{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003492898,0.00006584836,0.0002515192,0.00003227891,0.00005194631,0.00001748455,0.0005714832,0.00009829376,2.893927e-7],"category_scores_gemma":[0.005441218,0.00003496056,0.0001327178,0.0001055313,0.0001078573,0.00001163232,0.00004830293,0.0002142544,9.401329e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006104995,"about_ca_system_score_gemma":0.0002555165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005321738,"about_ca_topic_score_gemma":0.00001267148,"domain_scores_codex":[0.9985457,0.00009439712,0.0007752255,0.00005420308,0.0003923304,0.0001381565],"domain_scores_gemma":[0.9974941,0.0003636727,0.001726982,0.00019356,0.0001779786,0.00004368749],"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":[0.0005763063,0.0002478529,0.004739297,0.0002103291,0.0001443835,8.292837e-7,0.0006889642,0.000049154,0.0008557319,0.00001586337,0.009341326,0.98313],"study_design_scores_gemma":[0.01539226,0.005963478,0.1059999,0.002035734,0.000665937,0.0000700396,0.02767127,0.8034645,0.003029664,0.0002270496,0.03487801,0.0006020808],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9104869,0.002721311,0.07502011,0.01055867,0.0007056026,0.0004107282,0.00004826685,0.00000857579,0.00003977214],"genre_scores_gemma":[0.9921117,0.0001523259,0.006516897,0.0008730195,0.0003040947,0.000003638826,0.00002220814,0.000003830286,0.00001221635],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9825279,"threshold_uncertainty_score":0.6514039,"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."}}