{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007078212,0.0001367294,0.0002082892,0.00008265057,0.0001578086,0.00001508216,0.0005258281,0.00006529653,0.00000614934],"category_scores_gemma":[0.0001541122,0.0001142997,0.00002459363,0.0001695078,0.00008334076,0.00001501015,0.0001720801,0.0002977701,2.37942e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006271304,"about_ca_system_score_gemma":0.002670176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001511386,"about_ca_topic_score_gemma":0.0001401816,"domain_scores_codex":[0.9982908,0.0001510952,0.0005461825,0.0002054756,0.0004902125,0.0003162509],"domain_scores_gemma":[0.9990568,0.00004376655,0.0003819196,0.0003985004,0.00004870559,0.00007033637],"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":[0.0007163561,0.0003314302,0.006383657,0.006271149,0.0001317046,0.000003887573,0.0603986,0.003240461,0.0008284975,0.0000523491,0.1318457,0.7897962],"study_design_scores_gemma":[0.004801644,0.002004467,0.02031127,0.000296713,0.00002456538,0.00004591298,0.02648959,0.9219397,0.00009776993,0.00009415167,0.02335013,0.0005440538],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9849228,0.00855397,0.003770127,0.0003416663,0.0005141694,0.001412311,0.0003834472,0.00001506724,0.0000864602],"genre_scores_gemma":[0.9738469,0.00003723036,0.01959324,0.004857273,0.0001031316,0.0001564932,0.001383379,0.00001820141,0.000004202353],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9186993,"threshold_uncertainty_score":0.4736778,"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."}}