{"id":"W2799913286","doi":"10.1016/j.jcct.2018.04.011","title":"Maximization of the usage of coronary CTA derived plaque information using a machine learning based algorithm to improve risk stratification; insights from the CONFIRM registry","year":2018,"lang":"en","type":"article","venue":"Journal of cardiovascular computed tomography","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":169,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"National Heart, Lung, and Blood Institute","keywords":"Medicine; Risk stratification; Maximization; Coronary angiography; Stratification (seeds); Cardiology; Internal medicine; Radiology; Artificial intelligence; Machine learning; Computer science; Mathematical optimization; Myocardial infarction","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":[0.006269991,0.0007174938,0.0009925469,0.0008316827,0.0003568699,0.001278443,0.0009042374,0.0008932767,0.0009094623],"category_scores_gemma":[0.01579021,0.0003824013,0.000550151,0.0005129669,0.0004686179,0.001189733,0.0008523189,0.0007707172,0.000286244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004144269,"about_ca_system_score_gemma":0.00139595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001455834,"about_ca_topic_score_gemma":0.002678372,"domain_scores_codex":[0.9989498,0.0006062482,0.00005680737,0.0001286277,0.0002022459,0.00005629031],"domain_scores_gemma":[0.9934216,0.005150808,0.0003945455,0.000432151,0.0004923774,0.0001084485],"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":[0.00130022,0.0006823522,0.06301702,0.0001650582,0.0003092649,0.0002969837,0.0001860627,0.609777,0.01150983,0.01644029,0.002703511,0.2936125],"study_design_scores_gemma":[0.00002594161,0.0001170693,0.005402758,0.00001122648,0.00003536946,0.00006881198,0.00001215622,0.9885679,0.00174488,0.003709359,0.0002925423,0.00001189652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.462099,0.0009306372,0.5293888,0.001852812,0.00004325201,0.0001064452,0.0003076443,0.0006134713,0.004657801],"genre_scores_gemma":[0.8644957,0.0002604952,0.1332643,0.0001301022,0.00006270024,0.00005586272,0.0002696019,0.00007613446,0.001385076],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006269991,"threshold_uncertainty_score":0.03315926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008003719147528413,"score_gpt":0.213604891579119,"score_spread":0.2056011724315906,"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."}}