{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003842662,0.001234276,0.0009182535,0.001159446,0.0004822596,0.001265549,0.001744981,0.00153884,0.003280187],"category_scores_gemma":[0.008810434,0.0004235551,0.001120175,0.001082532,0.0004953197,0.001424801,0.001157706,0.002561409,0.001694413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002162474,"about_ca_system_score_gemma":0.001770138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02942063,"about_ca_topic_score_gemma":0.01453196,"domain_scores_codex":[0.9992507,0.0003133405,0.00006220188,0.0001795532,0.0000970403,0.00009705067],"domain_scores_gemma":[0.9950883,0.003412403,0.0002263256,0.0002237864,0.0009544263,0.00009482283],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00064157,0.0005517464,0.007991385,0.000325185,0.0002355939,0.0001660689,0.0001412931,0.6891233,0.001326695,0.002192804,0.006640607,0.2906637],"study_design_scores_gemma":[0.000009143587,0.00004062308,0.0004001011,0.00001179408,0.00001293628,0.00001344788,0.00001264926,0.9982462,0.0003775036,0.000685829,0.0001850212,0.000004703171],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6988618,0.01142176,0.2648677,0.003953572,0.000766556,0.0006926762,0.003627127,0.006007839,0.009800941],"genre_scores_gemma":[0.9208372,0.001775396,0.0655306,0.0003604913,0.0002240244,0.0006060785,0.005704413,0.0001244962,0.004837279],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02942063,"threshold_uncertainty_score":0.0584988,"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."}}