{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1809,"total_is_capped":false,"direct_labels_cover":15,"predictions_cover":1809,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"42d488d18bcf","filters":{"venue":"JMIR Medical Informatics"}},"results":[{"id":"W2991379615","doi":"10.2196/14325","title":"Mapping ICD-10 and ICD-10-CM Codes to Phecodes: Workflow Development and Initial Evaluation","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":561,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; U.S. National Library of Medicine; National Heart, Lung, and Blood Institute; China Scholarship Council; National Institutes of Health; Cancer Research UK; Georgia Clinical and Translational Science Alliance; Vanderbilt University Medical Center; Vanderbilt University; National Institute of General Medical Sciences; American Heart Association","keywords":"ICD-10; Medicine; Systematized Nomenclature of Medicine; Biorepository; Health informatics; Diagnosis code; Informatics; Medicaid; Concordance; Medical classification; SNOMED CT; Electronic health record; Biobank; Health care; Internal medicine; Public health; Pathology; Terminology; Bioinformatics; Population","retraction":null,"screen_n_in":null,"score":{"opus":0.1801527069750413,"gpt":0.473251173470247,"spread":0.2930984664952057,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005036595,0.0002184614,0.0004227724,0.0002566511,0.0006176769,0.0000421734,0.000189798,0.0005021158,0.006321845],"category_scores_gemma":[0.00144918,0.0001769965,0.00002482073,0.0002867219,0.00009114132,0.000438767,0.0002686996,0.0008362001,0.002566348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002279036,"about_ca_system_score_gemma":0.001338993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001179801,"about_ca_topic_score_gemma":0.00002707811,"domain_scores_codex":[0.9956657,0.0002170961,0.001727983,0.0001536384,0.001583171,0.0006523779],"domain_scores_gemma":[0.997306,0.0007438862,0.0003902767,0.0002471481,0.0003138225,0.0009988297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001708077,0.00006414374,0.005343297,0.005917815,0.00004606635,0.000002029469,0.1805626,0.00001610908,0.000003990183,0.0009990542,0.06686356,0.7400106],"study_design_scores_gemma":[0.004889952,0.0003125053,0.01729879,0.004894572,0.00002629891,0.00001410963,0.03538783,0.1379372,0.00002184595,0.0004122267,0.7982081,0.0005966504],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9513605,0.0001004972,0.00464454,0.003135821,0.0007085172,0.002632802,0.00001063673,0.0001619928,0.03724466],"genre_scores_gemma":[0.92898,0.0002172792,0.02906704,0.03549918,0.0008715148,0.001263066,0.0004202019,0.00004636663,0.003635386],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7394139,"threshold_uncertainty_score":0.9982103,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2966351171","doi":"10.2196/12239","title":"Natural Language Processing of Clinical Notes on Chronic Diseases: Systematic Review","year":2019,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":556,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"European Commission","keywords":"Complement (music); Health records; Data science; Electronic health record; Disease; Computer science; Medicine; Artificial intelligence; Domain (mathematical analysis); Natural language processing; Intensive care medicine; Health care; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.0602109193283869,"gpt":0.4754059535831966,"spread":0.4151950342548097,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002504317,0.000542461,0.005397147,0.0002110642,0.00006408372,0.00009178375,0.003183822,0.000563784,0.00004990604],"category_scores_gemma":[0.007183242,0.000320185,0.0009574158,0.0007263151,0.0001285149,0.000343864,0.0006666356,0.002420403,0.0004983792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001765092,"about_ca_system_score_gemma":0.003171285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000323747,"about_ca_topic_score_gemma":0.000001064641,"domain_scores_codex":[0.9909462,0.0009131726,0.005197926,0.0003252834,0.002150254,0.0004671445],"domain_scores_gemma":[0.9909269,0.002932828,0.003755481,0.001764713,0.000171508,0.0004486106],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[2.995852e-7,0.00002421336,7.169738e-7,0.5464225,0.00002894567,0.000006806371,0.0001847705,2.064256e-7,7.193394e-11,0.0001356764,0.0001950275,0.4530008],"study_design_scores_gemma":[0.0001499824,0.0002083294,0.000001096145,0.9255975,0.0005139916,0.00006405531,0.00002194927,0.03238119,7.25615e-9,0.000003065649,0.04074357,0.0003152593],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[5.141871e-7,0.9936925,0.001398254,0.0001392598,0.0007754367,0.003435492,0.00001595586,0.0001843558,0.0003582987],"genre_scores_gemma":[0.00003164822,0.9964658,0.001310626,0.0014185,0.0002964849,0.0002662525,0.00009963722,0.00003296562,0.00007806092],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4526855,"threshold_uncertainty_score":0.999925,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2523834880","doi":"10.2196/medinform.5909","title":"Prediction of Sepsis in the Intensive Care Unit With Minimal Electronic Health Record Data: A Machine Learning Approach","year":2016,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":533,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Science Foundation","keywords":"Sepsis; Medicine; Systemic inflammatory response syndrome; Mews; Intensive care unit; Early warning score; Machine learning; Intensive care medicine; Electronic health record; Intensive care; Artificial intelligence; Medical record; Computer science; Emergency medicine; Health care; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.09192372534928704,"gpt":0.3520840859675537,"spread":0.2601603606182666,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004917458,0.0001411413,0.0003633841,0.000113329,0.00004876882,0.000008347599,0.0002203959,0.0000962015,0.00005419671],"category_scores_gemma":[0.0002849049,0.00006120035,0.00004064236,0.0002758473,0.0001198531,0.0001540814,0.00007812413,0.0004041847,0.000007559313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001451425,"about_ca_system_score_gemma":0.000481399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001201507,"about_ca_topic_score_gemma":0.0001025419,"domain_scores_codex":[0.9982139,0.0000885695,0.0005694938,0.0001226447,0.0006941438,0.0003112144],"domain_scores_gemma":[0.9987847,0.0002090999,0.0002378791,0.0004337711,0.0001890142,0.0001455282],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.001127985,0.001235468,0.5220627,0.001720969,0.0005513614,0.00003778833,0.09134942,0.000008237284,0.000008707699,0.0003963471,0.008800834,0.3727002],"study_design_scores_gemma":[0.03858306,0.02493467,0.2529663,0.007775469,0.0007554769,0.001206295,0.4490366,0.05670244,0.0002948889,0.00005896444,0.1669574,0.0007284317],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9893699,0.0007126307,0.000884939,0.006325717,0.00004259496,0.001155161,0.00009993733,0.00004986482,0.001359313],"genre_scores_gemma":[0.9949916,0.0008292733,0.0008681454,0.002503105,0.00005325818,0.0001116213,0.0006033689,0.00001231008,0.00002731308],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3719718,"threshold_uncertainty_score":0.2495678,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3044626901","doi":"10.2196/18599","title":"Role of Artificial Intelligence in Patient Safety Outcomes: Systematic Literature Review","year":2020,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":410,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Patient safety; Artificial intelligence; Systematic review; Clinical decision support system; Machine learning; MEDLINE; Decision tree; Computer science; Medicine; Decision support system; Health care","retraction":null,"screen_n_in":null,"score":{"opus":0.09932253929292394,"gpt":0.447337276712411,"spread":0.348014737419487,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001035615,0.0004647156,0.00425805,0.0003607723,0.00003821513,0.00002434566,0.0003980616,0.0007716524,0.0002475043],"category_scores_gemma":[0.003427281,0.0003027335,0.0006218384,0.001532755,0.0001155482,0.0001435409,0.0001185587,0.001544785,0.000352782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003010689,"about_ca_system_score_gemma":0.001579081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001124741,"about_ca_topic_score_gemma":0.000009336471,"domain_scores_codex":[0.9912014,0.0002575396,0.006655016,0.0002081937,0.001302501,0.0003753569],"domain_scores_gemma":[0.9962859,0.0007546243,0.001507419,0.000629695,0.0002900073,0.0005323783],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.000005348251,0.00008854576,0.000001413866,0.4822581,0.00003610345,0.00002085532,0.003230134,6.126008e-8,5.073532e-9,0.0002798126,0.0001172997,0.5139623],"study_design_scores_gemma":[0.00001029023,0.0001870941,3.870174e-7,0.8192677,0.0004159977,0.0001993472,0.002536441,0.0005274843,0.00000171439,0.0001591389,0.1764833,0.000211091],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00000487801,0.9931353,0.0001580005,0.0005097276,0.0003248588,0.005196785,0.00003303165,0.00004129743,0.0005960695],"genre_scores_gemma":[0.00002179623,0.9965646,0.0005144409,0.001854938,0.000148611,0.000554649,0.0002963479,0.0000314582,0.00001318604],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.5137512,"threshold_uncertainty_score":0.9999425,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6379363503337271,"gpt":0.576138637263599,"spread":0.06179771307012805,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007194215,0.0004519367,0.005352641,0.0003678824,0.0001551663,0.000005303252,0.001428595,0.0009125626,0.0001172807],"category_scores_gemma":[0.00388304,0.0002711798,0.0001359243,0.0002097154,0.0002780724,0.0002285579,0.001160586,0.001602623,0.0001858088],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003745081,"about_ca_system_score_gemma":0.00675558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001118172,"about_ca_topic_score_gemma":0.0006343382,"domain_scores_codex":[0.9870268,0.00241115,0.008382259,0.0002714931,0.00118565,0.0007226344],"domain_scores_gemma":[0.989731,0.003411867,0.003929962,0.002034359,0.0002579419,0.0006348458],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[5.992807e-7,0.000008312615,2.936277e-7,0.5218803,0.00001824181,0.000003211007,0.005884712,1.835638e-10,1.910022e-11,0.001177566,0.0006608944,0.4703658],"study_design_scores_gemma":[0.00003799154,0.00003793617,8.83772e-8,0.5593507,0.00007080776,0.00001147951,0.00998519,0.000007645433,8.31595e-10,0.0000347507,0.4303394,0.0001240554],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.871684e-7,0.9854204,0.00001618363,0.002463558,0.0005864212,0.008376206,0.0003199836,0.00005250637,0.00276452],"genre_scores_gemma":[0.000001555121,0.9950524,0.00006108318,0.002780095,0.0002583834,0.001422332,0.0002812204,0.00004529764,0.00009761291],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4702418,"threshold_uncertainty_score":0.999974,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3013605954","doi":"10.2196/17984","title":"Clinical Text Data in Machine Learning: Systematic Review","year":2020,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":367,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Medical Research Council","keywords":"Machine learning; Computer science; Artificial intelligence; Natural language processing; Bottleneck; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.4199594948799194,"gpt":0.57648193156965,"spread":0.1565224366897306,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004699088,0.0004290029,0.005280077,0.0001993378,0.00005426382,0.00003210644,0.001092413,0.0008920414,0.0006168273],"category_scores_gemma":[0.01831074,0.0002838132,0.0004217962,0.0008775865,0.0001458156,0.0001936788,0.0004587162,0.003656999,0.002821741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001844283,"about_ca_system_score_gemma":0.002946711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003529908,"about_ca_topic_score_gemma":0.00001519296,"domain_scores_codex":[0.9902308,0.0006562583,0.007115846,0.0003222208,0.001262574,0.0004123219],"domain_scores_gemma":[0.9943209,0.001665855,0.001474893,0.001496939,0.0001262605,0.0009152114],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002062128,0.00007037138,0.00001462189,0.5556247,0.0000488886,0.00003347135,0.0001969917,5.201394e-9,4.778219e-11,0.00001464423,0.003569853,0.4404244],"study_design_scores_gemma":[0.00002659393,0.00009405671,2.723553e-7,0.474997,0.000810509,0.000178963,0.0001668211,0.001389239,4.193693e-9,0.000004559457,0.5222008,0.0001311609],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[5.788535e-7,0.9917862,0.00008866414,0.001591573,0.000461329,0.004882599,0.0000249821,0.00009229422,0.001071826],"genre_scores_gemma":[0.000001994308,0.9906178,0.0003732792,0.005456113,0.0005901615,0.0003605475,0.002327659,0.00004499393,0.0002274596],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.5186309,"threshold_uncertainty_score":0.9999614,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963852062","doi":"10.2196/10010","title":"Artificial Intelligence Versus Clinicians in Disease Diagnosis: Systematic Review","year":2019,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":365,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Medical diagnosis; CINAHL; MEDLINE; Scopus; Artificial intelligence; Medicine; Systematic review; Referral; Disease; Health care; Receiver operating characteristic; Applications of artificial intelligence; Cochrane Library; Inclusion and exclusion criteria; Health technology; Machine learning; Computer science; Meta-analysis; Family medicine; Alternative medicine; Pathology; Psychological