{"id":"W3009173546","doi":"10.1016/j.cjca.2020.02.096","title":"Usefulness of Machine Learning-Based Detection and Classification of Cardiac Arrhythmias With 12-Lead Electrocardiograms","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Cardiology","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":72,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Ministry of Science and Technology, Taiwan; China Medical University Hospital; Ministry of Health and Welfare","keywords":"Medicine; Lead (geology); Cardiology; Internal medicine; Artificial intelligence; Machine learning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003554702,0.0008392748,0.0006603816,0.002394233,0.0002423292,0.001735068,0.0005132324,0.001413288,0.001195349],"category_scores_gemma":[0.02038155,0.0001480402,0.0004680135,0.0008374258,0.0002931494,0.001084421,0.0003541347,0.0005794215,0.0007833387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002769053,"about_ca_system_score_gemma":0.0003514512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001676743,"about_ca_topic_score_gemma":0.001755618,"domain_scores_codex":[0.9973465,0.001319937,0.0002846285,0.0003840312,0.000542605,0.0001222108],"domain_scores_gemma":[0.9842882,0.01132991,0.000962487,0.0005717617,0.002513513,0.0003341654],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003214437,0.0005246441,0.6205922,0.0002565717,0.0004703577,0.0002660684,0.000130803,0.01601782,0.01509308,0.0003610705,0.002613939,0.340459],"study_design_scores_gemma":[0.0001216772,0.001225932,0.4447083,0.0001383574,0.0005621642,0.001492121,0.0002613803,0.5344757,0.01314542,0.001971636,0.001799415,0.00009790195],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9397104,0.004192732,0.04678466,0.0009403884,0.0003443461,0.00008841081,0.001474903,0.0008532712,0.005610769],"genre_scores_gemma":[0.9917149,0.0003683949,0.006810303,0.00008133045,0.0001454313,0.00001147649,0.0004653819,0.00002206089,0.0003806408],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003554702,"threshold_uncertainty_score":0.0187993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02119821056008354,"score_gpt":0.222940647610799,"score_spread":0.2017424370507155,"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."}}