{"id":"W2104381725","doi":"10.1136/amiajnl-2011-000150","title":"Machine-learned solutions for three stages of clinical information extraction: the state of the art at i2b2 2010","year":2011,"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":240,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine","keywords":"Narrative; Benchmark (surveying); Process (computing); Computer science; State (computer science); Data science; Health care; Artificial intelligence; Natural language processing; Political science; Art; Cartography; Literature; Geography; Law","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01553391,0.003427417,0.001870451,0.004682809,0.001953591,0.006802565,0.004790721,0.005742455,0.004803608],"category_scores_gemma":[0.03633727,0.001055418,0.001913185,0.00390966,0.001122116,0.006749342,0.003587563,0.004488295,0.005077991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003447847,"about_ca_system_score_gemma":0.005136654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01182042,"about_ca_topic_score_gemma":0.0131959,"domain_scores_codex":[0.9848445,0.00519685,0.001672037,0.003637938,0.003942329,0.0007063025],"domain_scores_gemma":[0.9769441,0.01452762,0.001061281,0.002330513,0.004370293,0.0007660954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009490907,0.001317953,0.005643842,0.002218942,0.0003668441,0.0002479476,0.0009187355,0.02967425,0.01183479,0.002572513,0.0545546,0.8897006],"study_design_scores_gemma":[0.0007935545,0.001314786,0.01067849,0.000898675,0.0004082909,0.0006474768,0.001656078,0.837189,0.04881126,0.02268168,0.07457717,0.0003437037],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1901831,0.03479063,0.6749485,0.01962122,0.001408796,0.002710633,0.01308563,0.04442485,0.0188266],"genre_scores_gemma":[0.2301668,0.005052824,0.7174981,0.00208776,0.0007114905,0.001400884,0.03464588,0.001249894,0.007186372],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01553391,"threshold_uncertainty_score":0.08215213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04653909334875948,"score_gpt":0.340871690572667,"score_spread":0.2943325972239075,"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."}}