{"id":"W4407135263","doi":"10.1001/jamanetworkopen.2024.57879","title":"Large Language Models for Chatbot Health Advice Studies","year":2025,"lang":"en","type":"review","venue":"JAMA Network Open","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":161,"is_retracted":false,"has_abstract":true,"ca_institutions":"Impact; University of Toronto; McMaster University","funders":"","keywords":"Advice (programming); Chatbot; MEDLINE; Data extraction; Medicine; Health care; Medical education; Computer science; Artificial intelligence","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":[0.3138537,0.003174869,0.009600172,0.02250579,0.001413664,0.009849242,0.00720905,0.003948147,0.01725075],"category_scores_gemma":[0.6539839,0.003286453,0.01759307,0.01434281,0.003085751,0.01241591,0.005982868,0.004470296,0.002236255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00839843,"about_ca_system_score_gemma":0.01530274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005048663,"about_ca_topic_score_gemma":0.01003428,"domain_scores_codex":[0.6034719,0.2819312,0.07712993,0.01014509,0.0262778,0.001044058],"domain_scores_gemma":[0.1621025,0.7629675,0.04325195,0.01730386,0.01363917,0.0007349466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001701924,0.0001746981,0.008035097,0.7511624,0.04593163,0.0005536922,0.003167195,0.00597478,0.0004699418,0.01393538,0.01453746,0.1543558],"study_design_scores_gemma":[0.004019901,0.001627389,0.01054202,0.686689,0.0987097,0.0007382432,0.002648752,0.0183969,0.001109173,0.07241526,0.102467,0.0006366828],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.01398409,0.6915517,0.188062,0.02420668,0.002775276,0.04905549,0.01786713,0.001807838,0.0106899],"genre_scores_gemma":[0.2946138,0.1552201,0.3686828,0.0111085,0.001764818,0.1566224,0.009819799,0.0004822005,0.001685475],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.3138537,"threshold_uncertainty_score":0.8461405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.388644817671735,"score_gpt":0.5757842107282994,"score_spread":0.1871393930565644,"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."}}