667714,0.00040930946,0.00081962545,0.0018060799,0.000994079,0.0021025685],"category_scores_gemma":[0.037160303,0.00040240234,0.001604475,0.00063190167,0.0007035858,0.0009213024,0.0020219493,0.0023255066,0.0013129945],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0054295226,0.004978026,0.4822684,0.00068784575,0.0037115305,0.00039976774,0.00073410344,0.16398367,0.004575641,0.0023546643,0.048788313,0.28208858],"study_design_scores_gemma":[0.0023481697,0.006095584,0.1821246,0.00025868817,0.0008593606,0.0005442772,0.00032092046,0.78882056,0.005248264,0.0027804293,0.010464515,0.00013459145],"about_ca_topic_score_codex":0.005284516,"about_ca_topic_score_gemma":0.004748964,"teacher_disagreement_score":0.029966794,"about_ca_system_score_codex":0.00073897943,"about_ca_system_score_gemma":0.0020398127,"threshold_uncertainty_score":0.15848142},"labels":[],"label_agreement":null},{"id":"W7117275416","doi":"10.36948/ijfmr.2025.v07i06.64396","title":"A Comprehensive Comparative Analysis of Machine Learning Algorithms for Predictive Diagnosis of Cardiovascular Disease","year":2025,"lang":"","type":"article","venue":"International Journal For Multidisciplinary Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Feature selection; Feature (linguistics); Disease; Decision support system; Support vector machine; Selection (genetic algorithm); Statistical classification","score_opus":0.41816687213577136,"score_gpt":0.595663351656734,"score_spread":0.17749647952096265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117275416","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5195487,0.09041158,0.36642548,0.002378515,0.0005147919,0.001291518,0.0029403446,0.002032398,0.014456612],"genre_scores_gemma":[0.8055558,0.010806123,0.17758581,0.00031761717,0.00019132483,0.00041384218,0.0042167925,0.00017966912,0.00073303946],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98438233,0.008150536,0.0017542794,0.0010577021,0.004317779,0.00033742673],"domain_scores_gemma":[0.91748613,0.06877249,0.0019022031,0.0036034717,0.007842997,0.0003926118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030968944,0.0013062827,0.00175814,0.007983126,0.0007041758,0.0027155369,0.0009910922,0.0009984586,0.00082756253],"category_scores_gemma":[0.07318201,0.0002443185,0.0017058889,0.0041668955,0.00046580614,0.0025987073,0.0010935096,0.00086826313,0.0002362207],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027303558,0.000923915,0.06888982,0.002366847,0.0041320957,0.000106972846,0.00024053335,0.10738791,0.0039293896,0.011514043,0.0036248812,0.7941532],"study_design_scores_gemma":[0.0005983074,0.010622132,0.13804959,0.002147652,0.005618759,0.0008506429,0.0007589232,0.7828861,0.017388506,0.024015505,0.01680925,0.00025467793],"about_ca_topic_score_codex":0.0020289093,"about_ca_topic_score_gemma":0.0023870321,"teacher_disagreement_score":0.030968944,"about_ca_system_score_codex":0.0011557698,"about_ca_system_score_gemma":0.0024394812,"threshold_uncertainty_score":0.1637814},"labels":[],"label_agreement":null},{"id":"W7117553059","doi":"10.1049/ipr2.70253","title":"MRI‐Based Heart Disease Diagnosis: An Automated IBNet9X‐DenseNet8X Framework for Optimal Feature Fusion and Classification","year":2025,"lang":"en","type":"article","venue":"IET Image Processing","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Convolutional neural network; Bottleneck; Pattern recognition (psychology); Preprocessor; Feature (linguistics); Artificial neural network; Histogram; Feature extraction","score_opus":0.09577174663410272,"score_gpt":0.5010855728588246,"score_spread":0.4053138262247219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117553059","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054735746,0.0008712798,0.93162274,0.0006046606,0.00012505233,0.00019829818,0.0007516892,0.008011868,0.0030786735],"genre_scores_gemma":[0.5514665,0.00043644913,0.4336133,0.00061992125,0.0001395256,0.00031177487,0.0034677582,0.0002784179,0.009666343],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996834,0.00004850296,0.00001754655,0.00009973597,0.00008817143,0.00006264837],"domain_scores_gemma":[0.9997838,0.000045103934,0.000019104127,0.000032707365,0.00009469824,0.000024619549],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096302194,0.0009993536,0.0008367148,0.0010287703,0.00038451765,0.0007424852,0.0015551554,0.0011309691,0.0036589564],"category_scores_gemma":[0.0013271392,0.00034900513,0.0007064019,0.0005507896,0.00029178843,0.00070028426,0.0014141116,0.001023197,0.0018453854],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054599636,0.00046995052,0.003514184,0.00011038347,0.00014002061,0.00022619385,0.000097774755,0.14037274,0.022552738,0.0039640926,0.0206464,0.8073596],"study_design_scores_gemma":[0.000017986546,0.00004690118,0.00058109674,0.000009811324,0.000012284195,0.00004384656,0.00001475458,0.9918846,0.0042455844,0.001682423,0.0014533536,0.0000073106526],"about_ca_topic_score_codex":0.011296555,"about_ca_topic_score_gemma":0.013254278,"teacher_disagreement_score":0.011296555,"about_ca_system_score_codex":0.00078037975,"about_ca_system_score_gemma":0.0013342121,"threshold_uncertainty_score":0.022461653},"labels":[],"label_agreement":null},{"id":"W7117562630","doi":"10.2196/82084","title":"Cardiorespiratory Markers of Type 2 Diabetes: Machine Learning–Based Analysis","year":2025,"lang":"en","type":"article","venue":"JMIR Diabetes","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cardiorespiratory fitness; Generalizability theory; Feature (linguistics); Sample (material); Heartbeat; Autonomic nervous