{"id":"W4385685508","doi":"10.1101/2023.08.04.551906","title":"Enhancing Fairness in Disease Prediction by Optimizing Multiple Domain Adversarial Networks","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Stanford Bio-X; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Alzheimer's Disease Neuroimaging Initiative; U.S. Department of Defense; Meso Scale Diagnostics; University of Southern California; University of Texas Health Science Center at Houston; Biogen; Cancer Prevention and Research Institute of Texas; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; Novartis Pharmaceuticals Corporation; Pfizer; Canadian Institutes of Health Research; National Science Foundation","keywords":"Leverage (statistics); Adversarial system; Computer science; Machine learning; Artificial intelligence; Receiver operating characteristic; Disadvantaged; Domain (mathematical analysis); Data mining; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006139451,0.001246823,0.001129275,0.0005327094,0.0006093921,0.001371558,0.001390238,0.001388102,0.001253561],"category_scores_gemma":[0.01397691,0.0004473611,0.0006577086,0.0003834466,0.001630068,0.00156073,0.002433401,0.002189173,0.0002561974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001502594,"about_ca_system_score_gemma":0.001710398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003914318,"about_ca_topic_score_gemma":0.003675723,"domain_scores_codex":[0.9984317,0.0007686041,0.00006041315,0.0003076371,0.000263538,0.0001680057],"domain_scores_gemma":[0.9930788,0.005150924,0.0005582337,0.0004585927,0.0005002343,0.0002532251],"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":[0.00009139675,0.0000388498,0.001990243,0.00002285392,0.00004317796,0.00004444308,0.0000389603,0.9741874,0.000807744,0.006904805,0.000832458,0.01499755],"study_design_scores_gemma":[0.000005455244,0.0000168224,0.0001379884,0.000005503507,0.00000583154,0.00001068557,0.00000502481,0.992615,0.000389644,0.006661216,0.0001425528,0.000004143036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06106346,0.0005069319,0.9334846,0.001723891,0.0001167507,0.00006733614,0.0001363046,0.0003070481,0.002593761],"genre_scores_gemma":[0.9044397,0.0003080138,0.09008783,0.0009042165,0.0001644057,0.0001406251,0.0002166198,0.00009756166,0.003640938],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006139451,"threshold_uncertainty_score":0.03246891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0459999519465106,"score_gpt":0.2980166929068569,"score_spread":0.2520167409603463,"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."}}