{"id":"W2991379615","doi":"10.2196/14325","title":"Mapping ICD-10 and ICD-10-CM Codes to Phecodes: Workflow Development and Initial Evaluation","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":561,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; U.S. National Library of Medicine; National Heart, Lung, and Blood Institute; China Scholarship Council; National Institutes of Health; Cancer Research UK; Georgia Clinical and Translational Science Alliance; Vanderbilt University Medical Center; Vanderbilt University; National Institute of General Medical Sciences; American Heart Association","keywords":"ICD-10; Medicine; Systematized Nomenclature of Medicine; Biorepository; Health informatics; Diagnosis code; Informatics; Medicaid; Concordance; Medical classification; SNOMED CT; Electronic health record; Biobank; Health care; Internal medicine; Public health; Pathology; Terminology; Bioinformatics; Population","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":[0.1360246,0.001346415,0.000954684,0.007336924,0.001956799,0.005066393,0.003276115,0.0008491388,0.002724168],"category_scores_gemma":[0.3365164,0.0008748339,0.001834165,0.005607329,0.001149983,0.003531234,0.005764648,0.002153745,0.001524637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004776424,"about_ca_system_score_gemma":0.0200663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02442237,"about_ca_topic_score_gemma":0.01655793,"domain_scores_codex":[0.9175683,0.05015577,0.01016859,0.005940927,0.01482236,0.001344207],"domain_scores_gemma":[0.6941948,0.1494257,0.01515914,0.03810963,0.09898091,0.004129843],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001729892,0.001437724,0.1583604,0.002735466,0.0004592302,0.0006963535,0.01894782,0.01831735,0.00549923,0.008378666,0.02779448,0.7556433],"study_design_scores_gemma":[0.002129054,0.003475556,0.3719802,0.006805893,0.0008985136,0.001964157,0.03792458,0.2840899,0.07046222,0.03867147,0.1806663,0.0009320601],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3153695,0.001379142,0.6089443,0.006051523,0.0005754916,0.02582991,0.01732679,0.01294578,0.01157752],"genre_scores_gemma":[0.2605907,0.0007722231,0.7091745,0.0005032138,0.00009128594,0.01153586,0.01471651,0.001297632,0.001318168],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1360246,"threshold_uncertainty_score":0.7193756,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1801527069750413,"score_gpt":0.473251173470247,"score_spread":0.2930984664952057,"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."}}