system","score_opus":0.052099291213126925,"score_gpt":0.42574918055154787,"score_spread":0.3736498893384209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117562630","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5826555,0.049507692,0.34111926,0.0043559745,0.00073502836,0.00058948336,0.008715327,0.0015640674,0.010757703],"genre_scores_gemma":[0.93882406,0.004789328,0.05181931,0.00042424904,0.00046012265,0.00022952835,0.002462115,0.00004957229,0.0009417539],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889404,0.0004919054,0.00009390471,0.00021701699,0.00025840907,0.000044719673],"domain_scores_gemma":[0.99744594,0.001329681,0.00047410963,0.00021382098,0.00045802363,0.00007853457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034953242,0.00074212835,0.00074878434,0.0021902001,0.0001746832,0.001369197,0.0005537856,0.0006116075,0.0010300728],"category_scores_gemma":[0.006238855,0.0001241111,0.00077856105,0.0017020847,0.00022801437,0.00047413624,0.00038184118,0.00094991596,0.0004961251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058556034,0.0004524536,0.46738675,0.0006293845,0.0014861197,0.00019472477,0.00010906331,0.04300733,0.006341733,0.0017830282,0.0061880574,0.47183573],"study_design_scores_gemma":[0.000041801155,0.00060249004,0.49704444,0.00051425153,0.0005721854,0.00066239596,0.00017550038,0.47608387,0.0048110317,0.010951676,0.008436996,0.000103315695],"about_ca_topic_score_codex":0.0013908566,"about_ca_topic_score_gemma":0.001373522,"teacher_disagreement_score":0.0034953242,"about_ca_system_score_codex":0.00042961453,"about_ca_system_score_gemma":0.00037812945,"threshold_uncertainty_score":0.018485248},"labels":[],"label_agreement":null},{"id":"W7117608423","doi":"10.6000/1929-6029.2025.14.77","title":"Early-Stage Cardiovascular Disease Prediction Using a Sigmoidtropy-Based Decision Tree","year":2025,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Decision tree; Naive Bayes classifier; Random forest; Tree (set theory); Disease; Cluster analysis","score_opus":0.2548215229229835,"score_gpt":0.5967117051398103,"score_spread":0.3418901822168268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117608423","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30171257,0.0026332748,0.68595904,0.0016838153,0.0002912495,0.00032618007,0.0026395114,0.0011750066,0.0035792869],"genre_scores_gemma":[0.90109414,0.0010103392,0.09349526,0.00026321734,0.00011143103,0.00015066254,0.0021678167,0.00003161973,0.001675493],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990709,0.00028956277,0.00011746225,0.00019940913,0.00019788883,0.00012475683],"domain_scores_gemma":[0.9979317,0.0012069474,0.00012353803,0.00009018432,0.0005188299,0.00012886808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028763548,0.0008178225,0.0010905587,0.0015587355,0.0005251887,0.0011641053,0.0011550621,0.00081993244,0.0015529076],"category_scores_gemma":[0.004875605,0.00031023257,0.001394093,0.0013798521,0.00029161794,0.0012587814,0.0007092198,0.0010313787,0.00059191283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011541473,0.00046725853,0.050902866,0.00024507544,0.00033421608,0.0004988052,0.00018789654,0.58263016,0.0026017397,0.0029025085,0.006130048,0.35194525],"study_design_scores_gemma":[0.000020602813,0.00011735833,0.001846333,0.000029267592,0.000051105013,0.00008332093,0.000031670028,0.9941882,0.00058410806,0.0024708246,0.00056213205,0.0000150402575],"about_ca_topic_score_codex":0.00789303,"about_ca_topic_score_gemma":0.006579931,"teacher_disagreement_score":0.00789303,"about_ca_system_score_codex":0.00072429347,"about_ca_system_score_gemma":0.0012680999,"threshold_uncertainty_score":0.015694141},"labels":[],"label_agreement":null},{"id":"W7117725052","doi":"10.18280/ts.420621","title":"A Vigilant Smart Colon Cancer Detection Network (CoCaDeNet) Model Using Tiki Taka-Convoluted Depthwise Sheep Capsule Network Methods","year":2025,"lang":"","type":"article","venue":"Traitement du signal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Colorectal cancer; Capsule; Cancer; Cancer detection","score_opus":0.18393915996657353,"score_gpt":0.482197130497981,"score_spread":0.29825797053140746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117725052","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04506022,0.0006475501,0.94969505,0.00061730616,0.00015011667,0.000060390976,0.00024414697,0.00047411438,0.0030510125],"genre_scores_gemma":[0.8174319,0.0005179959,0.16889074,0.00035070587,0.00011764284,0.00021256237,0.0005545833,0.00008501397,0.011838881],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99984753,0.000037107606,0.0000062306103,0.000056053785,0.00002709111,0.000025976453],"domain_scores_gemma":[0.999635,0.0001827903,0.000028827064,0.000019509647,0.000101101505,0.000032870532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005599158,0.0005615266,0.0006754469,0.00039892245,0.00035979165,0.00052021275,0.0014674852,0.0011783638,0.0019121605],"category_scores_gemma":[0.0014879282,0.00038711596,0.0005684258,0.00039583302,0.000406134,0.0008574945,0.00074245373,0.0010929009,0.0003050853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016839096,0.000047233596,0.0013494326,0.000050301103,0.000047758207,0.00010098521,0.00004347812,0.9292059,0.0017551404,0.0063605206,0.001968172,0.058902666],"study_design_scores_gemma":[0.0000016942162,0.000006160539,0.00004159215,0.0000010366713,0.0000029051882,0.0000046518417,0.0000011836686,0.99942195,0.0000803061,0.00035909476,0.00007802479,0.0000013365235],"about_ca_topic_score_codex":0.01719308,"about_ca_topic_score_gemma":0.016141025,"teacher_disagreement_score":0.01719308,"about_ca_system_score_codex":0.0006446108,"about_ca_system_score_gemma":0.0008963357,"threshold_uncertainty_score":0.034186006},"labels":[],"label_agreement":null},{"id":"W7124885315","doi":"10.1109/icaaic64647.2025.11330977","title":"Integrating Multi-Criteria Decision Making and Random Forest Framework for Product Advisory System","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Preference elicitation; Random forest; Ranking (information retrieval); Product (mathematics); Decision support system; Merge (version control); Variety (cybernetics); Preference