{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":35,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":35,"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":"328dc2475acf","filters":{"venue":"European Heart Journal - Digital Health"}},"results":[{"id":"W3127649143","doi":"10.1093/ehjdh/ztab005","title":"Barriers and facilitators of the uptake of digital health technology in cardiovascular care: a systematic scoping review","year":2021,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Mobile Health and mHealth Applications","field":"Health Professions","cited_by":260,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Population Health Research Institute; McMaster University; Impact","funders":"Canadian Institutes of Health Research","keywords":"CINAHL; Thematic analysis; Medicine; Workload; MEDLINE; Health care; Qualitative research; Family medicine; Nursing; Psychological intervention","retraction":null,"screen_n_in":null,"score":{"opus":0.04852115125765442,"gpt":0.3929353654732305,"spread":0.3444142142155761,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004303873,0.0002569837,0.0017505,0.0002586806,0.0008732806,0.00002971006,0.0003215148,0.00009114901,0.00001949566],"category_scores_gemma":[0.002731476,0.0001963484,0.0003544625,0.001213687,0.0001917777,0.0002634216,0.0002672381,0.00119508,0.00002752955],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004390414,"about_ca_system_score_gemma":0.00784172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004175501,"about_ca_topic_score_gemma":0.00005125638,"domain_scores_codex":[0.9922054,0.002055422,0.003764444,0.0004311143,0.0005919499,0.0009516539],"domain_scores_gemma":[0.9958708,0.000393164,0.001353927,0.0009446606,0.0004848115,0.0009526234],"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":[0.00002979316,0.00009820014,0.06792877,0.8893125,0.0001054145,0.00003408876,0.003431899,0.00002520552,0.000003865624,0.001124405,0.00284042,0.03506543],"study_design_scores_gemma":[0.002560544,0.0007250548,0.02517862,0.8971699,0.00006936039,0.001090947,0.02147727,0.000009084744,0.000006933447,0.0004805071,0.05080448,0.0004272441],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.07955088,0.8804961,0.0002321517,0.02428096,0.0007522017,0.0120129,0.0004187069,0.00008613599,0.002169944],"genre_scores_gemma":[0.9457225,0.04865474,0.0002592471,0.00471912,0.0001080183,0.0003321579,0.00002011203,0.0000731772,0.000110967],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8661716,"threshold_uncertainty_score":0.9977829,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4280518374","doi":"10.1093/ehjdh/ztac025","title":"Applications of artificial intelligence and machine learning in heart failure","year":2022,"lang":"en","type":"review","venue":"European Heart Journal - Digital Health","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":97,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Impact; Population Health Research Institute; McMaster University","funders":"","keywords":"Medicine; Artificial intelligence; Machine learning; Raw data; Cardiac decompensation; Decompensation; Health care; Heart failure; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.3049971717223502,"gpt":0.462322124839359,"spread":0.1573249531170087,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001961743,0.0003042688,0.001331349,0.0006579284,0.0003801365,0.0001181794,0.0001667681,0.00008475915,0.0002214945],"category_scores_gemma":[0.0004410202,0.0002729277,0.0003066968,0.0008391711,0.0001158094,0.0001878855,0.0001187928,0.002293942,0.0001212885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003600285,"about_ca_system_score_gemma":0.001476748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001196326,"about_ca_topic_score_gemma":0.00003313511,"domain_scores_codex":[0.9959002,0.000714796,0.002110675,0.000407093,0.0003988194,0.0004683775],"domain_scores_gemma":[0.997883,0.0005601525,0.0006740617,0.0002836377,0.00009845645,0.0005006752],"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":[0.00001681047,0.0001892656,0.0004349346,0.004885538,0.00001573166,0.00002078206,0.0004196631,0.000005752925,1.21531e-7,0.00007529071,0.0005028432,0.9934332],"study_design_scores_gemma":[0.00001413823,0.000733593,0.00003405874,0.004103373,0.00003553053,0.002423758,0.0008715997,0.00002395898,0.000001001008,0.0002573258,0.9913316,0.0001700653],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001071284,0.9949121,0.0005736193,0.002520874,0.0002271582,0.001139745,0.00004382673,0.00004056088,0.0004349249],"genre_scores_gemma":[0.003210104,0.9946331,0.000667737,0.0003562289,0.0006517027,0.00003184424,0.0001739415,0.0000904051,0.0001849625],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9932632,"threshold_uncertainty_score":0.9999723,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3195815158","doi":"10.1093/ehjdh/ztab048","title":"Deep learning analysis of resting electrocardiograms for the detection of myocardial dysfunction, hypertrophy, and ischaemia: a systematic review","year":2021,"lang":"en","type":"review","venue":"European Heart Journal - Digital Health","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":49,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Jewish General Hospital","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Cardiology; Internal medicine; Left ventricular hypertrophy; Myocardial ischaemia; Ischemia; Myocardial ischemia; Electrocardiography; Blood pressure","retraction":null,"screen_n_in":null,"score":{"opus":0.04898089170747566,"gpt":0.3461857832591219,"spread":0.2972048915516463,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003049144,0.0003147943,0.004926023,0.0005188427,0.0003546339,0.0001037783,0.0001119021,0.00006817903,0.000001580399],"category_scores_gemma":[0.002467249,0.0001935619,0.002917814,0.001865054,0.00005664164,0.00009217617,0.00005425863,0.0009118451,0.000002055948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000152478,"about_ca_system_score_gemma":0.0002306528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001411848,"about_ca_topic_score_gemma":0.000001410784,"domain_scores_codex":[0.9955909,0.001248006,0.002033442,0.0003210387,0.0004823538,0.0003243142],"domain_scores_gemma":[0.9961306,0.001014502,0.001740476,0.0003881313,0.0004929449,0.0002333682],"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":[0.00001114772,0.00003078025,0.0000991835,0.499534,0.007002886,0.00002058808,0.00004192619,0.00002866434,0.000001596717,7.686296e-7,0.00003427107,0.4931942],"study_design_scores_gemma":[0.0003657695,0.001547793,0.0001249398,0.7919277,0.09314858,0.004068706,0.0002921769,0.0005805934,8.565894e-7,0.00000120628,0.1076404,0.0003013044],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00003091204,0.9927323,0.00603857,0.000084384,0.0001436323,0.000875502,0.000008851091,0.00002079752,0.0000650178],"genre_scores_gemma":[0.004523055,0.9944546,0.0001517513,0.00007403015,0.0005442375,0.00001934201,0.00005221495,0.00006687608,0.0001138848],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4928929,"threshold_uncertainty_score":0.7893224,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3214762646","doi":"10.1093/ehjdh/ztab101","title":"Development of a machine learning model using electrocardiogram signals to improve acute pulmonary embolism screening","year":2021,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Venous Thromboembolism Diagnosis and Management","field":"Medicine","cited_by":33,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Impact; McMaster University; Population Health Research Institute","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Heart, Lung, and Blood Institute; National Institutes of Health; National Center for Advancing Translational Sciences; Icahn School of Medicine at Mount Sinai","keywords":"Medicine; Pulmonary embolism; Receiver operating characteristic; Artificial intelligence; Retrospective cohort study; Cohort; Internal medicine; Electrocardiography; Cardiology; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.05031416966398888,"gpt":0.3297902879970327,"spread":0.2794761183330439,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001084858,0.0002734978,0.0008643495,0.0002876309,0.0004540596,0.000185825,0.0001303656,0.00003245948,0.00002387645],"category_scores_gemma":[0.0000918346,0.0002562641,0.0003048922,0.0004214648,0.00002432105,0.0002728847,0.0002772575,0.0005955782,0.00003356706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002013405,"about_ca_system_score_gemma":0.0007528917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001040229,"about_ca_topic_score_gemma":0.000001687589,"domain_scores_codex":[0.9970506,0.0001863436,0.0009954395,0.0003965524,0.0006297564,0.0007412385],"domain_scores_gemma":[0.9983633,0.00003517573,0.0002998353,0.000248463,0.000263011,0.0007901909],"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":[0.0005377625,0.00259248,0.005075375,0.0009314668,0.002105891,0.003972861,0.005642143,0.03416105,0.09450551,0.0001045997,0.003300468,0.8470704],"study_design_scores_gemma":[0.01298623,0.01239223,0.1631827,0.0158615,0.001914094,0.04013784,0.006693776,0.2194841,0.03891386,0.0006255837,0.4827473,0.00506078],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9016764,0.00259217,0.08629492,0.002389708,0.0002157145,0.0006881857,0.0000296779,0.0001116392,0.006001545],"genre_scores_gemma":[0.9218962,0.0003322772,0.07392862,0.002843856,0.000293576,0.000003372858,0.0000441744,0.0001038012,0.0005540706],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8420096,"threshold_uncertainty_score":0.999989,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4409323950","doi":"10.1093/ehjdh/ztaf034","title":"Development and multinational validation of an ensemble deep learning algorithm for detecting and predicting structural heart disease using noisy single-lead electrocardiograms","year":2025,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institutes of Health; Yale University; National Heart, Lung, and Blood Institute; Bristol-Myers Squibb Canada; National Institute on