{"id":"W4411230079","doi":"10.2196/70047","title":"Evaluating Large Language Models for Preoperative Patient Education in Superior Capsular Reconstruction: Comparative Study of Claude, GPT, and Gemini","year":2025,"lang":"en","type":"article","venue":"JMIR Perioperative Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychology; Medicine; Medical physics","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":[0.01911356,0.0007078032,0.0006846717,0.001517485,0.0004187182,0.001828938,0.0006504947,0.0006638637,0.001820854],"category_scores_gemma":[0.1115354,0.0002665114,0.001003457,0.0008251974,0.0006815747,0.002203714,0.00154749,0.00102606,0.000443157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001502988,"about_ca_system_score_gemma":0.001685754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002533547,"about_ca_topic_score_gemma":0.00284245,"domain_scores_codex":[0.9859121,0.01068743,0.001080996,0.0008343075,0.001287526,0.0001975461],"domain_scores_gemma":[0.8469923,0.1365793,0.005728156,0.00306488,0.005609892,0.002025489],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"nonrandomized_trial","study_design_scores_codex":[0.0221222,0.009280358,0.2905742,0.004771057,0.001114858,0.0007238201,0.03457557,0.02866703,0.01433802,0.001616365,0.005818541,0.5863981],"study_design_scores_gemma":[0.00413027,0.05281151,0.4614888,0.002174774,0.003548887,0.0026184,0.03622349,0.3770067,0.02917308,0.005015866,0.02492251,0.0008857824],"study_design_candidate":"nonrandomized_trial","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9895023,0.0004315871,0.006786174,0.0003177863,0.00003514074,0.0006417506,0.0003221535,0.0002803398,0.001682792],"genre_scores_gemma":[0.9786017,0.0002776918,0.01900168,0.0001802939,0.00003004975,0.0006138547,0.0007465433,0.00007026427,0.00047798],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01911356,"threshold_uncertainty_score":0.1010835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1629329300717069,"score_gpt":0.5154731456468635,"score_spread":0.3525402155751566,"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."}}