Evaluation of four chatbots in autoimmune liver disease: A comparative analysis

Jimmy Daza 1Lucas Soares Bezerra 1Laura Santamaría 2Roberto Rueda-Esteban 2Heike Bantel 3Marcos Girala 4Matthias Ebert 5Florian Van Bömmel 6Andreas Geier 7Andres Gomez Aldana 8Kevin Yau 9Mario Alvares-da-Silva 10Markus Peck-Radosavljevic 11Ezequiel Ridruejo 12Arndt Weinmann 13Andreas Teufel 14

Affiliations

  1. Department of Medicine II, Division of Hepatology, Division of Clinical Bioinformatics, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany.
  2. Universidad de Los Andes School of Medicine, Bogotá, Colombia.
  3. Department of Gastroenterology, Hepatology, Infectious Diseases and Endocrinology, Hannover Medical School, Hannover, Germany.
  4. Department of Gastroenterology, Hospital de Clínicas, Universidad Nacional de Asunción, Asunción, Paraguay.
  5. Department of Medicine II, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany.
  6. Department of Medicine II, Clinic of Gastroenterology, Hepatology, Infectious Diseases and Pneumology, Leipzig University Medical Center, Leipzig, Germany.
  7. Department of Internal Medicine II, Division of Hepatology, University Hospital Würzburg, Würzburg, Germany.
  8. Texas Liver Institute, University of Texas Health Science Center, San Antonio, United States.
  9. Division of Nephrology, Department of Medicine, University of Toronto, Toronto, Ontario, Canada.
  10. Department of Gastroenterology, Hospital de Clinicas de Porto Alegre, Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil.
  11. Internal Medicine and Gastroenterology (IMuG), Clinic Klagenfurt am Woerthersee, Klagenfurt, Austria.
  12. Department of Medicine, Section of Hepatology, Centro de Educación Médica e Investigaciones Clínicas Norberto Quirno „CEMIC“, Buenos Aires, Argentina.
  13. Department of Internal Medicine I, University Medical Center of the Johannes Gutenberg-University Mainz, Mainz, Germany.
  14. Department of Medicine II, Division of Hepatology, Division of Clinical Bioinformatics, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany. Electronic address: andreas.teufel@medma.uni-heidelberg.de.


Autoimmune liver diseases (AILDs) are rare and challenging to evaluate, prompting the exploration of chatbots as clinical decision support tools. This study involved ten liver specialists who systematically assessed four chatbots—ChatGPT 3.5, Claude, Microsoft Copilot, and Google Bard—using a 56-question survey focused on AILDs. Claude received the highest rating, followed by ChatGPT, with Microsoft Copilot and Google Bard trailing. Common chatbot deficiencies included general information over specific advice, limited dosing options, inaccuracies for pregnant patients, outdated data, over-reliance on imaging, and inadequate discussion of off-label treatments. The study highlights the potential of chatbots in AILD management but emphasizes the need for improvements in providing specific, accurate, and up-to-date information to enhance their effectiveness as clinical decision-support tools.

PMID: 39147133
DOI: 10.1016/j.aohep.2024.101537

Schreibe einen Kommentar

Deine E-Mail-Adresse wird nicht veröffentlicht. Erforderliche Felder sind mit * markiert