{"id":"W4396831225","doi":"10.1016/j.cjca.2024.04.026","title":"Advancing Fairness in Cardiac Care: Strategies for Mitigating Bias in Artificial Intelligence Models Within Cardiology","year":2024,"lang":"en","type":"review","venue":"Canadian Journal of Cardiology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute; Montreal Heart Institute","funders":"Fonds de recherche du Québec – Nature et technologies; Canadian Institutes of Health Research; Fonds de Recherche du Québec - Santé; Institut de Valorisation des Données; Canadian Institute for Advanced Research","keywords":"Medicine; Field (mathematics); Health care; Reliability (semiconductor); Artificial intelligence; Patient care; Cardiology; Internal medicine; Computer science; Nursing","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03518332,0.0008889193,0.003106382,0.002789774,0.0009130164,0.004575515,0.003287995,0.004354871,0.005067068],"category_scores_gemma":[0.08663693,0.0004103514,0.001474652,0.002832733,0.003645498,0.005502397,0.003201783,0.006795236,0.0005615935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00569481,"about_ca_system_score_gemma":0.01462658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008933073,"about_ca_topic_score_gemma":0.01278469,"domain_scores_codex":[0.984287,0.01094703,0.0009658236,0.0006998845,0.002738722,0.0003614928],"domain_scores_gemma":[0.903238,0.08660237,0.003198937,0.001463805,0.004606513,0.0008904017],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001199394,0.00009063457,0.001314973,0.01680812,0.0006707304,0.00006593044,0.0004206327,0.002636817,0.00007787895,0.1336224,0.01605317,0.8281188],"study_design_scores_gemma":[0.0002828021,0.0002480326,0.004080862,0.09697301,0.001732457,0.0004030783,0.0007466876,0.005633672,0.0004921819,0.3934591,0.4957913,0.0001568286],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0004622804,0.9686896,0.005100768,0.02206768,0.0007286938,0.00004840799,0.00003825368,0.00002135043,0.002843067],"genre_scores_gemma":[0.03022482,0.945066,0.01042156,0.01087502,0.00249333,0.0001762779,0.00006247695,0.00001980584,0.0006606188],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9648167,"threshold_uncertainty_score":0.1860694,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.318590171118013,"score_gpt":0.4571640839556551,"score_spread":0.138573912837642,"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."}}