intervention; Psychiatry","retraction":null,"screen_n_in":null,"score":{"opus":0.3838209004827958,"gpt":0.5453718196699511,"spread":0.1615509191871553,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002108748,0.0005597295,0.004184623,0.0004398038,0.00006246364,0.00004751672,0.000604298,0.0007943081,0.0006895385],"category_scores_gemma":[0.008312445,0.0004061899,0.0007920318,0.001086251,0.0001661253,0.0002036199,0.0001270492,0.001712758,0.004990342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005207263,"about_ca_system_score_gemma":0.003806854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002646004,"about_ca_topic_score_gemma":0.00003180598,"domain_scores_codex":[0.9908738,0.0003184905,0.006419312,0.0003133648,0.001449563,0.0006255326],"domain_scores_gemma":[0.9938765,0.002438634,0.001307037,0.001169877,0.0002131421,0.0009948252],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00001817297,0.0001655807,0.000004265168,0.5736704,0.0000459775,0.00002743389,0.0004113599,1.27097e-7,5.215562e-11,0.0001969426,0.0006225558,0.4248371],"study_design_scores_gemma":[0.00002163551,0.0001873133,4.148104e-7,0.8559833,0.0024828,0.00002831883,0.0009279452,0.000395269,1.077483e-7,0.0001280269,0.1395047,0.0003402009],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000007946037,0.9876137,0.0001011522,0.000945826,0.001886474,0.008885319,0.00002470158,0.00008169924,0.0004531866],"genre_scores_gemma":[0.00002656183,0.992136,0.0000893381,0.002926538,0.0005219319,0.003807338,0.0003628341,0.00005359401,0.00007586357],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4244969,"threshold_uncertainty_score":0.999839,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2799930623","doi":"10.2196/medinform.8912","title":"Reasons For Physicians Not Adopting Clinical Decision Support Systems: Critical Analysis","year":2018,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":357,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Clinical decision support system; Computer science; Adaptation (eye); Task (project management); Decision support system; Implementation; User requirements document; Knowledge management; Artificial intelligence; Software engineering; Systems engineering; Engineering; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.2051662262378013,"gpt":0.5933476856428958,"spread":0.3881814594050944,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.02002296,0.0009204492,0.007559279,0.0008157706,0.001201198,0.00007844587,0.001580741,0.004619899,0.0006232804],"category_scores_gemma":[0.01860843,0.0006889491,0.002493063,0.001858972,0.000475964,0.0003211354,0.0005182163,0.005315546,0.003021208],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001197297,"about_ca_system_score_gemma":0.01094263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005564371,"about_ca_topic_score_gemma":0.0001257451,"domain_scores_codex":[0.9781977,0.002810186,0.01311126,0.0006781533,0.002529308,0.002673423],"domain_scores_gemma":[0.9565156,0.03475952,0.004051689,0.001758761,0.001151828,0.001762683],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003072511,0.0001455411,0.00004334495,0.1245306,0.000955091,0.000008722757,0.0009656415,2.073623e-7,4.377338e-10,0.001496157,0.1771304,0.6946935],"study_design_scores_gemma":[0.0006455277,0.0004604379,0.000004691552,0.06323928,0.003625694,0.00002634984,0.001423919,0.006061855,2.398453e-9,0.0000157721,0.9239227,0.0005737181],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002247342,0.8488369,0.1138742,0.0004319233,0.01356045,0.01547262,0.001222131,0.0007347596,0.005844523],"genre_scores_gemma":[0.00001341914,0.9712626,0.009275073,0.002895002,0.00843108,0.005599305,0.001070847,0.0001832209,0.0012695],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7467923,"threshold_uncertainty_score":0.9995562,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3040316091","doi":"10.2196/20359","title":"Utilization Barriers and Medical Outcomes Commensurate With the Use of Telehealth Among Older Adults: Systematic Review","year":2020,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Telemedicine and Telehealth Implementation","field":"Medicine","cited_by":283,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Telehealth; CINAHL; eHealth; Psychological intervention; Medicine; MEDLINE; mHealth; Telecare; Telemedicine; Systematic review; Quality of life (healthcare); Health care; Gerontology; Nursing","retraction":null,"screen_n_in":null,"score":{"opus":0.07198293453629405,"gpt":0.4006316719725751,"spread":0.328648737436281,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001575471,0.0005508383,0.004495677,0.0001805534,0.0001242999,0.00002854296,0.0003369692,0.0004568384,0.0003688047],"category_scores_gemma":[0.003662327,0.000251418,0.0002414642,0.000752144,0.0004682879,0.0002343238,0.000137949,0.001212671,0.00001271174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000106999,"about_ca_system_score_gemma":0.001933822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003830469,"about_ca_topic_score_gemma":0.00003353116,"domain_scores_codex":[0.9923134,0.0004651326,0.003794865,0.0002144862,0.002778184,0.0004339556],"domain_scores_gemma":[0.993874,0.001381563,0.002350919,0.0006128562,0.0002635931,0.001517139],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00001044426,0.00002827574,0.0002344427,0.7746036,0.0002719242,0.00002991883,0.001276063,5.291565e-9,9.156195e-11,0.00003738818,0.01323143,0.2102765],"study_design_scores_gemma":[0.001316493,0.0003532744,0.00009877546,0.6859102,0.002874285,0.0003974459,0.001465132,0.0003837819,2.697374e-8,4.479366e-7,0.3070023,0.0001978719],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001166843,0.9804227,0.0005233209,0.007224106,0.00009503507,0.01141419,0.00006948032,0.00009161495,0.00004283644],"genre_scores_gemma":[0.00005549325,0.973966,0.000242254,0.024248,0.00008159922,0.0007787775,0.0005521089,0.00005166717,0.00002410638],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.2937709,"threshold_uncertainty_score":0.9999938,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3172260675","doi":"10.2196/21929","title":"The Fast Health Interoperability Resources (FHIR) Standard: Systematic Literature Review of Implementations, Applications, Challenges and Opportunities","year":2021,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":280,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Interoperability; Computer science; Systematic review; Documentation; Health care; Health information technology; Health informatics; Implementation; Data science; Knowledge management; MEDLINE; Medicine; World Wide Web; Software engineering; Nursing; Public health","retraction":null,"screen_n_in":null,"score":{"opus":0.1448242637845235,"gpt":0.507788053023976,"spread":0.3629637892394525,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0145686,0.0005168127,0.004424529,0.0001813504,0.0009217449,0.00004941451,0.0007865746,0.0006198848,0.0001142053],"category_scores_gemma":[0.001090296,0.0002886101,0.0003171163,0.0003923769,0.0002710251,0.0001731195,0.0004394908,0.002441706,0.000022812],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007525298,"about_ca_system_score_gemma":0.007525947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001182778,"about_ca_topic_score_gemma":0.0001129858,"domain_scores_codex":[0.9827787,0.00646522,0.008120391,0.0002751483,0.001507649,0.0008529345],"domain_scores_gemma":[0.988319,0.004354475,0.00464203,0.00128364,0.0007513925,0.0006494011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001010362,0.0000117824,2.41076e-7,0.5431655,0.00007642024,7.326532e-7,0.006827607,3.581029e-10,9.355734e-11,0.002641192,0.005007048,0.4422685],"study_design_scores_gemma":[0.0000920525,0.0000658322,1.707831e-7,0.4746467,0.0000864215,0.00004030851,0.01675808,0.000002018303,1.235397e-9,0.00001265269,0.5081951,0.0001006823],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[4.585018e-7,0.9807556,0.00009812854,0.004041559,0.0002847524,0.01330878,0.0003794161,0.00007042943,0.001060829],"genre_scores_gemma":[3.437705e-7,0.9850432,0.0001441723,0.002529575,0.0002578176,0.01108975,0.0005223663,0.00004732901,0.0003654734],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.503188,"threshold_uncertainty_score":0.9999566,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2286621504","doi":"10.2196/medinform.4514","title":"The Impact of Information Technology on Patient Engagement and Health Behavior Change: A Systematic Review of the Literature","year":2016,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Digital Mental Health Interventions","field":"Psychology","cited_by":273,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"PsycINFO; Usability; Psychological intervention; Inclusion (mineral); MEDLINE; Health care; Medicine; Health information technology; Behavior change; Medical education; Psychology; Applied psychology; Nursing; Computer science; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.07575827349535766,"gpt":0.4797367282505871,"spread":0.4039784547552294,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001783695,0.0003171979,0.001583159,0.0002732399,0.0001164868,0.0000296458,0.0006943406,0.0003730123,0.00005897012],"category_scores_gemma":[0.0004309328,0.0001211005,0.000564431,0.0006186921,0.000250969,0.0002066422,0.0003344298,0.0007404278,0.00007886109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002983149,"about_ca_system_score_gemma":0.0003191645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007553004,"about_ca_topic_score_gemma":0.000001077564,"domain_scores_codex":[0.994688,0.0004564757,0.003685206,0.0000845854,0.0007503503,0.0003353582],"domain_scores_gemma":[0.9944769,0.0003167148,0.003967231,0.0009197033,0.0001462515,0.000173225],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.000001544719,0.00008855971,5.575192e-7,0.4932494,0.00007424157,3.085145e-7,0.0009741182,4.475964e-10,1.134432e-10,0.002251991,0.001923512,0.5014358],"study_design_scores_gemma":[0.0001458561,0.0009194015,0.00001170225,0.9011722,0.0001400692,0.00010188,0.0003068248,6.979384e-7,6.143667e-8,0.00004581865,0.09706143,0.00009401372],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001533743,0.9861135,0.000005350639,0.0006993701,0.0005297603,0.01153114,0.0004657067,0.00002434649,0.0006154655],"genre_scores_gemma":[0.0001609087,0.9916071,0.00001636167,0.0007174161,0.00002085775,0.007340802,0.00007244582,0.0000146189,0.00004944605],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.5013418,"threshold_uncertainty_score":0.4938334,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2801958627","doi":"10.2196/medinform.8805","title":"Secure Logistic Regression Based on Homomorphic Encryption: Design and Evaluation","year":2018,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Cryptography and Data Security","field":"Computer Science","cited_by":247,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Institute of General Medical Sciences; National Institute of Biomedical Imaging and Bioengineering; National Human Genome Research Institute; National Research Foundation of Korea; National Research Foundation","keywords":"Homomorphic encryption; Computer science; Encryption; Logistic regression; Machine learning; Cloud computing; Discriminative model; Support vector machine; Computation; Data mining; Artificial intelligence; Outsourcing; Classifier (UML); Algorithm; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.05255794342517325,"gpt":0.3334524473528274,"spread":0.2808945039276542,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001578264,0.000130943,0.0001318922,0.0001418054,0.0001900051,0.0001272619,0.0004705136,0.0001726161,0.0001987481],"category_scores_gemma":[0.000291482,0.00009467638,0.00003211098,0.0003966504,0.0002744684,0.0005082685,0.0001350234,0.0002439902,0.0001049474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000250184,"about_ca_system_score_gemma":0.0001932519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001477745,"about_ca_topic_score_gemma":0.000001098432,"domain_scores_codex":[0.997924,0.0001475895,0.0003362378,0.0001430946,0.001246623,0.0002024828],"domain_scores_gemma":[0.998702,0.0002668625,0.0001350033,0.0004866763,0.0001664546,0.0002430055],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002272788,0.0007340004,0.0004868955,0.0004835666,0.00004040034,0.00004240918,0.0192977,0.0002759455,0.000048278,0.2561085,0.09616396,0.6260911],"study_design_scores_gemma":[0.0006806469,0.0004091094,0.0007113006,0.0001866493,0.00000783454,0.00001707297,0.0000750308,0.9853123,0.00007701844,0.009444594,0.002947939,0.000130441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01336133,0.00003139083,0.9841853,0.0006870196,0.0002707239,0.0003976868,0.000003465664,0.0001680787,0.000895042],"genre_scores_gemma":[0.877753,0.00002465083,0.1194472,0.002513952,0.0001691632,0.00005887715,0.00002602613,0.000005852524,0.000001386723],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9850364,"threshold_uncertainty_score":0.386079,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4285315819","doi":"10.2196/35724","title":"Fast Healthcare Interoperability Resources (FHIR) for Interoperability in Health Research: Systematic Review","year":2022,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":233,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Deutsche Forschungsgemeinschaft","keywords":"Interoperability; Systematic review; Standardization; Health care; Computer science; MEDLINE; Data science; Health informatics; Medicine; World Wide Web; Public health; Knowledge