{"id":"W4414167289","doi":"10.1007/s10067-025-07640-4","title":"Comparative evaluation of large language models in delivering guideline-compliant recommendations for topical NSAID use in musculoskeletal pain: a multidimensional analysis","year":2025,"lang":"en","type":"article","venue":"Clinical Rheumatology","topic":"Health Literacy and Information Accessibility","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hospital for Sick Children","funders":"Zhejiang Chinese Medical University","keywords":"Readability; Limiting; Function (biology); Clinical Practice; MEDLINE; Usability; Clinical judgment; Clinical trial","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08728024,0.001267264,0.00221884,0.00309939,0.0007220409,0.004819575,0.001707414,0.001429825,0.003716943],"category_scores_gemma":[0.3463567,0.000700049,0.004871491,0.002170755,0.001467705,0.003199591,0.004103426,0.001933977,0.0007792491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004022148,"about_ca_system_score_gemma":0.004654777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003830109,"about_ca_topic_score_gemma":0.003855856,"domain_scores_codex":[0.9151631,0.06507275,0.00886013,0.003011232,0.00719289,0.0006998743],"domain_scores_gemma":[0.4741229,0.4787441,0.01932469,0.01064499,0.01515838,0.002004965],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.07865085,0.009764776,0.3268682,0.01484479,0.01040413,0.0005626718,0.03727983,0.05921487,0.00499304,0.004829597,0.009747243,0.44284],"study_design_scores_gemma":[0.01708985,0.05343995,0.4613661,0.008461617,0.01745506,0.0008701188,0.02572437,0.353039,0.01230679,0.02032653,0.02826362,0.001657001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9644581,0.001582421,0.02236905,0.000932062,0.0001189292,0.004656787,0.002114616,0.0007296483,0.003038326],"genre_scores_gemma":[0.9322063,0.0007116841,0.05558566,0.0003889063,0.00006151489,0.007559634,0.002691505,0.0001582171,0.0006366719],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9127197,"threshold_uncertainty_score":0.4615875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2507076386285519,"score_gpt":0.5934160365773098,"score_spread":0.3427083979487578,"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."}}