Aging; Bristol-Myers Squibb; Doris Duke Charitable Foundation","keywords":"Computer science; Multinational corporation; Artificial intelligence; Ensemble learning; Lead (geology); Algorithm; Cross-validation; Machine learning; Pattern recognition (psychology); Finance","retraction":null,"screen_n_in":null,"score":{"opus":0.03511543079916488,"gpt":0.3273124225099162,"spread":0.2921969917107513,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007558546,0.0001404007,0.0002978859,0.0002349374,0.0006574072,0.0001934236,0.00003269187,0.00002161481,4.552477e-7],"category_scores_gemma":[0.000328707,0.0001324775,0.00008307199,0.0001936059,0.00003510105,0.0003166854,0.00003868774,0.0002736411,2.533912e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001352813,"about_ca_system_score_gemma":0.0001513004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008128855,"about_ca_topic_score_gemma":9.698865e-7,"domain_scores_codex":[0.9985748,0.000146172,0.0005042028,0.0002369561,0.0002415986,0.0002962719],"domain_scores_gemma":[0.9990926,0.0001292469,0.0001998008,0.00007233195,0.0002005279,0.0003054539],"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":[0.00008479584,0.00005988513,0.1491712,0.0002468434,0.00009260228,0.00001302977,0.0005407146,0.000309084,0.003564296,0.000001546879,0.000003345859,0.8459126],"study_design_scores_gemma":[0.004773976,0.002191911,0.3972726,0.00320392,0.0003690998,0.002057955,0.003972591,0.5706272,0.01275574,0.000178904,0.0019809,0.0006151517],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9613214,0.0007973675,0.03736794,0.0001714196,0.00008818591,0.0001722221,0.000004281841,0.00003731635,0.00003985772],"genre_scores_gemma":[0.9040173,0.000007766724,0.09551822,0.00008000339,0.0002788741,0.0000010923,0.00003001249,0.00002381684,0.00004293678],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8452975,"threshold_uncertainty_score":0.5402275,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4224250841","doi":"10.1093/ehjdh/ztac004","title":"Harnessing feature extraction capacities from a pre-trained convolutional neural network (VGG-16) for the unsupervised distinction of aortic outflow velocity profiles in patients with severe aortic stenosis","year":2022,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Cardiac Valve Diseases and Treatments","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Technische Universität München","keywords":"Cardiology; Internal medicine; Medicine; Stenosis; Aortic valve stenosis; Aortic valve; Hazard ratio; Confidence interval","retraction":null,"screen_n_in":null,"score":{"opus":0.02370293776615857,"gpt":0.3027257709217228,"spread":0.2790228331555642,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002955928,0.000186564,0.0003545079,0.00006856483,0.0006708796,0.0000904321,0.00006560983,0.0000195394,0.00004021033],"category_scores_gemma":[0.00007436609,0.000129088,0.0003702519,0.0002065054,0.00008342831,0.0002895956,0.00004128515,0.0004037711,0.000001241198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004968569,"about_ca_system_score_gemma":0.0002907494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009667882,"about_ca_topic_score_gemma":0.000006509686,"domain_scores_codex":[0.9981703,0.0002749898,0.0004445534,0.0002336398,0.0005248118,0.0003517023],"domain_scores_gemma":[0.9989646,0.0002035489,0.0003071088,0.0001623876,0.0001614355,0.0002008903],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003323634,0.0005914217,0.9717737,0.0001083994,0.000275173,0.000008791363,0.0005308962,0.001369951,0.000002436378,0.000003078864,0.001393699,0.02061878],"study_design_scores_gemma":[0.003646445,0.001236478,0.9916901,0.0002330757,0.0001661949,0.00004508111,0.001169794,0.001416763,7.388782e-7,0.00004018348,0.0002399855,0.0001151318],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9960284,0.0005232443,0.0001627501,0.0009701878,0.0003898561,0.0009925325,0.0008405464,0.00002563459,0.00006680096],"genre_scores_gemma":[0.998252,0.00001137576,0.0001519795,0.0003595025,0.0003300747,0.00003292653,0.0006997061,0.00004191355,0.0001205],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02050365,"threshold_uncertainty_score":0.5264057,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388667507","doi":"10.1093/ehjdh/ztad071","title":"Feasibility and accuracy of real-time 3D-holographic graft length measurements","year":2023,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"St. Paul's Hospital; University of British Columbia","funders":"University of Galway","keywords":"Medicine; Artery; Nuclear medicine; Holography; Radiology; Surgery","retraction":null,"screen_n_in":null,"score":{"opus":0.2012091056447465,"gpt":0.3971525682336164,"spread":0.1959434625888699,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002084088,0.0001322622,0.000359799,0.0002077714,0.0001792578,0.0000683278,0.00006070434,0.00002561815,0.00006598506],"category_scores_gemma":[0.000691129,0.0001053023,0.0001345236,0.0004488521,0.00009758596,0.0002336445,0.00004966992,0.0003009105,0.0001551965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004802774,"about_ca_system_score_gemma":0.0001227032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007106124,"about_ca_topic_score_gemma":7.454742e-7,"domain_scores_codex":[0.9980704,0.0002917536,0.0006150617,0.000220287,0.0004521807,0.0003503654],"domain_scores_gemma":[0.9986497,0.0002876259,0.0002041213,0.0001859631,0.0001081697,0.0005643946],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004921099,0.0003584682,0.8632004,0.0001890153,0.00009333851,0.0002801654,0.0006424327,0.00002088095,0.0002659457,0.00001895062,0.002306896,0.1321314],"study_design_scores_gemma":[0.002737602,0.0006596636,0.9859806,0.0002633005,0.00001172892,0.0004440038,0.00009330983,0.0001281202,0.000008405784,0.0001016271,0.009474921,0.00009677194],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9789459,0.0002279621,0.000006367518,0.001223914,0.00009902145,0.0002333594,0.00001167075,0.0001265152,0.01912534],"genre_scores_gemma":[0.9986612,0.0003219108,0.0001369967,0.0004884,0.0001316377,3.763793e-7,0.00001933773,0.00003022079,0.00020991],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1320346,"threshold_uncertainty_score":0.4294104,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3170186245","doi":"10.1093/ehjdh/ztab055","title":"Voice-based screening for SARS-CoV-2 exposure in cardiovascular clinics","year":2021,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"Montreal Heart Institute; University of Ottawa; McGill University; Université de Montréal; McGill University Health Centre","funders":"McGill University Health Centre; Amazon Web Services","keywords":"Medicine; Context (archaeology); Cohen's kappa; Inter-rater reliability; Health care; Confidence interval; Kappa; Family medicine; Rating scale; Internal medicine; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.3217032978222115,"gpt":0.4592702664062936,"spread":0.1375669685840821,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002427998,0.000171799,0.0005259388,0.0001749825,0.0002769867,0.000184285,0.0000906214,0.00006191681,0.000009453817],"category_scores_gemma":[0.001105346,0.0001667478,0.0005211156,0.000360591,0.00004230503,0.0002722191,0.00002563297,0.0006401277,0.0001091832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002124183,"about_ca_system_score_gemma":0.001554224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005029998,"about_ca_topic_score_gemma":0.00003416113,"domain_scores_codex":[0.9972121,0.0003733827,0.001098656,0.000345185,0.0003919625,0.0005787371],"domain_scores_gemma":[0.9983108,0.0003190787,0.0001697684,0.0003752025,0.0004699258,0.0003552352],"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":[0.0005489283,0.000746175,0.1228904,0.0007726655,0.0001443951,0.0009199425,0.001586297,0.0005536021,0.0002498289,0.00003331178,0.01412602,0.8574284],"study_design_scores_gemma":[0.001788506,0.004188569,0.08927369,0.003235289,0.00009164657,0.004061259,0.004158392,0.001902718,0.006924896,0.0006838001,0.8830164,0.00067483],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9473327,0.0115888,0.01819136,0.0188249,0.001466468,0.0008273044,0.00003585474,0.00008118884,0.00165142],"genre_scores_gemma":[0.9830658,0.0002157223,0.005120074,0.009770174,0.001518129,0.000005974741,0.00007623426,0.00006730579,0.0001605752],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8688904,"threshold_uncertainty_score":0.6799779,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3158681032","doi":"10.1093/ehjdh/ztab044","title":"Remote monitoring of patients with heart failure during the first national lockdown for COVID-19 in France","year":2021,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"COVID-19 Clinical Research Studies","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Agence Nationale de la Recherche","keywords":"Medicine; Coronavirus disease 2019 (COVID-19); Atrial fibrillation; Heart failure; Heart rate; Blood pressure; Internal medicine; Vital signs; Emergency medicine; Cardiology; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Anesthesia","retraction":null,"screen_n_in":null,"score":{"opus":0.06166184558678729,"gpt":0.415034096047281,"spread":0.3533722504604938,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001397608,0.0001537121,0.0004112535,0.0001238977,0.0004518849,0.00008599235,0.000135126,0.00002479406,0.00001675933],"category_scores_gemma":[0.0156399,0.0001033799,0.0001576222,0.0004031777,0.0001342721,0.0002096157,0.0001376611,0.0006393948,0.00001268324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005938833,"about_ca_system_score_gemma":0.001746325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002043959,"about_ca_topic_score_gemma":0.00001851691,"domain_scores_codex":[0.997382,0.0001719782,0.0007129392,0.0002914965,0.0009681013,0.0004734717],"domain_scores_gemma":[0.9961034,0.0022914,0.0001956653,0.0002269265,0.0006810714,0.0005015341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003883651,0.0002568527,0.9935417,0.001046981,0.00004050195,0.00006250804,0.0002929059,0.0004528441,0.00001079875,0.000004665135,0.002970316,0.0009315182],"study_design_scores_gemma":[0.002738103,0.0006012313,0.8297508,0.0007272862,0.000003949069,0.00004274732,0.0001025933,0.00003301781,0.00002110455,0.00005080464,0.1658473,0.0000810066],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9148726,0.0004932189,0.000390432,0.08302308,0.0001538081,0.0007519571,0.000109586,0.00002794712,0.0001773813],"genre_scores_gemma":[0.9936916,0.0001080767,0.001174908,0.00411051,0.0004652743,0.000003337725,0.00001012788,0.00003655209,0.0003996242],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1637909,"threshold_uncertainty_score":0.9926518,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4376140131","doi":"10.1093/ehjdh/ztad032","title":"The