{"id":"W3102749286","doi":"10.2196/23104","title":"Clinical Term Normalization Using Learned Edit Patterns and Subconcept Matching: System Development and Evaluation","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Normalization (sociology); Natural language processing; Edit distance; Unified Medical Language System; Artificial intelligence; Term (time); Information retrieval","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":[],"consensus_categories":[],"category_scores_codex":[0.0007214177,0.0001151944,0.0001794553,0.00002012783,0.00008385717,0.00003545292,0.0001060005,0.0003088198,0.00001549316],"category_scores_gemma":[0.0002401656,0.00009328468,0.00002554517,0.00004874475,0.0001479474,0.000009822772,0.0001814244,0.0001589444,0.000003852754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001392891,"about_ca_system_score_gemma":0.000170833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000273563,"about_ca_topic_score_gemma":0.000002393561,"domain_scores_codex":[0.9986277,0.00008142518,0.000563458,0.0001402429,0.0004276007,0.0001595704],"domain_scores_gemma":[0.9993709,0.00002946003,0.0001532677,0.00009490329,0.0000610077,0.0002904443],"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":[0.0001140374,0.00007635843,0.07203627,0.001499332,0.0001509327,0.00001086951,0.01420832,0.00002761631,0.0007103981,0.0001182827,0.001368517,0.9096791],"study_design_scores_gemma":[0.01288773,0.002288178,0.1029605,0.001862876,0.0003358297,0.0004682665,0.05314108,0.6838499,0.007221313,0.00005880427,0.1328573,0.002068203],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9658749,0.0001480953,0.03327639,0.0002373554,0.0001455129,0.0001801832,0.000003304193,0.00003168598,0.0001026149],"genre_scores_gemma":[0.9926921,0.00008536164,0.005798499,0.0009436146,0.0003413083,0.000014272,0.0001100458,0.000008164061,0.000006662502],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9076108,"threshold_uncertainty_score":0.3804039,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07249807901364434,"score_gpt":0.3738195623385964,"score_spread":0.301321483324952,"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."}}