{"id":"W4415788501","doi":"10.1186/s12891-025-09227-1","title":"Evaluating the performance of five large language models in answering Delphi consensus questions relating to patellar instability and medial patellofemoral ligament reconstruction","year":2025,"lang":"en","type":"article","venue":"BMC Musculoskeletal Disorders","topic":"Total Knee Arthroplasty Outcomes","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba; University of Calgary; University of Ottawa; McMaster University","funders":"Göteborgs Universitet","keywords":"Medial patellofemoral ligament; Sports medicine; Delphi method; Orthopedic surgery; Rehabilitation; Patellofemoral pain syndrome; Multidisciplinary approach; Delphi","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":[0.0008075024,0.0001691992,0.0003067715,0.0001762,0.0001302561,0.00001155368,0.00006378416,0.00008092549,0.00001517691],"category_scores_gemma":[0.0008493233,0.0001369596,0.0001095784,0.0003914857,0.0001733294,0.0001044047,0.0001209202,0.000246876,0.000002557978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008957704,"about_ca_system_score_gemma":0.0001431459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005004597,"about_ca_topic_score_gemma":0.003140025,"domain_scores_codex":[0.9984881,0.0001696953,0.0005129986,0.0003095959,0.0002380701,0.0002815443],"domain_scores_gemma":[0.9991571,0.0003228473,0.000103566,0.0002809551,0.00006675596,0.00006877275],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003838032,0.0001707339,0.8392656,0.001069349,0.00005397112,0.000001930958,0.008321646,0.02131209,0.005375708,0.0002647228,0.000004701034,0.1237757],"study_design_scores_gemma":[0.003279357,0.0005917528,0.7190116,0.001251295,0.0001038639,0.00001208285,0.01504116,0.2597355,0.0003595925,0.0003602677,0.00001119515,0.0002423038],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966481,0.0005929364,0.0003197624,0.0004975987,0.0001988694,0.0009649876,0.00000916532,0.00004401305,0.000724591],"genre_scores_gemma":[0.996056,0.0001053181,0.003616152,0.00005979396,0.0000170581,0.00004777328,0.000005082118,0.00001374378,0.00007904335],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2384234,"threshold_uncertainty_score":0.5585051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02078384556795142,"score_gpt":0.3217574911141608,"score_spread":0.3009736455462094,"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."}}