AppCare-HF randomized clinical trial: a feasibility study of a novel self-care support mobile app for individuals with chronic heart failure","year":2023,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Heart Failure Treatment and Management","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Japan Science and Technology Agency; Center of Innovation Program; Japan Society for the Promotion of Science; Fukuda Foundation for Medical Technology; Pfizer Health Research Foundation; Pfizer; Japan Agency for Medical Research and Development; Health Research Foundation","keywords":"Medicine; Heart failure; Randomized controlled trial; Self care; Physical therapy; Intensive care medicine; Internal medicine; Health care","retraction":null,"screen_n_in":null,"score":{"opus":0.08915800788675032,"gpt":0.410836304254698,"spread":0.3216782963679477,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01089863,0.0003773849,0.001643243,0.0002144324,0.0006131919,0.0002725408,0.0002406666,0.0000586864,0.0000178977],"category_scores_gemma":[0.0005929794,0.0002142468,0.0007508777,0.0005190382,0.0001944433,0.0002478203,0.0001666795,0.0005915044,0.00008826757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002940972,"about_ca_system_score_gemma":0.001261129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001344081,"about_ca_topic_score_gemma":0.00005538448,"domain_scores_codex":[0.994293,0.001264684,0.002093767,0.0005818409,0.0009258748,0.0008408295],"domain_scores_gemma":[0.9960565,0.001581056,0.0005934063,0.0007282819,0.0003643084,0.0006764582],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","study_design_scores_codex":[0.4635763,0.02134084,0.1362779,0.001998313,0.004564269,0.0003225906,0.01381937,0.0001004854,0.00000711252,0.00009603857,0.3280465,0.02985034],"study_design_scores_gemma":[0.5674967,0.03917797,0.0105758,0.0002624134,0.0003133994,0.0002158304,0.006573443,0.00004259174,0.000002048772,0.00001094874,0.3751121,0.0002166714],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9660003,0.0004898806,0.0001883652,0.009790453,0.0004950777,0.02215688,0.0001020178,0.0003559653,0.0004211167],"genre_scores_gemma":[0.9954036,0.0001333793,0.001922781,0.0005014415,0.0008394846,0.0003218766,0.0001098659,0.0001106081,0.0006569581],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1257021,"threshold_uncertainty_score":0.8736729,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4319340692","doi":"10.1093/ehjdh/ztad010","title":"The association of electronic health literacy with behavioural and psychological coronary artery disease risk factors in patients after percutaneous coronary intervention: a 12-month follow-up study","year":2023,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Health Literacy and Information Accessibility","field":"Health Professions","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Public Health Ontario; University of Toronto","funders":"St. Olavs Hospital Universitetssykehuset i Trondheim; Helse Vest","keywords":"eHealth; Medicine; Health literacy; Percutaneous coronary intervention; Conventional PCI; Literacy; The Internet; Population; Psychological intervention; Gerontology; Physical therapy; Internal medicine; Health care; Psychiatry; Myocardial infarction; Environmental health; World Wide Web; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.04854058281020193,"gpt":0.3972469304124254,"spread":0.3487063476022235,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.005895288,0.0002781368,0.0005067213,0.0002251105,0.001504062,0.0001824266,0.0002248959,0.00005987041,0.00005008732],"category_scores_gemma":[0.0004545297,0.0001770792,0.000143515,0.0004012403,0.00007005497,0.001537139,0.0001589081,0.001763043,0.00006821166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001021417,"about_ca_system_score_gemma":0.0005241124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001145763,"about_ca_topic_score_gemma":0.0003543612,"domain_scores_codex":[0.9906632,0.004427753,0.002682095,0.000375857,0.00070675,0.001144349],"domain_scores_gemma":[0.9961389,0.0007752207,0.001677273,0.0003648208,0.0002997549,0.0007439828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002595302,0.0008477503,0.9633365,0.0001456824,0.00002567438,0.00004846021,0.009323798,0.000003281381,1.337298e-8,0.000003389654,0.00110223,0.02256789],"study_design_scores_gemma":[0.003057937,0.005950663,0.9854919,0.00045504,0.000009661455,0.00003583307,0.002944495,0.00008444829,6.442291e-9,0.00006072835,0.001759959,0.0001493388],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9956689,0.0002669046,0.00001511369,0.001113321,0.0005741996,0.001903685,0.0002819097,0.0000768548,0.0000991531],"genre_scores_gemma":[0.997784,0.0002758517,0.00001773577,0.001126636,0.00007963443,0.00003134983,0.0001577324,0.00003790986,0.0004891819],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02241855,"threshold_uncertainty_score":0.9997959,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4407429394","doi":"10.1093/ehjdh/ztaf006","title":"Machine-learning phenotyping of patients with functional mitral regurgitation undergoing transcatheter edge-to-edge repair: the MITRA-AI study","year":2025,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Cardiac Valve Diseases and Treatments","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Surgical Specialties (Canada)","funders":"","keywords":"Clinical endpoint; Medicine; Mitral regurgitation; Internal medicine; Cardiology; Cohort; Ejection fraction; Heart failure; Functional mitral regurgitation; Atrial fibrillation; Clinical trial","retraction":null,"screen_n_in":null,"score":{"opus":0.0205815233149,"gpt":0.3206287653366506,"spread":0.3000472420217506,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004628856,0.0001993991,0.0003444139,0.0001854825,0.0004435893,0.0001183656,0.00006652642,0.00001580226,0.0000172787],"category_scores_gemma":[0.0001219232,0.0001291688,0.001036767,0.0003182369,0.0000414451,0.0002390588,0.00003190665,0.000394091,0.00002522438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001753948,"about_ca_system_score_gemma":0.0003489193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001158519,"about_ca_topic_score_gemma":0.000004740554,"domain_scores_codex":[0.9980818,0.0003330429,0.0005376775,0.0002699654,0.0004573209,0.0003201895],"domain_scores_gemma":[0.9989053,0.0001654187,0.0001598878,0.0002233733,0.000251706,0.0002942939],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001440885,0.001194114,0.9830497,0.0001225489,0.001148149,0.00001579243,0.0009251179,0.0002171226,0.000001190015,0.00003273065,0.001097613,0.01075502],"study_design_scores_gemma":[0.003713657,0.001970394,0.9902973,0.0004842912,0.0003131513,0.00003123664,0.000683638,0.00004411996,9.076132e-7,0.00002836726,0.002330544,0.0001023979],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9919087,0.0009679468,0.0007659465,0.001555637,0.0002949437,0.0009285659,0.00004470401,0.00007014869,0.003463453],"genre_scores_gemma":[0.9975625,0.00001521092,0.00009003779,0.001561,0.000132754,0.000004622014,0.00006474191,0.0000419353,0.0005271477],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01065262,"threshold_uncertainty_score":0.526735,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4406895577","doi":"10.1093/ehjdh/ztaf005","title":"Artificial intelligence for the analysis of intracoronary optical coherence tomography images: a systematic review","year":2025,"lang":"en","type":"review","venue":"European Heart Journal - Digital Health","topic":"Coronary Interventions and Diagnostics","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University; Population Health Research Institute; Hamilton General Hospital; McGill University; Hamilton Health Sciences; Royal Victoria Hospital","funders":"Ministerie van Economische Zaken en Klimaat; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Optical coherence tomography; Computer science; Artificial intelligence; Revascularization; Interpretation (philosophy); Medical physics; Radiology; Medicine; Cardiology","retraction":null,"screen_n_in":null,"score":{"opus":0.1113657544975806,"gpt":0.4274971845208105,"spread":0.3161314300232299,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002528725,0.0003913147,0.003860159,0.0006630456,0.0002177573,0.0001656672,0.0004438837,0.0000595947,0.00008445788],"category_scores_gemma":[0.002977802,0.0002308896,0.003852271,0.001785621,0.0001572704,0.000116857,0.000128283,0.0007291017,0.0000411356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001400995,"about_ca_system_score_gemma":0.0008918906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003393285,"about_ca_topic_score_gemma":0.000002632733,"domain_scores_codex":[0.9947554,0.000569368,0.003487076,0.0003473295,0.0004462944,0.0003944588],"domain_scores_gemma":[0.9931725,0.004179281,0.00118942,0.0006993904,0.0004162033,0.0003431753],"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":[0.0000135147,0.0002406488,0.000004597813,0.5512573,0.00135283,0.00005731263,0.0000123822,0.000001327871,5.832186e-9,0.0001011658,0.002542863,0.4444161],"study_design_scores_gemma":[0.0000441394,0.0009836528,0.00006723449,0.9110503,0.02364774,0.001297476,0.00007828348,0.00002842734,9.905779e-8,0.00005488134,0.06254987,0.0001978951],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[9.309384e-7,0.9867265,0.007720465,0.0008134063,0.0002555036,0.003461977,0.0005025127,0.00002356887,0.0004950968],"genre_scores_gemma":[0.000192842,0.9978579,0.000462696,0.0007212026,0.0001762384,0.00007302269,0.0001769745,0.00004014668,0.000298946],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4442182,"threshold_uncertainty_score":0.9415404,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4410588928","doi":"10.1093/ehjdh/ztaf009","title":"Examination