{"id":"W4318195334","doi":"10.1186/s12911-023-02117-3","title":"Entity and relation extraction from clinical case reports of COVID-19: a natural language processing approach","year":2023,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Topic Modeling","field":"Computer Science","cited_by":29,"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":"Coronavirus disease 2019 (COVID-19); Health informatics; Computer science; Relation (database); Natural language processing; 2019-20 coronavirus outbreak; Information extraction; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Relationship extraction; Natural language; Artificial intelligence; Medicine; Data mining; Pathology; Public health","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":[],"consensus_categories":[],"category_scores_codex":[0.00211318,0.00007543698,0.0001799097,0.0001254715,0.0001335281,0.0001357257,0.0001023587,0.0001308947,0.0000054898],"category_scores_gemma":[0.002827298,0.00005970506,0.00003525572,0.0002378304,0.0000525166,0.0005719652,0.0003178037,0.0002221359,0.00000128156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001586675,"about_ca_system_score_gemma":0.000183995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003229407,"about_ca_topic_score_gemma":0.00002225256,"domain_scores_codex":[0.9981673,0.00004998322,0.0009044555,0.0001786702,0.0005832256,0.0001164108],"domain_scores_gemma":[0.9978064,0.00132977,0.000380832,0.0002511021,0.00004417171,0.0001877269],"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":[0.00001324264,0.00001769596,0.004011459,0.0001885095,0.000004841117,0.000578083,0.003615112,0.0006838038,0.000002257603,0.0005782474,0.00008334072,0.9902234],"study_design_scores_gemma":[0.0002643289,0.000009518448,0.001454112,0.0001133196,0.000005956868,0.002001421,0.001085259,0.9919565,9.604756e-7,0.002982439,0.00006020243,0.00006595407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.433025,0.0001917123,0.5664588,0.00001138706,0.0001439398,0.00005497528,5.0312e-7,0.00004604626,0.00006770224],"genre_scores_gemma":[0.6133999,0.00002320346,0.3864249,0.0001066042,0.0000359504,0.00000165574,0.000003539736,0.000001927042,0.000002402665],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9912727,"threshold_uncertainty_score":0.3384744,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08397814884412258,"score_gpt":0.4160037932922904,"score_spread":0.3320256444481678,"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."}}