{"id":"W4417524748","doi":"10.5435/jaaosglobal-d-25-00341","title":"Evaluation of ChatGPT-4o as a Patient Information Tool for Common Orthopaedic Surgeries: Accuracy, Completeness, and Clinical Utility","year":2025,"lang":"en","type":"article","venue":"JAAOS Global Research and Reviews","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Object Research Systems (Canada)","funders":"","keywords":"Information system; Orthopedic surgery; MEDLINE; Patient care","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01306619,0.00009116725,0.0004266658,0.00009285233,0.0001859037,0.0000353421,0.00005730913,0.0001185369,0.0000440401],"category_scores_gemma":[0.01940804,0.00006688807,0.00009356072,0.0004238348,0.0002747521,0.0002047577,0.00006747353,0.0001847603,0.00001266269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001316341,"about_ca_system_score_gemma":0.001066279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009165416,"about_ca_topic_score_gemma":0.0002854613,"domain_scores_codex":[0.9971491,0.0007000191,0.001137078,0.0001938905,0.0005760484,0.0002438409],"domain_scores_gemma":[0.9960566,0.001084787,0.0002089445,0.0002859029,0.002213295,0.0001504292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003481091,0.0001179181,0.1154923,0.000987291,0.0000190949,1.509037e-7,0.000173394,9.331519e-8,0.000003397005,0.0008133702,0.004376521,0.8776683],"study_design_scores_gemma":[0.0007279619,0.002805532,0.3087234,0.002565605,0.000307057,0.0000154465,0.002608327,0.007628515,0.0003485802,0.03951936,0.6345556,0.0001945392],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9757285,0.01544662,0.0002361544,0.002809223,0.0002866552,0.004141849,0.00003303681,0.00000908437,0.001308869],"genre_scores_gemma":[0.9729995,0.02586267,0.0001778107,0.0004923643,0.00006754467,0.0002831549,0.0000953856,0.000002324924,0.00001924467],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8774738,"threshold_uncertainty_score":0.9888519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.528192822504121,"score_gpt":0.6212552639638854,"score_spread":0.09306244145976439,"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."}}