{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001310562,0.00007635479,0.0002488498,0.00005497599,0.00005084696,0.00002034461,0.00009234751,0.0002600686,0.00001239119],"category_scores_gemma":[0.003555807,0.00005703561,0.00004834167,0.00005382275,0.0003427563,0.000006418555,0.0001155096,0.00009333089,9.741838e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002406972,"about_ca_system_score_gemma":0.00005716196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002908336,"about_ca_topic_score_gemma":0.0001328951,"domain_scores_codex":[0.9987905,0.00003109016,0.0007282913,0.0001138901,0.0002122129,0.0001239917],"domain_scores_gemma":[0.9985238,0.001016329,0.000186852,0.0001203386,0.00006731365,0.00008542315],"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":[0.000220073,0.00006523554,0.0589464,0.00009761367,0.00001260271,2.905446e-7,0.0001340006,0.000002125306,0.0002280593,0.0001236423,0.0005325138,0.9396374],"study_design_scores_gemma":[0.006810732,0.003900714,0.1504466,0.001369428,0.000100221,0.00007404284,0.004370394,0.7687904,0.006057444,0.007090111,0.05031563,0.0006742181],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5811393,0.000364872,0.4182437,0.000009520301,0.0001165944,0.00005443877,0.000002290584,0.000003185369,0.00006610093],"genre_scores_gemma":[0.7769631,0.0001552987,0.2226563,0.0001096425,0.000101275,0.000003467369,0.000005225997,0.000002917133,0.00000279557],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9389632,"threshold_uncertainty_score":0.425689,"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."}}