BMC Medicine (Aug 2025)
Reporting guideline for Chatbot Health Advice studies: the CHART statement
- Bright Huo,
- Gary Collins,
- David Chartash,
- Arun Thirunavukarasu,
- Annette Flanagin,
- Alfonso Iorio,
- Giovanni Cacciamani,
- Xi Chen,
- Nan Liu,
- Piyush Mathur,
- An-Wen Chan,
- Christine Laine,
- Daniela Pacella,
- Michael Berkwits,
- Stavros A. Antoniou,
- Jennifer C. Camaradou,
- Carolyn Canfield,
- Michael Mittelman,
- Timothy Feeney,
- Elizabeth Loder,
- Riaz Agha,
- Ashirbani Saha,
- Julio Mayol,
- Anthony Sunjaya,
- Hugh Harvey,
- Jeremy Y. Ng,
- Tyler McKechnie,
- Yung Lee,
- Nipun Verma,
- Gregor Stiglic,
- Melissa McCradden,
- Karim Ramji,
- Vanessa Boudreau,
- Monica Ortenzi,
- Joerg Meerpohl,
- Per Olav Vandvik,
- Thomas Agoritsas,
- Diana Samuel,
- Helen Frankish,
- Michael Anderson,
- Xiaomei Yao,
- Stacy Loeb,
- Cynthia Lokker,
- Xiaoxuan Liu,
- Eliseo Guallar,
- Gordon Guyatt,
- The CHART Collaborative
Affiliations
- Bright Huo
- Division of General Surgery, Department of Surgery, McMaster University
- Gary Collins
- UK EQUATOR Centre, University of Oxford
- David Chartash
- Department of Biomedical Informatics and Data Science, Yale University School of Medicine
- Arun Thirunavukarasu
- Nuffield Department of Clinical Neurosciences, Medical Sciences Division, University of Oxford
- Annette Flanagin
- JAMA and JAMA Network, American Medical Association
- Alfonso Iorio
- Department of Health Research Methods, Evidence, and Impact; Department of Medicine, McMaster University
- Giovanni Cacciamani
- USC Institute of Urology and Catherine and Joseph Aresty Department of Urology, Keck School of Medicine, University of Southern California
- Xi Chen
- Sports Medicine Center, West China Hospital, Sichuan University
- Nan Liu
- Duke-NUS Medical School, National University of Singapore
- Piyush Mathur
- Cleveland Clinic, Case Western Reserve University
- An-Wen Chan
- Department of Medicine, Women’s College Research Institute, University of Toronto
- Christine Laine
- Annals of Internal Medicine, American College of Physicians
- Daniela Pacella
- Department of Public Health, University of Naples Federico II
- Michael Berkwits
- Director, Office of Science Dissemination, Office of Science, Centers for Disease Control and Prevention
- Stavros A. Antoniou
- Department of General Surgery, Papageorgiou General Hospital
- Jennifer C. Camaradou
- British Psychological Society, University of Plymouth
- Carolyn Canfield
- Innovation Support Unit, Department of Family Practice, University of British Columbia
- Michael Mittelman
- Patient SME, Independent Cybersecurity Professional
- Timothy Feeney
- The BMJ
- Elizabeth Loder
- The BMJ
- Riaz Agha
- International Journal of Surgery
- Ashirbani Saha
- Department of Oncology, McMaster University
- Julio Mayol
- Hospital Clinico San Carlos, Instituto de Investigación Sanitaria San Carlos, Facultad de Medicina Universidad Complutense de Madrid
- Anthony Sunjaya
- The George Institute for Global Health; Tyree Institute of Health Engineering, UNSW Engineering; School of Population Health, UNSW Medicine and Health
- Hugh Harvey
- Hardian Health
- Jeremy Y. Ng
- Centre for Journalology, Ottawa Hospital Research Institute
- Tyler McKechnie
- Division of General Surgery, Department of Surgery, McMaster University
- Yung Lee
- Division of General Surgery, Department of Surgery, McMaster University
- Nipun Verma
- Postgraduate Institute of Medical Education and Research
- Gregor Stiglic
- University of Maribor
- Melissa McCradden
- Australian Institute for Machine Learning (AIML)
- Karim Ramji
- Phelix AI
- Vanessa Boudreau
- Division of General Surgery, Department of Surgery, McMaster University
- Monica Ortenzi
- Università Politecnica delle Marche, Clinica di Chirurgia Generale e d’Urgenza
- Joerg Meerpohl
- Institute for Evidence in Medicine, Medical Center & Faculty of Medicine, University of Freiburg
- Per Olav Vandvik
- Cochrane Germany, Cochrane Germany Foundation
- Thomas Agoritsas
- Department of Health Research Methods, Evidence, and Impact; Department of Medicine, McMaster University
- Diana Samuel
- The Lancet Digital Health
- Helen Frankish
- The Lancet
- Michael Anderson
- NIHR Clinical Lecturer, Health Organisation, Policy, Economics (HOPE), Centre for Primary Care & Health Services Research, The University of Manchester
- Xiaomei Yao
- Department of Oncology, McMaster University
- Stacy Loeb
- New York University Langone Health
- Cynthia Lokker
- Department of Health Research Methods, Evidence, and Impact; Department of Medicine, McMaster University
- Xiaoxuan Liu
- College of Medicine and Health, University of Birmingham
- Eliseo Guallar
- School of Global Public Health, New York University
- Gordon Guyatt
- Department of Health Research Methods, Evidence, and Impact; Department of Medicine, McMaster University
- The CHART Collaborative
- DOI
- https://doi.org/10.1186/s12916-025-04274-w
- Journal volume & issue
-
Vol. 23,
no. 1
pp. 1 – 12
Abstract
Abstract Background The Chatbot Assessment Reporting Tool (CHART) is a reporting guideline developed to provide reporting recommendations for studies evaluating the performance of generative artificial intelligence (AI)-driven chatbots when summarizing clinical evidence and providing health advice, referred to as Chatbot Health Advice (CHA) studies. Methods CHART was developed in several phases after performing a comprehensive systematic review to identify variation in the conduct, reporting, and methodology in CHA studies. Findings from the review were used to develop a draft checklist that was revised through an international, multidisciplinary modified asynchronous Delphi consensus process of 531 stakeholders, three synchronous panel consensus meetings of 48 stakeholders, and subsequent pilot testing of the checklist. Results CHART includes 12 items and 39 subitems to promote transparent and comprehensive reporting of CHA studies. These include Title (subitem 1a), Abstract/Summary (subitem 1b), Background (subitems 2ab), Model Identifiers (subitems 3ab), Model Details (subitems 4abc), Prompt Engineering (subitems 5ab), Query Strategy (subitems 6abcd), Performance Evaluation (subitems 7ab), Sample Size (subitem 8), Data Analysis (subitem 9a), Results (subitems 10abc), Discussion (subitems 11abc), Disclosures (subitem 12a), Funding (subitem 12b), Ethics (subitem 12c), Protocol (subitem 12d), and Data Availability (subitem 12e). Conclusion The CHART checklist and corresponding methodological diagram were designed to support key stakeholders including clinicians, researchers, editors, peer reviewers, and readers in reporting, understanding, and interpreting the findings of CHA studies.
Keywords
