{"id":"W4288048604","doi":"10.2196/39235","title":"Issues With Variability in Electronic Health Record Data About Race and Ethnicity: Descriptive Analysis of the National COVID Cohort Collaborative Data Enclave","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Racial and Ethnic Identity Research","field":"Social Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; U.S. National Library of Medicine; National Institutes of Health","keywords":"Ethnic group; Health care; Descriptive statistics; Consistency (knowledge bases); Race (biology); Health equity; Medicine; Computer science; Database; Data science; Statistics; Political science; Sociology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0182318,0.00008387719,0.0003598325,0.0001617627,0.0006643609,0.00005902831,0.001700666,0.00007412021,0.0004889723],"category_scores_gemma":[0.00401318,0.00006058317,0.00002214887,0.00328841,0.0009330589,0.0006684951,0.001630897,0.0007294033,0.000001244355],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006120606,"about_ca_system_score_gemma":0.0070976,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01442751,"about_ca_topic_score_gemma":0.09664049,"domain_scores_codex":[0.9944556,0.001567655,0.0005687164,0.0002103365,0.002834006,0.0003636523],"domain_scores_gemma":[0.998004,0.0006907925,0.0003079641,0.0005555066,0.000257459,0.0001843198],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003769069,0.0007916354,0.3214435,0.0002818614,0.001564691,0.000004203426,0.5628219,0.0002146717,0.000002029879,0.02858414,0.05584238,0.02807212],"study_design_scores_gemma":[0.001396606,0.0004634866,0.1503019,0.000110203,0.0002995899,0.000004034768,0.2732709,0.1864384,0.000003010639,0.00520969,0.3820319,0.0004703161],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9174418,0.0008706402,0.002266522,0.05789945,0.0003070732,0.004465153,0.003907707,0.00007308055,0.01276851],"genre_scores_gemma":[0.992891,0.002872501,0.00062423,0.001999901,0.00009287301,0.0001285258,0.0007816431,0.000007870404,0.0006014986],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3261895,"threshold_uncertainty_score":0.9985312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07326107058090033,"score_gpt":0.4426929443615468,"score_spread":0.3694318737806465,"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."}}