of the performance of machine learning-based automated coronary plaque characterization by near-infrared spectroscopy–intravascular ultrasound and optical coherence tomography with histology","year":2025,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Coronary Interventions and Diagnostics","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"British Heart Foundation","keywords":"Optical coherence tomography; Intravascular ultrasound; Medicine; Histology; Radiology; Biomedical engineering; Materials science; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.008423267700267857,"gpt":0.2551061414386032,"spread":0.2466828737383354,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003183822,0.0001111059,0.0002538412,0.00009590515,0.0001649266,0.00003800907,0.00006767951,0.00002633102,0.00002448607],"category_scores_gemma":[0.0001222652,0.00007949226,0.00007338966,0.0002332788,0.0002421875,0.0001228717,0.00002263389,0.00028978,0.000001272766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005970049,"about_ca_system_score_gemma":0.0002219504,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006423845,"about_ca_topic_score_gemma":0.00000202558,"domain_scores_codex":[0.998886,0.0002010535,0.0004327146,0.0001319681,0.0001902998,0.0001579543],"domain_scores_gemma":[0.999229,0.0001487034,0.0002390567,0.0001374367,0.0001441741,0.0001016784],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006835331,0.0007954598,0.9767622,0.0007380467,0.0001040145,0.00003681441,0.000219319,0.0001942556,0.01097109,0.00004218677,0.0008518785,0.008601198],"study_design_scores_gemma":[0.001089499,0.00342119,0.9846985,0.0009175211,0.00003456102,0.0006533492,0.00002834167,0.006054422,0.0015468,0.000002006311,0.001491646,0.00006217298],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9970213,0.0004912852,0.001034445,0.0004903091,0.00006772915,0.0002551935,0.00004508618,0.00003529842,0.0005593945],"genre_scores_gemma":[0.9989305,0.0001274535,0.0003300078,0.0002195201,0.00001188476,0.000001332203,0.0001229664,0.00001385363,0.0002425251],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009424288,"threshold_uncertainty_score":0.32416,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4407871197","doi":"10.1093/ehjdh/ztaf008","title":"An investigation into the causes of race bias in artificial intelligence–based cine cardiac magnetic resonance segmentation","year":2025,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"St. Thomas Hospital","funders":"","keywords":"Segmentation; Artificial intelligence; Interpretability; Computer science; Race (biology); Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.06333906124269503,"gpt":0.3621886258317769,"spread":0.2988495645890819,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001505163,0.0001252645,0.0003011103,0.0002479384,0.0001423519,0.0001200155,0.00008107013,0.00002024428,0.000006123414],"category_scores_gemma":[0.0007574654,0.000097039,0.0001041727,0.0005436281,0.0001544572,0.0002024043,0.00002279339,0.0003476187,0.00001844698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000151994,"about_ca_system_score_gemma":0.0005998024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001547177,"about_ca_topic_score_gemma":0.00002654692,"domain_scores_codex":[0.9980837,0.0005224072,0.0006882058,0.0001800914,0.0003011888,0.0002243733],"domain_scores_gemma":[0.9988426,0.0004103203,0.0001483555,0.0002486939,0.0001649665,0.000185086],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000324565,0.0003175457,0.5894068,0.0002449553,0.00001637472,0.00008218356,0.004564361,0.0009227665,0.00115173,0.0003150912,0.004998961,0.3976547],"study_design_scores_gemma":[0.0006028438,0.001424343,0.9810766,0.001671456,0.00004458236,0.00007300734,0.00296308,0.001239738,0.004491606,0.001189173,0.005055571,0.0001680065],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9793952,0.00688099,0.0007205083,0.01143606,0.0004575426,0.0003927072,0.00001687572,0.00003140997,0.0006687128],"genre_scores_gemma":[0.9959651,0.0002040936,0.0008714594,0.00257775,0.0002285565,0.000002612544,0.00003156052,0.00001968148,0.00009920953],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3974867,"threshold_uncertainty_score":0.3957136,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4408577077","doi":"10.1093/ehjdh/ztaf018","title":"Racial and ethnic disparities in aortic stenosis within a universal healthcare system characterized by natural language processing for targeted intervention","year":2025,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Cardiac Valve Diseases and Treatments","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Network for Business Sustainability","funders":"King's College London; British Heart Foundation; King’s College Hospital Charity; King’s College London; Australian Mammal Society","keywords":"Ethnic group; Intervention (counseling); Health care; Stenosis; Natural (archaeology); Medicine; Healthcare system; Cardiology; Nursing; Sociology; Economic growth; Geography; Economics; Anthropology","retraction":null,"screen_n_in":null,"score":{"opus":0.01997162733823016,"gpt":0.3693509752662998,"spread":0.3493793479280697,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003618814,0.0001584539,0.000410943,0.0001778666,0.000189153,0.0001715198,0.0000409842,0.00002805971,0.000001352514],"category_scores_gemma":[0.00005296925,0.0001359476,0.0003240364,0.0001832496,0.00003575611,0.0003171981,0.00003603693,0.0002826696,0.000002406299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000398462,"about_ca_system_score_gemma":0.0002223386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008666386,"about_ca_topic_score_gemma":0.000007799951,"domain_scores_codex":[0.9985896,0.0002003266,0.0005080272,0.0002188752,0.0001623303,0.0003208861],"domain_scores_gemma":[0.9993346,0.00003993318,0.0001853031,0.00008510859,0.00008851098,0.0002665126],"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":[0.00568638,0.00102978,0.4514005,0.01429147,0.0006142747,0.0003667013,0.004555639,0.000001461093,0.0002849438,0.00009480286,0.001128584,0.5205454],"study_design_scores_gemma":[0.007345111,0.001103456,0.9791346,0.005638659,0.0001313521,0.0001526883,0.005551117,0.0003581069,0.00001911815,0.00001074179,0.0003673438,0.0001876838],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9760472,0.02107169,0.00009651338,0.001414728,0.0002804983,0.0007664036,0.0001872095,0.00005310502,0.00008260416],"genre_scores_gemma":[0.9985273,0.00008770941,0.00005354425,0.0005997514,0.0001187851,0.00001107759,0.0002049914,0.00002792883,0.0003689233],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5277341,"threshold_uncertainty_score":0.5543784,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391919090","doi":"10.1093/ehjdh/ztae012","title":"Impact of age and comorbid heart failure on the utility of smart voice-assistant devices","year":2024,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"AI in Service Interactions","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Montreal Heart Institute; McGill University; Université de Montréal; McGill University Health Centre","funders":"McGill University Health Centre; McGill University; Amazon Web Services; American Welding Society","keywords":"Concordance; Medicine; Subgroup analysis; Population; Heart failure; Gerontology; Audiology; Physical therapy; Family medicine; Internal medicine; Confidence interval","retraction":null,"screen_n_in":null,"score":{"opus":0.05652378643529181,"gpt":0.3492112892225513,"spread":0.2926875027872595,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001175065,0.0001746639,0.0002917503,0.0001452643,0.0002253389,0.0006939902,0.00049501,0.00002062196,0.00003960075],"category_scores_gemma":[0.000080258,0.0001087881,0.0002399553,0.0003949189,0.0001125422,0.0009577592,0.0002176341,0.0005922054,0.00009113345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008283256,"about_ca_system_score_gemma":0.0003132324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001148558,"about_ca_topic_score_gemma":0.00006354399,"domain_scores_codex":[0.9979343,0.0004327568,0.0006435597,0.0002691286,0.0004015294,0.0003186801],"domain_scores_gemma":[0.9982974,0.0006278026,0.0002076336,0.0004703118,0.000123013,0.0002738472],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0004421565,0.002393624,0.1667406,0.002245843,0.000955508,0.001683766,0.01875804,0.0001457016,0.001628015,0.01170497,0.6903185,0.1029833],"study_design_scores_gemma":[0.0002308374,0.002700625,0.8444588,0.001597626,0.0000102719,0.002583722,0.0003813666,0.004016613,0.00009422981,0.0009385135,0.1427367,0.0002506589],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9679539,0.0009753447,0.001598023,0.02294211,0.0005230549,0.0002274426,0.00009358882,0.00009171782,0.005594772],"genre_scores_gemma":[0.9982163,0.00002795974,0.0007928836,0.0007784273,0.00009402171,5.806075e-7,0.00000153208,0.00002030514,0.00006801351],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6777182,"threshold_uncertainty_score":0.6692163,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388892778","doi":"10.1093/ehjdh/ztad073","title":"Development and internal validation of machine learning–based models and external validation of existing risk scores for outcome prediction in patients with ischaemic stroke","year":2023,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"National Institute on Minority Health and Health Disparities","keywords":"Medicine; Random forest; Receiver operating characteristic; Support vector machine; Gradient boosting; Predictive modelling; Stroke (engine); Outcome (game theory); Machine learning; Failure