{"id":"W4408612469","doi":"10.2196/73264","title":"Peer Review of “Large Language Models for Pediatric Differential Diagnoses in Rural Health Care: Multicenter Retrospective Cohort Study Comparing GPT-3 With Pediatrician Performance”","year":2025,"lang":"en","type":"article","venue":"JMIRx Med","topic":"Child and Adolescent Health","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Medical diagnosis; Medicine; Retrospective cohort study; Cohort; Pediatrics; Cohort study; Family medicine; Internal medicine; Pathology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02761929,0.0005510781,0.001473918,0.004168076,0.00390164,0.005074271,0.003572603,0.003473864,0.03828358],"category_scores_gemma":[0.3460836,0.0005691883,0.001761937,0.002496658,0.002966972,0.003198996,0.0033459,0.00194187,0.01365632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002272895,"about_ca_system_score_gemma":0.009514426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005191722,"about_ca_topic_score_gemma":0.006296256,"domain_scores_codex":[0.9636706,0.01305742,0.006451312,0.00251792,0.01261549,0.00168725],"domain_scores_gemma":[0.5292177,0.06821585,0.03399019,0.02277706,0.3323311,0.01346812],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005399096,0.0001658015,0.07973726,0.002870203,0.000396788,0.001469233,0.001673493,0.00009654693,0.000951747,0.001070635,0.8498766,0.06115186],"study_design_scores_gemma":[0.000718835,0.0004531809,0.2282725,0.009450203,0.0006462563,0.003847693,0.009772115,0.002773852,0.003449252,0.003071151,0.7373142,0.0002307243],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.2831502,0.02301861,0.01301206,0.3462652,0.1970136,0.008150185,0.02864502,0.002348171,0.09839708],"genre_scores_gemma":[0.7851931,0.01079267,0.01552222,0.04705527,0.04041115,0.003366218,0.0189963,0.00200327,0.07665982],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.9723807,"threshold_uncertainty_score":0.1460665,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02316779950438205,"score_gpt":0.4009411151111602,"score_spread":0.3777733156067782,"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."}}