{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002567071,0.0003373832,0.002353002,0.0001132626,0.0003549278,0.00009724624,0.0004563299,0.0003332713,0.00004876292],"category_scores_gemma":[0.0004959939,0.0002647059,0.00032458,0.0005432537,0.00002707156,0.0001707075,0.0003139997,0.0004626491,0.00005885645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004107077,"about_ca_system_score_gemma":0.002534739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005478357,"about_ca_topic_score_gemma":0.0005396981,"domain_scores_codex":[0.997177,0.0002742937,0.001161119,0.0005398453,0.0001669633,0.000680749],"domain_scores_gemma":[0.9971426,0.001216737,0.0005413911,0.0006224624,0.0002840435,0.0001927323],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003956453,0.00005816863,0.000002908559,0.04049819,0.0002011282,0.000002811911,0.001752756,0.00001391737,5.849268e-10,0.001728384,0.2066724,0.7490298],"study_design_scores_gemma":[0.00007226056,0.0001710173,5.756296e-7,0.07152274,0.0004147459,0.000007865076,0.002631897,0.0003380882,1.015716e-7,0.001607372,0.9230492,0.0001841643],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[9.803508e-7,0.9823821,0.0008933438,0.005190433,0.001478002,0.006946027,0.00009582285,0.0000728314,0.002940446],"genre_scores_gemma":[0.000007819865,0.9718129,0.002191446,0.005691422,0.003469283,0.001935723,0.0008658973,0.00005267818,0.01397283],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7488456,"threshold_uncertainty_score":0.9999805,"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."}}