{"id":"W2891469329","doi":"10.1186/s12911-018-0654-2","title":"Comparison of MetaMap and cTAKES for entity extraction in clinical notes","year":2018,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":88,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Unified Medical Language System; Health informatics; Computer science; Information retrieval; Recall; Information extraction; Context (archaeology); Process (computing); Precision and recall; Natural language processing; Data extraction; MEDLINE; Medicine; Pathology; 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":[0.01920103,0.002531921,0.001699854,0.023588,0.001593787,0.004230453,0.00197887,0.002405076,0.002352499],"category_scores_gemma":[0.06715396,0.0008235564,0.003195305,0.01065466,0.0005972417,0.007301164,0.004455771,0.001470935,0.001713505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001600024,"about_ca_system_score_gemma":0.003550709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008370379,"about_ca_topic_score_gemma":0.01131131,"domain_scores_codex":[0.9816942,0.008094941,0.00360636,0.002759528,0.003209679,0.0006353816],"domain_scores_gemma":[0.9068625,0.07192241,0.003354422,0.006573385,0.009858023,0.001429183],"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":[0.007747408,0.001750279,0.06344677,0.01136213,0.004797722,0.001555197,0.00357265,0.02956132,0.0342584,0.008071179,0.03321491,0.800662],"study_design_scores_gemma":[0.0009265303,0.002573192,0.1402432,0.003131913,0.00399294,0.005188388,0.006586765,0.5900936,0.1270011,0.02366022,0.09554858,0.001053596],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3872619,0.01033073,0.5016409,0.002772507,0.0008420519,0.002958467,0.03589497,0.050297,0.008001461],"genre_scores_gemma":[0.3511583,0.002315604,0.5949071,0.0003918755,0.0001554536,0.001262964,0.04725283,0.0009037697,0.001651959],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.023588,"threshold_uncertainty_score":0.1015459,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1173298955708512,"score_gpt":0.4807227514955384,"score_spread":0.3633928559246872,"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."}}