{"id":"W2408866005","doi":"10.1093/eurheartj/ehw188","title":"Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: a 5-year multicentre prospective registry analysis","year":2016,"lang":"en","type":"article","venue":"European Heart Journal","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":705,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Université de Montréal; St. Paul's Hospital; University of Ottawa; Montreal Heart Institute","funders":"National Heart, Lung, and Blood Institute; National Research Foundation of Korea; National Research Foundation; Dowager Countess Eleanor Peel Trust; Dalio Foundation","keywords":"Medicine; Coronary artery disease; SSS*; Framingham Risk Score; Computed tomographic angiography; Internal medicine; Radiology; Clinical trial; Machine learning; Angiography; Cardiology; Disease","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":[0.007918394,0.0004934579,0.0007070987,0.001096673,0.0003408725,0.001056008,0.000686195,0.0007139763,0.0007588381],"category_scores_gemma":[0.0117951,0.0003097786,0.001125092,0.001023836,0.0002808015,0.0009336002,0.0006496945,0.0007862955,0.0003446795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003205521,"about_ca_system_score_gemma":0.000490725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00127118,"about_ca_topic_score_gemma":0.001205002,"domain_scores_codex":[0.9974196,0.001471717,0.0002224081,0.0004236042,0.0003140865,0.0001484345],"domain_scores_gemma":[0.9921367,0.003277123,0.002058881,0.001226815,0.0006719214,0.0006286285],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006848363,0.0001047439,0.9961029,0.000009662439,0.0001816152,0.00004688655,0.00001974569,0.0005644211,0.00007918972,0.00001870266,0.0001712385,0.002016035],"study_design_scores_gemma":[0.0001169507,0.0009118323,0.9832457,0.00001333557,0.0002441606,0.0003055089,0.00006992684,0.01464741,0.00016368,0.00006781842,0.0001978482,0.00001577643],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9984762,0.0002224331,0.0005804903,0.00006060003,0.00001076294,0.00001937547,0.0004660376,0.00001810466,0.0001459959],"genre_scores_gemma":[0.9984424,0.00009131063,0.0004368367,0.00001604197,0.00001673964,0.00002422959,0.0009096973,0.000004456722,0.00005826911],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007918394,"threshold_uncertainty_score":0.04187691,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02030593075488308,"score_gpt":0.2737254518784147,"score_spread":0.2534195211235317,"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."}}