learning; Preference","score_opus":0.16291592161193288,"score_gpt":0.5119099495172492,"score_spread":0.3489940279053163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124885315","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012311718,0.0005585036,0.983125,0.0004094709,0.00004436229,0.00013775898,0.000077437195,0.00019332189,0.003142539],"genre_scores_gemma":[0.5787006,0.0006206812,0.4171827,0.00015164087,0.00011066163,0.0003408017,0.00021920179,0.00004663481,0.0026271713],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99668485,0.0017579818,0.00016072234,0.00043861152,0.00070900226,0.0002488438],"domain_scores_gemma":[0.9981882,0.001137146,0.00016765886,0.00007428663,0.00033029498,0.00010242614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003965819,0.0010584363,0.0012467365,0.0020538403,0.0009313537,0.0020254913,0.0015058452,0.001197035,0.0029023392],"category_scores_gemma":[0.004183869,0.0003796863,0.001452849,0.0019609875,0.0007535029,0.0018811094,0.0009893596,0.0012114138,0.00036004148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065917724,0.00011825516,0.0018812278,0.00022119642,0.000108475964,0.00021379575,0.00014877046,0.8690079,0.000717866,0.04259048,0.0016622911,0.083263814],"study_design_scores_gemma":[0.0000064719625,0.000034993303,0.00017377688,0.000017110337,0.00001607821,0.00002503983,0.000020713143,0.98220485,0.00013838155,0.016649602,0.00070211844,0.000010930654],"about_ca_topic_score_codex":0.012047274,"about_ca_topic_score_gemma":0.012282394,"teacher_disagreement_score":0.012047274,"about_ca_system_score_codex":0.0019167783,"about_ca_system_score_gemma":0.0024464559,"threshold_uncertainty_score":0.023954272},"labels":[],"label_agreement":null},{"id":"W7125490738","doi":"10.1109/nkcon66957.2025.11345795","title":"Diagnosing the Future: Predicting Diabetes Onset Using Machine Learning and EHR","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Diabetes mellitus; Feature (linguistics); MEDLINE; Training set","score_opus":0.09045881235992738,"score_gpt":0.4471107209890586,"score_spread":0.3566519086291312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125490738","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.977839,0.0018489982,0.007891805,0.0025259545,0.0001379171,0.000055141143,0.004834605,0.00014171597,0.004724893],"genre_scores_gemma":[0.989489,0.000757842,0.0066030566,0.00016100095,0.00009565445,0.000013558925,0.0023315786,0.000008415814,0.00053989416],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995536,0.00014590775,0.00005422498,0.00008889415,0.00007795807,0.000079410565],"domain_scores_gemma":[0.9972728,0.0014712142,0.00047834264,0.00011854838,0.00036617645,0.00029292863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010441327,0.0003723247,0.00046523788,0.0018789816,0.0003174719,0.0015806517,0.00033470173,0.0007858419,0.0016799466],"category_scores_gemma":[0.006822749,0.00019136212,0.00053824286,0.0010033059,0.00012115783,0.0011474015,0.000489119,0.0011461186,0.0004774891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000316145,0.0003221536,0.96673477,0.00003002571,0.00007693498,0.00013600262,0.000036972433,0.0017472962,0.00022419065,0.00018572235,0.0013756806,0.02881413],"study_design_scores_gemma":[0.00009324248,0.00044815976,0.7704874,0.00017475514,0.00033000475,0.0009421846,0.0005725284,0.21872987,0.00146528,0.0035872324,0.0031205257,0.00004884413],"about_ca_topic_score_codex":0.01029893,"about_ca_topic_score_gemma":0.016643025,"teacher_disagreement_score":0.01029893,"about_ca_system_score_codex":0.00049268553,"about_ca_system_score_gemma":0.000571402,"threshold_uncertainty_score":0.02047801},"labels":[],"label_agreement":null},{"id":"W7126160705","doi":"10.18280/isi.301216","title":"A Comparative Analysis of Six Machine Learning Classifiers for Early-Stage Diabetes Risk Prediction Using a Kaggle Dataset","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Diabetes mellitus; Artificial neural network; Support vector machine; Interpretability; Pattern recognition (psychology)","score_opus":0.11110010107719724,"score_gpt":0.40798305807607016,"score_spread":0.2968829569988729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126160705","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93724865,0.010959881,0.007840061,0.0012351504,0.00052171334,0.00024280601,0.03588847,0.0015901141,0.0044731325],"genre_scores_gemma":[0.8597428,0.0024378584,0.020317452,0.00035696465,0.00018368587,0.0001681284,0.113089316,0.00014162071,0.0035620683],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986858,0.00031286775,0.00016611339,0.00031028356,0.00035684448,0.00016822928],"domain_scores_gemma":[0.99527454,0.002807908,0.00019488607,0.00035393419,0.0011708753,0.00019775335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029908887,0.001136064,0.0013533636,0.003367475,0.0006557407,0.0015433487,0.0009639229,0.0011269968,0.001424952],"category_scores_gemma":[0.0060144244,0.0001885438,0.0011587819,0.0015904421,0.00023148525,0.0013645543,0.0006906583,0.00078771356,0.0008409622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013031926,0.0038493543,0.2657003,0.0017671172,0.0044175107,0.00089648424,0.00038335114,0.049874324,0.010981698,0.0013331333,0.10135679,0.54640806],"study_design_scores_gemma":[0.0011309257,0.0047333934,0.40269953,0.00054748636,0.0028232015,0.0014365588,0.0017969663,0.522885,0.018533384,0.002580187,0.04051028,0.00032306195],"about_ca_topic_score_codex":0.015708633,"about_ca_topic_score_gemma":0.023062428,"teacher_disagreement_score":0.015708633,"about_ca_system_score_codex":0.0007688836,"about_ca_system_score_gemma":0.0010576013,"threshold_uncertainty_score":0.031234384},"labels":[],"label_agreement":null},{"id":"W7128742363","doi":"10.1109/gitcon65266.2025.11377145","title":"Optimized Feature Selection And Machine Learning Techniques for Early Detection of Chronic Kidney Disease","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Feature selection; Random forest; Categorical variable; Support vector machine; Feature (linguistics); Reliability (semiconductor); Construct (python library); Selection (genetic algorithm); Kidney disease","score_opus":0.05471903014373603,"score_gpt":0.4169879235585047,"score_spread":0.3622688934147687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7128742363","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052763242,0.0014962484,0.9439549,0.00027363613,0.000058840094,0.00006815163,0.00022301903,0.00069427537,0.00046762024],"genre_scores_gemma":[0.61877793,0.0006970245,0.3784243,0.00013818107,0.00012806208,0.00015108855,0.0008539936,0.00007470679,0.0007546687],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998428,0.0007186894,0.0001283384,0.00024988476,0.00035770593,0.00011752882],"domain_scores_gemma":[0.9982041,0.0011091857,0.00018487478,0.00015443891,0.0003143093,0.000033034004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031837195,0.0008168684,0.0011855508,0.002274906,0.000317264,0.0007246859,0.0005737287,0.00048496554,0.0005244186],"category_scores_gemma":[0.005734413,0.00029340555,0.0011026884,0.0018174433,0.00026716347,0.0006907785,0.0005738118,0.00068986,0.00025206414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004171433,0.00028259048,0.01926634,0.0001893613,0.00040744385,0.00024398256,0.00009518361,0.19323093,0.011951323,0.00405277,0.0034272443,0.7664356],"study_design_scores_gemma":[0.000028315464,0.00019310419,0.009106468,0.00002965339,0.00007639731,0.00016194796,0.000031833202,0.97845995,0.004416251,0.005950933,0.0015167102,0.000028426288],"about_ca_topic_score_codex":0.0021871491,"about_ca_topic_score_gemma":0.002058874,"teacher_disagreement_score":0.0031837195,"about_ca_system_score_codex":0.00041875898,"about_ca_system_score_gemma":0.0007614441,"threshold_uncertainty_score":0.016837358},"labels":[],"label_agreement":null},{"id":"W7129243037","doi":"10.1109/icecmsn68058.2025.11383225","title":"AI-Powered