management; Nursing; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.4284319628944909,"gpt":0.6008191873530828,"spread":0.1723872244585919,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.09547801,0.001104703,0.01162779,0.001123671,0.001766546,0.00005343191,0.003312147,0.001641276,0.001965525],"category_scores_gemma":[0.01954969,0.0007772116,0.001025646,0.002667849,0.000432445,0.0003178845,0.00176125,0.01652782,0.0006014967],"about_ca_system_candidate":true,"about_ca_system_consensus":true,"about_ca_system_score_codex":0.01491995,"about_ca_system_score_gemma":0.02181662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001396788,"about_ca_topic_score_gemma":0.002627614,"domain_scores_codex":[0.9283589,0.0417725,0.02041793,0.001005272,0.004311714,0.004133657],"domain_scores_gemma":[0.9728404,0.01585815,0.005144739,0.003214227,0.000793329,0.002149188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001902407,0.000165605,0.000005871415,0.8400804,0.00006672454,0.000004829396,0.01686912,1.864035e-8,3.377856e-10,0.0002092051,0.01396885,0.1286104],"study_design_scores_gemma":[0.0003201593,0.000471319,3.587842e-7,0.4816506,0.0000501391,0.00003079287,0.009369648,0.00005428445,9.384734e-10,0.000034185,0.5077536,0.000264929],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001745355,0.9302247,0.00004485455,0.004200932,0.001479597,0.06243828,0.0003658919,0.0002499905,0.0009783277],"genre_scores_gemma":[0.000009231538,0.9231895,0.000142497,0.008814177,0.0004566754,0.06568897,0.0006152436,0.0001815823,0.0009021541],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4937848,"threshold_uncertainty_score":0.9996548,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2998524378","doi":"10.2196/15182","title":"Real-World Integration of a Sepsis Deep Learning Technology Into Routine Clinical Care: Implementation Study","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":233,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Duke Institute for Health Innovation; John D. and Catherine T. MacArthur Foundation","keywords":"Workflow; Health care; Artificial intelligence; Quality management; Multidisciplinary approach; Medicine; Clinical decision support system; Deep learning; Computer science; Knowledge management; Machine learning; Engineering; Decision support system; Management system; Operations management","retraction":null,"screen_n_in":null,"score":{"opus":0.05064018169356722,"gpt":0.4546535408726954,"spread":0.4040133591791282,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005903703,0.0001597339,0.000553052,0.0003337549,0.00004678632,0.0000124364,0.0001211654,0.0001900907,0.000668156],"category_scores_gemma":[0.0002244988,0.0001164793,0.0001240388,0.0005281623,0.00008570871,0.0001186698,0.000103709,0.0004658215,0.0001211192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001668615,"about_ca_system_score_gemma":0.0001519826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002019314,"about_ca_topic_score_gemma":0.0003851218,"domain_scores_codex":[0.9975042,0.00007622963,0.001356738,0.0001364822,0.0007225323,0.0002038221],"domain_scores_gemma":[0.9986742,0.0002007708,0.0004032943,0.0003215357,0.0002285101,0.0001717576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000643794,0.0006619318,0.7615997,0.0001315675,0.0001533441,0.000006208728,0.01226333,0.000001730946,0.00001956752,0.0002313045,0.0001887145,0.2246782],"study_design_scores_gemma":[0.01506278,0.008132896,0.6720094,0.000490042,0.0005123068,0.00001713553,0.2910488,0.0056321,0.002567916,0.00008926806,0.004133672,0.0003036835],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9954977,0.00004315611,0.0001437765,0.0006956903,0.0001576133,0.0013953,0.000001466671,0.00009393013,0.001971337],"genre_scores_gemma":[0.9962221,0.0001471997,0.002835839,0.0003286429,0.00006204942,0.0001602594,0.0001658325,0.00001417955,0.00006389771],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2787855,"threshold_uncertainty_score":0.731584,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2982280746","doi":"10.2196/16023","title":"Sentiment Analysis in Health and Well-Being: Systematic Review","year":2019,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":218,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Cardiff University","keywords":"Computer science; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.03407258699547368,"gpt":0.3668961208757042,"spread":0.3328235338802305,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003019609,0.0004219867,0.005139409,0.0009963352,0.0000591528,0.0002090771,0.001272137,0.0002436379,0.0001145318],"category_scores_gemma":[0.0001384296,0.0002864803,0.0007882209,0.002903619,0.00003725314,0.000327478,0.0005970051,0.0005266115,0.000369091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001517477,"about_ca_system_score_gemma":0.0005143803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005505005,"about_ca_topic_score_gemma":0.000001937849,"domain_scores_codex":[0.993538,0.0004287281,0.003848019,0.0003060836,0.001445353,0.0004338619],"domain_scores_gemma":[0.996158,0.0003575417,0.001877931,0.001075439,0.00004386912,0.0004871999],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[7.663886e-8,0.00002863307,0.000004909938,0.9390082,0.000632974,0.000004388871,0.0008645929,4.934122e-7,4.269551e-11,0.001452213,0.0009455462,0.05705802],"study_design_scores_gemma":[0.000127164,0.00003339421,3.261767e-7,0.7217528,0.001897993,0.00002553076,0.0001147402,0.03412141,5.693665e-9,0.00001354768,0.241582,0.0003310878],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[2.387246e-7,0.9905993,0.006327736,0.0002370532,0.0001298639,0.001823375,9.522548e-7,0.00004513153,0.0008363593],"genre_scores_gemma":[5.667222e-7,0.9952673,0.001651008,0.002460033,0.00002370451,0.0001496049,0.00008779566,0.00001100702,0.0003490365],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.2406365,"threshold_uncertainty_score":0.9999588,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3118996476","doi":"10.2196/24207","title":"Federated Learning of Electronic Health Records to Improve Mortality Prediction in Hospitalized Patients With COVID-19: Machine Learning Approach","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":211,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Center for Advancing Translational Sciences","keywords":"Machine learning; Artificial intelligence; Lasso (programming language); Computer science; Logistic regression; Generalizability theory; Health records; Multilayer perceptron; Predictive modelling; Deep learning; Electronic health record; Health care; Artificial neural network; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01285349720121259,"gpt":0.3090294637525138,"spread":0.2961759665513012,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001892889,0.0002420985,0.0005375631,0.0002232458,0.0002511624,0.00009855992,0.0004791382,0.0001978199,0.00006693904],"category_scores_gemma":[0.002097124,0.0002095435,0.00005732744,0.001360932,0.00005886731,0.000438725,0.0003559044,0.001779896,0.000007816302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000569745,"about_ca_system_score_gemma":0.002808928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008109197,"about_ca_topic_score_gemma":0.0002171662,"domain_scores_codex":[0.99562,0.0006306219,0.001256842,0.0003417462,0.00144362,0.0007072138],"domain_scores_gemma":[0.9977359,0.000167436,0.0006091835,0.0003708344,0.0002853054,0.0008313299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008009739,0.0004417449,0.92623,0.001825508,0.00005749016,0.00001000813,0.01675447,0.01346942,0.000001243598,0.001389234,0.0002347273,0.03950612],"study_design_scores_gemma":[0.002095596,0.001506024,0.09360258,0.0001714916,0.000004617181,0.00001287573,0.00053052,0.8984975,0.000008311243,0.00005656392,0.003280792,0.0002331143],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6007665,0.00006186117,0.3960352,0.001390027,0.0001433923,0.0008028501,0.000009229083,0.0002570757,0.0005337837],"genre_scores_gemma":[0.9826149,0.00003804366,0.01438789,0.002347361,0.00003412112,0.0001188615,0.0003286792,0.00002154445,0.0001085783],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8850281,"threshold_uncertainty_score":0.8544935,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2966705814","doi":"10.2196/13042","title":"Electronic Consultation in Primary Care Between Providers and Patients: Systematic Review","year":2019,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Healthcare Systems and Technology","field":"Business, Management and Accounting","cited_by":208,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Primary care; Medicine; Telehealth; Systematic review; Medical emergency; MEDLINE; Telemedicine; Family medicine; Health care","retraction":null,"screen_n_in":null,"score":{"opus":0.02154616885431484,"gpt":0.3067114982341452,"spread":0.2851653293798304,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00086215,0.0003776071,0.002886244,0.0004732522,0.0000496781,0.0000923902,0.0003970416,0.0006847968,0.00001533574],"category_scores_gemma":[0.0008050394,0.0002670541,0.0001472616,0.0006656986,0.00006554659,0.0006252729,0.0002214895,0.0008735688,0.0003201319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003591094,"about_ca_system_score_gemma":0.0005808261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008091085,"about_ca_topic_score_gemma":0.00003954359,"domain_scores_codex":[0.9962094,0.00006187493,0.002482989,0.0001860078,0.0005948266,0.0004648602],"domain_scores_gemma":[0.997618,0.0002199457,0.001549162,0.0003721563,0.0002022209,0.00003852628],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[2.623336e-7,0.000007111951,0.00005452568,0.6760174,0.00002574064,7.666676e-7,0.00006881739,2.079839e-9,4.299702e-11,0.0004914053,0.0002315041,0.3231025],"study_design_scores_gemma":[0.0002682105,0.00001487031,0.0000097535,0.5152704,0.0004064213,0.000003212851,0.0001854762,0.00001011745,4.047105e-10,0.0000233906,0.4836088,0.0001993212],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00004822712,0.9891062,0.00001158739,0.00008412377,0.0001280375,0.008554025,0.00001036699,0.0001036157,0.001953843],"genre_scores_gemma":[0.0001268071,0.9958821,0.00001507174,0.001846156,0.0001346681,0.000863455,0.001076671,0.00003568015,0.00001941333],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4833773,"threshold_uncertainty_score":0.9999782,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3035916362","doi":"10.2196/19866","title":"The Role of Health Technology and Informatics in a Global Public Health Emergency: Practices and Implications From the COVID-19 Pandemic","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":198,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Pandemic; Telemedicine; Health care; Medicine; Public health; Telehealth; Coronavirus disease 2019 (COVID-19); Middle East respiratory syndrome; Digital health; Global health; Health informatics; Medical emergency; Business; Disease; Economic growth; Nursing; Infectious disease (medical specialty)","retraction":null,"screen_n_in":null,"score":{"opus":0.089719897220137,"gpt":0.4288465134815742,"spread":0.3391266162614371,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001838328,0.0001517304,0.0004272735,0.00009431294,0.0002865068,0.00004251957,0.0003518937,0.0001871089,0.0000249904],"category_scores_gemma":[0.008788922,0.00009209327,0.00003470657,0.001069298,0.0004832593,0.0002387505,0.0003274899,0.0005817592,0.000005394623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002454252,"about_ca_system_score_gemma":0.003172158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005980206,"about_ca_topic_score_gemma":0.0006703217,"domain_scores_codex":[0.9972723,0.0001340829,0.001548434,0.0001069739,0.0005500778,0.0003881128],"domain_scores_gemma":[0.9962587,0.001146427,0.00136187,0.0003968429,0.00008680202,0.0007493488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003739995,0.0001374928,0.6700038,0.000826003,0.00007962176,7.882616e-7,0.04921738,0.00000289233,0.000002305155,0.007073464,0.02452814,0.2480908],"study_design_scores_gemma":[0.001604374,0.0003974222,0.06065296,0.0001495914,0.00002563128,0.0001028102,0.04354992,0.01338143,0.000001110269,0.003318487,0.876684,0.0001323063],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2392131,0.00384897,0.001112542,0.7546793,0.00003828499,0.000878224,0.00005905716,0.0000939172,0.00007652809],"genre_scores_gemma":[0.7693472,0.01238645,0.001490709,0.2164979,0.00006505313,0.0001449622,0.0000545203,0.00001110422,0.000002074538],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8521558,"threshold_uncertainty_score":0.9995605,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2797870998","doi":"10.2196/medinform.7744","title":"Privacy-Preserving Patient Similarity Learning in a Federated Environment: Development and Analysis","year":2018,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":191,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; U.S. National Library of Medicine; National Institute of General Medical Sciences; National Human Genome Research Institute; National Heart, Lung, and Blood Institute; National Science Foundation","keywords":"Homomorphic encryption; Computer science; Hash function; Similarity (geometry); Encryption; Context (archaeology); Matching (statistics); Data mining; Information retrieval; Computer security; Artificial intelligence; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.01643724248623696,"gpt":0.2847583559313596,"spread":0.2683211134451227,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008252106,0.0001462517,0.000250311,0.0002751961,0.000264527,0.0001476257,0.0005883512,0.0001513344,0.0001479569],"category_scores_gemma":[0.000451463,0.0001288398,0.00003020032,0.0006994372,0.00008729164,0.0003797609,0.001344448,0.0006406764,0.00004455971],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001057336,"about_ca_system_score_gemma":0.000161226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004459916,"about_ca_topic_score_gemma":0.0000514914,"domain_scores_codex":[0.9977294,0.0001562473,0.000725251,0.0001839573,0.0008384029,0.0003667779],"domain_scores_gemma":[0.9989753,0.0001471644,0.0002004561,0.0003266198,0.00004706816,0.0003033686],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001408844,0.0001465081,0.3122685,0.0003227435,0.0001412049,0.00003902906,0.1509317,0.0008547208,0.000002672115,0.000756863,0.0003098291,0.5342122],"study_design_scores_gemma":[0.0002393589,0.00009780368,0.05866943,0.00006355751,0.000005821033,0.000006473233,0.0004305706,0.9215349,0.0000407152,0.00005815802,0.01869273,0.0001604952],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8414192,0.00003047665,0.1556727,0.001230226,0.00005280377,0.0002215305,3.923476e-7,0.0001342726,0.001238441],"genre_scores_gemma":[0.9246827,0.00001367281,0.07418453,0.001017112,0.00002270791,0.00003028337,0.00001240199,0.000005646682,0.00003096979],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9206802,"threshold_uncertainty_score":0.5253935,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4220718380","doi":"10.2196/36388","title":"Evaluation