{"id":"W2883963541","doi":"10.2196/medinform.9878","title":"Validating a Framework for Coding Patient-Reported Health Information to the Medical Dictionary for Regulatory Activities Terminology: An Evaluative Study","year":2018,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Pharmacovigilance and Adverse Drug Reactions","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Terminology; Coding (social sciences); Computer science; Medical terminology; Health informatics; Medical classification; Natural language processing; Knowledge management; Data science; Information retrieval; Medicine; Linguistics; Public health; Nursing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.003443523,0.0002633122,0.0003858856,0.0002040073,0.001338964,0.000055271,0.0004839855,0.0004464481,0.0004685674],"category_scores_gemma":[0.001961064,0.0001989466,0.0001164556,0.0003120503,0.0003659726,0.001068418,0.0001646809,0.001010985,0.00005565303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002145303,"about_ca_system_score_gemma":0.001031107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009073855,"about_ca_topic_score_gemma":0.00002265344,"domain_scores_codex":[0.996556,0.0003580938,0.001301894,0.0001831148,0.0009616319,0.0006391936],"domain_scores_gemma":[0.9962034,0.001678095,0.0006977097,0.0003352167,0.0003433835,0.0007422128],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001662179,0.00201341,0.003061889,0.000424677,0.0009730034,0.000009030206,0.224125,0.0002658803,0.00008781745,0.005379227,0.07671792,0.68528],"study_design_scores_gemma":[0.006744751,0.005101997,0.002591989,0.0003336389,0.0003186608,0.0001808711,0.1238596,0.2046856,0.001558426,0.001862625,0.6520331,0.0007287897],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9363118,0.00001780899,0.04668036,0.005968612,0.003004915,0.006937445,0.0002360488,0.0002656064,0.0005773988],"genre_scores_gemma":[0.9569436,0.00002707325,0.002714308,0.03513228,0.001223002,0.003672778,0.0002290954,0.00002234789,0.00003556587],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6845512,"threshold_uncertainty_score":0.9999611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1535582157098413,"score_gpt":0.5209795949836761,"score_spread":0.3674213792738348,"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."}}