Liver Cancer Detection System using Genetic Algorithm Feature Selection and Random Forest Classification for Healthcare","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Random forest; Feature selection; Classifier (UML); Decision tree; Liver cancer; Visualization; Analytics; Genetic algorithm; Hepatocellular carcinoma","score_opus":0.12694388966485357,"score_gpt":0.45268278071222623,"score_spread":0.32573889104737264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7129243037","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09466851,0.00055067695,0.8729935,0.0006398554,0.000143935,0.00041103282,0.00090732716,0.024260713,0.00542441],"genre_scores_gemma":[0.5314882,0.00037764912,0.46003267,0.00029459625,0.000060754017,0.00038473395,0.0015504424,0.00024308897,0.0055678603],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99976,0.000043901862,0.000019708585,0.000055414857,0.00009086524,0.000030279818],"domain_scores_gemma":[0.9997527,0.000097487646,0.000025898082,0.00001758563,0.00009086518,0.0000156029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046662046,0.00042799645,0.0003439985,0.0010656386,0.00027611025,0.00048400633,0.00044304508,0.00041069114,0.0025422703],"category_scores_gemma":[0.000944067,0.0001363752,0.0005065263,0.00064087624,0.00009705708,0.00037177262,0.00025571176,0.0002869482,0.00088781427],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063579506,0.0004447533,0.009782796,0.00019505665,0.00010105673,0.0004963411,0.000127852,0.05982548,0.045770437,0.0027184687,0.015407226,0.8644947],"study_design_scores_gemma":[0.00007311173,0.0002018616,0.0061350623,0.000030278848,0.000054485718,0.00034327927,0.00003564065,0.95789176,0.024961706,0.0024705115,0.0077591366,0.00004317432],"about_ca_topic_score_codex":0.003751922,"about_ca_topic_score_gemma":0.0031052819,"teacher_disagreement_score":0.003751922,"about_ca_system_score_codex":0.00036432844,"about_ca_system_score_gemma":0.0005254879,"threshold_uncertainty_score":0.008504689},"labels":[],"label_agreement":null},{"id":"W7129726002","doi":"10.1109/icecmsn68058.2025.11382564","title":"An Effective Heart Risk Prediction using Machine Learning Approach","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Random forest; Counterfactual thinking; Consistency (knowledge bases); Decision tree; Support vector machine; Pipeline (software); Calibration","score_opus":0.1191244244588135,"score_gpt":0.4784028614364009,"score_spread":0.3592784369775874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7129726002","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055305608,0.0019933428,0.92747223,0.003303604,0.00025920122,0.00019876982,0.0007205412,0.0022113156,0.008535401],"genre_scores_gemma":[0.74764305,0.0008191096,0.24514794,0.00056272285,0.00029138243,0.00016392686,0.0009928241,0.00006109461,0.0043179584],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916494,0.00025102522,0.0000602684,0.00018118815,0.0002809299,0.000061674866],"domain_scores_gemma":[0.99866486,0.0008051859,0.000090386675,0.000095246185,0.00029405227,0.000050344428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011990989,0.0006006729,0.0007345809,0.0013806327,0.00042169006,0.0014060952,0.00090724236,0.0009663546,0.002843698],"category_scores_gemma":[0.0042824354,0.00020581167,0.0005567462,0.0009110959,0.00024480422,0.001174401,0.00074565195,0.0010184583,0.0009258104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025409204,0.0005111795,0.013257241,0.00019348913,0.00016185072,0.0003580495,0.00017753767,0.23376021,0.003898305,0.016059458,0.013301279,0.71806735],"study_design_scores_gemma":[0.000013150027,0.00004972129,0.001393582,0.000030273039,0.000029121014,0.00007233577,0.000038822673,0.9791158,0.0012682823,0.015345896,0.0026270475,0.000015966223],"about_ca_topic_score_codex":0.0034043593,"about_ca_topic_score_gemma":0.002556277,"teacher_disagreement_score":0.0034043593,"about_ca_system_score_codex":0.00060049404,"about_ca_system_score_gemma":0.0012693433,"threshold_uncertainty_score":0.00951314},"labels":[],"label_agreement":null},{"id":"W7130601166","doi":"10.5220/0013827600004708","title":"Diabetes Risk Assessment: A Logistic Regression Modelling Study Based on Large-Scale Data","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Logistic regression; Diabetes mellitus; Regression analysis; Risk assessment; Linear regression; Population","score_opus":0.3461126710548111,"score_gpt":0.5363972811147728,"score_spread":0.19028461005996172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130601166","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99795973,0.00008630823,0.0013109858,0.00013403321,0.00001029396,0.00003089253,0.0002795507,0.000017863886,0.00017020604],"genre_scores_gemma":[0.9963833,0.000109854336,0.0021924172,0.00006316664,0.000017381099,0.000072752344,0.00083924836,0.000021890075,0.00030008671],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99505806,0.0038925468,0.00018169293,0.00043236619,0.00028840164,0.00014700786],"domain_scores_gemma":[0.95648384,0.03595032,0.0018589663,0.0034886845,0.0014438583,0.000774248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008134814,0.0008826072,0.0007998038,0.0007195944,0.0010117125,0.0012027978,0.0013616165,0.0010032175,0.0016320196],"category_scores_gemma":[0.026756069,0.0005459108,0.0020479222,0.0015067791,0.00060075306,0.0015107557,0.00092329807,0.0022605322,0.00057513826],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008845356,0.00970073,0.94264317,0.00022159074,0.0024053643,0.0010451709,0.0015737236,0.00740311,0.0010142683,0.0006925701,0.0018590972,0.022595838],"study_design_scores_gemma":[0.0014079385,0.006507697,0.86243415,0.00010175445,0.002316356,0.0018031995,0.0035238385,0.11755143,0.0012207233,0.0011391493,0.0017875747,0.00020617238],"about_ca_topic_score_codex":0.015165136,"about_ca_topic_score_gemma":0.010585675,"teacher_disagreement_score":0.015165136,"about_ca_system_score_codex":0.0007366542,"about_ca_system_score_gemma":0.0010217329,"threshold_uncertainty_score":0.0430215},"labels":[],"label_agreement":null},{"id":"W7130614257","doi":"10.1109/icec2nt65402.2025.11380114","title":"An