{"id":"W4412479499","doi":"10.1038/s41586-025-09227-0","title":"Detecting structural heart disease from electrocardiograms using AI","year":2025,"lang":"en","type":"article","venue":"Nature","topic":"Cardiac Valve Diseases and Treatments","field":"Medicine","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"Montreal Heart Institute","funders":"National Heart, Lung, and Blood Institute; National Institutes of Health; Fondation Institut de Cardiologie de Montréal; Amyloidosis Foundation; Patient-Centered Outcomes Research Institute; Institut de Cardiologie de Montréal; American Heart Association","keywords":"Medical diagnosis; Heart disease; Heart Rhythm; Artificial intelligence; Machine learning; Computer science; Disease; Medicine; Cardiology; Internal medicine; Pathology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006606744,0.001037065,0.0005955972,0.001260653,0.0001801286,0.0009897918,0.0009568873,0.0007612471,0.002794563],"category_scores_gemma":[0.003383645,0.0002666449,0.0006992196,0.0007977342,0.0002785202,0.0007284654,0.000655691,0.001214136,0.001307676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000411839,"about_ca_system_score_gemma":0.0005567831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007477692,"about_ca_topic_score_gemma":0.01021759,"domain_scores_codex":[0.9997416,0.00004624016,0.00002425473,0.0000914413,0.00007136638,0.00002497007],"domain_scores_gemma":[0.9992257,0.0004239099,0.0000870946,0.00009325129,0.0001237172,0.00004625219],"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":[0.0005271728,0.000486685,0.09116599,0.000434732,0.0004551024,0.000541273,0.0000981037,0.3348832,0.008835052,0.005127456,0.02875304,0.5286921],"study_design_scores_gemma":[0.00003233697,0.00009414917,0.01076821,0.00006276743,0.00006395147,0.0002288701,0.00001827075,0.9726638,0.002052261,0.009927888,0.004060065,0.00002729884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1724718,0.006361615,0.7838194,0.00391668,0.0006811534,0.000315504,0.01389991,0.005742532,0.01279145],"genre_scores_gemma":[0.8644226,0.003585601,0.1104249,0.001183974,0.0005724776,0.0002401574,0.01293767,0.0001380276,0.006494756],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007477692,"threshold_uncertainty_score":0.01486838,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005807712169683931,"score_gpt":0.3504153721509162,"score_spread":0.3446076599812322,"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."}}