{"id":"W4412048689","doi":"10.1016/j.ijcard.2025.133584","title":"Predicting coronary artery disease using machine learning with optimized feature selection","year":2025,"lang":"en","type":"letter","venue":"International Journal of Cardiology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill Genome Centre","funders":"Lady Davis Institute for Medical Research; Canadian Institutes of Health Research; Watanabe Foundation; TD Bank; Japan Student Services Organization; Fonds de Recherche du Québec - Santé","keywords":"Medicine; Coronary artery disease; Feature selection; Cardiology; Selection (genetic algorithm); Feature (linguistics); Internal medicine; Artificial intelligence; Disease; Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0008642931,0.0003334396,0.0008753965,0.0006527466,0.0004481873,0.00002474893,0.0005833099,0.00100613,0.0001367077],"category_scores_gemma":[0.001051788,0.0002705703,0.000329095,0.0001602769,0.0001174761,0.0001983145,0.0001607026,0.008798661,0.00001348652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001014697,"about_ca_system_score_gemma":0.002106858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001571281,"about_ca_topic_score_gemma":0.00005846711,"domain_scores_codex":[0.9951321,0.002059842,0.001156528,0.0003565765,0.0007813429,0.0005135715],"domain_scores_gemma":[0.9936454,0.001614544,0.001712215,0.000176904,0.002715578,0.0001353988],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002799606,0.00001127065,0.7411004,0.0002629204,0.00183182,0.006087246,0.0003145454,0.03974293,0.0000509587,0.00003178259,0.2070252,0.0007412671],"study_design_scores_gemma":[0.001798252,0.0006181297,0.008678618,0.005668135,0.00100443,0.004358231,0.0008645207,0.03791558,0.00002142585,0.0008047684,0.9375778,0.0006900487],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.0908931,0.001973097,0.02231091,0.8579596,0.02331981,0.00127352,0.0003482894,0.0001584185,0.001763286],"genre_scores_gemma":[0.373878,0.001411124,0.008589298,0.496032,0.10859,0.0001214005,0.001127309,0.00028224,0.009968565],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.7324218,"threshold_uncertainty_score":0.9999747,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06951126247498594,"score_gpt":0.4230502619147882,"score_spread":0.3535389994398023,"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."}}