Interpretable TabNet Deep Learning Approach for Kidney Disease Classification","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Interpretability; Categorical variable; Deep learning; Outlier; Preprocessor; Categorization; Pattern recognition (psychology)","score_opus":0.1527694512013306,"score_gpt":0.47513825386391295,"score_spread":0.3223688026625824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130614257","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07980771,0.0007765322,0.9106756,0.0010761656,0.0002029051,0.000085745174,0.00069663307,0.0017699875,0.004908679],"genre_scores_gemma":[0.8139667,0.0005076101,0.17630947,0.00066996773,0.00012541785,0.00017931488,0.0014919006,0.00008021293,0.0066693267],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998356,0.000050767918,0.0000093966655,0.000037722184,0.00004072615,0.000025652442],"domain_scores_gemma":[0.9996606,0.000130463,0.000029640138,0.000029928555,0.00012879142,0.000020550986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066200714,0.0005691248,0.00043390028,0.0005011439,0.00025506673,0.00072691037,0.0010972692,0.00080124295,0.0027198805],"category_scores_gemma":[0.0018086109,0.00019842584,0.00043891708,0.0004818899,0.00030142826,0.00078873435,0.00068101886,0.0010097644,0.00046126317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022627368,0.0001873429,0.004501554,0.00009783901,0.00010127888,0.00017845859,0.00009353295,0.7058051,0.00454225,0.013354722,0.006569294,0.26434228],"study_design_scores_gemma":[0.0000042242687,0.00002599474,0.00018128131,0.000007463402,0.0000069480757,0.000014260294,0.0000057035923,0.99468404,0.00046632523,0.004135603,0.00046485904,0.0000032817507],"about_ca_topic_score_codex":0.005700229,"about_ca_topic_score_gemma":0.008943781,"teacher_disagreement_score":0.005700229,"about_ca_system_score_codex":0.00078698056,"about_ca_system_score_gemma":0.00095405744,"threshold_uncertainty_score":0.011334121},"labels":[],"label_agreement":null},{"id":"W7131129494","doi":"10.1109/upwiecon67212.2025.11390545","title":"Multi-Disease Risk Prediction: Leveraging Machine Learning for Heart Disease and Diabetes Prediction","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadiana.org","funders":"","keywords":"Heart disease; Diabetes mellitus; Logistic regression; Disease; Support vector machine; Empirical research","score_opus":0.09510172832330697,"score_gpt":0.41366700573519943,"score_spread":0.31856527741189244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131129494","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31200176,0.010612482,0.65309566,0.009469691,0.0008060063,0.00031001895,0.0017286333,0.0043675383,0.007608283],"genre_scores_gemma":[0.8993527,0.0010391667,0.09650157,0.0004785405,0.00030308575,0.000070261885,0.00083710003,0.00003843969,0.001379152],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896646,0.00043181627,0.00008230181,0.00020697659,0.00019343852,0.00011906472],"domain_scores_gemma":[0.99645597,0.0023414537,0.00029879095,0.00030908897,0.00042970106,0.00016510137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027584448,0.0008771226,0.0010948172,0.0018227092,0.00042986544,0.001258486,0.0008010238,0.0010266291,0.0009149339],"category_scores_gemma":[0.008339401,0.00030649605,0.00089129485,0.0014486547,0.00025322396,0.0015910706,0.0011551017,0.0017853309,0.0005373908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004040145,0.001256318,0.08791063,0.00015876463,0.00048586144,0.00038434067,0.00017451755,0.3320966,0.0023630213,0.0027593656,0.007968594,0.56403804],"study_design_scores_gemma":[0.000010260542,0.000116321906,0.005592231,0.0000395456,0.000050710867,0.000085359374,0.00003597153,0.9867775,0.0007483535,0.005377412,0.0011440464,0.000022383188],"about_ca_topic_score_codex":0.0068183723,"about_ca_topic_score_gemma":0.008880135,"teacher_disagreement_score":0.0068183723,"about_ca_system_score_codex":0.0004477907,"about_ca_system_score_gemma":0.00075402146,"threshold_uncertainty_score":0.014588237},"labels":[],"label_agreement":null},{"id":"W7131392993","doi":"10.1109/icaiihi67124.2025.11403441","title":"An Enhanced Approach to Predict Heart Disease for Genx using Machine Learning Algorithms","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Task (project management); Heart disease; Logistic regression; Statistical classification; Quality (philosophy); Deep learning; Disease","score_opus":0.192613255881977,"score_gpt":0.49717131419779603,"score_spread":0.30455805831581906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131392993","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14363535,0.0013139268,0.8427787,0.0013967976,0.0002198493,0.00030670906,0.0016219717,0.0037801398,0.0049464963],"genre_scores_gemma":[0.5286467,0.00052145106,0.46219632,0.000317129,0.00018127699,0.00021320047,0.0023334518,0.000097123266,0.0054933215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99940205,0.00018900566,0.00005634313,0.00014812732,0.00015011156,0.000054390144],"domain_scores_gemma":[0.99872845,0.000635549,0.00008455364,0.000110475994,0.00039806744,0.000043008626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014735647,0.0006432845,0.00083511573,0.0020879286,0.00038387836,0.0011835272,0.0009541116,0.00089752965,0.003057449],"category_scores_gemma":[0.004350157,0.00025233874,0.0007780441,0.001408067,0.00016356308,0.0009356256,0.0007078693,0.00091100176,0.0011355744],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033820307,0.00067118736,0.094912894,0.0001422104,0.00025571865,0.0005432228,0.00024427898,0.27116036,0.0032391208,0.004044758,0.007208959,0.617239],"study_design_scores_gemma":[0.000019381774,0.0000796633,0.006291834,0.00001943825,0.000028743189,0.00012593878,0.00007330939,0.9884466,0.0008925604,0.0021165977,0.0018922887,0.000013725397],"about_ca_topic_score_codex":0.010261287,"about_ca_topic_score_gemma":0.007756149,"teacher_disagreement_score":0.010261287,"about_ca_system_score_codex":0.00044915162,"about_ca_system_score_gemma":0.0010524647,"threshold_uncertainty_score":0.020403147},"labels":[],"label_agreement":null},{"id":"W7131841982","doi":"10.5376/ijccr.2025.15.0022","title":"Comparative