{"id":"W4286653255","doi":"10.2196/37842","title":"Identifying Patients Who Meet Criteria for Genetic Testing of Hereditary Cancers Based on Structured and Unstructured Family Health History Data in the Electronic Health Record: Natural Language Processing Approach","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"BRCA gene mutations in cancer","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine; National Cancer Institute; National Institutes of Health","keywords":"Family history; Medicine; Unstructured data; Genetic testing; Artificial intelligence; Machine learning; Electronic health record; Cancer; Natural language processing; Computer science; Data mining; Internal medicine; Health care; Big data","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":[0.007013798,0.0005961375,0.0007538469,0.003623813,0.0004738997,0.002214252,0.001000167,0.0009963699,0.001265535],"category_scores_gemma":[0.03430881,0.0003379219,0.0009894001,0.002060418,0.000474207,0.001545583,0.001148143,0.001106113,0.0005832771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008796309,"about_ca_system_score_gemma":0.002086909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005035347,"about_ca_topic_score_gemma":0.006255459,"domain_scores_codex":[0.9937651,0.00314658,0.0008056189,0.001316454,0.0008356166,0.0001305825],"domain_scores_gemma":[0.9559128,0.03668612,0.002776225,0.001469904,0.002895218,0.0002597441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002256051,0.001561514,0.2188074,0.002297062,0.0007082596,0.002558887,0.003626505,0.05178527,0.02361224,0.00424409,0.01392441,0.6746184],"study_design_scores_gemma":[0.0005049816,0.0007597437,0.0839126,0.0007219875,0.0007475974,0.003865149,0.003736996,0.8425653,0.0255932,0.02072402,0.01668066,0.0001877318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3731132,0.001543983,0.5992972,0.004089111,0.0001615903,0.002648613,0.01109101,0.004232195,0.003823107],"genre_scores_gemma":[0.4324433,0.0004044688,0.5573465,0.0008374995,0.00009420388,0.000608371,0.007646085,0.00007035051,0.0005492613],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007013798,"threshold_uncertainty_score":0.03709292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02690331635060951,"score_gpt":0.3287228416131256,"score_spread":0.3018195252625162,"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."}}