to thrive; Artificial intelligence; Internal medicine; Computer science; Engineering; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0723013014128489,"gpt":0.3224504234544739,"spread":0.250149122041625,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001034559,0.0001252602,0.0002758807,0.000325813,0.00008701783,0.00003834824,0.00004371276,0.00001713698,0.000002397504],"category_scores_gemma":[0.0001702182,0.0001031327,0.00003544258,0.0001172507,0.00003769203,0.0002768198,0.00006168014,0.0002416596,0.000001264627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009640629,"about_ca_system_score_gemma":0.00007021752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001521795,"about_ca_topic_score_gemma":0.00000112328,"domain_scores_codex":[0.9984347,0.00009029804,0.0007381348,0.000181379,0.0003598376,0.0001956101],"domain_scores_gemma":[0.9990999,0.00007396092,0.0005013925,0.0000756359,0.0001196523,0.000129516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005164562,0.00007976554,0.9848638,0.0003314897,0.00003285456,0.000005147529,0.0005432954,0.00206809,0.000103667,0.000002820595,0.00008384106,0.01136876],"study_design_scores_gemma":[0.005423632,0.001826862,0.9725735,0.00134999,0.00003486108,0.00004062728,0.000205716,0.01669575,0.001371965,0.00001524038,0.0003503635,0.0001114904],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9841139,0.00005439199,0.01495022,0.0000766267,0.00005087086,0.0004226028,0.00007515496,0.00002379365,0.0002324148],"genre_scores_gemma":[0.9933581,0.00002127532,0.006207928,0.0000353082,0.00004315292,0.000002890889,0.0001067079,0.00002891927,0.0001957327],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01462766,"threshold_uncertainty_score":0.4205628,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411668162","doi":"10.1093/ehjdh/ztaf061","title":"The hope and the hype of artificial intelligence for syncope management","year":2025,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Cardiovascular Syncope and Autonomic Disorders","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; Libin Cardiovascular Institute of Alberta; Ottawa Public Health; University of Calgary","funders":"","keywords":"Syncope (phonology); Business; Psychology; Medicine; Cardiology","retraction":null,"screen_n_in":null,"score":{"opus":0.02663198031836012,"gpt":0.3137272678009762,"spread":0.2870952874826161,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002089781,0.00009714072,0.0002789577,0.00006292299,0.0003731157,0.0001893857,0.0001288731,0.00001053208,0.000003159865],"category_scores_gemma":[0.000140333,0.00005259921,0.0002700659,0.0001410634,0.0002278674,0.00007617098,0.00009262488,0.0001727303,0.00001682066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003859328,"about_ca_system_score_gemma":0.0001402499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005283001,"about_ca_topic_score_gemma":0.000002541434,"domain_scores_codex":[0.9988185,0.0001367107,0.0005164744,0.0001369658,0.0001602105,0.0002311027],"domain_scores_gemma":[0.9992374,0.0002413978,0.0001078529,0.0002494391,0.00006885261,0.0000950269],"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":[0.0005824738,0.00005582446,0.0001091873,0.0001523337,0.0002456746,0.00001371238,0.0001803281,0.000020206,0.000002178773,0.01310479,0.008537123,0.9769962],"study_design_scores_gemma":[0.002152439,0.0005911367,0.009106212,0.000750402,0.0001459002,0.0005459651,0.00341398,0.0004232985,0.00004852592,0.008321259,0.9743556,0.0001452859],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1915369,0.09060329,0.09582972,0.239508,0.004357782,0.008777653,0.00007807825,0.0001595778,0.369149],"genre_scores_gemma":[0.9915217,0.002875756,0.0004093923,0.002581015,0.0001781263,0.000005941812,0.000003010783,0.00002166656,0.002403385],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9768509,"threshold_uncertainty_score":0.2869742,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4410191686","doi":"10.1093/ehjdh/ztaf047","title":"A deep learning phenome wide association study of the electrocardiogram","year":2025,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Heart, Lung, and Blood Institute; Bristol-Myers Squibb Canada; Norges Idrettshøgskole; Johnson and Johnson; Boston Scientific Corporation; National Institutes of Health; Apple","keywords":"Phenome; Association (psychology); Artificial intelligence; Computer science; Medicine; Psychology; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.01768993546488477,"gpt":0.3133076825284766,"spread":0.2956177470635918,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001085969,0.0001008133,0.0003384153,0.0001551408,0.0003581806,0.0001095009,0.0001007534,0.0000172757,0.000003443038],"category_scores_gemma":[0.0008377544,0.00007039862,0.0002502803,0.0005982384,0.00001340678,0.00009840137,0.00005195156,0.0006998985,0.00001696924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003003627,"about_ca_system_score_gemma":0.0001196393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002168267,"about_ca_topic_score_gemma":0.000003830696,"domain_scores_codex":[0.9981866,0.0005031499,0.0004778658,0.0001386878,0.0004075403,0.0002861229],"domain_scores_gemma":[0.999055,0.0001866584,0.0002877374,0.0001756536,0.000157108,0.000137804],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002846603,0.0003083205,0.9800398,0.00003259763,0.0002280698,0.00001354249,0.0005337783,0.0001737942,0.00002520623,0.000001836483,0.001202209,0.01741239],"study_design_scores_gemma":[0.0009885419,0.001278686,0.9783934,0.0002976737,0.000107679,0.00004188768,0.001786816,0.0001167831,0.00001279258,0.00002961239,0.01687801,0.00006807714],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9845423,0.0006799644,0.0002815012,0.003528638,0.0002510649,0.0001962356,6.057923e-7,0.00004250324,0.01047723],"genre_scores_gemma":[0.9946504,0.00007225864,0.00004345388,0.0006276437,0.0002891027,7.33424e-7,0.000001512957,0.00001769503,0.004297187],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01734431,"threshold_uncertainty_score":0.304075,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4403736505","doi":"10.1093/ehjdh/ztae079","title":"Fine-tuned large language models can generate expert-level echocardiography reports","year":2024,"lang":"en","type":"editorial","venue":"European Heart Journal - Digital Health","topic":"Cardiovascular Function and Risk Factors","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Montreal Heart Institute","funders":"Institut de Cardiologie de Montréal; Fondation Institut de Cardiologie de Montréal; Canadian Institute for Advanced Research","keywords":"Computer science; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.03605042373573915,"gpt":0.3149609740743287,"spread":0.2789105503385896,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002525659,0.0007678359,0.001617399,0.0008736313,0.0004390324,0.0008717826,0.0001871522,0.0003619402,0.00007538571],"category_scores_gemma":[0.0004222389,0.0006015089,0.002843898,0.0006020683,0.00007457766,0.0003338387,0.0001938251,0.003457451,0.0002614108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005453179,"about_ca_system_score_gemma":0.002040444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001640854,"about_ca_topic_score_gemma":0.00003704884,"domain_scores_codex":[0.9936792,0.0005220947,0.001554999,0.0009814646,0.002170737,0.001091544],"domain_scores_gemma":[0.9962846,0.0001263202,0.0004814516,0.001059026,0.0004668627,0.001581759],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001065747,0.0001248997,0.000176614,0.0003118142,0.0008476183,0.01380964,0.0008484239,0.00003199777,0.000008405183,0.000002327527,0.9775906,0.006141147],"study_design_scores_gemma":[0.001103959,0.0005145749,0.0003262665,0.001276346,0.0001701361,0.006577796,0.00026796,0.00002599718,0.000009824301,0.00002963578,0.989168,0.0005294958],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.003710325,0.03318209,0.000932849,0.001704619,0.9484254,0.0008041736,0.002222911,0.000562564,0.008455072],"genre_scores_gemma":[0.04051431,0.005332167,0.0002597808,0.001546626,0.9348028,0.000009322873,0.002856393,0.0006118748,0.01406669],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.03680399,"threshold_uncertainty_score":0.9996436,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411187709","doi":"10.1093/ehjdh/ztaf063","title":"Effect of a digital health intervention on outpatients with heart failure: a randomized, controlled trial","year":2025,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Heart Failure Treatment and Management","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"SickKids Foundation","funders":"Rannís; Landspítali Háskólasjúkrahús; Icelandic Centre for Research","keywords":"Heart failure; Randomized controlled trial; Intervention (counseling); Medicine; Physical therapy; Digital health; Psychology; Nursing; Health care; Internal medicine; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.01412803283190781,"gpt":0.3234214515458203,"spread":0.3092934187139125,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004314587,0.0004337603,0.002773313,0.0005717669,0.0002471723,0.000312516,0.0001173357,0.00004155296,0.00003392501],"category_scores_gemma":[0.0007558374,0.0002579798,0.001169574,0.0003563573,0.0001363144,0.0003986616,0.00007262365,0.0005189325,0.0001288503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003515723,"about_ca_system_score_gemma":0.0004401458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001980159,"about_ca_topic_score_gemma":0.000004278256,"domain_scores_codex":[0.994601,0.001749017,0.001835676,0.0004077576,0.0007745418,0.0006320651],"domain_scores_gemma":[0.9974176,0.0007800288,0.000695524,0.0003742095,0.0001528982,0.0005797449],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","study_design_scores_codex":[0.9424525,0.00166166,0.00214361,0.0006038081,0.0006635984,0.0000576401,0.0001513031,0.000006642307,0.000001029848,0.0001319004,0.03425398,0.01787231],"study_design_scores_gemma":[0.9212986,0.0435299,0.0003762121,0.00318993,0.0001667138,0.0001690222,0.0000858592,0.00002487908,0.00001503553,0.00003720837,0.03094918,0.0001574249],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.892256,0.001217132,0.001275071,0.06434587,0.00136547,0.02170171,0.00005187558,0.0002367708,0.01755015],"genre_scores_gemma":[0.9940948,0.00004094654,0.0002547966,0.001840533,0.0002478861,0.00007116447,0.00006411671,0.00005549796,0.00333029],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1018388,"threshold_uncertainty_score":0.9999872,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4412600169","doi":"10.1093/ehjdh/ztaf083","title":"Artificial