{"id":"W4408887841","doi":"10.1016/j.landig.2025.01.003","title":"Weighing the benefits and risks of collecting race and ethnicity data in clinical settings for medical artificial intelligence","year":2025,"lang":"en","type":"review","venue":"The Lancet Digital Health","topic":"Race, Genetics, and Society","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; York University","funders":"National Institute of Biomedical Imaging and Bioengineering; Horizon 2020; Innovative Medicines Initiative; European Federation of Pharmaceutical Industries and Associations; National Institutes of Health; National Science Foundation","keywords":"Ethnic group; Race (biology); Medicine; Data science; Psychology; Computer science; Sociology; Anthropology; Gender studies","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006503222,0.0009326391,0.001994728,0.00448027,0.0006040674,0.002860039,0.002084136,0.003695484,0.003635315],"category_scores_gemma":[0.01243146,0.0004830168,0.001130735,0.003575843,0.002544813,0.004650287,0.00188811,0.004898337,0.001874809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002280697,"about_ca_system_score_gemma":0.003934361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004626834,"about_ca_topic_score_gemma":0.007128101,"domain_scores_codex":[0.997784,0.001039083,0.0002416776,0.0002154504,0.0006216523,0.00009824176],"domain_scores_gemma":[0.9870855,0.01062286,0.0005147197,0.0002284403,0.001283768,0.0002646891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006554534,0.00002796916,0.0001794277,0.01866226,0.0001767178,0.0001206148,0.0002068745,0.0002552428,0.0001886744,0.0125259,0.02843373,0.9391571],"study_design_scores_gemma":[0.00003827595,0.00007733658,0.001009958,0.02723501,0.0002142957,0.0009665118,0.0003285833,0.0001325011,0.0001919914,0.0125621,0.9571915,0.00005195223],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00003952227,0.9964509,0.0001830667,0.002141508,0.0003262083,0.000005587788,0.00001021567,0.000006293782,0.000836759],"genre_scores_gemma":[0.0006243663,0.9964743,0.0005108503,0.00161253,0.0004005072,0.00001509867,0.0000193007,0.000004254593,0.0003386912],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.006503222,"threshold_uncertainty_score":0.03439277,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2531679896051939,"score_gpt":0.4940701634746422,"score_spread":0.2409021738694483,"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."}}