{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01666679,0.0007839125,0.0005702453,0.005009908,0.001102218,0.002948436,0.001392358,0.001464387,0.001537358],"category_scores_gemma":[0.06068219,0.0002662668,0.0007212445,0.00212234,0.0008290061,0.002176794,0.002061697,0.001116339,0.001133706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001548702,"about_ca_system_score_gemma":0.003930771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004089124,"about_ca_topic_score_gemma":0.004048103,"domain_scores_codex":[0.987225,0.006555056,0.002384447,0.002011498,0.001573744,0.0002502427],"domain_scores_gemma":[0.9077283,0.0730242,0.005595269,0.002900512,0.01001867,0.0007330386],"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":[0.002006865,0.00199442,0.1513173,0.003878522,0.0003330908,0.001971703,0.01291171,0.0192944,0.04081401,0.00505571,0.01573709,0.7446852],"study_design_scores_gemma":[0.0007443374,0.001177695,0.07661328,0.001317473,0.0004092116,0.00341229,0.01112314,0.7943891,0.06299654,0.01582698,0.03174113,0.0002488309],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5648168,0.001209733,0.4062353,0.002479781,0.0002218114,0.005251172,0.008295676,0.005942988,0.005546764],"genre_scores_gemma":[0.375267,0.0002506502,0.6157276,0.0002935692,0.00005301614,0.001529316,0.006019359,0.00009563971,0.0007639127],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01666679,"threshold_uncertainty_score":0.08814341,"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."}}