{"id":"W4410391103","doi":"10.2196/68143","title":"Identifying People Living With or Those at Risk for HIV in a Nationally Sampled Electronic Health Record Repository Called the National Clinical Cohort Collaborative: Computational Phenotyping Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"HIV/AIDS Research and Interventions","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences; National Center for Advancing Translational Sciences; National Institute of Mental Health","keywords":"Preprint; Electronic health record; Medicine; Health records; Cohort; Human immunodeficiency virus (HIV); Gerontology; Cohort study; Environmental health; Family medicine; World Wide Web; Health care; Computer science; Political science; Pathology","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":[],"consensus_categories":[],"category_scores_codex":[0.01770988,0.0005346796,0.0006624471,0.001296858,0.001402142,0.001545612,0.002587073,0.00140719,0.001429736],"category_scores_gemma":[0.05842089,0.0005546469,0.00164852,0.00167174,0.001215981,0.001566904,0.003549361,0.001965159,0.0004982644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001960803,"about_ca_system_score_gemma":0.002894494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03259307,"about_ca_topic_score_gemma":0.04040884,"domain_scores_codex":[0.9852542,0.009136571,0.0008030921,0.003361804,0.0008971089,0.0005472047],"domain_scores_gemma":[0.9649237,0.01539086,0.004589819,0.01079006,0.002814563,0.001490922],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001506991,0.001351279,0.9421476,0.0002634312,0.00100895,0.0003505443,0.001840696,0.01800233,0.000568025,0.002732906,0.009040602,0.02118662],"study_design_scores_gemma":[0.001011798,0.001597307,0.5292663,0.0004421651,0.0009693129,0.001447106,0.005291461,0.4324659,0.002244027,0.00809685,0.0168999,0.0002679528],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9700504,0.0001704987,0.01267569,0.001818505,0.00007417091,0.001126295,0.01262257,0.0002025446,0.001259374],"genre_scores_gemma":[0.9336168,0.00009291683,0.0409251,0.001127726,0.00005888864,0.0009942463,0.02262824,0.00004514765,0.0005108463],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03259307,"threshold_uncertainty_score":0.09365994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03770918638979474,"score_gpt":0.4404318016093903,"score_spread":0.4027226152195956,"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."}}