{"id":"W4405318361","doi":"10.1172/jci178722","title":"Estimation of prevalence of autoimmune diseases in the United States using electronic health record data","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Investigation","topic":"Diabetes and associated disorders","field":"Biochemistry, Genetics and Molecular Biology","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Population and Public Health","funders":"National Center for Advancing Translational Sciences; University of Southern California; National Institute of Environmental Health Sciences; National Institutes of Health; National Heart, Lung, and Blood Institute; Massachusetts General Hospital","keywords":"Estimation; Electronic health record; Medicine; Health records; Environmental health; Statistics; Data science; Computer science; Mathematics; Political science; Health care; Law","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00192411,0.00005128163,0.0001709503,0.00006214936,0.00001490306,0.00001302067,0.0002277956,0.00005400624,0.000002551336],"category_scores_gemma":[0.001160949,0.00003649116,0.00006762356,0.000221124,0.00009672452,0.00001950402,0.00003399042,0.0001512576,1.454357e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001210353,"about_ca_system_score_gemma":0.0005021985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006474543,"about_ca_topic_score_gemma":0.00001084963,"domain_scores_codex":[0.9984629,0.0003205381,0.0008803365,0.00009740021,0.0001459403,0.00009284016],"domain_scores_gemma":[0.9988719,0.0001846191,0.0006596894,0.0001730218,0.00007892816,0.00003187301],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006225072,0.00168025,0.4853095,0.003978725,0.001074862,0.000007477101,0.001435205,0.1289596,0.03827797,0.001829233,0.01314975,0.3236749],"study_design_scores_gemma":[0.001617418,0.003338209,0.2701116,0.00240699,0.0003748187,0.00000815547,0.0005789501,0.6949081,0.003725284,0.017797,0.004890794,0.0002426278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9936864,0.004043612,0.001014835,0.001041431,0.0001023513,0.0000705842,0.00003633016,0.000001570478,0.000002919754],"genre_scores_gemma":[0.9954951,0.003357085,0.0006391691,0.0002285291,0.0000516473,4.372637e-7,0.0002165078,0.000005213638,0.00000632517],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5659485,"threshold_uncertainty_score":0.1488066,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06678148431522449,"score_gpt":0.4007699903572485,"score_spread":0.333988506042024,"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."}}