intelligence-driven electrocardiogram analysis for risk stratification in pulmonary embolism","year":2025,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Venous Thromboembolism Diagnosis and Management","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"North York General Hospital; Artificial Intelligence in Medicine (Canada); University of Toronto","funders":"National Institute of General Medical Sciences; Center for Research Computing, University of Pittsburgh; National Heart, Lung, and Blood Institute; University of Pittsburgh; National Science Foundation","keywords":"Risk stratification; Pulmonary embolism; Stratification (seeds); Cardiology; Internal medicine; Artificial intelligence; Medicine; Computer science; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.04538234022334274,"gpt":0.3536731328578321,"spread":0.3082907926344893,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001254209,0.000191643,0.0006903497,0.0009293875,0.0002999926,0.0002692791,0.0001459726,0.00003841441,0.0000189731],"category_scores_gemma":[0.0001647067,0.0001756288,0.0004826774,0.001273277,0.00004469416,0.000220889,0.00004421276,0.0004274427,0.00004423345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002394614,"about_ca_system_score_gemma":0.0002634253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005179873,"about_ca_topic_score_gemma":0.00004804295,"domain_scores_codex":[0.9976158,0.0002430114,0.0009772466,0.0003690779,0.0002723126,0.0005226008],"domain_scores_gemma":[0.9989248,0.0001209052,0.000247032,0.0003071045,0.0001332607,0.0002669297],"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":[0.0003746773,0.002575003,0.08546811,0.0002995656,0.001523619,0.0001554457,0.0007023533,0.003825854,0.00008489246,0.007173108,0.008069796,0.8897476],"study_design_scores_gemma":[0.0003496554,0.001363153,0.9483535,0.0003756722,0.0006924407,0.0001023724,0.0009667585,0.006609705,0.0001059236,0.007998101,0.03277103,0.0003116977],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6708095,0.003833235,0.2456689,0.0304559,0.001185592,0.004531094,0.0001546912,0.0002845306,0.04307658],"genre_scores_gemma":[0.9959152,0.001117865,0.00104254,0.001209045,0.0003400951,0.00001833281,0.00009349066,0.00002857293,0.0002348601],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8894359,"threshold_uncertainty_score":0.7161934,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388184188","doi":"10.1093/ehjdh/ztad067","title":"Cardiology professionals’ views of social robots in augmenting heart failure patient care","year":2023,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Mechanical Circulatory Support Devices","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Ottawa Hospital; Wilfrid Laurier University; University of Ottawa","funders":"University of Ottawa; Oracle","keywords":"Medicine; Heart failure; Cardiology; Robot; Intensive care medicine; Medical emergency; Internal medicine; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.04763480954619882,"gpt":0.3129958880750097,"spread":0.2653610785288109,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007919826,0.0001897679,0.0005358252,0.0002318113,0.0001701463,0.00005670557,0.0001563262,0.00005560743,0.00003509285],"category_scores_gemma":[0.00005817179,0.0001765319,0.0001991539,0.0004132586,0.00002613393,0.0002744835,0.0001037422,0.0005614554,0.0002675693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000158372,"about_ca_system_score_gemma":0.0001118553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001956161,"about_ca_topic_score_gemma":0.000009212103,"domain_scores_codex":[0.9974933,0.0004002095,0.0009483095,0.0002094201,0.0003589083,0.000589877],"domain_scores_gemma":[0.9992971,0.00007221836,0.0001476616,0.0001541214,0.00007128261,0.0002575652],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001032305,0.0003398925,0.2943764,0.007016373,0.0003176474,0.001911735,0.03227364,0.05176865,0.003154311,0.0004069138,0.522605,0.08572621],"study_design_scores_gemma":[0.001618204,0.001004246,0.3832143,0.001795545,0.00001748297,0.0009836685,0.01172727,0.00106291,0.0003239603,0.0001444063,0.5970997,0.001008369],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9939688,0.001303316,0.00004912307,0.0008845782,0.0007759049,0.0003568848,0.00004874861,0.0001978019,0.002414791],"genre_scores_gemma":[0.999106,0.00001522328,0.0001588301,0.0002958082,0.0002889958,0.000004115021,0.00003865753,0.0000666487,0.00002565432],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0888379,"threshold_uncertainty_score":0.7198762,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3174952152","doi":"10.1093/ehjdh/ztab056","title":"Wearables for cardiac monitoring in athletes: precious metal or fool’s gold?","year":2021,"lang":"en","type":"editorial","venue":"European Heart Journal - Digital Health","topic":"Cardiovascular Effects of Exercise","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; St. Michael's Hospital; Western University","funders":"","keywords":"Medicine; Athletes; Wearable computer; Cardiology; Internal medicine; Physical therapy; Embedded system","retraction":null,"screen_n_in":null,"score":{"opus":0.03764696446877958,"gpt":0.3434399096485602,"spread":0.3057929451797806,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004590343,0.0007851593,0.00291625,0.0005579076,0.000247638,0.0008034174,0.000363867,0.0003745185,0.00001396189],"category_scores_gemma":[0.006362741,0.0006717651,0.002361514,0.0005093446,0.00008482949,0.0005475488,0.0002578502,0.003004886,0.0001053655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001349404,"about_ca_system_score_gemma":0.003532899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004944039,"about_ca_topic_score_gemma":0.00001112453,"domain_scores_codex":[0.9931933,0.0009377745,0.001577223,0.0009820035,0.001929751,0.001379895],"domain_scores_gemma":[0.9947454,0.001912849,0.0004952963,0.0009337148,0.0007356016,0.001177121],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001071071,0.0002602974,0.000264083,0.002005755,0.0006622401,0.002908084,0.0002644547,0.00002486312,0.00002626568,5.391493e-7,0.9422742,0.05023818],"study_design_scores_gemma":[0.003517775,0.002302901,0.0008441996,0.01048456,0.0002835537,0.001046183,0.0002666423,0.000004664675,0.0000364394,0.00000892128,0.9806337,0.0005704031],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.009091939,0.08652519,0.00006599355,0.0006004271,0.8964167,0.003003159,0.0008412391,0.0001904273,0.003264965],"genre_scores_gemma":[0.004286679,0.01098057,0.001590268,0.0001268448,0.973101,0.00005500558,0.0005474905,0.0006000718,0.008712068],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.07668435,"threshold_uncertainty_score":0.9995733,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391445827","doi":"10.1093/ehjdh/ztae005","title":"Predicting heart failure outcomes by integrating breath-by-breath measurements from cardiopulmonary exercise testing and clinical data through a deep learning survival neural network","year":2024,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Cardiovascular and exercise physiology","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Ted Rogers Centre for Heart Research; University Health Network","funders":"University Health Network","keywords":"Machine learning; Medicine; Predictive modelling; Artificial intelligence; Heart failure; Event (particle physics); Cohort; Artificial neural network; Computer science; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.09999185926657315,"gpt":0.3581610837628442,"spread":0.258169224496271,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003438519,0.0004743509,0.001557503,0.0000688818,0.0006897641,0.0006629838,0.0002782536,0.0001062578,0.00001201022],"category_scores_gemma":[0.001043997,0.0003788526,0.0005163412,0.000313221,0.0001401781,0.0009956935,0.0005544869,0.002323995,0.00005333034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000131995,"about_ca_system_score_gemma":0.0002224304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005229861,"about_ca_topic_score_gemma":0.00001290884,"domain_scores_codex":[0.9948391,0.001124399,0.001349778,0.0009933988,0.0007796516,0.0009137191],"domain_scores_gemma":[0.997307,0.0009249236,0.0002166161,0.0006393199,0.0001448912,0.0007672554],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003909076,0.0001616377,0.8310979,0.0002108492,0.0007838602,0.0006414258,0.0004164455,0.0001755913,0.0001406887,7.361118e-7,0.04659379,0.1193862],"study_design_scores_gemma":[0.005493484,0.003354044,0.826018,0.01067625,0.001445317,0.01655494,0.003070519,0.02080294,0.00001358327,0.0001763268,0.1107434,0.001651141],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9396099,0.05108026,0.0007513518,0.003161354,0.001739544,0.0007147638,0.0003800187,0.0005059869,0.002056767],"genre_scores_gemma":[0.9924769,0.000745539,0.002847005,0.000830931,0.002139872,0.000002678859,0.0006891197,0.0001671002,0.0001008765],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1177351,"threshold_uncertainty_score":0.9999777,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400578756","doi":"10.1093/ehjdh/ztae051","title":"Machine learning-based prediction of 1-year all-cause mortality in patients undergoing CRT implantation: validation of the SEMMELWEIS-CRT score in the European CRT Survey I dataset","year":2024,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Cardiac pacing and defibrillation studies","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Nemzeti Kutatási