{"id":"W4410817084","doi":"10.1001/jamanetworkopen.2025.12621","title":"Evaluating the Quality of Guidelines Using the AGREE II Tool by a Large Language Model vs Human Appraisers","year":2025,"lang":"en","type":"article","venue":"JAMA Network Open","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Quality (philosophy); Computer science; Medical physics; Medicine","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":[0.0188176,0.0001632344,0.0004313861,0.0000250962,0.0006211363,0.000112908,0.0006685078,0.00009907778,0.0001610763],"category_scores_gemma":[0.01097682,0.00009716014,0.0001384311,0.0004267129,0.00008247641,0.0002691441,0.001067602,0.0003935852,0.000002664568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006720738,"about_ca_system_score_gemma":0.000336126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002301546,"about_ca_topic_score_gemma":0.0005269777,"domain_scores_codex":[0.996156,0.0008231112,0.001840633,0.0003191283,0.0005382011,0.0003229338],"domain_scores_gemma":[0.9955516,0.002166016,0.000802542,0.0009103427,0.0005273496,0.00004212722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003176469,0.0005312011,0.02777591,0.0002307983,0.0008018626,0.000004054118,0.003695204,0.0836244,0.0267038,0.00987306,0.772305,0.0712783],"study_design_scores_gemma":[0.006157433,0.0002616686,0.008370448,0.0005337765,0.000678052,0.000003997444,0.005492937,0.9649205,0.0002039662,0.002255562,0.01089866,0.0002229712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9315116,0.0005400235,0.01741396,0.04547034,0.000185304,0.002056486,0.00004550848,0.00002860336,0.002748218],"genre_scores_gemma":[0.9477702,0.00002860471,0.02288232,0.02570463,0.0006154326,0.00007263029,0.0001526083,0.00002654427,0.002747057],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8812962,"threshold_uncertainty_score":0.9973541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5471494929472598,"score_gpt":0.6434007615904526,"score_spread":0.09625126864319278,"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."}}