Assessing the performance of ChatGPT in answering questions regarding cirrhosis and hepatocellular carcinoma
- PMID: 36946005
- PMCID: PMC10366809
- DOI: 10.3350/cmh.2023.0089
Assessing the performance of ChatGPT in answering questions regarding cirrhosis and hepatocellular carcinoma
Abstract
Background/aims: Patients with cirrhosis and hepatocellular carcinoma (HCC) require extensive and personalized care to improve outcomes. ChatGPT (Generative Pre-trained Transformer), a large language model, holds the potential to provide professional yet patient-friendly support. We aimed to examine the accuracy and reproducibility of ChatGPT in answering questions regarding knowledge, management, and emotional support for cirrhosis and HCC.
Methods: ChatGPT's responses to 164 questions were independently graded by two transplant hepatologists and resolved by a third reviewer. The performance of ChatGPT was also assessed using two published questionnaires and 26 questions formulated from the quality measures of cirrhosis management. Finally, its emotional support capacity was tested.
Results: We showed that ChatGPT regurgitated extensive knowledge of cirrhosis (79.1% correct) and HCC (74.0% correct), but only small proportions (47.3% in cirrhosis, 41.1% in HCC) were labeled as comprehensive. The performance was better in basic knowledge, lifestyle, and treatment than in the domains of diagnosis and preventive medicine. For the quality measures, the model answered 76.9% of questions correctly but failed to specify decision-making cut-offs and treatment durations. ChatGPT lacked knowledge of regional guidelines variations, such as HCC screening criteria. However, it provided practical and multifaceted advice to patients and caregivers regarding the next steps and adjusting to a new diagnosis.
Conclusion: We analyzed the areas of robustness and limitations of ChatGPT's responses on the management of cirrhosis and HCC and relevant emotional support. ChatGPT may have a role as an adjunct informational tool for patients and physicians to improve outcomes.
Keywords: Artificial intelligence; Chronic disease management; Health communication; Patient education as topic; Telemedicine.
Conflict of interest statement
The authors have no conflictsto disclose.
Figures
Comment in
-
Letter 1 regarding "Assessing the performance of ChatGPT in answering questions regarding cirrhosis and hepatocellular carcinoma".Clin Mol Hepatol. 2023 Jul;29(3):813-814. doi: 10.3350/cmh.2023.0120. Epub 2023 May 19. Clin Mol Hepatol. 2023. PMID: 37211355 Free PMC article. No abstract available.
-
Letter 2 regarding "Assessing the performance of ChatGPT in answering questions regarding cirrhosis and hepatocellular carcinoma".Clin Mol Hepatol. 2023 Jul;29(3):815-816. doi: 10.3350/cmh.2023.0170. Epub 2023 May 24. Clin Mol Hepatol. 2023. PMID: 37221834 Free PMC article. No abstract available.
-
Letter 1 regarding "Assessing the performance of ChatGPT in answering questions regarding cirrhosis and hepatocellular carcinoma".Clin Mol Hepatol. 2024 Jan;30(1):111-112. doi: 10.3350/cmh.2023.0394. Epub 2023 Oct 13. Clin Mol Hepatol. 2024. PMID: 37828840 Free PMC article. No abstract available.
-
Letter 2 regarding "Assessing the performance of ChatGPT in answering questions regarding cirrhosis and hepatocellular carcinoma".Clin Mol Hepatol. 2024 Jan;30(1):113-117. doi: 10.3350/cmh.2023.0440. Epub 2023 Nov 10. Clin Mol Hepatol. 2024. PMID: 37946373 Free PMC article. No abstract available.
References
-
- Tsochatzis EA, Bosch J, Burroughs AK. Liver cirrhosis. Lancet. 2014;383:1749–1761. - PubMed
MeSH terms
LinkOut - more resources
Full Text Sources
Medical
