{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00296998,0.0012981,0.0006225707,0.0008326739,0.0003512751,0.0008009288,0.001465342,0.001140433,0.002337021],"category_scores_gemma":[0.0107033,0.0002894632,0.0006677993,0.0005350938,0.0003196394,0.001721651,0.00122485,0.001741764,0.002164633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009064923,"about_ca_system_score_gemma":0.001850682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005846623,"about_ca_topic_score_gemma":0.005574728,"domain_scores_codex":[0.9985623,0.0004465333,0.0001388012,0.0005334046,0.0002051352,0.0001138623],"domain_scores_gemma":[0.9949963,0.002800371,0.0002669806,0.0005059792,0.001171167,0.0002591626],"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":[0.002658089,0.002440569,0.0135303,0.0005180881,0.000221139,0.0006437628,0.0005053087,0.06029816,0.02592797,0.0009507272,0.02753007,0.8647758],"study_design_scores_gemma":[0.0002560587,0.0007786399,0.004362541,0.00003148063,0.00007814801,0.0001959976,0.0001808092,0.966815,0.02338942,0.001450969,0.002406212,0.00005475997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6340849,0.0009795544,0.298937,0.001321178,0.0009538359,0.001164125,0.0052958,0.05451449,0.002749029],"genre_scores_gemma":[0.7430776,0.0003094896,0.240564,0.000629584,0.0001335048,0.0006291629,0.01095169,0.0003796595,0.003325236],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005846623,"threshold_uncertainty_score":0.01570696,"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."}}