{"id":"W4402181615","doi":"10.1016/j.jhsg.2024.07.011","title":"Large Language Models in the Diagnosis of Hand and Peripheral Nerve Injuries: An Evaluation of ChatGPT and the Isabel Differential Diagnosis Generator","year":2024,"lang":"en","type":"article","venue":"Journal of Hand Surgery Global Online","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of Toronto","funders":"","keywords":"Generator (circuit theory); Peripheral nerve; Differential diagnosis; Peripheral; Differential (mechanical device); Medicine; Computer science; Physical medicine and rehabilitation; Medical emergency; Anatomy; Engineering; Pathology; Physics; Internal medicine; Aerospace engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00244403,0.0001073162,0.0004172965,0.0001020493,0.00007535789,0.0000674284,0.00006364682,0.00007641183,0.00005080109],"category_scores_gemma":[0.000466339,0.00005701574,0.0001169295,0.0002185005,0.0002094746,0.0002219599,0.00001827491,0.0001712437,9.535624e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005808307,"about_ca_system_score_gemma":0.0003198102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005654544,"about_ca_topic_score_gemma":0.0006910759,"domain_scores_codex":[0.9981464,0.0003755533,0.0007292525,0.0001161142,0.0004879975,0.0001447081],"domain_scores_gemma":[0.9985786,0.0006480841,0.0002188829,0.0001279118,0.0003494251,0.00007709752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002266881,0.002426088,0.6057365,0.0007730008,0.0003818367,0.00007218637,0.06471854,0.0003279704,0.001063706,0.001286052,0.002187835,0.3187594],"study_design_scores_gemma":[0.005028392,0.00322518,0.4379417,0.007025316,0.004370989,0.0008570199,0.1161297,0.3671918,0.03090891,0.02460861,0.001859345,0.0008529763],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9698035,0.02521797,0.0001365057,0.004085993,0.0004118719,0.0002348018,0.0001007506,0.000002234487,0.000006345353],"genre_scores_gemma":[0.9958035,0.003411521,0.0000393074,0.0002032308,0.0004899421,0.00001908182,0.00002348833,0.000006709515,0.000003272882],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3668638,"threshold_uncertainty_score":0.2325035,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1126998629274872,"score_gpt":0.4197429704993473,"score_spread":0.3070431075718602,"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."}}