{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007879043,0.001579811,0.001608672,0.002440672,0.0009273955,0.002116353,0.003750026,0.002409709,0.004957115],"category_scores_gemma":[0.02593679,0.0005349118,0.001034466,0.002069714,0.0007015259,0.003188984,0.002446744,0.001654233,0.003436908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001806857,"about_ca_system_score_gemma":0.003575843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009306178,"about_ca_topic_score_gemma":0.007401658,"domain_scores_codex":[0.9928923,0.00184557,0.0009159276,0.002289452,0.001789046,0.0002678363],"domain_scores_gemma":[0.9895685,0.004808106,0.0005265513,0.001382612,0.003229634,0.0004844642],"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":[0.00185121,0.00161133,0.009256686,0.002342708,0.0006308139,0.001009052,0.0008245718,0.01362504,0.04145963,0.001017226,0.04804993,0.8783217],"study_design_scores_gemma":[0.00143181,0.002776477,0.02127729,0.0003931822,0.0007626401,0.004417958,0.0009495306,0.7600504,0.1567198,0.004598302,0.04624727,0.0003755311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3912005,0.007358082,0.4466022,0.00215092,0.001544573,0.005871616,0.01218533,0.1253067,0.007780011],"genre_scores_gemma":[0.3469439,0.001626679,0.606833,0.001075541,0.0002100388,0.002273997,0.0339478,0.001826718,0.005262386],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009306178,"threshold_uncertainty_score":0.04166889,"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."}}