{"id":"W4382630739","doi":"10.1038/s41591-023-02396-3","title":"Machine learning for ECG diagnosis and risk stratification of occlusion myocardial infarction","year":2023,"lang":"en","type":"article","venue":"Nature Medicine","topic":"Acute Myocardial Infarction Research","field":"Medicine","cited_by":268,"is_retracted":false,"has_abstract":true,"ca_institutions":"North York General Hospital; Artificial Intelligence in Medicine (Canada); University of Toronto","funders":"National Center for Advancing Translational Sciences; National Institute of Nursing Research; National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Medicine; Triage; Myocardial infarction; Chest pain; Risk stratification; Observational study; Boosting (machine learning); Internal medicine; Electrocardiography; Cohort; Cardiology; Emergency medicine; Machine learning; Medical emergency; Artificial intelligence; Computer science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004621334,0.0005784624,0.0005892807,0.001090863,0.0002652738,0.001083268,0.0006840957,0.0006968931,0.0008002784],"category_scores_gemma":[0.01477691,0.0002005048,0.0005821891,0.0005555027,0.0003363108,0.000487278,0.0006404857,0.001248989,0.0003867355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007009572,"about_ca_system_score_gemma":0.0008622071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003748338,"about_ca_topic_score_gemma":0.0030367,"domain_scores_codex":[0.9984862,0.0009740581,0.00009020501,0.0002013445,0.0001651146,0.00008307009],"domain_scores_gemma":[0.9939592,0.004795129,0.0003982708,0.0003375924,0.000399983,0.0001098315],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000539118,0.0005879006,0.1577865,0.0001332902,0.000593061,0.0003056834,0.0001574589,0.5497322,0.001659198,0.00436197,0.004714472,0.2794291],"study_design_scores_gemma":[0.00001250397,0.0000582957,0.00597038,0.0000238504,0.00002134964,0.00004213761,0.00001484267,0.9877163,0.0003612087,0.005364463,0.0004046732,0.00001002189],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5623316,0.006550509,0.4166348,0.005768885,0.000378271,0.0002826013,0.001656406,0.001191286,0.005205683],"genre_scores_gemma":[0.9660968,0.0004341011,0.03186886,0.0002173438,0.0001297144,0.00007363918,0.0004833808,0.00001781028,0.0006783788],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004621334,"threshold_uncertainty_score":0.02444023,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02200361571062593,"score_gpt":0.3459350898462811,"score_spread":0.3239314741356552,"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."}}