{"id":"W2109977913","doi":"10.1197/jamia.m3083","title":"Description of a Rule-based System for the i2b2 Challenge in Natural Language Processing for Clinical Data","year":2009,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lockheed Martin (Canada)","funders":"","keywords":"Computer science; Informatics; Health informatics; Domain (mathematical analysis); Rule-based system; Replicate; Natural language processing; Artificial intelligence; Data science; Medicine; Pathology; Engineering; Public health","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009983857,0.00145487,0.001734755,0.002224107,0.001592596,0.006617323,0.005750418,0.004560371,0.018052],"category_scores_gemma":[0.0267435,0.001363434,0.001646734,0.001547979,0.001134517,0.004575984,0.002678349,0.003918643,0.01354576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001165716,"about_ca_system_score_gemma":0.003136744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007554048,"about_ca_topic_score_gemma":0.007143334,"domain_scores_codex":[0.993165,0.001550458,0.00130512,0.001680876,0.002084681,0.0002139166],"domain_scores_gemma":[0.9832531,0.009571032,0.0005641478,0.002492732,0.0031884,0.0009305323],"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":[0.001486815,0.002224074,0.01054584,0.001651095,0.0008606769,0.006245217,0.001735338,0.0515382,0.07054152,0.02207107,0.181832,0.649268],"study_design_scores_gemma":[0.0007179619,0.0004340702,0.001983464,0.0002960856,0.0002119935,0.002227261,0.0003556751,0.8100956,0.04780052,0.02312538,0.1124149,0.0003369625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005444541,0.0001703074,0.9064571,0.001820129,0.0002348179,0.002451617,0.001960831,0.07821562,0.003245007],"genre_scores_gemma":[0.03956202,0.0001283479,0.9471949,0.001528288,0.0001218586,0.001373162,0.004009323,0.002192108,0.003889888],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.018052,"threshold_uncertainty_score":0.06039,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04810710542172068,"score_gpt":0.3755095698646421,"score_spread":0.3274024644429214,"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."}}