{"id":"W4408893162","doi":"10.2196/67591","title":"Biases in Race and Ethnicity Introduced by Filtering Electronic Health Records for “Complete Data”: Observational Clinical Data Analysis","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine; National Heart, Lung, and Blood Institute","keywords":"Biobank; Ethnic group; Missing data; Data quality; Medicine; Filter (signal processing); Computer science; Database; Demography; Engineering; Machine learning; Bioinformatics; Biology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1790856,0.0006779116,0.0009096417,0.002279094,0.001804537,0.002613903,0.002088562,0.001145911,0.001083807],"category_scores_gemma":[0.3374405,0.0005565738,0.003114798,0.004937454,0.002106555,0.001761284,0.002557993,0.001835699,0.0002250124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001846374,"about_ca_system_score_gemma":0.004436151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01217318,"about_ca_topic_score_gemma":0.01137974,"domain_scores_codex":[0.7939737,0.1511872,0.0239188,0.01231118,0.01642357,0.002185531],"domain_scores_gemma":[0.5773148,0.2816224,0.06829194,0.05380749,0.01756456,0.001398784],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000565386,0.0001299969,0.9439138,0.0006032051,0.003509572,0.0001623418,0.002365595,0.003801703,0.000894315,0.004297058,0.003754632,0.03600242],"study_design_scores_gemma":[0.000328704,0.0006458571,0.8990143,0.001665695,0.003369423,0.0009212997,0.002503076,0.03090009,0.009603948,0.02202361,0.02881335,0.0002107348],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.738102,0.003876385,0.2362797,0.006054608,0.0006856008,0.002444411,0.007388844,0.000393076,0.004775338],"genre_scores_gemma":[0.9049388,0.0004185974,0.08597723,0.00288399,0.0002669696,0.001711176,0.003287253,0.000123875,0.0003921446],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8209144,"threshold_uncertainty_score":0.9471065,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6979200855163302,"score_gpt":0.6503641927546403,"score_spread":0.04755589276168992,"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."}}