{"id":"W4412823839","doi":"10.1136/bmj-2024-083305","title":"Reporting guidelines for chatbot health advice studies: explanation and elaboration for the Chatbot Assessment Reporting Tool (CHART)","year":2025,"lang":"en","type":"article","venue":"BMJ","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"McMaster University","keywords":"Chatbot; Advice (programming); Computer science; Elaboration; Chart; World Wide Web; Data science; Information retrieval; Medicine","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":["metaresearch"],"category_scores_codex":[0.2874217,0.003107856,0.004065577,0.02154452,0.003427792,0.007550196,0.006592672,0.008985004,0.0334603],"category_scores_gemma":[0.5617864,0.003500919,0.008065565,0.0122625,0.003838866,0.00746011,0.01083592,0.008218854,0.02367995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008350312,"about_ca_system_score_gemma":0.03071855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008043073,"about_ca_topic_score_gemma":0.01212545,"domain_scores_codex":[0.6081072,0.2101627,0.1444575,0.004057203,0.02871822,0.004497123],"domain_scores_gemma":[0.2949847,0.3527396,0.08650613,0.03507707,0.2255737,0.005118853],"domain_codex":null,"domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007087129,0.0004468839,0.003194666,0.03656387,0.0002454375,0.0005497159,0.00860528,0.002016519,0.001750785,0.01181358,0.7459205,0.188184],"study_design_scores_gemma":[0.001456112,0.0006318052,0.007939201,0.07520263,0.0003269214,0.0008507603,0.005859803,0.003676059,0.003275483,0.01626754,0.8839471,0.0005666788],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"protocol","genre_gemma":"methods","genre_scores_codex":[0.005590608,0.007515437,0.3763176,0.0908738,0.01073453,0.4111279,0.05796274,0.01503406,0.02484341],"genre_scores_gemma":[0.006162252,0.00383377,0.5319555,0.01439659,0.001140548,0.4219451,0.01289535,0.001425403,0.006245427],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7125783,"threshold_uncertainty_score":0.8787359,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6018087408408437,"score_gpt":0.648344324389144,"score_spread":0.04653558354830034,"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."}}