Study on Construction Methods of Chronic Disease Prediction Models Based on Big Data","year":2025,"lang":"","type":"article","venue":"International Journal of Clinical Case Reports","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Big data; Predictive modelling; Data modeling; Chronic disease; Identification (biology)","score_opus":0.7061699001427565,"score_gpt":0.683735565586375,"score_spread":0.02243433455638144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131841982","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53314877,0.0051999683,0.44841656,0.002312133,0.0005731307,0.00034954122,0.0024701178,0.0021777581,0.0053519583],"genre_scores_gemma":[0.8415105,0.0017923507,0.14950506,0.00016516779,0.00017157856,0.00023145496,0.005162191,0.00026856185,0.0011932241],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956306,0.0023177809,0.00033409687,0.0005306138,0.0010007829,0.00018608809],"domain_scores_gemma":[0.95546055,0.035308674,0.00077834213,0.0026862496,0.0052237357,0.00054242444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011602801,0.001025227,0.00086913677,0.0026497205,0.0008248098,0.0024063052,0.0016631142,0.00080882123,0.0021031287],"category_scores_gemma":[0.03637947,0.00048778206,0.0016284814,0.001983216,0.0005259595,0.003528693,0.0014136194,0.0014105855,0.0004883943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022403868,0.0009529861,0.15881115,0.00092877314,0.0015121624,0.00035921152,0.0013460948,0.26337212,0.0026748856,0.015743906,0.010642017,0.5414163],"study_design_scores_gemma":[0.00005944762,0.00018060858,0.014171859,0.00008263959,0.00025557558,0.00008802687,0.00048178757,0.9749108,0.0015463931,0.00625459,0.0019396587,0.000028715041],"about_ca_topic_score_codex":0.009513522,"about_ca_topic_score_gemma":0.007475909,"teacher_disagreement_score":0.011602801,"about_ca_system_score_codex":0.001270568,"about_ca_system_score_gemma":0.0023108555,"threshold_uncertainty_score":0.061362207},"labels":[],"label_agreement":null},{"id":"W7131846106","doi":"10.5376/ijccr.2025.15.0030","title":"Accuracy Analysis of AI Prediction Models in Early Screening for Diabetes","year":2025,"lang":"","type":"article","venue":"International Journal of Clinical Case Reports","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Predictive modelling; Diabetes mellitus; MEDLINE; Risk assessment","score_opus":0.3394062598177158,"score_gpt":0.597893557271149,"score_spread":0.2584872974534332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131846106","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94203544,0.0035698707,0.04508792,0.00147052,0.00039436787,0.000083309875,0.0024079469,0.00082837977,0.004122139],"genre_scores_gemma":[0.9915941,0.00030245236,0.005748061,0.00007779117,0.00007191592,0.00001776115,0.0016381387,0.000026714053,0.00052315503],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971294,0.0010275876,0.00034965813,0.00040611252,0.0007869807,0.000300188],"domain_scores_gemma":[0.9585884,0.034124017,0.0011024348,0.0013924405,0.0042776056,0.0005151888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009243116,0.00096892304,0.0010030972,0.002722378,0.0005273643,0.0022314335,0.001205697,0.0012713785,0.0011736271],"category_scores_gemma":[0.035302814,0.0002522644,0.0009868587,0.0011919525,0.0003036686,0.0011253473,0.0006631839,0.0013040577,0.00050720514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002950302,0.0007749019,0.52040315,0.0002737034,0.0009413339,0.00036965485,0.00022207007,0.2706255,0.002122467,0.0015255165,0.006245444,0.193546],"study_design_scores_gemma":[0.000024277408,0.00025221973,0.02720501,0.000048937993,0.0002424593,0.0001427234,0.000087129825,0.9689549,0.0015603234,0.00091535214,0.0005493828,0.000017223438],"about_ca_topic_score_codex":0.012802411,"about_ca_topic_score_gemma":0.0064695673,"teacher_disagreement_score":0.012802411,"about_ca_system_score_codex":0.000987209,"about_ca_system_score_gemma":0.0010317566,"threshold_uncertainty_score":0.048882842},"labels":[],"label_agreement":null},{"id":"W7135204176","doi":"10.47363/jcbr/icbr2025/2025(7)5","title":"Artificial Intelligence and Cloud-Enabled Big Data Analytics for Genomic Research: Transforming Healthcare Management Through RealTime Decision Support Systems and Predictive Modeling","year":2025,"lang":"","type":"article","venue":"Journal of Clinical & Biomedical Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Optech (Canada)","funders":"","keywords":"Big data; Predictive analytics; Analytics; Decision support system; Health care; Cloud computing; Precision medicine; Personalized medicine; Transformative learning","score_opus":0.8516596710866454,"score_gpt":0.6781968466733077,"score_spread":0.1734628244133377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7135204176","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049252346,0.03314061,0.61930054,0.25068954,0.0030583772,0.0003679015,0.0017521145,0.0013610176,0.041077532],"genre_scores_gemma":[0.6763328,0.029960636,0.27149466,0.013204516,0.0029129058,0.00024321994,0.0012801533,0.00022423809,0.0043469416],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967784,0.0015720672,0.00017310122,0.00040712746,0.0008550988,0.00021425639],"domain_scores_gemma":[0.98923486,0.0072502727,0.0007584505,0.0011969438,0.0010125488,0.00054690544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064434176,0.0004890334,0.0005369129,0.0013999622,0.000904389,0.007240506,0.001243625,0.0014121211,0.0018229088],"category_scores_gemma":[0.014342664,0.00034151916,0.00059481576,0.0026989973,0.0026082105,0.0057916436,0.0030204295,0.0032511037,0.0005732824],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027290356,0.00027571368,0.015661508,0.0008405894,0.00017092959,0.0004726219,0.0009812596,0.038996454,0.0033121142,0.49908003,0.04386629,0.39606953],"study_design_scores_gemma":[0.00004910347,0.00009051075,0.0035287181,0.0006378142,0.000057705874,0.00031237004,0.0012550639,0.23759505,0.0028051517,0.6499263,0.10366226,0.00007996019],"about_ca_topic_score_codex":0.0047407025,"about_ca_topic_score_gemma":0.004588346,"teacher_disagreement_score":0.007240506,"about_ca_system_score_codex":0.0023299705,"about_ca_system_score_gemma":0.0051479856,"threshold_uncertainty_score":0.034076393},"labels":[],"label_agreement":null},{"id":"W7140104552","doi":"10.1109/icaiqsa67794.2025.11440617","title":"Designing