{"id":"W2928818852","doi":"10.2196/12596","title":"Identifying Clinical Terms in Medical Text Using Ontology-Guided Machine Learning","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":69,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"","keywords":"Computer science; Ontology; Natural language processing; Unified Medical Language System; Artificial intelligence; Information retrieval","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002112068,0.0002407487,0.0005132967,0.0001263689,0.00006942178,0.00003501399,0.0006425936,0.001244901,0.0007435907],"category_scores_gemma":[0.002031398,0.0001924018,0.0001682944,0.0002065027,0.0004537672,0.00001414737,0.000523885,0.001191925,0.0001703231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003261885,"about_ca_system_score_gemma":0.0003580235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004078164,"about_ca_topic_score_gemma":0.00008228764,"domain_scores_codex":[0.9965807,0.0002177821,0.001399529,0.0002780127,0.0009632387,0.0005607418],"domain_scores_gemma":[0.9986604,0.0001575998,0.0002729663,0.0003773706,0.00004926506,0.0004824328],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002547541,0.0006274253,0.6317163,0.0006264423,0.0002386629,0.0002369757,0.002068481,0.00006226546,0.001637063,0.0002702483,0.00674897,0.3555124],"study_design_scores_gemma":[0.01919108,0.002702731,0.0595713,0.002388448,0.00009403931,0.002410986,0.005131632,0.4383367,0.001877532,0.0005147754,0.4652553,0.002525381],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9920852,0.0003135685,0.003085206,0.0004441439,0.0006818486,0.0002379334,0.000003242025,0.00006145717,0.003087357],"genre_scores_gemma":[0.9900755,0.0004198086,0.005527581,0.002916958,0.000375252,0.00001878285,0.0001230367,0.00002772005,0.0005153602],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.572145,"threshold_uncertainty_score":0.9601819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05108806052573915,"score_gpt":0.3965789011479377,"score_spread":0.3454908406221985,"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."}}