{"id":"W4403673188","doi":"10.5435/jaaos-d-24-00595","title":"Can ChatGPT-4 Diagnose and Treat Like an Orthopaedic Surgeon? Testing Clinical Decision Making and Diagnostic Ability in Soft-Tissue Pathologies of the Foot and Ankle","year":2024,"lang":"en","type":"article","venue":"Journal of the American Academy of Orthopaedic Surgeons","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Object Research Systems (Canada)","funders":"","keywords":"Medicine; Ankle; Soft tissue; Foot and ankle surgery; Foot (prosody); Grading (engineering); Physical therapy; Orthopedic surgery; Surgery","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002225368,0.0003394631,0.0002901315,0.00104781,0.0006186524,0.0009880484,0.0006675772,0.0007174627,0.005073559],"category_scores_gemma":[0.01477901,0.0001978212,0.0003908143,0.0004437554,0.000929552,0.0009246207,0.001031405,0.0006088205,0.001003259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005299971,"about_ca_system_score_gemma":0.0008400556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002288954,"about_ca_topic_score_gemma":0.00381558,"domain_scores_codex":[0.9986135,0.0003913306,0.0001141079,0.0001298808,0.0004164859,0.0003345926],"domain_scores_gemma":[0.9939613,0.001538483,0.002094522,0.0001834637,0.001046323,0.00117585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009609537,0.0001434457,0.9905298,0.00002483717,0.00002048406,0.0004770218,0.0007117965,0.00007106906,0.000393837,0.00003406823,0.000312432,0.007185007],"study_design_scores_gemma":[0.00001954361,0.0007947342,0.9851905,0.00007142212,0.00003894197,0.003359398,0.007698176,0.0009223211,0.0005741538,0.0002778267,0.001031131,0.00002183972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9976047,0.00008124782,0.0001387604,0.0001986594,0.00002273482,0.00002163599,0.00004036079,0.000005095953,0.001886797],"genre_scores_gemma":[0.9992899,0.0000545463,0.0002920574,0.00004999415,0.000007618172,0.00001064842,0.00004334204,0.000001676695,0.0002502138],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005073559,"threshold_uncertainty_score":0.01697272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09992354957893693,"score_gpt":0.4324015850325328,"score_spread":0.3324780354535959,"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."}}