{"id":"W1994715541","doi":"10.2196/medinform.3172","title":"Next Generation Phenotyping Using the Unified Medical Language System","year":2014,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Institutes of Health; National Center for Research Resources; Medical College of Wisconsin","keywords":"Computer science; Unified Medical Language System; Natural language processing","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":[0.001026995,0.000138346,0.0001715111,0.000030701,0.000165078,0.00005184477,0.0004395141,0.0004614236,0.00006793789],"category_scores_gemma":[0.0008166138,0.00008529258,0.00006641413,0.0001064991,0.000276362,0.000007083961,0.0001906008,0.0002792471,0.00002601575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000206607,"about_ca_system_score_gemma":0.000176582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001458768,"about_ca_topic_score_gemma":0.00001537309,"domain_scores_codex":[0.998293,0.0001220735,0.0004588338,0.0001136345,0.0007359011,0.0002765512],"domain_scores_gemma":[0.9991613,0.00006189743,0.0001293105,0.0003468694,0.00004966537,0.0002509551],"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":[0.00009005675,0.0001894939,0.000358796,0.0009080126,0.0002655973,0.00003165123,0.01092271,0.000114017,0.03582625,0.008112186,0.03447749,0.9087037],"study_design_scores_gemma":[0.001145246,0.0001855473,0.00008242866,0.0002685012,0.0000337815,0.0002471965,0.01142282,0.8749419,0.004673368,0.00001659887,0.1066223,0.000360333],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8448639,0.0003103382,0.1509516,0.0008283407,0.000545943,0.0001834283,0.000003081512,0.00008915324,0.002224194],"genre_scores_gemma":[0.9918486,0.00003292104,0.003435374,0.003158138,0.001340106,0.00001942012,0.00008431569,0.0000132678,0.00006781414],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9083434,"threshold_uncertainty_score":0.3558921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03375254166050839,"score_gpt":0.3076729091988636,"score_spread":0.2739203675383552,"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."}}