{"id":"W4206103793","doi":"10.2196/29803","title":"Identification of Prediabetes Discussions in Unstructured Clinical Documentation: Validation of a Natural Language Processing Algorithm","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Heart, Lung, and Blood Institute; Johns Hopkins University","keywords":"Prediabetes; Documentation; Computer science; Artificial intelligence; Machine learning; Psychological intervention; Natural language processing; Medicine; Nursing","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":[0.0004069353,0.00007120595,0.0001796984,0.00004222553,0.00001914791,0.00001182509,0.0001362247,0.0002149239,0.00003263517],"category_scores_gemma":[0.0006937307,0.00005289378,0.00005961435,0.0001873449,0.0002188903,0.00001332863,0.0000825048,0.0001482789,0.00000100043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006538302,"about_ca_system_score_gemma":0.0001746249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001585404,"about_ca_topic_score_gemma":0.00000398084,"domain_scores_codex":[0.9985213,0.00007212179,0.0008807061,0.0000902941,0.0003263761,0.0001091652],"domain_scores_gemma":[0.9993295,0.00004098568,0.0003001304,0.0001589533,0.0001071182,0.00006331338],"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":[0.00002186814,0.000168842,0.00501011,0.0003343635,0.00003600364,0.00000334333,0.003127681,0.000005929429,0.02484266,0.00001979123,0.0005404325,0.965889],"study_design_scores_gemma":[0.003534203,0.0003553475,0.04258408,0.000677987,0.00006204999,0.00004177642,0.02442333,0.03771221,0.8881071,0.000296568,0.001818504,0.0003868873],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9930192,0.0006168022,0.005786699,0.0001802048,0.0001869562,0.0001053762,0.00001836072,0.000009554556,0.00007687176],"genre_scores_gemma":[0.9898848,0.00007743647,0.00945643,0.00007691082,0.00007649224,0.00001294231,0.0003325636,0.000004163958,0.00007826245],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9655021,"threshold_uncertainty_score":0.2156946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01038389281619116,"score_gpt":0.3551081211015509,"score_spread":0.3447242282853598,"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."}}