Fejlesztési és Innovációs Hivatal; Nemzeti Kutatási, Fejlesztési és Innovaciós Alap; Ministry of Advanced Education; Magyar Tudományos Akadémia; European Commission","keywords":"Medicine; Cardiac resynchronization therapy; Receiver operating characteristic; Internal medicine; Cohort; Heart failure; Odds ratio; Area under the curve; Ejection fraction; Cardiology","retraction":null,"screen_n_in":null,"score":{"opus":0.1207262393877813,"gpt":0.3622328724889506,"spread":0.2415066331011693,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004232053,0.000145537,0.0003281841,0.0001991096,0.0001304848,0.0001090378,0.00006105667,0.00001890437,0.00000385636],"category_scores_gemma":[0.000565331,0.00009452552,0.000122047,0.0005001663,0.00006724272,0.0002508073,0.00006036807,0.000470605,0.00001768668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001108791,"about_ca_system_score_gemma":0.0002113537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001598938,"about_ca_topic_score_gemma":0.00008126781,"domain_scores_codex":[0.9960084,0.002128733,0.0008477739,0.0002104804,0.000591767,0.0002128529],"domain_scores_gemma":[0.9988236,0.0004291006,0.0002739422,0.0002626952,0.0001234254,0.00008718859],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001129658,0.000105942,0.9920902,0.0001883172,0.00007726636,0.00001980487,0.0006881719,0.00126919,0.000005644641,0.00000574385,0.004901452,0.0005352724],"study_design_scores_gemma":[0.001056628,0.0004488826,0.9946508,0.0007972841,0.00003841675,0.0001593055,0.0001711033,0.0001261534,0.00001263062,0.000007859381,0.002466866,0.00006409529],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9918062,0.0003342251,0.00005993806,0.0003826351,0.0003013849,0.0003270631,0.001921111,0.00002567807,0.004841777],"genre_scores_gemma":[0.997622,0.0001345198,0.00001001479,0.0002339344,0.0001317839,5.828717e-7,0.001814086,0.00002990533,0.00002320194],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005815783,"threshold_uncertainty_score":0.3854639,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4415482982","doi":"10.1093/ehjdh/ztaf121","title":"Artificial intelligence implementation in automated heart chambers quantification during pharmacological stress echocardiography","year":2025,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Cardiovascular Function and Risk Factors","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Cytodiagnostics (Canada)","funders":"","keywords":"Workflow; Reliability (semiconductor); Heart failure; Matching (statistics); Expert system; Automated method","retraction":null,"screen_n_in":null,"score":{"opus":0.0525100625431907,"gpt":0.392811334598755,"spread":0.3403012720555643,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001060782,0.0001744334,0.0003788301,0.0005191618,0.000337701,0.0002421947,0.00007095403,0.00004036899,0.00006079116],"category_scores_gemma":[0.00006174583,0.0001519156,0.0004073353,0.0008630693,0.00007548043,0.0002685339,0.00003992787,0.0005303518,0.00008904881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002697634,"about_ca_system_score_gemma":0.0002496405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004001485,"about_ca_topic_score_gemma":0.000008791493,"domain_scores_codex":[0.9976724,0.000411119,0.0008402346,0.000309595,0.000361757,0.000404934],"domain_scores_gemma":[0.9992397,0.00005088811,0.0001272005,0.0001801912,0.0001067756,0.0002952014],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009265301,0.0008626652,0.8741024,0.0003223012,0.0004945197,0.000441733,0.0009533576,0.002063551,0.002655012,0.0001301002,0.01033019,0.1067176],"study_design_scores_gemma":[0.0005729016,0.0002577725,0.9888407,0.0002583335,0.00003765611,0.000488003,0.001257905,0.0006611407,0.001697908,0.00003956886,0.005738912,0.0001491883],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9928495,0.0004250784,0.001176134,0.003230784,0.0008129717,0.0005320269,0.00002426949,0.000265343,0.0006838983],"genre_scores_gemma":[0.9984248,0.0003074756,0.0001708338,0.0007741805,0.0001899767,0.000003920324,0.00006114076,0.00002245609,0.00004515974],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1147383,"threshold_uncertainty_score":0.6194939,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4200023582","doi":"10.1093/ehjdh/ztab104.3080","title":"Assessment of cognitive dysfunction using the Montreal Cognitive Assessment test: rate, severity and comparison with the Clock test alone in a population of patients referred for TAVI","year":2021,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Cardiac, Anesthesia and Surgical Outcomes","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Montreal Cognitive Assessment; Medicine; Kappa; Internal medicine; Concordance; Interquartile range; Population; Cardiology; Cognitive impairment","retraction":null,"screen_n_in":null,"score":{"opus":0.04708190296957084,"gpt":0.361291010055323,"spread":0.3142091070857522,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001034889,0.0001416136,0.0006137568,0.00006118192,0.0001774489,0.00006416237,0.00003007157,0.0000241611,0.000003905955],"category_scores_gemma":[0.0007922299,0.0000808683,0.0001299575,0.0002178439,0.0000847765,0.0001660296,0.00003038112,0.0003129818,2.551898e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001278344,"about_ca_system_score_gemma":0.0003359149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009520949,"about_ca_topic_score_gemma":0.00006782015,"domain_scores_codex":[0.998148,0.0005125937,0.0005904667,0.0001792491,0.0003606867,0.0002090474],"domain_scores_gemma":[0.9958825,0.002988942,0.0003985357,0.00009580677,0.0004822133,0.0001520197],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004287726,0.0007370547,0.9934987,0.00009237706,0.00005901172,0.00003582891,0.0003604332,0.00002033538,0.00001757645,0.00001202729,0.000049179,0.004688651],"study_design_scores_gemma":[0.003748544,0.001767039,0.990735,0.0006985511,0.00009790794,0.000273957,0.00162469,0.0007764845,0.00001489438,0.000006208867,0.0001789943,0.00007772392],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9962886,0.0001542255,0.0004855093,0.0009979474,0.00005113622,0.0007201393,0.0001113518,0.00000614792,0.001184966],"genre_scores_gemma":[0.9990476,0.00003679531,0.0002107761,0.0004123127,0.00006386334,0.000003824351,0.0001439314,0.00002079238,0.00006010579],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004610927,"threshold_uncertainty_score":0.3297714,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3124651630","doi":"10.1093/ehjdh/ztab004","title":"‘How to do’: digital-interactive-interpretation course for stress echocardiography","year":2021,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Ultrasound in Clinical Applications","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta Hospital","funders":"TOMTEC Imaging Systems","keywords":"Medicine; Logbook; Accreditation; Interpretation (philosophy); Medical education; Certificate; Course (navigation); Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.04487278802020309,"gpt":0.3901220063629869,"spread":0.3452492183427838,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004850546,0.000219648,0.0004746615,0.0001424332,0.0002650298,0.001448818,0.0001581293,0.00003869929,0.00002937194],"category_scores_gemma":[0.001351369,0.0001970985,0.0005717775,0.0004228172,0.00006525796,0.0008218687,0.00006857187,0.0005276328,0.0002107906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001459017,"about_ca_system_score_gemma":0.0003571309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.230173e-7,"about_ca_topic_score_gemma":0.00000110159,"domain_scores_codex":[0.9978209,0.0001241312,0.0007090117,0.0004517781,0.0004130575,0.0004811924],"domain_scores_gemma":[0.996812,0.0007994755,0.0002367812,0.0004427486,0.0006678287,0.001041134],"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":[0.002070412,0.005006685,0.1511613,0.0007076242,0.001212635,0.0005298499,0.00306975,0.0001645724,0.0007437039,0.0007642055,0.2286184,0.6059509],"study_design_scores_gemma":[0.002805924,0.003824415,0.1849426,0.001735734,0.0001109031,0.0034587,0.002826695,0.0001087343,0.0003617604,0.001863635,0.7973964,0.0005645265],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5141326,0.002300325,0.26315,0.1538569,0.002400252,0.003805259,0.003424891,0.0004993559,0.05643047],"genre_scores_gemma":[0.9872919,0.00007801651,0.004219938,0.00511055,0.0009654647,0.00001593387,0.0002272304,0.00008225796,0.002008663],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6053864,"threshold_uncertainty_score":0.9995878,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400003197","doi":"10.1093/ehjdh/ztae046","title":"Feasibility of anticoagulation on demand after percutaneous coronary intervention in high-bleeding risk patients with paroxysmal atrial fibrillation: the INTERMITTENT registry","year":2024,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Atrial Fibrillation Management and Outcomes","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Montreal Heart Institute","funders":"","keywords":"Medicine; Paroxysmal atrial fibrillation; Percutaneous coronary intervention; Atrial fibrillation; Internal medicine; Cardiology; Major bleeding; On demand; Percutaneous; Intervention (counseling); Myocardial