{"id":"W4206681774","doi":"10.2196/26353","title":"Neural Translation and Automated Recognition of ICD-10 Medical Entities From Natural Language: Model Development and Performance Assessment","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Named-entity recognition; Natural language; Unified Medical Language System; Natural language processing; Task (project management); Data science; Engineering","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":[0.0006349624,0.0001082191,0.0001749853,0.0001023351,0.000203296,0.00004201858,0.0003148755,0.00008243004,0.0002226934],"category_scores_gemma":[0.00006302819,0.00009661755,0.00001757917,0.0001503923,0.00008068621,0.0003439469,0.0003261548,0.0005733659,0.000001659823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004982217,"about_ca_system_score_gemma":0.0003530116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003131778,"about_ca_topic_score_gemma":0.0000124079,"domain_scores_codex":[0.9977098,0.0000964372,0.0005606006,0.0001124399,0.001344248,0.000176524],"domain_scores_gemma":[0.9993074,0.0001611464,0.000171416,0.0001381922,0.00004834263,0.0001735353],"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":[0.00001649916,0.00004886375,0.002310156,0.0004734267,0.00001913949,0.000007959091,0.04678292,0.0004527587,0.00000522597,0.000152191,0.0002628971,0.949468],"study_design_scores_gemma":[0.0004764136,0.00008133294,0.007287388,0.00006856641,0.000003420825,0.00003228005,0.0009641038,0.9906775,0.00002043617,0.00003437109,0.0002474301,0.0001067409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9887959,0.0001888239,0.009414296,0.0008883022,0.0001505163,0.0001826014,0.00001427995,0.0001654327,0.0001998556],"genre_scores_gemma":[0.9455582,0.00002290548,0.05359006,0.0005834282,0.00001898552,0.00005006597,0.0001528532,0.000004998745,0.00001847471],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9902248,"threshold_uncertainty_score":0.393995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02235879909556478,"score_gpt":0.3216896959560136,"score_spread":0.2993308968604488,"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."}}