and Mitigation of Racial Bias in Clinical Machine Learning Models: Scoping Review","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":184,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Scopus; Machine learning; Artificial intelligence; MEDLINE; Computer science; Systematic review; Publication bias; Meta-analysis; Selection bias; Medicine; Data science; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.4425374768641928,"gpt":0.5513769212540904,"spread":0.1088394443898976,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00789671,0.00006719551,0.0003046022,0.0001141808,0.00008459113,0.000004859947,0.00005777366,0.00008260001,0.0004548557],"category_scores_gemma":[0.003249428,0.00006126336,0.00004666489,0.0002860903,0.0000796749,0.0001588347,0.00006177017,0.0006064842,0.000004797317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009425062,"about_ca_system_score_gemma":0.0009465854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006516064,"about_ca_topic_score_gemma":0.00005043349,"domain_scores_codex":[0.996699,0.0003661211,0.00155018,0.00007731829,0.001178087,0.0001292835],"domain_scores_gemma":[0.998852,0.0003361634,0.0003476046,0.000111668,0.0002112148,0.0001414096],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007017574,0.0002239622,0.01824749,0.007771036,0.0000148457,0.000002430774,0.01335526,0.0003963187,0.000002110621,0.0003254129,0.0002712364,0.9593197],"study_design_scores_gemma":[0.0003417532,0.0005349993,0.001182067,0.01755688,0.00008226824,0.00003918243,0.00441375,0.9740191,0.00004446064,0.001264007,0.0004163847,0.0001051369],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.983185,0.009730686,0.0006235517,0.002671502,0.0002974792,0.001972481,0.000002309035,0.00002591997,0.001491083],"genre_scores_gemma":[0.9885899,0.008074421,0.0005176233,0.002360797,0.0001076008,0.0002137345,0.000114026,0.00000700374,0.00001483589],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9736228,"threshold_uncertainty_score":0.4980351,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2972483465","doi":"10.2196/14830","title":"Fine-Tuning Bidirectional Encoder Representations From Transformers (BERT)–Based Models on Large-Scale Electronic Health Record Notes: An Empirical Study","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":175,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Heart, Lung, and Blood Institute; U.S. Department of Veterans Affairs","keywords":"Normalization (sociology); Computer science; Natural language processing; Named-entity recognition; Artificial intelligence; SNOMED CT; Transformer; Encoder; Language model; Information retrieval; Health records; Electronic health record; Machine learning; Task (project management); Health care; Linguistics; Terminology","retraction":null,"screen_n_in":null,"score":{"opus":0.03612909331573435,"gpt":0.3803868410582724,"spread":0.3442577477425381,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001271333,0.0002623808,0.0004193122,0.0002623851,0.0003168323,0.0001205712,0.0008935378,0.0002031376,0.0003804799],"category_scores_gemma":[0.0001402801,0.000230055,0.0001114307,0.0006606716,0.00004212408,0.0009654575,0.0001067666,0.001394664,0.0001491079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002892932,"about_ca_system_score_gemma":0.001496106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000662384,"about_ca_topic_score_gemma":0.001577355,"domain_scores_codex":[0.9956073,0.0004211962,0.001047682,0.0004072821,0.001725767,0.0007907955],"domain_scores_gemma":[0.9973677,0.0008073308,0.0002791842,0.0007923749,0.0001204452,0.0006329571],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003461954,0.005765596,0.3067727,0.0005980383,0.0002305933,0.00002501595,0.2637541,0.09083769,0.000006233219,0.004687914,0.00646803,0.3205079],"study_design_scores_gemma":[0.001359873,0.001363571,0.006813373,0.00009600774,0.000004757541,0.000004629826,0.001941036,0.9849116,0.000004230589,0.0006881669,0.002575147,0.0002376679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4348921,0.00001644606,0.556284,0.006170683,0.0003909167,0.0009440218,0.00001838349,0.00034014,0.0009433262],"genre_scores_gemma":[0.964292,0.00001124929,0.02689104,0.008243214,0.0001436545,0.0001533282,0.0001630395,0.00002740927,0.00007510203],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8940738,"threshold_uncertainty_score":0.9381369,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2906029872","doi":"10.2196/11949","title":"Using Blockchain Technology to Manage Clinical Trials Data: A Proof-of-Concept Study","year":2018,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":174,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false},"ca_institutions":"Queen's University","funders":"Southeastern Ontario Academic Medical Organization","keywords":"Blockchain; Proof of concept; Computer science; Clinical trial; Data management; Data science; Process management; Medicine; Data mining; Computer security; Business; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.1397321832481064,"gpt":0.4593035411746271,"spread":0.3195713579265207,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008157441,0.0001762358,0.0007323388,0.0004252156,0.0001512891,0.00004203401,0.004492699,0.0005147823,0.00003324909],"category_scores_gemma":[0.002458716,0.000140118,0.00006907343,0.001686783,0.0006920641,0.0001797662,0.003381909,0.0005848469,0.00003654362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002295401,"about_ca_system_score_gemma":0.0001941863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008861721,"about_ca_topic_score_gemma":0.00001969272,"domain_scores_codex":[0.9961365,0.0002484776,0.002243758,0.0003416051,0.0006638364,0.0003658052],"domain_scores_gemma":[0.9958347,0.0004110896,0.0006015302,0.002691485,0.0002114955,0.0002497032],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001952439,0.001697603,0.0009734561,0.00005314601,0.0001674669,0.00001747405,0.01017927,0.000008684186,0.000007649658,0.05786623,0.004722087,0.9242874],"study_design_scores_gemma":[0.002125572,0.00183135,0.0001465866,0.0001314328,0.00006363155,0.00006903571,0.004832213,0.9428547,0.001486875,0.01093149,0.03506088,0.0004662008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3059753,0.00002701289,0.6894974,0.002159575,0.0002677417,0.001534327,0.00001113901,0.0002824928,0.0002450224],"genre_scores_gemma":[0.8394793,0.00000178589,0.1592376,0.0009503101,0.0001954251,0.0001093594,0.000003726411,0.000008153604,0.00001434497],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9428461,"threshold_uncertainty_score":0.8348626,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2791458756","doi":"10.2196/medinform.8960","title":"Characterizing and Managing Missing Structured Data in Electronic Health Records: Data Analysis","year":2018,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":174,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"U.S. National Library of Medicine; National Institute of Environmental Health Sciences; National Institute of Allergy and Infectious Diseases; National Human Genome Research Institute; University of Pennsylvania; National Institutes of Health; Pennsylvania Department of Health","keywords":"Missing data; Imputation (statistics); Health records; Computer science; Data science; Electronic health record; Data mining; Health care; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.08677746776859628,"gpt":0.4334871571936644,"spread":0.3467096894250681,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003003762,0.0001791736,0.0005578861,0.0002496297,0.0001280447,0.0001286018,0.001092804,0.0001242004,0.000307475],"category_scores_gemma":[0.002248151,0.0001465887,0.00001929797,0.0007025594,0.0002070679,0.0005718438,0.0009949419,0.0004946358,0.000006599061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006598208,"about_ca_system_score_gemma":0.0002903678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006948588,"about_ca_topic_score_gemma":0.0004598227,"domain_scores_codex":[0.9973879,0.0001676557,0.001035693,0.0002822892,0.0005649219,0.000561522],"domain_scores_gemma":[0.9970308,0.0007620195,0.0003523854,0.001515546,0.00003874646,0.0003005067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002254849,0.00005224134,0.001702011,0.0006350051,0.000181626,0.000007894357,0.003868597,1.443559e-8,0.000004908723,0.04932584,0.001740091,0.9424592],"study_design_scores_gemma":[0.000823977,0.0001861368,0.008353455,0.00069359,0.0002208136,0.00004722894,0.001864535,0.6203794,0.00001412577,0.361256,0.005674283,0.0004864906],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0144456,0.00007652992,0.9822434,0.00183154,0.0001066844,0.0002802384,0.0001696598,0.00006744883,0.0007789119],"genre_scores_gemma":[0.09233689,0.0002667306,0.9045528,0.002107236,0.0002148677,0.000007023798,0.0004837643,0.00001975283,0.0000109418],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9419727,"threshold_uncertainty_score":0.5977713,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2418503617","doi":"10.2196/medinform.5525","title":"Adoption Factors of the Electronic Health Record: A Systematic Review","year":2016,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":165,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Texas State University","keywords":"CINAHL; Facilitator; Health information technology; MEDLINE; Clinical decision support system; Electronic health record; Health care; Medicine; Health information exchange; Nursing; Health informatics; Cochrane Library; Family medicine; Medical education; Psychological intervention; Psychology; Health information; Political science; Public health","retraction":null,"screen_n_in":null,"score":{"opus":0.0782695182775771,"gpt":0.4817229635460851,"spread":0.403453445268508,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.009455984,0.0007655855,0.007500189,0.000260534,0.0005336805,0.000007818005,0.001833767,0.001449266,0.0007980262],"category_scores_gemma":[0.003170735,0.0003412111,0.001100318,0.001074571,0.0001507157,0.0001822729,0.0003868364,0.004438073,0.001113651],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003681129,"about_ca_system_score_gemma":0.02648094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009571597,"about_ca_topic_score_gemma":0.0001437156,"domain_scores_codex":[0.9784701,0.005919827,0.0110754,0.0002703443,0.002240375,0.002023957],"domain_scores_gemma":[0.9824009,0.003167783,0.01148784,0.001897741,0.0002955988,0.0007501508],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[9.838573e-7,0.00002667839,0.000004092279,0.9001663,0.000121285,2.000419e-7,0.0007381465,1.171317e-9,9.037561e-10,0.001323809,0.01507046,0.08254809],"study_design_scores_gemma":[0.0001229436,0.00008569927,4.071796e-7,0.5223404,0.0002139466,0.0000137631,0.0002201919,0.000003695224,4.449754e-9,0.00002499958,0.4768176,0.000156367],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00000254875,0.9734932,0.0002323294,0.0006862405,0.001580369,0.02216993,0.00008382128,0.0001369992,0.001614588],"genre_scores_gemma":[0.000003701678,0.9906928,0.00002162821,0.003199128,0.0003237143,0.003968329,0.00008549466,0.00009765162,0.001607537],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4617472,"threshold_uncertainty_score":0.999904,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3033682799","doi":"10.2196/18910","title":"Reliability of Supervised Machine Learning Using Synthetic Data in Health Care: Model to Preserve Privacy for Data Sharing","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":164,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Horizon 2020 Framework Programme; European Commission","keywords":"Synthetic data; Machine learning; Computer science; Artificial intelligence; Random forest; Decision tree; Support vector machine; Generalizability theory; Data mining; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.152395735813922,"gpt":0.379612199091731,"spread":0.227216463277809,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.002808229,0.0002100934,0.0005100409,0.0001481006,0.0001030797,0.0001189527,0.07274007,0.0001798532,0.000009563107],"category_scores_gemma":[0.09358283,0.0001927567,0.00003481019,0.0007789507,0.0001076456,0.002608313,0.2674657,0.0007268533,0.000003821685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001408259,"about_ca_system_score_gemma":0.0006516877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001984152,"about_ca_topic_score_gemma":0.00002646544,"domain_scores_codex":[0.9962461,0.00007820796,0.001449096,0.0006770248,0.0009951548,0.0005544378],"domain_scores_gemma":[0.981392,0.0004172313,0.0003571034,0.01731072,0.0001201952,0.0004027874],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000670567,0.001562608,0.02320031,0.05558467,0.0002620775,0.00004801121,0.1471804,0.08986101,0.000450938,0.005492823,0.2321336,0.443553],"study_design_scores_gemma":[0.0005300288,0.0001128107,0.00003047314,0.0003379884,0.000004349483,0.000002879328,0.0003029119,0.99463,0.00006130926,0.0018955,0.001911305,0.0001804856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03779091,0.0001249076,0.9346687,0.02539369,0.00006927026,0.001122745,0.0004354553,0.0003551312,0.00003916757],"genre_scores_gemma":[0.2050835,0.00003978672,0.7931794,0.001131074,0.00002127414,0.00002517953,0.0005027241,0.00001619077,8.680049e-7],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9047689,"threshold_uncertainty_score":0.9322768,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4394579747","doi":"10.2196/55318","title":"An