{"id":"W4412822184","doi":"10.1093/bjs/znaf142","title":"Reporting guideline for chatbot health advice studies: the Chatbot Assessment Reporting Tool (CHART) statement","year":2025,"lang":"en","type":"article","venue":"British journal of surgery","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Hamilton General Hospital","funders":"Medizinische Fakultät der Albert-Ludwigs-Universität Freiburg; Office of Science; Centers for Disease Control and Prevention; Univerza v Mariboru; Astellas Pharma; Sichuan University; Universidad Complutense de Madrid; Yale University; University of Toronto; British Psychological Society; University of New South Wales; University of Oxford; Department of Health and Social Care; National Institute for Health and Care Research; York University; Albert-Ludwigs-Universität Freiburg; National University of Singapore; Postgraduate Institute of Medical Education and Research, Chandigarh; University of North Carolina at Chapel Hill; Brigham and Women's Hospital; Cleveland Clinic; Case Western Reserve University; West China Hospital, Sichuan University; London School of Economics and Political Science; McMaster University; Ottawa Hospital Research Institute; Duke-NUS Medical School; Università degli Studi di Napoli Federico II; George Institute for Global Health; University of Southern California; Australian Government","keywords":"Medicine; Chatbot; Guideline; Chart; Statement (logic); Advice (programming); Family medicine; World Wide Web; Pathology; Computer science","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03012829,0.0001425188,0.0009464212,0.0001901293,0.0005340439,0.00008358169,0.00008881435,0.0000601393,0.00003583618],"category_scores_gemma":[0.02870599,0.0001205702,0.0003779858,0.0003412325,0.0000604281,0.0001910781,0.00003902374,0.0004033897,0.000001136275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005781043,"about_ca_system_score_gemma":0.003601628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009722301,"about_ca_topic_score_gemma":0.0001086614,"domain_scores_codex":[0.9857868,0.0001449873,0.01289164,0.0002432338,0.0004892815,0.0004440409],"domain_scores_gemma":[0.9790824,0.001421183,0.01647057,0.0002587674,0.002620805,0.0001462756],"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":[0.00008623172,0.0001817054,0.02906744,0.0007249446,0.0002539317,0.0002927506,0.0006315205,0.00004980585,0.0000742163,0.00004265329,0.4275528,0.541042],"study_design_scores_gemma":[0.0008579279,0.001349247,0.1206971,0.0398729,0.0008318026,0.01759108,0.1675052,0.003570486,0.005101387,0.007031573,0.6346386,0.0009527334],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7276307,0.03874964,0.02314942,0.2002677,0.007497634,0.002004736,0.00001611104,0.00008823065,0.0005958363],"genre_scores_gemma":[0.946515,0.01900229,0.01371005,0.01636373,0.002869441,0.0001415186,0.00005123797,0.00004613654,0.001300552],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5400892,"threshold_uncertainty_score":0.998687,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4142862146136758,"score_gpt":0.5588817495515985,"score_spread":0.1445955349379228,"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."}}