{"id":"W4413104980","doi":"10.1109/tbme.2025.3597527","title":"Adversarial Debiasing for Equitable and Fair Detection of Acute Coronary Syndrome Using 12-Lead ECG","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Biomedical Engineering","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"North York General Hospital; University of Toronto","funders":"National Institutes of Health","keywords":"Debiasing; Adversarial system; Acute coronary syndrome; Electrocardiography; Lead (geology); Cardiology; Computer science; Internal medicine; Medicine; Artificial intelligence; Psychology; Myocardial infarction; Geology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001551388,0.0001329466,0.0003033661,0.0004331937,0.00012435,0.000009745252,0.00004271514,0.0001462352,0.000005532577],"category_scores_gemma":[0.00001650587,0.0001310164,0.0001397146,0.0003657878,0.00005659431,0.00007079418,0.00000223523,0.0001925039,5.643123e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001140109,"about_ca_system_score_gemma":0.0000548676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006421913,"about_ca_topic_score_gemma":0.000002278135,"domain_scores_codex":[0.9990957,0.000008191852,0.0002597932,0.0002060255,0.0001688424,0.0002614023],"domain_scores_gemma":[0.9995764,0.0001175794,0.00003268991,0.0001288801,0.00003969825,0.0001047923],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003202475,0.000205945,0.00009458622,0.00052996,0.00108894,0.00003414227,0.00006274039,0.01150198,0.8954189,0.000005142027,0.000005918542,0.09073155],"study_design_scores_gemma":[0.002172895,0.0005246129,0.000720661,0.0007962651,0.00159807,0.0001755053,0.00008105364,0.8253661,0.1681214,0.00001158854,0.0002547498,0.000177059],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3053268,0.00005593102,0.693671,0.00006944984,0.0006688353,0.0001199323,0.00001668906,0.00006538612,0.000005897372],"genre_scores_gemma":[0.987631,0.00004820174,0.01206242,0.00001672648,0.00005312205,0.00001693655,0.000004272787,0.00001802909,0.0001492755],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8138641,"threshold_uncertainty_score":0.5342692,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0141386637111304,"score_gpt":0.2667190186986918,"score_spread":0.2525803549875614,"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."}}