Empirical Evaluation of Prompting Strategies for Large Language Models in Zero-Shot Clinical Natural Language Processing: Algorithm Development and Validation Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":162,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; U.S. National Library of Medicine; National Institutes of Health","keywords":"Computer science; Natural language processing; Artificial intelligence; Heuristic; Context (archaeology); Task (project management); Relationship extraction; Machine learning; Information extraction","retraction":null,"screen_n_in":null,"score":{"opus":0.2913679776604406,"gpt":0.5726627397999422,"spread":0.2812947621395016,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004391661,0.0001101547,0.0002548617,0.0001653212,0.00005688392,0.00006682854,0.00007220377,0.0001653211,0.00002070973],"category_scores_gemma":[0.0003411733,0.00008479851,0.00003095441,0.0002279425,0.00004498681,0.0005732632,0.00002422956,0.00034404,0.000002634912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000944765,"about_ca_system_score_gemma":0.00174938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002750584,"about_ca_topic_score_gemma":0.00006605112,"domain_scores_codex":[0.9975318,0.0001033166,0.001175014,0.0001447609,0.0008357737,0.0002093158],"domain_scores_gemma":[0.9991419,0.0001868027,0.0001261275,0.0001225968,0.0002722704,0.0001503179],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003386458,0.0004997615,0.00289046,0.0007746319,0.00001657171,0.000003782858,0.2210771,0.00001898869,0.000009008902,0.00003839014,0.0000544675,0.7745829],"study_design_scores_gemma":[0.0002819856,0.0003134517,0.002342795,0.0004053786,0.00004359762,0.000008653274,0.1929663,0.8029857,0.0002788335,0.0002542336,0.00004086566,0.00007829987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9794784,0.0005317995,0.01791421,0.0001726819,0.0001831867,0.001569208,0.000003655848,0.00005342894,0.00009345898],"genre_scores_gemma":[0.9900499,0.000007269221,0.009185138,0.0001639491,0.0001687326,0.0002343777,0.0001687326,0.00001104365,0.00001084104],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8029667,"threshold_uncertainty_score":0.3457983,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2765292139","doi":"10.2196/medinform.8092","title":"Patient Portal Use and Experience Among Older Adults: Systematic Review","year":2017,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":159,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Agency for Healthcare Research and Quality; University of Washington; National Science Foundation","keywords":"Patient portal; Inclusion (mineral); Thematic analysis; Medicine; Population; Health care; Focus group; The Internet; MEDLINE; Gerontology; Systematic review; Qualitative research; Psychology; Medical education; World Wide Web; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.03896772021135633,"gpt":0.4241418357765376,"spread":0.3851741155651813,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001581105,0.0002367418,0.0009120186,0.00005720319,0.001115298,0.00006328549,0.0004904271,0.0003766696,0.0004324274],"category_scores_gemma":[0.005173654,0.0001631972,0.00006838497,0.0000741282,0.0002481069,0.001079665,0.0003238349,0.001049055,0.0002463037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001375446,"about_ca_system_score_gemma":0.0005669122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002642127,"about_ca_topic_score_gemma":0.0001910566,"domain_scores_codex":[0.9948661,0.0003652793,0.002682588,0.0001608782,0.001119254,0.0008059224],"domain_scores_gemma":[0.9952175,0.0005627119,0.001958743,0.00116364,0.0002432177,0.0008541977],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.000008630826,0.00005480029,0.02457489,0.9040689,0.0000294088,0.00002827359,0.05397284,1.208205e-8,8.843494e-8,0.0004508699,0.0152913,0.001519946],"study_design_scores_gemma":[0.001372738,0.0001823955,0.01711163,0.9479536,0.00006951037,0.00007903133,0.0267009,0.002774221,0.000001552967,0.00001494398,0.003307833,0.0004316835],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9789811,0.003588896,0.0001617081,0.0008701774,0.001067027,0.01001991,0.00001572612,0.0001645311,0.005130927],"genre_scores_gemma":[0.9773176,0.004992615,0.0002673679,0.01212217,0.0001961274,0.004412155,0.00002256328,0.00003889027,0.000630511],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04388462,"threshold_uncertainty_score":0.8578087,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Big data; Data science; Computer science; Pace; Data quality; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.5332844092986461,"gpt":0.6082372109656298,"spread":0.0749528016669837,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01448208,0.0002894217,0.001517548,0.0001017135,0.0008448465,0.00001562017,0.004130363,0.0003708269,0.0001579866],"category_scores_gemma":[0.01712632,0.0001169383,0.0001420826,0.001006855,0.001805286,0.0001296653,0.00243572,0.003149678,0.0004913806],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001069181,"about_ca_system_score_gemma":0.005718697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006027545,"about_ca_topic_score_gemma":0.0001254521,"domain_scores_codex":[0.992202,0.001296176,0.003878675,0.0002333241,0.001814096,0.0005757187],"domain_scores_gemma":[0.9868176,0.006985242,0.002538861,0.003005763,0.0003180141,0.0003344947],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[8.864981e-7,0.00001005544,0.000004973665,0.1234024,0.000008852335,2.458079e-7,0.001249759,1.371522e-8,6.483604e-10,0.00051525,0.01584503,0.8589625],"study_design_scores_gemma":[0.00001722105,0.00002940595,0.000001416534,0.2443032,0.00006713094,0.000002808017,0.0005097532,0.0006101863,3.746868e-8,0.0001882706,0.7541812,0.00008933447],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0000258705,0.9872458,0.00003865977,0.003464151,0.001736996,0.004982343,0.0002010547,0.00002829095,0.002276836],"genre_scores_gemma":[0.00001157316,0.9836839,0.00003806161,0.01543513,0.0003586287,0.000288287,0.00002687062,0.00002089418,0.000136685],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8588732,"threshold_uncertainty_score":0.999918,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3098474649","doi":"10.2196/23811","title":"Role of Machine Learning Techniques to Tackle the COVID-19 Crisis: Systematic Review","year":2020,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":158,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Institutes of Health","keywords":"Systematic review; CINAHL; MEDLINE; Pandemic; Coronavirus disease 2019 (COVID-19); Epidemiology; Data science; Grey literature; Medicine; Computer science; Disease; Political science; Pathology; Infectious disease (medical specialty)","retraction":null,"screen_n_in":null,"score":{"opus":0.04515323600969522,"gpt":0.4093970256434307,"spread":0.3642437896337354,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003003846,0.0006574682,0.005785959,0.0003419365,0.0001270629,0.00004797324,0.001155856,0.0005745498,0.0004015426],"category_scores_gemma":[0.02016778,0.0003659282,0.0009618834,0.001431889,0.0001507074,0.0000942179,0.0006244981,0.002011144,0.0004108157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005324655,"about_ca_system_score_gemma":0.002653472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004662796,"about_ca_topic_score_gemma":0.000004186799,"domain_scores_codex":[0.9925624,0.0005839542,0.003923102,0.0002702769,0.002225333,0.000434967],"domain_scores_gemma":[0.9932661,0.002095072,0.001861962,0.00121446,0.0002125314,0.001349898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003912737,0.0000637599,3.229499e-7,0.826791,0.0002343737,0.00002436083,0.001244702,1.713869e-7,4.518519e-8,0.00005635331,0.1181325,0.05344849],"study_design_scores_gemma":[0.00009741747,0.0001583322,1.350464e-8,0.406953,0.002596149,0.00024982,0.0002134902,0.00008762888,0.000001130259,0.000006379854,0.5894492,0.0001874169],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[6.214498e-8,0.9500129,0.0004242026,0.04011267,0.00005936526,0.008708255,0.00004612628,0.0003653799,0.0002711007],"genre_scores_gemma":[5.242805e-7,0.7927501,0.0009041004,0.2038846,0.0001389995,0.002054235,0.0001401276,0.00006696459,0.00006030874],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4713167,"threshold_uncertainty_score":0.9998792,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2927642672","doi":"10.2196/13064","title":"Clinical Requirements of Future Patient Monitoring in the Intensive Care Unit: Qualitative Study","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Healthcare Technology and Patient Monitoring","field":"Medicine","cited_by":146,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Deutsche Forschungsgemeinschaft","keywords":"Usability; Patient safety; Medicine; Medical emergency; Interoperability; Situation awareness; Workload; Intensive care unit; Guideline; Intensive care; Remote patient monitoring; Health care; Nursing; Intensive care medicine; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.1195997942315243,"gpt":0.4955384760203954,"spread":0.3759386817888711,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001260873,0.0001398335,0.000452881,0.0001493333,0.00004081537,0.000004658672,0.0002529625,0.0003333664,0.00002716368],"category_scores_gemma":[0.0006389096,0.00008743054,0.00007595536,0.000371084,0.000128842,0.0001108228,0.0001145638,0.001203623,0.00003669514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006123551,"about_ca_system_score_gemma":0.0002063089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002748622,"about_ca_topic_score_gemma":0.000008363235,"domain_scores_codex":[0.996921,0.0003282884,0.001349458,0.0001076471,0.001036647,0.0002569555],"domain_scores_gemma":[0.9981037,0.0004159028,0.0003139523,0.0004489767,0.0005802096,0.0001372896],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.00008368252,0.0001859887,0.516594,0.0002916931,0.00003335892,0.00001842037,0.4527891,2.93086e-7,8.027563e-7,0.00005083048,0.00005958809,0.02989224],"study_design_scores_gemma":[0.001770251,0.002639968,0.0944562,0.0006888766,0.00002012321,0.000007766756,0.8995193,0.0000403141,0.00003699664,0.00001274065,0.0007340852,0.00007337456],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9959962,0.0001076575,0.000005219807,0.0005476794,0.001124555,0.001606397,0.00000388756,0.00003645834,0.0005719156],"genre_scores_gemma":[0.9986749,0.00003978657,0.0002100647,0.000785294,0.0001930681,0.00006670345,0.00001497546,0.000008201642,0.000007031604],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4467302,"threshold_uncertainty_score":0.522921,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2044738929","doi":"10.2196/medinform.3525","title":"Dynamic Consent: A Possible Solution to Improve Patient Confidence and Trust in How Electronic Patient Records Are Used in Medical Research","year":2015,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":145,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Economic and Social Research Council; Medical Research Council; Versus Arthritis; Wellcome Trust","keywords":"Internet privacy; Leverage (statistics); Health care; Public trust; Medical record; Informed consent; Public health; Data collection; Medicine; Business; Medical emergency; Public relations; Computer science; Nursing; Alternative medicine; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.222121077537781,"gpt":0.5227497604227325,"spread":0.3006286828849515,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01274862,0.0002183861,0.0006167541,0.0006961708,0.00007365283,0.0000797607,0.0004175486,0.001071214,0.000145449],"category_scores_gemma":[0.07626292,0.0001785094,0.00005763505,0.001133161,0.0009283787,0.0002217987,0.0007251074,0.00626336,0.00008285476],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001233276,"about_ca_system_score_gemma":0.007205474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004251313,"about_ca_topic_score_gemma":0.009455981,"domain_scores_codex":[0.9895186,0.0004602594,0.001447503,0.0003516559,0.006948057,0.001273867],"domain_scores_gemma":[0.9905555,0.00558532,0.0001983975,0.0005880942,0.000856242,0.002216431],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0079796,0.006780074,0.2280227,0.009117295,0.0002280085,0.003539693,0.159427,0.00002730982,0.0003203559,0.02105943,0.03100271,0.5324959],"study_design_scores_gemma":[0.03495025,0.03222916,0.04769915,0.02591514,0.00005030255,0.0008621929,0.1472652,0.6448544,0.0007751971,0.04393854,0.0196453,0.001815149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9620686,0.0001929704,0.0003303858,0.03400658,0.0002057958,0.001777864,0.000009695061,0.00003923358,0.001368904],"genre_scores_gemma":[0.9951987,0.0007236908,0.0007003495,0.0027135,0.00004893376,0.0003270795,0.00002025214,0.00002300211,0.0002445406],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6448271,"threshold_uncertainty_score":0.9984227,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3045837041","doi":"10.2196/21798","title":"AutoScore: A Machine Learning–Based Automatic Clinical Score Generator and Its Application to Mortality Prediction Using Electronic Health Records","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":143,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Medical Research Council; Medical Research Council","keywords":"Health records; Clinical decision support system; Medical record; Electronic health record; Computer science; Risk stratification; Electronic medical record; Machine learning; Health care; Generator (circuit theory); Artificial intelligence; Data mining; Medicine; Medical emergency; Decision support system; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1200558269226375,"gpt":0.4225546257764097,"spread":0.3024987988537723,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007623764,0.0002083273,0.0005590615,0.00007694149,0.0001288671,0.00002751662,0.00009259267,0.0001936631,0.0001145524],"category_scores_gemma":[0.000514276,0.0001663027,0.00009998574,0.0003579967,0.00004907906,0.0001082102,0.00006314942,0.0005680315,0.00004725769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000235235,"about_ca_system_score_gemma":0.0009045193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003523814,"about_ca_topic_score_gemma":0.00001397699,"domain_scores_codex":[0.9973617,0.0001086131,0.001180203,0.0002250116,0.0007490275,0.0003754097],"domain_scores_gemma":[0.9980794,0.0001064464,0.0003142904,0.0002142418,0.00008510231,0.001200578],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004339096,0.002446329,0.6648762,0.004161668,0.0007365863,0.00003452891,0.005756098,0.0006000622,0.0002112865,0.0004078061,0.006733274,0.3136023],"study_design_scores_gemma":[0.002040596,0.00180985,0.04111144,0.0002177131,0.0001164191,0.00002232687,0.00009690411,0.9496113,0.0001826719,0.000006619327,0.004659519,0.0001246186],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9811897,0.0003352039,0.00973974,0.006712857,0.00008497582,0.001623382,0.00002637318,0.0002548752,0.00003287473],"genre_scores_gemma":[0.9759712,0.0002694906,0.002664586,0.02029614,0.0002857055,0.0002146268,0.0002680248,0.00002491659,0.000005312525],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9490113,"threshold_uncertainty_score":0.6781626,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2996889063","doi":"10.2196/16492","title":"Analyzing Medical Research Results Based on Synthetic Data and Their Relation to Real Data Results: Systematic Comparison From Five Observational Studies","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":143,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Synthetic data; Computer science; Data mining; Observational study; Process (computing); Relation (database); Statistics; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2485650051275908,"gpt":0.4320103665125674,"spread":0.1834453613849766,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.01545124,0.0002914108,0.0008047344,0.000445155,0.0002554276,0.0003315375,0.04002834,0.0004293341,0.00001942646],"category_scores_gemma":[0.2796405,0.0002060669,0.00002933613,0.001199848,0.000371516,0.00200118,0.1061118,0.001347039,0.000228042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001960951,"about_ca_system_score_gemma":0.0005433701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001088973,"about_ca_topic_score_gemma":0.00007900177,"domain_scores_codex":[0.9917853,0.0006682579,0.002204903,0.0008952847,0.003877407,0.0005688414],"domain_scores_gemma":[0.9486431,0.02137919,0.0007548516,0.02815062,0.0005145422,0.0005576688],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003010869,0.0003080048,0.001143469,0.004276535,0.000290248,0.0000321323,0.008968694,0.0001576174,0.000005414392,0.002261064,0.9667652,0.01549059],"study_design_scores_gemma":[0.0009810821,0.0001755947,0.0009042998,0.008614815,0.00001255753,0.000004960364,0.002699301,0.9814203,0.00001077335,0.003556933,0.00139612,0.000223283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2170988,0.001011771,0.3734674,0.3799792,0.002616845,0.007479009,0.009531265,0.00251877,0.006296983],"genre_scores_gemma":[0.723318,0.0005557066,0.2659751,0.001995066,0.0002369371,0.0001398048,0.007673775,0.00003871553,0.00006680809],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9812627,"threshold_uncertainty_score":0.9651656,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2947577769","doi":"10.2196/13802","title":"Assessing the Availability of Data on Social and Behavioral Determinants in Structured and Unstructured Electronic Health Records: A Retrospective Analysis of a Multilevel Health Care System","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Food Security and Health in Diverse Populations","field":"Health Professions","cited_by":135,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Center for Advancing Translational Sciences","keywords":"Unstructured data; Health care; Medicine; Population; Data collection; Social determinants of health; Medical record; Health information technology; Population health; Medical emergency; Computer science; Big data; Public health; Nursing; Data mining; Environmental health","retraction":null,"screen_n_in":null,"score":{"opus":0.1616464065474127,"gpt":0.5235938640613984,"spread":0.3619474575139857,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001926644,0.0001518974,0.0008952989,0.0002664193,0.0004700357,0.00001199266,0.0003032251,0.0002894037,0.00004633696],"category_scores_gemma":[0.00014889,0.0001099985,0.00004654915,0.0005481297,0.0001988463,0.0003059171,0.0002641213,0.001053247,0.000001115491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006318711,"about_ca_system_score_gemma":0.001787742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002416957,"about_ca_topic_score_gemma":0.01227067,"domain_scores_codex":[0.9964114,0.000608244,0.001669515,0.0002051799,0.0006205135,0.0004851828],"domain_scores_gemma":[0.9975976,0.0003264065,0.001277432,0.000501647,0.0001176309,0.000179244],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008378578,0.00006671177,0.7854415,0.005379512,0.00008324395,3.862772e-7,0.182414,0.000002516284,5.167652e-7,0.001388918,0.0001600199,0.02497889],"study_design_scores_gemma":[0.001042441,0.0002509675,0.8730352,0.000592374,0.00005864606,0.000001151698,0.1027781,0.02203398,4.744015e-7,0.00004515704,0.00007862256,0.00008285097],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9970966,0.0001286135,0.00002675152,0.0004481403,0.0001488631,0.001492221,0.0005926812,0.00001876513,0.00004735753],"genre_scores_gemma":[0.9987926,0.00005210173,0.0004813795,0.0004512256,0.00002919425,0.00002423903,0.0001590575,0.000007833878,0.000002377875],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08759371,"threshold_uncertainty_score":0.6847321,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4223646541","doi":"10.2196/32578","title":"The Use of Artificial Intelligence–Based Conversational Agents (Chatbots) for Weight Loss: Scoping Review and Practical Recommendations","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Digital Mental Health Interventions","field":"Psychology","cited_by":135,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Chatbot; CINAHL; PsycINFO; MEDLINE; Weight loss; Overweight; Scopus; Artificial intelligence; Personalization; Medicine; World Wide Web; Computer science; Psychology; Obesity; Psychological intervention; Internal medicine; Nursing","retraction":null,"screen_n_in":null,"score":{"opus":0.2219394628413439,"gpt":0.4957736810802575,"spread":0.2738342182389136,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009127917,0.00008437641,0.0001785471,0.00005837885,0.0003188026,0.00003406916,0.0001380969,0.0000491836,0.00324058],"category_scores_gemma":[0.0006532805,0.0000679691,0.00008082802,0.0001624538,0.000226738,0.0002464682,0.0001295594,0.000245697,0.00003822762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006430194,"about_ca_system_score_gemma":0.0002243922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004616423,"about_ca_topic_score_gemma":0.000009302536,"domain_scores_codex":[0.9979968,0.0001334169,0.001140051,0.00008306621,0.0004390567,0.0002075897],"domain_scores_gemma":[0.9975148,0.0016603,0.0003942376,0.0001910455,0.00008586863,0.000153695],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003145141,0.00186369,0.0001643938,0.008569655,0.0002113743,0.000008393477,0.002885983,0.00001431689,1.773082e-7,0.3215071,0.2881588,0.3763016],"study_design_scores_gemma":[0.001785668,0.002485422,0.0002284306,0.01622379,0.0003295695,0.0002801652,0.0072891,0.0835029,0.00006110986,0.01227208,0.8748631,0.0006786775],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.01392076,0.005017848,0.3749183,0.5581292,0.01308218,0.02572156,0.003693203,0.0003267511,0.005190256],"genre_scores_gemma":[0.5400219,0.005183291,0.1550262,0.2474202,0.001077324,0.03958572,0.006108813,0.0002782944,0.00529822],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.5867043,"threshold_uncertainty_score":0.9976706,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4386710076","doi":"10.2196/48808","title":"ChatGPT-Generated Differential Diagnosis Lists for Complex Case–Derived Clinical Vignettes: Diagnostic Accuracy Evaluation","year":2023,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":135,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Differential diagnosis; Medical diagnosis; Medicine; Radiology; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.3661866926666326,"gpt":0.5378131142135208,"spread":0.1716264215468882,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001845013,0.0002294851,0.0005037449,0.0002130472,0.0002909749,0.00006908324,0.0001762852,0.0004556694,0.00172487],"category_scores_gemma":[0.01997758,0.0001918545,0.0002022645,0.0005722288,0.0002110259,0.0002263848,0.00007619557,0.0004478114,0.0005153716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001374363,"about_ca_system_score_gemma":0.0007982797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009446785,"about_ca_topic_score_gemma":0.00008440697,"domain_scores_codex":[0.9960736,0.0001710312,0.001902293,0.0002181055,0.001094678,0.0005403082],"domain_scores_gemma":[0.9913231,0.006442694,0.0003626632,0.0003990867,0.000771917,0.0007005564],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001706231,0.0006851147,0.01835295,0.0009015232,0.0001390391,0.0001323156,0.011914,0.00003078638,0.00006398957,0.0001083434,0.1535621,0.8139393],"study_design_scores_gemma":[0.001525008,0.001363442,0.03238315,0.0008123448,0.000442822,0.0004341496,0.009602868,0.9228379,0.001546825,0.0006865863,0.02783247,0.00053244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9857705,0.00005101939,0.002804343,0.006268243,0.001714763,0.002967911,0.00004421506,0.0002587168,0.0001202594],"genre_scores_gemma":[0.9884288,0.0006646374,0.000750311,0.003768423,0.001957378,0.002304959,0.002043298,0.00003147651,0.00005071714],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9228071,"threshold_uncertainty_score":0.9991877,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3104873923","doi":"10.2196/16503","title":"Comparison of Multivariable Logistic Regression and Other Machine Learning Algorithms for Prognostic Prediction Studies in Pregnancy Care: Systematic Review and Meta-Analysis","year":2020,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Preterm Birth and Chorioamnionitis","field":"Medicine","cited_by":134,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Ministry of Science and Technology, Taiwan","keywords":"Logistic regression; Medicine; Multivariable calculus; Pregnancy; Population; Receiver operating characteristic; Machine learning; Scopus; MEDLINE; Predictive modelling; Systematic review; Meta-analysis; Artificial intelligence; Computer science; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.2103419185048788,"gpt":0.4610943651254286,"spread":0.2507524466205497,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006500261,0.0004470212,0.009140506,0.0002749018,0.00006458738,0.00001777269,0.0001403567,0.000361761,0.00003160603],"category_scores_gemma":[0.003666272,0.0002500501,0.0006557911,0.0005725136,0.0001906382,0.00008522353,0.00014094,0.0007053638,0.000001689745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007430268,"about_ca_system_score_gemma":0.0001614291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006683161,"about_ca_topic_score_gemma":0.000004161036,"domain_scores_codex":[0.9958687,0.0002859361,0.00273767,0.0002357475,0.0006307695,0.0002411253],"domain_scores_gemma":[0.9967752,0.0009981258,0.001499619,0.0002811515,0.0001787956,0.0002671759],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","study_design_scores_codex":[0.000005594652,0.00004195036,0.0001425634,0.9589832,0.0213201,0.000007897235,0.002233558,3.574706e-7,4.099835e-9,0.000009990998,0.00005614915,0.01719861],"study_design_scores_gemma":[0.0005946552,0.0004164996,0.000002015282,0.4154029,0.5586054,0.00007362731,0.0008037075,0.00760163,1.880406e-7,0.00000450304,0.01628433,0.0002105544],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000001167077,0.9923075,0.0006987561,0.00004854441,0.00003716877,0.006580099,0.0002434294,0.00004128336,0.0000419993],"genre_scores_gemma":[0.0001340193,0.9953297,0.001751963,0.0001346117,0.00002538916,0.00216987,0.0003713305,0.00002761919,0.00005548738],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.5435804,"threshold_uncertainty_score":0.9999952,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2211648215","doi":"10.2196/medinform.5215","title":"Outcomes From Health Information Exchange: Systematic Review and Future Research Needs","year":2015,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":134,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"U.S. National Library of Medicine; Agency for Healthcare Research and Quality; U.S. Department of Health and Human Services","keywords":"Health information exchange; Systematic review; Computer science; Data science; MEDLINE; Medicine; Health care; Knowledge management; Health information; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.1509178671729377,"gpt":0.5194668474988611,"spread":0.3685489803259234,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01726394,0.0002657849,0.001480747,0.0004199365,0.0005890075,0.00003882087,0.0005156864,0.0005781319,0.0004536521],"category_scores_gemma":[0.002904396,0.0001802021,0.00006052801,0.000920373,0.0001125301,0.0009804851,0.000328578,0.002520042,0.002011478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000978855,"about_ca_system_score_gemma":0.004233337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007109165,"about_ca_topic_score_gemma":0.0001645575,"domain_scores_codex":[0.9899585,0.002473846,0.003585313,0.0001083566,0.00260487,0.001269175],"domain_scores_gemma":[0.9941168,0.001409446,0.001116543,0.0007358377,0.0007759125,0.001845476],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001023442,0.00002712487,0.001012705,0.6248605,0.0000473072,9.773615e-7,0.07543033,2.05176e-8,9.932723e-9,0.001595698,0.2925205,0.004494608],"study_design_scores_gemma":[0.003060543,0.0005018748,0.0008532936,0.1357606,0.00009065752,0.00003102947,0.1618288,0.001045167,1.275027e-7,0.000443144,0.6959378,0.0004470755],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.03328009,0.3063055,0.002680717,0.471532,0.01083329,0.07929347,0.0005133165,0.002116613,0.09344499],"genre_scores_gemma":[0.03603506,0.2252945,0.00509727,0.6902793,0.008463301,0.02395622,0.002324565,0.000288513,0.008261289],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.4890999,"threshold_uncertainty_score":0.9997812,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4393870852","doi":"10.2196/50048","title":"Toward Fairness, Accountability, Transparency, and Ethics in AI for Social Media and Health Care: Scoping Review","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":130,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"York University; University of Waterloo; Saint Mary's University; Lakehead University","funders":"","keywords":"Accountability; Transparency (behavior); Social media; Health care; Public relations; Psychology; Internet privacy; Political science; Sociology; Computer science; World Wide Web; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.3493996880040418,"gpt":0.5522561175184422,"spread":0.2028564295144004,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001910199,0.0001270027,0.0004273988,0.00009616214,0.0001112702,0.00004519837,0.00006619449,0.0003010611,0.00005917131],"category_scores_gemma":[0.0007339871,0.0001045979,0.00004729997,0.000241011,0.0001975342,0.0002268683,0.00002790815,0.0007942539,0.000005553961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001515123,"about_ca_system_score_gemma":0.002655697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001434511,"about_ca_topic_score_gemma":0.001107003,"domain_scores_codex":[0.9979812,0.00004412963,0.001043326,0.0001421667,0.0005054327,0.0002837716],"domain_scores_gemma":[0.9987221,0.0006841425,0.00007124542,0.000101773,0.0001423143,0.000278478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00002342827,0.00004054244,0.0008102246,0.238559,0.00001009691,0.000003190419,0.3089821,7.17023e-8,2.61902e-7,0.001991805,0.004343234,0.4452361],"study_design_scores_gemma":[0.001416181,0.001667846,0.007154229,0.7041125,0.0003658218,0.0004199026,0.2118302,0.012793,0.0002055386,0.02115294,0.03741123,0.001470604],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.09743888,0.2265489,0.01003538,0.6527526,0.0024766,0.009652007,0.00007847123,0.0003310919,0.0006860329],"genre_scores_gemma":[0.9010081,0.06182758,0.001013725,0.03480344,0.000669502,0.0004679557,0.0001818734,0.00002281604,0.000005047734],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8035692,"threshold_uncertainty_score":0.4711093,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2592665192","doi":"10.2196/medinform.6730","title":"Patient Similarity in Prediction Models Based on Health Data: A Scoping Review","year":2017,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":130,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"University of Waterloo; Natural Sciences and Engineering Research Council of Canada; Queen's University","keywords":"Context (archaeology); Computer science; Similarity (geometry); Scopus; Data mining; Field (mathematics); Predictive modelling; Data science; Health care; MEDLINE; Information retrieval; Medicine; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.2501120553890433,"gpt":0.4906599825597756,"spread":0.2405479271707323,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004457916,0.0004784173,0.002358283,0.0003477042,0.0002502259,0.0001862491,0.00412427,0.0005273008,0.00002457225],"category_scores_gemma":[0.001719975,0.00037104,0.0001958582,0.0004557556,0.0000746716,0.001112444,0.001554536,0.002649686,0.00005459618],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004306804,"about_ca_system_score_gemma":0.00645061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007160559,"about_ca_topic_score_gemma":0.00005536975,"domain_scores_codex":[0.9927329,0.0008134127,0.003177227,0.0004994926,0.002150242,0.0006266758],"domain_scores_gemma":[0.9921212,0.00059969,0.00229563,0.004284261,0.00008608146,0.0006131561],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[4.504936e-7,0.00004282938,7.797163e-7,0.2816795,0.000004146247,0.000007876389,0.0001810768,0.00006651321,2.10614e-12,0.0001565637,0.003135242,0.714725],"study_design_scores_gemma":[0.00007915193,0.00008696493,3.985727e-7,0.3865509,0.00000755594,0.00001203265,0.000001815227,0.3714903,2.980466e-10,0.00002335279,0.2416238,0.000123769],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[2.706429e-8,0.9468445,0.04468941,0.00218649,0.0005961495,0.004313473,0.0001074114,0.0001926514,0.001069855],"genre_scores_gemma":[6.965565e-7,0.9820161,0.008009848,0.008676205,0.0001062857,0.0004182442,0.0007450293,0.00002349127,0.00000411825],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7146013,"threshold_uncertainty_score":0.9998742,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3082085807","doi":"10.2196/20477","title":"Applying Blockchain Technology to Address the Crisis of Trust During the COVID-19 Pandemic","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":129,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Blockchain; Computer security; Data sharing; General partnership; Pandemic; Internet privacy; Computer science; Corporate governance; Information privacy; Business; Harm; Government (linguistics); Coronavirus disease 2019 (COVID-19); Political science; Medicine; Law","retraction":null,"screen_n_in":null,"score":{"opus":0.02430840816648665,"gpt":0.3036607728144869,"spread":0.2793523646480002,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006327563,0.0001320087,0.0002193456,0.0001232854,0.0003407956,0.00003360994,0.003125385,0.000283042,0.00003198835],"category_scores_gemma":[0.0005216825,0.00007660865,0.0000581645,0.001514363,0.0003501627,0.00005415267,0.001219771,0.0007023902,0.00003470677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000393627,"about_ca_system_score_gemma":0.0001520365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001105564,"about_ca_topic_score_gemma":0.000009235809,"domain_scores_codex":[0.9983937,0.00003973475,0.0005919674,0.0001524656,0.00052788,0.0002942251],"domain_scores_gemma":[0.9983856,0.0002137379,0.0002024808,0.0008499153,0.00006258683,0.0002856483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005485513,0.0003073911,0.01005922,0.001156831,0.000232358,0.00003176915,0.1455816,0.0009677574,0.0006633766,0.6361241,0.0518441,0.1529767],"study_design_scores_gemma":[0.001667899,0.0002554864,0.0003863945,0.00006656994,0.00003319822,0.0004359639,0.03451777,0.5048125,0.002076289,0.0151306,0.4399849,0.0006324601],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4072396,0.0001328084,0.3742432,0.2152577,0.00007755266,0.001824484,0.0000114222,0.000862743,0.0003504259],"genre_scores_gemma":[0.9679509,0.00002492601,0.004610896,0.0263703,0.00004364767,0.0009850514,8.211396e-7,0.00000588787,0.000007536692],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6209934,"threshold_uncertainty_score":0.5807796,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3033328382","doi":"10.2196/19515","title":"Using Information Technology to Manage the COVID-19 Pandemic: Development of a Technical Framework Based on Practical Experience in China","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"COVID-19 Digital Contact Tracing","field":"Computer Science","cited_by":128,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Health informatics; Informatics; Information technology; Telemedicine; Public health informatics; Computer science; Big data; Cloud computing; The Internet; Health care; Data science; Knowledge management; Medicine; HRHIS; Public health; Health policy; World Wide Web; Engineering; Data mining; Political science; Nursing","retraction":null,"screen_n_in":null,"score":{"opus":0.08854208323539685,"gpt":0.4071249031781292,"spread":0.3185828199427324,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007780448,0.0001739442,0.0002613461,0.0003488536,0.0001081445,0.0001203333,0.001317291,0.0002781998,0.00001737604],"category_scores_gemma":[0.007242871,0.0001284593,0.00004339062,0.001877923,0.0001371213,0.001177988,0.0007642266,0.0007984492,0.00003530614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000364353,"about_ca_system_score_gemma":0.001095266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006752551,"about_ca_topic_score_gemma":0.000009003917,"domain_scores_codex":[0.9972126,0.00004545071,0.001085226,0.0001473441,0.001165764,0.0003436368],"domain_scores_gemma":[0.9980113,0.0007253551,0.0002627618,0.0004887934,0.0000499208,0.0004618719],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004999295,0.0007674902,0.02018342,0.002613772,0.00004952644,0.0001770419,0.5105271,0.01892396,0.0002619017,0.1823133,0.001074316,0.2626082],"study_design_scores_gemma":[0.0008389672,0.0002844251,0.001667397,0.0004917606,0.00000437402,0.00006613226,0.002838562,0.9490818,0.0003120562,0.001054736,0.04295107,0.0004087702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06221278,0.000001913536,0.9167606,0.01970054,0.00005049073,0.0005610255,0.000001328758,0.0002141005,0.0004972357],"genre_scores_gemma":[0.7345403,7.646149e-7,0.2300835,0.03528184,0.00001134986,0.0000761323,0.000001693273,0.000004064841,3.526958e-7],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9301578,"threshold_uncertainty_score":0.8670917,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4205865577","doi":"10.2196/32875","title":"Operationalizing and Implementing Pretrained, Large Artificial Intelligence Linguistic Models in the US Health Care System: Outlook of Generative Pretrained Transformer 3 (GPT-3) as a Service Model","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":126,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Patient-Centered Outcomes Research Institute","keywords":"Operationalization; Computer science; Software portability; Generative grammar; Health Insurance Portability and Accountability Act; Health care; Transformer; Benchmarking; Artificial intelligence; Knowledge management; Computer security; Engineering; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.108211482481031,"gpt":0.4219746385367421,"spread":0.3137631560557111,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002112747,0.000174731,0.0003727465,0.0001781119,0.000493991,0.00003717393,0.0002230191,0.0001048551,0.0000988576],"category_scores_gemma":[0.0002292756,0.0001382164,0.00006090096,0.0004967294,0.00007304092,0.0001800171,0.00006588389,0.0006346553,0.000003386049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002895558,"about_ca_system_score_gemma":0.001857818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005810492,"about_ca_topic_score_gemma":0.0006739693,"domain_scores_codex":[0.9964581,0.0001676293,0.001623399,0.0001648476,0.001120081,0.0004659824],"domain_scores_gemma":[0.9987771,0.0001933929,0.0002727903,0.0002256061,0.0003436903,0.0001874082],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001571334,0.0002612156,0.0002802073,0.003445879,0.00003680631,0.000008587192,0.8917942,0.008432123,0.00002862836,0.07479133,0.0001689272,0.02059493],"study_design_scores_gemma":[0.00009159723,0.0002964903,0.00001128217,0.000229923,0.00002061529,0.00005642232,0.2547494,0.7425525,0.0002000402,0.001472011,0.0002205609,0.00009916147],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8792855,0.0007342001,0.1023436,0.009234894,0.0003229151,0.003847207,0.0001792719,0.000071047,0.003981424],"genre_scores_gemma":[0.9881773,0.00004701428,0.002555528,0.008384956,0.0001593016,0.0004092295,0.0002402868,0.00001508542,0.00001129585],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7341203,"threshold_uncertainty_score":0.5636302,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2612815242","doi":"10.2196/medinform.7271","title":"Virtual Reality as an Adjunct Home Therapy in Chronic Pain Management: An Exploratory Study","year":2017,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Pediatric Pain Management Techniques","field":"Medicine","cited_by":124,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; Physical therapy; Adjunct; Chronic pain; Brief Pain Inventory; Virtual reality; Adverse effect; Intervention (counseling); Rating scale; Psychology; Internal medicine; Psychiatry","retraction":null,"screen_n_in":null,"score":{"opus":0.03863839473126612,"gpt":0.3597144760575411,"spread":0.321076081326275,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006620249,0.0003021894,0.0005207105,0.0003869648,0.0002133954,0.0001350325,0.001083566,0.0002447564,0.0002548875],"category_scores_gemma":[0.0003074489,0.000254256,0.00007373062,0.000221407,0.0002481483,0.001404753,0.0003831198,0.0006335084,0.00008338195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003488314,"about_ca_system_score_gemma":0.0002744727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007784432,"about_ca_topic_score_gemma":0.0001969331,"domain_scores_codex":[0.996269,0.0004089941,0.0009524408,0.0002657293,0.0015868,0.0005170626],"domain_scores_gemma":[0.9969426,0.00008011077,0.0003645844,0.001970401,0.00006793906,0.0005743113],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005382853,0.006020799,0.1321793,0.0008975789,0.0003390684,0.00141352,0.02871849,0.000005398652,0.00001524581,0.001955891,0.0182473,0.8096691],"study_design_scores_gemma":[0.02743435,0.02545847,0.7784944,0.000980028,0.0002247617,0.00003219238,0.07532204,0.04907764,0.00005198712,0.003498735,0.03768771,0.001737756],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9856309,0.00004051158,0.002257128,0.000410443,0.0001231222,0.002754747,0.000003508637,0.00043072,0.008348888],"genre_scores_gemma":[0.9950178,0.0007350541,0.0004509422,0.002609618,0.0003861654,0.0005216844,0.00007375899,0.00003343286,0.0001715882],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8079314,"threshold_uncertainty_score":0.9999909,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400270729","doi":"10.2196/54345","title":"Reference