{"id":"W4402112527","doi":"10.1093/eurheartj/ehae595","title":"Prediction of incident atrial fibrillation using deep learning, clinical models, and polygenic scores","year":2024,"lang":"en","type":"article","venue":"European Heart Journal","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Université de Montréal; Montreal Heart Institute","funders":"Canadian Institutes of Health Research; Takeda Canada; Institute of Genetics; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Medicine; Atrial fibrillation; Internal medicine; Cardiology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001291021,0.00007410485,0.0002030414,0.000167269,0.0001128724,0.00006634446,0.00002352127,0.00003350304,0.00002206533],"category_scores_gemma":[0.0001802457,0.00006070971,0.0002514252,0.0001281887,0.00004157764,0.0001292112,0.00003143973,0.0004234353,0.00000865691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003225928,"about_ca_system_score_gemma":0.00005542009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001090551,"about_ca_topic_score_gemma":4.634432e-7,"domain_scores_codex":[0.9987375,0.0003293499,0.0004431723,0.0001427568,0.0002367983,0.0001104636],"domain_scores_gemma":[0.9995482,0.00007500034,0.00009594354,0.00007490435,0.00006844955,0.0001375265],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001402209,0.000009826043,0.9367011,0.00005637931,0.0002504681,0.0001005028,0.000321174,0.01452453,0.002049891,0.000009490876,0.0001735193,0.04566297],"study_design_scores_gemma":[0.0006717152,0.0005326074,0.3859041,0.0006345082,0.0005214916,0.00155581,0.00009061558,0.6058521,0.00005530636,0.00004251302,0.004066152,0.00007299838],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9854495,0.007796863,0.005687521,0.0001230427,0.0006431628,0.00003897347,0.000001043094,0.00004106258,0.0002188169],"genre_scores_gemma":[0.990467,0.001954159,0.001450529,0.000009397938,0.00585044,2.145747e-8,0.000002727041,0.00002294008,0.0002427805],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5913276,"threshold_uncertainty_score":0.247567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1400441098688014,"score_gpt":0.3785306211130712,"score_spread":0.2384865112442698,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}