{"id":"W3012330081","doi":"10.1016/s0735-1097(20)34165-6","title":"COMPARISON OF MACHINE LEARNING (ML) METHODS WITH CONVENTIONAL STATISTICAL MODELS (CSM) FOR PREDICTION OF MORTALITY IN MYOCARDIAL INFARCTION (MI) PATIENTS","year":2020,"lang":"en","type":"article","venue":"Journal of the American College of Cardiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University Health Network","funders":"","keywords":"Medicine; Logistic regression; Myocardial infarction; Proportional hazards model; Regression; Internal medicine; Cardiology; Regression analysis; Predictive modelling; Statistics","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":[0.008302859,0.0007502718,0.0008809873,0.001393756,0.0002432994,0.0009799224,0.0009443819,0.0008722296,0.001170288],"category_scores_gemma":[0.02263871,0.0001588104,0.0008638905,0.0008162067,0.0002689755,0.001078743,0.0006308336,0.0009982069,0.0002554042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005568786,"about_ca_system_score_gemma":0.0009038036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003683035,"about_ca_topic_score_gemma":0.002006269,"domain_scores_codex":[0.9974104,0.001752948,0.0001937972,0.0002710828,0.0002940192,0.00007781481],"domain_scores_gemma":[0.9679979,0.02865507,0.0007019057,0.0007067425,0.001577363,0.0003610333],"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":[0.01684161,0.002428486,0.25063,0.0008009283,0.002672798,0.0001743202,0.0002892599,0.2287523,0.002109119,0.003076401,0.00529721,0.4869275],"study_design_scores_gemma":[0.0002514579,0.001695239,0.02793199,0.00004455009,0.0002753207,0.00006750834,0.0001078465,0.9664815,0.0006444275,0.002044663,0.0004268189,0.00002861882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8791509,0.0072053,0.1072676,0.001692736,0.0005711837,0.0001253789,0.001134395,0.0007405595,0.002111887],"genre_scores_gemma":[0.9758671,0.0007811877,0.02187513,0.0001642728,0.0002131705,0.00005360135,0.0006255085,0.00003890528,0.000381232],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008302859,"threshold_uncertainty_score":0.04391021,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1854837547979666,"score_gpt":0.496391547598259,"score_spread":0.3109077928002924,"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."}}