{"id":"W4378472501","doi":"10.1038/s41598-023-35482-0","title":"Constructing a disease database and using natural language processing to capture and standardize free text clinical information","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Topic Modeling","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Public Health Ontario","funders":"Institute of Health Services and Policy Research; Canadian Institutes of Health Research","keywords":"Computer science; Benchmark (surveying); Infectious disease (medical specialty); Disease; Natural language processing; Protocol (science); Data science; Artificial intelligence; Machine learning; Medicine; Pathology; Alternative medicine","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001895857,0.0000945986,0.0001293979,0.0001905167,0.0003785878,0.001151168,0.0001880421,0.00003027115,0.000001748764],"category_scores_gemma":[0.001344021,0.00008359927,0.00002435787,0.0005721801,0.0001412442,0.001555761,0.000716389,0.0001285381,0.000002213478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000290648,"about_ca_system_score_gemma":0.0002226023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000368,"about_ca_topic_score_gemma":0.00001935184,"domain_scores_codex":[0.9983447,0.00003560594,0.000434948,0.0005256499,0.0004262908,0.0002327788],"domain_scores_gemma":[0.9986877,0.00005295472,0.000183652,0.0007242576,0.0001205761,0.0002309036],"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":[0.00001980392,0.00001695376,0.02970259,0.0003604067,0.00001600354,0.001435256,0.01276636,0.0005986854,0.001884218,0.00136033,0.003466896,0.9483725],"study_design_scores_gemma":[0.0002665225,0.00000698955,0.002286798,0.0002372358,0.00001628273,0.0003435934,0.002021263,0.9908679,0.0001815795,0.001625877,0.00186565,0.0002803742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8244092,0.0003456136,0.1716446,0.0003873847,0.002715794,0.0002211178,0.00001201887,0.0001801195,0.00008407909],"genre_scores_gemma":[0.9524488,8.931277e-7,0.04728876,0.00009515225,0.00005215218,0.000003089868,0.00002064783,0.000004196077,0.00008624432],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9902691,"threshold_uncertainty_score":0.9998857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02654819782817638,"score_gpt":0.3204444185690802,"score_spread":0.2938962207409038,"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."}}