an application for Chronic kidney disease (CKD) prediction","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Kidney disease; Disease; MEDLINE; Dialysis; Population","score_opus":0.14519330090523686,"score_gpt":0.4859785628774188,"score_spread":0.34078526197218195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7140104552","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03869704,0.00031989886,0.9212276,0.0006723531,0.00018255113,0.00046778255,0.00061539747,0.032716986,0.0051003722],"genre_scores_gemma":[0.33739752,0.0004828493,0.6495779,0.00053354114,0.00009949165,0.00048383023,0.0013713778,0.0006884593,0.009365024],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99955124,0.000099394834,0.0000372129,0.00012916402,0.0001283657,0.000054659315],"domain_scores_gemma":[0.99944586,0.00021342297,0.000024402892,0.00006416161,0.00020568461,0.000046461522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009672555,0.0007068066,0.00050908903,0.0006034177,0.0005041994,0.00077259564,0.0009610627,0.0009280386,0.0046846764],"category_scores_gemma":[0.0025843987,0.00037033064,0.000593218,0.00054046395,0.0001821671,0.00084724603,0.0010895462,0.0006818541,0.0025590896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008290509,0.000577422,0.028463162,0.0005008056,0.00017883665,0.0018229964,0.0006441107,0.044349976,0.05260727,0.0061032893,0.036256418,0.8276666],"study_design_scores_gemma":[0.000060144685,0.00031818872,0.008781117,0.00009947153,0.00013939213,0.0010675713,0.00017559786,0.8950242,0.036358606,0.007716568,0.050186418,0.000072767085],"about_ca_topic_score_codex":0.0025662722,"about_ca_topic_score_gemma":0.0023618673,"teacher_disagreement_score":0.0046846764,"about_ca_system_score_codex":0.0002075476,"about_ca_system_score_gemma":0.000638344,"threshold_uncertainty_score":0.01567185},"labels":[],"label_agreement":null},{"id":"W7140888381","doi":"10.1109/etcom66606.2025.11436411","title":"An Efficient TabNet-Based Obesity Classification and Risk Prediction System Optimized with Dove Flocking Optimizer","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Flocking (texture); Computation; Dove","score_opus":0.06610227187463627,"score_gpt":0.3905219271328124,"score_spread":0.3244196552581762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7140888381","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25137773,0.0014598271,0.69827193,0.0013379765,0.0005174905,0.0004633966,0.00536295,0.034177817,0.0070309634],"genre_scores_gemma":[0.6476149,0.00039551538,0.32806262,0.00076686003,0.00016230834,0.0004976569,0.012812121,0.00035175614,0.0093362825],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99975437,0.000036302605,0.000024927036,0.00009263558,0.000055656375,0.000036118472],"domain_scores_gemma":[0.999617,0.00011401729,0.000042271295,0.000031170977,0.00016552595,0.000030022298],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008204225,0.00085056777,0.0010118146,0.0010539814,0.00042074866,0.00074960757,0.0012257607,0.0007300305,0.0037197466],"category_scores_gemma":[0.0017322765,0.00035778526,0.00066130783,0.00068780105,0.00018715765,0.0008204636,0.0006406851,0.0006136371,0.001121793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011438587,0.00055070943,0.017416993,0.0002326422,0.00023926086,0.000402538,0.00009597095,0.40120807,0.007333748,0.0018577212,0.02841632,0.5411021],"study_design_scores_gemma":[0.000029007491,0.000046742978,0.0010478937,0.000008356699,0.000018454855,0.00003283752,0.000015006553,0.9959615,0.0012487711,0.0006834278,0.0008989699,0.0000090282865],"about_ca_topic_score_codex":0.017002244,"about_ca_topic_score_gemma":0.0172021,"teacher_disagreement_score":0.017002244,"about_ca_system_score_codex":0.0011299492,"about_ca_system_score_gemma":0.0011856045,"threshold_uncertainty_score":0.033806562},"labels":[],"label_agreement":null},{"id":"W7143599063","doi":"10.71465/ajdsa869","title":"Artificial Intelligence in Data Science: Bridging the Gap Between Theory and Application","year":2020,"lang":"","type":"article","venue":"American Journal of Data Science and Analysis","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bridging (networking); Cornerstone; Applications of artificial intelligence; Big data; Group method of data handling","score_opus":0.29854168697267885,"score_gpt":0.5115941980727564,"score_spread":0.21305251110007756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7143599063","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039902306,0.38045076,0.1847293,0.3954113,0.005750147,0.00010877537,0.00015624736,0.00026071022,0.029142566],"genre_scores_gemma":[0.15996663,0.53041106,0.22144713,0.056367837,0.027022855,0.00047395137,0.00027610981,0.00031160368,0.0037228873],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9719945,0.01694722,0.0017926104,0.0014169874,0.0073993686,0.0004493029],"domain_scores_gemma":[0.8265231,0.1582757,0.0019352918,0.006056523,0.005303562,0.0019058187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034915835,0.0009854462,0.0021429064,0.0068841362,0.0025338854,0.01727461,0.0026327004,0.0065290597,0.0027210086],"category_scores_gemma":[0.06851007,0.0009244353,0.00073690765,0.007987583,0.023058018,0.030315692,0.008908794,0.01766383,0.0011247976],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037803435,0.00007529843,0.0012706586,0.0021298337,0.00008501337,0.00015322384,0.0013157256,0.0016449582,0.0004849317,0.8157441,0.018743856,0.15831457],"study_design_scores_gemma":[0.000014851954,0.000034069613,0.00037218214,0.0023426705,0.000020310204,0.00019272763,0.00089415244,0.004364162,0.00024176434,0.87893826,0.112539396,0.000045438657],"about_ca_topic_score_codex":0.0013555133,"about_ca_topic_score_gemma":0.0012629763,"teacher_disagreement_score":0.034915835,"about_ca_system_score_codex":0.0038608173,"about_ca_system_score_gemma":0.0074409344,"threshold_uncertainty_score":0.18465477},"labels":[],"label_agreement":null},{"id":"W7162416197","doi":"10.32628/cseit24103218","title":"Comparative