{"id":"W4404518274","doi":"10.2196/63020","title":"Autonomous International Classification of Diseases Coding Using Pretrained Language Models and Advanced Prompt Learning Techniques: Evaluation of an Automated Analysis System Using Medical Text","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Computer science; Coding (social sciences); Natural language processing; Artificial intelligence; World Wide Web","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":[0.00245262,0.0001403482,0.0003320689,0.0005977561,0.00008038474,0.0000968913,0.0005089045,0.0001978805,0.00002739339],"category_scores_gemma":[0.0007105934,0.0001235907,0.00007170693,0.0009165979,0.0001072684,0.001040841,0.0001899374,0.0003673563,4.754825e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003070988,"about_ca_system_score_gemma":0.0008080899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005856304,"about_ca_topic_score_gemma":0.000005289605,"domain_scores_codex":[0.996051,0.0003257992,0.001020703,0.0002033452,0.002218832,0.0001802844],"domain_scores_gemma":[0.9984331,0.0002133522,0.0004597532,0.0002922437,0.0003707385,0.0002307852],"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":[0.00003861446,0.0002309173,0.003929509,0.007960976,0.0007309978,0.00003590549,0.06193798,0.1906903,0.001626096,0.02437014,0.00001219774,0.7084363],"study_design_scores_gemma":[0.0002023228,0.00005685339,0.000990738,0.001116085,0.0001416892,0.00004012503,0.001947902,0.9952282,0.0001127992,0.00004794926,0.000005654049,0.0001096725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5555406,0.0001074886,0.4430566,0.00007717847,0.0001010466,0.0003489878,0.000008339947,0.0005995887,0.0001601922],"genre_scores_gemma":[0.9445937,0.000007205126,0.0552295,0.00002034681,0.00004104453,0.00003018875,0.00006535611,0.00001036288,0.000002320343],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8045379,"threshold_uncertainty_score":0.5039881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04104098665763008,"score_gpt":0.4120332805821453,"score_spread":0.3709922939245153,"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."}}