infarction; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.05237946508011087,"gpt":0.3373750106531037,"spread":0.2849955455729928,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009218093,0.0001544811,0.0002938034,0.0001706171,0.0001149291,0.0001802592,0.00005717752,0.00002764668,0.00004000443],"category_scores_gemma":[0.0001534693,0.00009665675,0.0002626703,0.0002083701,0.00006160117,0.0003497834,0.00005092687,0.0003268898,0.00002725718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002193509,"about_ca_system_score_gemma":0.00006483016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001636744,"about_ca_topic_score_gemma":0.000004716474,"domain_scores_codex":[0.9980682,0.0003086789,0.0007497045,0.0002358897,0.0004323329,0.0002052444],"domain_scores_gemma":[0.9991485,0.0001908116,0.0002718337,0.0001876579,0.00008437991,0.0001167428],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0026052,0.00001965458,0.9646311,0.0002173906,0.00005580894,0.0001185057,0.0002467429,0.0005364452,9.739404e-7,0.00002304755,0.0001957182,0.03134935],"study_design_scores_gemma":[0.001583277,0.001569659,0.9930466,0.001163011,0.00004880828,0.0003440785,0.00009966104,0.0004685823,8.756004e-7,0.00007775189,0.001509292,0.00008842193],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9955773,0.0006924887,0.0001615931,0.002150883,0.000536275,0.0006018273,0.00002548139,0.00003393405,0.0002202165],"genre_scores_gemma":[0.9983908,0.00008330372,0.00009312511,0.00008178288,0.001086609,1.686743e-7,0.00004155317,0.00002807785,0.0001945809],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03126093,"threshold_uncertainty_score":0.3941548,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4312191841","doi":"10.1093/ehjdh/ztac076.2825","title":"Sustained usage of an app-based clinical-decision making aid for the management of atherosclerotic cardiovascular disease","year":2022,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Cardiac Health and Mental Health","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Cambridge Cardiac Care Centre; University of Ottawa","funders":"","keywords":"Medicine; Psychological intervention; Disease; Atherosclerotic cardiovascular disease; Residual risk; Comorbidity; Disease management; Test (biology); Intensive care medicine; Emergency medicine; Physical therapy; Internal medicine; Nursing","retraction":null,"screen_n_in":null,"score":{"opus":0.07369225856301877,"gpt":0.3925985813010558,"spread":0.3189063227380371,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008073266,0.0001880781,0.0007205101,0.0001476767,0.0006561399,0.00003810659,0.0002353419,0.00001780318,0.00002986618],"category_scores_gemma":[0.0001609114,0.0001414847,0.001077527,0.0003139308,0.00009843696,0.0001289567,0.0001986606,0.0004981817,0.000005129757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003470033,"about_ca_system_score_gemma":0.0008806327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001084104,"about_ca_topic_score_gemma":4.033924e-7,"domain_scores_codex":[0.9957116,0.0007982262,0.001491207,0.000351224,0.001060808,0.0005869585],"domain_scores_gemma":[0.9970074,0.0004740651,0.0005958402,0.0007842398,0.0001494283,0.0009890377],"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":[0.009803627,0.002090404,0.01288055,0.005353977,0.0004819118,0.0004421031,0.0003435288,0.004319897,0.00000346867,0.0001134481,0.003332641,0.9608344],"study_design_scores_gemma":[0.02407769,0.01807416,0.5833311,0.003849932,0.0008768322,0.001026294,0.006492369,0.004808693,0.000008498208,0.0004780793,0.3564142,0.0005621256],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9712632,0.00623967,0.01090892,0.002581717,0.001429764,0.005112069,0.0004777163,0.00007564465,0.001911264],"genre_scores_gemma":[0.9929914,0.0003653504,0.002930623,0.003119669,0.0003455951,0.00002356111,0.00003983697,0.00007176738,0.0001121751],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9602723,"threshold_uncertainty_score":0.5769578,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4312191769","doi":"10.1093/ehjdh/ztac076.2801","title":"The effectiveness of eHealth interventions on moderate-to-vigorous intensity physical activity among cardiac rehabilitation participants: a systematic review and meta-analysis","year":2022,"lang":"en","type":"review","venue":"European Heart Journal - Digital Health","topic":"Cardiac Health and Mental Health","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; eHealth; Rehabilitation; Psychological intervention; Physical therapy; Cochrane Library; Randomized controlled trial; Systematic review; Meta-analysis; MEDLINE; Health care; Internal medicine; Nursing","retraction":null,"screen_n_in":null,"score":{"opus":0.1867857310347926,"gpt":0.4620862598370352,"spread":0.2753005288022425,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01852668,0.0006070611,0.01177875,0.0004722114,0.0008750728,0.0001381882,0.0002058686,0.00005890336,0.00001102736],"category_scores_gemma":[0.002730639,0.0003621987,0.006942232,0.001304114,0.000152717,0.0002034924,0.0002167111,0.00167397,0.00003164861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001389258,"about_ca_system_score_gemma":0.001114849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001056674,"about_ca_topic_score_gemma":0.000009461723,"domain_scores_codex":[0.9795216,0.01558431,0.002392661,0.0006914264,0.0009438518,0.0008662099],"domain_scores_gemma":[0.9897355,0.005582574,0.001741346,0.0009800519,0.000269195,0.001691323],"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":[0.0003054103,0.000618929,0.00002709161,0.9685483,0.0160347,0.00002321466,0.0001739905,0.000004577188,1.288891e-8,0.00002173395,0.0003778619,0.01386418],"study_design_scores_gemma":[0.0006908266,0.01154978,0.005287457,0.3239887,0.6195793,0.0009188327,0.0003559628,0.00001753175,2.220541e-7,0.00003604456,0.03684457,0.000730778],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001946454,0.9855651,0.00003735283,0.001080366,0.000257722,0.01028183,0.0005550162,0.00003996646,0.0002362316],"genre_scores_gemma":[0.04233243,0.9558363,0.00002251062,0.000900052,0.0001067884,0.0004972082,0.00009415439,0.0001032546,0.0001073129],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.6445596,"threshold_uncertainty_score":0.999883,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4415117676","doi":"10.1093/ehjdh/ztaf116","title":"Deep learning-based quantification of epicardial adipose tissue volume from non-contrast computed tomography images: a multi-centre study","year":2025,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Cardiovascular Disease and Adiposity","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Naval Medical Research Center; National Medical Research Council; Medical Research Council; Singapore Energy Centre; Duke-NUS Medical School","keywords":"Computed tomography; Volume (thermodynamics); Adipose tissue; Epicardial adipose tissue; Tomography","retraction":null,"screen_n_in":null,"score":{"opus":0.01761559718864034,"gpt":0.2934292360366167,"spread":0.2758136388479764,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007006228,0.0002368281,0.0007383493,0.0002978363,0.0002749841,0.0001747996,0.000147756,0.00004004159,0.00002438393],"category_scores_gemma":[0.000140747,0.0002222138,0.0006362858,0.0004342637,0.00008586911,0.0001877927,0.00005850002,0.0005981618,0.00008671078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006630408,"about_ca_system_score_gemma":0.0002885253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007705409,"about_ca_topic_score_gemma":0.000006734107,"domain_scores_codex":[0.997255,0.0007692883,0.0007735281,0.000395924,0.0004321954,0.0003741088],"domain_scores_gemma":[0.9984161,0.0001085593,0.0002539473,0.0004280709,0.000249756,0.0005436274],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001364129,0.006524192,0.8834128,0.0003805685,0.002202412,0.000916846,0.000992307,0.002387827,0.0012994,0.000002351963,0.004343104,0.09617404],"study_design_scores_gemma":[0.005791534,0.0007602127,0.9835863,0.0005654996,0.0003706189,0.00006099024,0.0004125907,0.003050819,0.0002536946,0.000002322993,0.004973351,0.0001720936],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9038321,0.006962264,0.08417892,0.001799004,0.0005750919,0.001645045,0.0001335643,0.000155067,0.0007189345],"genre_scores_gemma":[0.9980915,0.00002734405,0.0006794172,0.0004346999,0.0002904614,0.000001755278,0.0001714354,0.00004044876,0.0002629973],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1001735,"threshold_uncertainty_score":0.9061617,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4415022001","doi":"10.1093/ehjdh/ztaf115","title":"Unsupervised machine learning analysis to enhance risk stratification in patients with asymptomatic aortic stenosis","year":2025,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Cardiac Valve Diseases and Treatments","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval; Centre hospitalier de l'Université Laval; Institut universitaire de cardiologie et de pneumologie de Québec","funders":"Agence Nationale de la Recherche","keywords":"Risk stratification; Asymptomatic; Risk assessment; Stenosis; Unsupervised learning; Medical imaging","retraction":null,"screen_n_in":null,"score":{"opus":0.01063695023781039,"gpt":0.3348840971275104,"spread":0.3242471468897,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003548049,0.0001785897,0.0004704433,0.0005085318,0.0002074952,0.0001741726,0.00006474306,0.00001544371,0.00002589923],"category_scores_gemma":[0.0001493475,0.0001376937,0.000386784,0.001192639,0.00001731606,0.0001968638,0.00002925015,0.0003143326,0.00007845078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002756795,"about_ca_system_score_gemma":0.000177178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006462774,"about_ca_topic_score_gemma":0.000008302566,"domain_scores_codex":[0.9981504,0.0003003187,0.0005675088,0.000290229,0.0003668468,0.0003247077],"domain_scores_gemma":[0.9989125,0.00006582654,0.000179143,0.0002560765,0.0001473609,0.0004390858],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002790738,0.0005449103,0.9644843,0.00005303756,0.0008405622,0.0000118426,0.0001732549,0.0004106658,0.000001074639,0.000001926105,0.00008052927,0.03311878],"study_design_scores_gemma":[0.001300984,0.0009949994,0.9962831,0.0003080455,0.0005315323,0.000002105179,0.0000887968,0.0002542737,0.000003073017,0.000007974018,0.0001241175,0.0001010377],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9967718,0.0002735689,0.000431098,0.000595635,0.00004645187,0.0004838783,0.00005244343,0.00003627345,0.001308927],"genre_scores_gemma":[0.9986311,0.00006093414,0.0002220311,0.000577528,0.00002860449,0.000004752504,0.0001557015,0.0000259661,0.0002933404],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03301774,"threshold_uncertainty_score":0.5614988,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}