Analysis of Machine learning Model for Diabetes Prediction","year":2024,"lang":"","type":"article","venue":"International Journal of Scientific Research in Computer Science Engineering and Information Technology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Naive Bayes classifier; Diabetes mellitus; Artificial neural network; Random forest; Focus (optics); Stability (learning theory); Disease","score_opus":0.13960181104597635,"score_gpt":0.4712912813648319,"score_spread":0.33168947031885554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7162416197","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.756442,0.066260576,0.12939711,0.0071976925,0.0024270618,0.00043861632,0.013479088,0.003620898,0.020736944],"genre_scores_gemma":[0.95338655,0.0057204086,0.025456542,0.00040945533,0.00037548767,0.00015784525,0.011554187,0.00012165086,0.0028179197],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971956,0.0013362815,0.00024849502,0.00039929262,0.0005862649,0.00023402614],"domain_scores_gemma":[0.97936994,0.016775772,0.00040821437,0.0005907155,0.002580506,0.00027495986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00845056,0.0015113062,0.0019232488,0.0034562259,0.00062377495,0.0017465176,0.0014192348,0.0013805401,0.0033100354],"category_scores_gemma":[0.018125992,0.00025445074,0.0016522038,0.0025555575,0.00025592785,0.001496548,0.0006485358,0.0015723071,0.00079075125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031254685,0.0008014456,0.06004462,0.0008098534,0.0011180879,0.00034151736,0.00010006675,0.6964579,0.0004956577,0.0033407537,0.021909976,0.21145461],"study_design_scores_gemma":[0.000044964774,0.0003016572,0.007614189,0.00007486803,0.00016627238,0.000063900334,0.000077197175,0.98830354,0.00033801375,0.0017208854,0.0012681411,0.000026445681],"about_ca_topic_score_codex":0.026918042,"about_ca_topic_score_gemma":0.011648485,"teacher_disagreement_score":0.026918042,"about_ca_system_score_codex":0.0018231529,"about_ca_system_score_gemma":0.0014067086,"threshold_uncertainty_score":0.053522766},"labels":[],"label_agreement":null},{"id":"W756025961","doi":"","title":"Towards Privacy Compliance in the Management of Raw Genomic Data","year":2013,"lang":"en","type":"article","venue":"Infoscience (Ecole Polytechnique Fédérale de Lausanne)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Medicine; rs6265; Body mass index; Internal medicine; Type 2 diabetes; Dementia; Diabetes mellitus; Coronary artery disease; Disease; Psychiatry; Endocrinology; Brain-derived neurotrophic factor; Neurotrophic factors","score_opus":0.21273685753109256,"score_gpt":0.4616522796949062,"score_spread":0.24891542216381363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W756025961","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035098657,0.0012292332,0.89460963,0.042199913,0.0010300982,0.0014805009,0.0025127286,0.004324467,0.017514847],"genre_scores_gemma":[0.61060643,0.0014237895,0.35173407,0.014047682,0.0016964758,0.0019648108,0.0062754042,0.0013507863,0.0109005],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.76288193,0.14982924,0.022245076,0.013943158,0.045776937,0.0053235414],"domain_scores_gemma":[0.46320912,0.24605823,0.033184964,0.2193668,0.034967147,0.0032137414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1515893,0.0010765807,0.0020592296,0.00398318,0.004439153,0.021406913,0.005041356,0.007865852,0.0046071243],"category_scores_gemma":[0.38290852,0.0020697776,0.0019588163,0.004982778,0.0074867723,0.026715867,0.016010048,0.01021996,0.0034933668],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017767217,0.00053759187,0.033892598,0.0010166581,0.00052048406,0.0031658916,0.017528804,0.014885696,0.011328722,0.5199255,0.05210857,0.3433127],"study_design_scores_gemma":[0.00025173265,0.00032811027,0.00543432,0.0014822196,0.0003340655,0.0025158853,0.005157693,0.10393123,0.03594538,0.665812,0.17854431,0.00026294673],"about_ca_topic_score_codex":0.002905645,"about_ca_topic_score_gemma":0.0011375801,"teacher_disagreement_score":0.1515893,"about_ca_system_score_codex":0.0031040215,"about_ca_system_score_gemma":0.013803606,"threshold_uncertainty_score":0.80169046},"labels":[],"label_agreement":null},{"id":"W91933998","doi":"10.3402/ehtj.v4i0.7176","title":"Automatically tracking diabetes using information in physicians’ notes","year":2011,"lang":"en","type":"article","venue":"Emerging Health Threats Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Tracking (education); Diabetes mellitus; Medicine; Psychology","score_opus":0.2858084487539536,"score_gpt":0.4891519534471003,"score_spread":0.20334350469314666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W91933998","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87333035,0.0054102307,0.04933173,0.0023245348,0.0011365606,0.00030247774,0.05314612,0.0041563,0.010861708],"genre_scores_gemma":[0.915765,0.001554812,0.04853443,0.00033140165,0.00038199613,0.000070446324,0.029571416,0.00006049858,0.0037299653],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995685,0.000049841405,0.0000651815,0.00013930195,0.00013059338,0.00004655869],"domain_scores_gemma":[0.99677664,0.0016268647,0.00052910816,0.00022095184,0.00061350287,0.00023293961],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046627587,0.0004829593,0.00031884745,0.004615654,0.00028730158,0.00092878786,0.00060862355,0.0008855125,0.0011839563],"category_scores_gemma":[0.0033611949,0.00021266296,0.00033141702,0.00197393,0.00008421082,0.000731958,0.00046713452,0.0005556946,0.0012587749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016498452,0.0005249389,0.433433,0.00052212935,0.00020096151,0.0017255325,0.00042225907,0.0042966544,0.036583386,0.0005940284,0.033423007,0.48662415],"study_design_scores_gemma":[0.00022136382,0.00061261264,0.6113297,0.00050282304,0.00075921696,0.0033078087,0.0014760678,0.24896577,0.07328499,0.0021922556,0.057173915,0.00017356993],"about_ca_topic_score_codex":0.012243593,"about_ca_topic_score_gemma":0.020999037,"teacher_disagreement_score":0.012243593,"about_ca_system_score_codex":0.00047912548,"about_ca_system_score_gemma":0.0006510495,"threshold_uncertainty_score":0.024344683},"labels":[],"label_agreement":null}]}