{"id":"W4308726062","doi":"10.2196/38037","title":"Modeling the Potential Impact of Missing Race and Ethnicity Data in Infectious Disease Surveillance Systems on Disparity Measures: Scenario Analysis of Different Imputation Strategies","year":2022,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for HIV/AIDS, Viral Hepatitis, STD, and TB Prevention; Centers for Disease Control and Prevention; New York State Department of Health","keywords":"Gonorrhea; Imputation (statistics); Ethnic group; Chlamydia; Demography; Missing data; Medicine; Population; Medical diagnosis; Environmental health; Statistics; Family medicine; Immunology; Political science","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":[0.003548655,0.0002699101,0.001182241,0.0004511336,0.0002965069,0.0001033054,0.0002962343,0.00005349035,0.000009879792],"category_scores_gemma":[0.0007848046,0.0001981436,0.0001391072,0.00124425,0.0001603948,0.000233915,0.0003233035,0.0004247809,1.242535e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000295522,"about_ca_system_score_gemma":0.001469346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005433718,"about_ca_topic_score_gemma":0.002669151,"domain_scores_codex":[0.9953377,0.001769093,0.0008950941,0.0006669644,0.0008255233,0.0005056788],"domain_scores_gemma":[0.9972317,0.0003972363,0.0004928388,0.001083025,0.0002210896,0.0005740969],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007858031,0.00043352,0.9201224,0.0006292706,0.000373867,0.00001174826,0.0004847825,0.07035877,0.00002364431,0.00008617633,0.00006660021,0.006623451],"study_design_scores_gemma":[0.0006627397,0.0001658407,0.5704122,0.00002414014,0.00001299829,0.00000592903,0.0003468394,0.4282217,3.083027e-8,0.0000234008,0.00002730125,0.00009684675],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9874926,0.004211611,0.003850162,0.001326243,0.00009851368,0.0009638272,0.00198261,0.00004920423,0.00002524868],"genre_scores_gemma":[0.9974108,0.000725804,0.00001192242,0.000117039,0.00003638386,0.00005769606,0.001616636,0.00002014604,0.000003612987],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3578629,"threshold_uncertainty_score":0.8214192,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04843104351523602,"score_gpt":0.3529417469302488,"score_spread":0.3045107034150128,"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."}}