Hallucination Score for Medical Artificial Intelligence Chatbots: Development and Usability Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":122,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Preprint; Natural language processing; Computer science; Artificial intelligence; Psychology; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.2320138201162752,"gpt":0.4742133288584646,"spread":0.2421995087421894,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002287183,0.0001740291,0.0002936946,0.000170568,0.0001705447,0.00008983232,0.0001560117,0.0003207776,0.0005024762],"category_scores_gemma":[0.001901462,0.0001344466,0.00004067945,0.0003157897,0.0002067849,0.0002593765,0.00007811557,0.0005337714,0.0001213925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001764035,"about_ca_system_score_gemma":0.001661348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004366033,"about_ca_topic_score_gemma":0.0001578846,"domain_scores_codex":[0.9967407,0.00004005818,0.001403123,0.0002300578,0.001258984,0.0003270642],"domain_scores_gemma":[0.9982493,0.0005876599,0.00008656774,0.0002274423,0.000268241,0.0005808239],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007119456,0.0004197488,0.001689908,0.001253798,0.00003109693,0.00001213816,0.02794047,7.428945e-7,0.00000196074,0.004214385,0.0003210326,0.9640436],"study_design_scores_gemma":[0.0004481079,0.00566653,0.01521813,0.007146742,0.0003048735,0.000548917,0.1894936,0.6408246,0.00547763,0.02115306,0.1122024,0.001515502],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9393993,0.0001855594,0.05241342,0.0048122,0.0006997421,0.001852011,0.000003988247,0.0001674605,0.0004663074],"genre_scores_gemma":[0.9932675,0.00008244257,0.00475293,0.0008844984,0.0004138755,0.0004448505,0.00006787958,0.00001450652,0.0000715508],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.962528,"threshold_uncertainty_score":0.5501763,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4290775674","doi":"10.2196/36199","title":"Application of Artificial Intelligence in Shared Decision Making: Scoping Review","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Patient-Provider Communication in Healthcare","field":"Health Professions","cited_by":120,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false},"ca_institutions":"Université Laval; McGill University Health Centre; Jewish General Hospital; Centre intégré universitaire de santé et de services sociaux de la Capitale-Nationale; McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"McGill University","keywords":"Systematic review; Grey literature; Psychological intervention; MEDLINE; Health care; Guideline; Inclusion (mineral); Identification (biology); Computer science; Medicine; Artificial intelligence; Data science; Psychology; Nursing","retraction":null,"screen_n_in":null,"score":{"opus":0.2432077694218231,"gpt":0.5194289814827286,"spread":0.2762212120609056,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001422939,0.0001064882,0.0003634241,0.0001972495,0.0003963019,0.000003466252,0.0008121787,0.0001325929,0.00172855],"category_scores_gemma":[0.001653596,0.0001036654,0.00004892581,0.0008662934,0.00006995823,0.0001768351,0.0009023341,0.001190656,0.0001178603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003013816,"about_ca_system_score_gemma":0.0009356262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003874098,"about_ca_topic_score_gemma":0.00008882462,"domain_scores_codex":[0.9951302,0.000526036,0.002782313,0.0001096519,0.001140549,0.0003112963],"domain_scores_gemma":[0.9964875,0.001468531,0.0009721858,0.0007452643,0.0001920839,0.0001344277],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001443221,0.0003210837,0.006666913,0.04783128,0.000008947972,0.000002336284,0.0588344,0.0001967338,0.000003669724,0.01441636,0.003831587,0.8677424],"study_design_scores_gemma":[0.001021556,0.0004591308,0.003951235,0.34015,0.00003167073,0.00001715346,0.105515,0.5135198,0.00001600454,0.02129376,0.01320196,0.0008227451],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1104945,0.09091098,0.6308089,0.03723923,0.006594046,0.08921214,0.0005276653,0.001412184,0.03280038],"genre_scores_gemma":[0.9553922,0.002392665,0.0213269,0.01311231,0.00008247083,0.007482586,0.00017101,0.00002903778,0.00001079857],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8669196,"threshold_uncertainty_score":0.999184,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2757433884","doi":"10.2196/medinform.7958","title":"Impact of Electronic Health Records on Long-Term Care Facilities: Systematic Review","year":2017,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Nursing Diagnosis and Documentation","field":"Nursing","cited_by":120,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Long-term care; Business; Health care; Health records; Incentive; Health information technology; Incentive program; Electronic health record; Medicine; Medical emergency; Population; Environmental health; Nursing; Economic growth","retraction":null,"screen_n_in":null,"score":{"opus":0.0198344199812552,"gpt":0.3984922646788377,"spread":0.3786578446975825,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006210564,0.0001914649,0.0007616133,0.00008052818,0.0002442047,0.00009555716,0.0004510336,0.0001109205,0.0002759833],"category_scores_gemma":[0.0006510214,0.0001365238,0.0002334018,0.00006575056,0.0001191047,0.0003856097,0.00003608597,0.0003038051,0.00007897647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006794145,"about_ca_system_score_gemma":0.0002707372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001405222,"about_ca_topic_score_gemma":0.00004720761,"domain_scores_codex":[0.9973453,0.0001046774,0.00116529,0.00009369352,0.0008725635,0.0004184213],"domain_scores_gemma":[0.9975992,0.0001357955,0.001121611,0.0007764219,0.0001155921,0.0002513501],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00008485207,0.0002675343,0.005898433,0.918699,0.0001189484,0.000002256192,0.02065876,0.000002436558,6.317712e-7,0.0002448272,0.02052732,0.03349504],"study_design_scores_gemma":[0.003003462,0.009310505,0.0406882,0.9388923,0.0003088915,0.00006373612,0.005382469,0.0006681429,0.000120512,0.0002545643,0.0005543098,0.0007529037],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9596831,0.01951775,0.0002375156,0.004448089,0.001965832,0.006929975,0.000151958,0.0002047543,0.006861022],"genre_scores_gemma":[0.9952285,0.002503532,0.00005072278,0.001745176,0.00007909437,0.0001480502,0.0001154637,0.00001881519,0.0001106845],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03554535,"threshold_uncertainty_score":0.5567279,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3014693099","doi":"10.2196/15653","title":"Appropriateness of Overridden Alerts in Computerized Physician Order Entry: Systematic Review","year":2020,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":119,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Ministry of Education, India","keywords":"Computerized physician order entry; Computer science; Order entry; Order (exchange); Data science; Medicine; Medical emergency; Data mining; Health care; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.0670936181451619,"gpt":0.4609841237750105,"spread":0.3938905056298486,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.004023989,0.0007808303,0.01093745,0.0002963661,0.0001329106,0.00001193637,0.001414974,0.001435927,0.0002425372],"category_scores_gemma":[0.001776454,0.0005336245,0.0005167437,0.001822686,0.0001021338,0.0001899179,0.0005244746,0.003590175,0.0009853387],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000918135,"about_ca_system_score_gemma":0.009052004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007136649,"about_ca_topic_score_gemma":0.00002887225,"domain_scores_codex":[0.9826636,0.003500599,0.01037097,0.0003143518,0.001927215,0.001223314],"domain_scores_gemma":[0.9899909,0.002039987,0.005848014,0.001087127,0.0002979305,0.0007360333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.000004198573,0.00006904142,0.000001113709,0.8952771,0.0001438594,0.00001442802,0.001408571,3.401556e-8,3.135272e-9,0.0002712749,0.005616842,0.09719351],"study_design_scores_gemma":[0.0004751452,0.00004837139,2.069535e-7,0.5810489,0.0003161831,0.00001383873,0.0002364362,0.0003969502,8.523107e-9,0.000009298749,0.417206,0.0002486326],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000001297921,0.9743407,0.0004266583,0.0002632102,0.0009998077,0.01978832,0.00005926409,0.0001306359,0.003990103],"genre_scores_gemma":[0.000001439694,0.9885643,0.0003088888,0.005298373,0.0004634956,0.004773641,0.0003257755,0.00009750549,0.000166587],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4115892,"threshold_uncertainty_score":0.9998604,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2104793920","doi":"10.2196/medinform.3503","title":"Adoption of Clinical Decision Support in Multimorbidity: A Systematic Review","year":2015,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":118,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Patient Safety Translational Research Centre; Medical Research Council; National Institute for Health and Care Research","keywords":"Decision support system; Clinical decision support system; Systematic review; Computer science; Multimorbidity; MEDLINE; Medicine; Intensive care medicine; Data mining; Chronic disease","retraction":null,"screen_n_in":null,"score":{"opus":0.1907562015689149,"gpt":0.5116538272873198,"spread":0.3208976257184049,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006530993,0.0004770271,0.007672513,0.0004209157,0.00001328358,0.00002001231,0.000551733,0.000745093,0.0007319204],"category_scores_gemma":[0.004869244,0.0003119587,0.001014807,0.0007228419,0.0002076883,0.0002091919,0.0003428062,0.001090309,0.0007640515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002856741,"about_ca_system_score_gemma":0.003641136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002779793,"about_ca_topic_score_gemma":0.000003085749,"domain_scores_codex":[0.9883152,0.000305121,0.008194631,0.000220791,0.002610871,0.000353409],"domain_scores_gemma":[0.9948501,0.0006782931,0.002426702,0.001124043,0.0002409833,0.0006798537],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00001132075,0.0002462218,0.000002512463,0.6921542,0.0001354927,0.00007842113,0.0000432817,4.259722e-8,4.555516e-11,0.00008071529,0.01632597,0.2909218],"study_design_scores_gemma":[0.001109784,0.0001503888,0.000003081668,0.6343839,0.002992064,0.00008907685,0.0001152668,0.0003552674,1.257671e-9,0.00001574723,0.3606201,0.0001653431],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000005095113,0.9844097,0.000106794,0.00003544791,0.0003702224,0.007421049,0.00002901687,0.00006884721,0.007553811],"genre_scores_gemma":[0.000002877202,0.99662,0.0009730026,0.0005816584,0.000146112,0.00057059,0.0008869835,0.00003710653,0.0001816709],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.3442941,"threshold_uncertainty_score":0.9999332,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2802355308","doi":"10.2196/medinform.8403","title":"Implementing an Open Source Electronic Health Record System in Kenyan Health Care Facilities: Case Study","year":2018,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"ICT in Developing Communities","field":"Computer Science","cited_by":117,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Medical Research Council; National Institute for Health and Care Research; National Institute of General Medical Sciences; Wellcome Trust","keywords":"Electronic health record; Open source; Health care; Health records; Medical emergency; Medicine; Patient portal; Computer science; Software; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.04300816973493849,"gpt":0.3742949347614814,"spread":0.3312867650265429,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004553793,0.0002433622,0.000521895,0.0002766333,0.0009380864,0.0005399177,0.003339561,0.00009047207,0.00003016617],"category_scores_gemma":[0.00007109512,0.0002255719,0.00002933833,0.0006238364,0.0001130578,0.001350089,0.003058535,0.0006946858,0.00003742106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00125256,"about_ca_system_score_gemma":0.003308916,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01426234,"about_ca_topic_score_gemma":0.03622238,"domain_scores_codex":[0.9953204,0.000644661,0.001602418,0.0001989861,0.0008904191,0.001343063],"domain_scores_gemma":[0.9974977,0.0001585487,0.0004792127,0.001261433,0.0001706425,0.0004324507],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.000005320816,0.0001251359,0.001220053,0.0006907278,0.00001788351,0.0000497589,0.8253767,0.000001770044,1.407245e-8,0.003153488,0.001282498,0.1680766],"study_design_scores_gemma":[0.001050751,0.002696103,0.0001302315,0.0004205927,0.000001313684,0.0007721463,0.903237,0.03413333,0.000001527231,0.00005537791,0.05720625,0.0002953744],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9228724,0.0001027215,0.0704266,0.000840827,0.0004507651,0.002633892,0.00001076895,0.0005349616,0.00212705],"genre_scores_gemma":[0.9823914,0.00001159377,0.01489448,0.002314541,0.00009710902,0.0001758378,0.00001953006,0.00001774846,0.00007771717],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1677812,"threshold_uncertainty_score":0.9923018,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}