{"id":"W1965466476","doi":"10.1016/j.jbi.2012.05.006","title":"A study of terminology auditors’ performance for UMLS semantic type assignments","year":2012,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"New York Institute of Technology","funders":"U.S. National Library of Medicine","keywords":"Unified Medical Language System; Computer science; Audit; Terminology; Recall; Task (project management); Reliability (semiconductor); Information retrieval; Natural language processing; Sample (material); Measure (data warehouse); Semantics (computer science); Artificial intelligence; Data mining; Accounting; Linguistics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05288736,0.0007513103,0.00113896,0.0058322,0.002371758,0.004222052,0.001836233,0.001718258,0.001867528],"category_scores_gemma":[0.3100224,0.0007014902,0.001161258,0.005119205,0.001405103,0.004768519,0.002990863,0.002423021,0.001166936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002206292,"about_ca_system_score_gemma":0.005066078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007570338,"about_ca_topic_score_gemma":0.005632633,"domain_scores_codex":[0.9308395,0.03056558,0.00997436,0.008484074,0.01726319,0.002873213],"domain_scores_gemma":[0.4215508,0.4227958,0.0409767,0.04691398,0.06196875,0.005793972],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.008846403,0.003193866,0.5024312,0.0009579387,0.001100873,0.001174343,0.01376219,0.01461603,0.03517051,0.002480462,0.01146443,0.4048017],"study_design_scores_gemma":[0.0008115208,0.006977251,0.483613,0.0006847469,0.001891749,0.004665181,0.02217782,0.3250674,0.1188798,0.004761901,0.02985532,0.000614356],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9875542,0.000361257,0.007645475,0.0004307516,0.0001329809,0.000150241,0.0006253134,0.001614215,0.001485621],"genre_scores_gemma":[0.9798483,0.0001639076,0.01570576,0.0001254193,0.00004516399,0.00008085293,0.001687881,0.0004245236,0.001918125],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9471126,"threshold_uncertainty_score":0.2796985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0362487039255609,"score_gpt":0.3222454193852722,"score_spread":0.2859967154597113,"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."}}