{"id":"W4416962170","doi":"10.1109/embc58623.2025.11252877","title":"Enhancing Fairness in Ultrasound Imaging: Evaluating Adversarial Debiasing Across Diverse Patient Demographics","year":2025,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Debiasing; Adversarial system; Demographics; Learning curve; Commit","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":[0.01297501,0.001148449,0.0008739309,0.0008167049,0.0006315482,0.001149788,0.001139117,0.001499319,0.001293736],"category_scores_gemma":[0.0440717,0.0002589488,0.0005091507,0.0003469608,0.002020082,0.001359193,0.001940404,0.001589245,0.000357429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001126091,"about_ca_system_score_gemma":0.001164437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002475111,"about_ca_topic_score_gemma":0.0018593,"domain_scores_codex":[0.9961866,0.002121777,0.0001679867,0.0006431713,0.0006301149,0.0002503388],"domain_scores_gemma":[0.9741864,0.02044499,0.001540772,0.001913241,0.001182614,0.0007320695],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.002250715,0.0004170256,0.0242218,0.0002991849,0.000300106,0.0003224231,0.0003313574,0.7959833,0.008793669,0.00810758,0.003898044,0.1550747],"study_design_scores_gemma":[0.00008055898,0.0007709552,0.004220824,0.0000893784,0.00005552262,0.0003985098,0.0001123007,0.9701343,0.01071518,0.01200322,0.001375745,0.00004347509],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4623026,0.004778354,0.520185,0.003049626,0.0006423264,0.0005044558,0.0005405403,0.001703104,0.006294004],"genre_scores_gemma":[0.9493786,0.0003848719,0.04733617,0.0007974074,0.0001455453,0.00008421172,0.0002915915,0.00008732782,0.001494251],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01297501,"threshold_uncertainty_score":0.06861919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1084497056534117,"score_gpt":0.4714918965899598,"score_spread":0.363042190936548,"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."}}