Assessing the performance of ChatGPT in answering questions regarding cirrhosis and hepatocellular carcinoma

Abstract

Background: Patients with cirrhosis and hepatocellular carcinoma (HCC) require extensive care. Personalized education can improve their outcomes. ChatGPT (Generative Pre-trained Transformer), a natural language processing model, has shown potential to provide professional yet patient-freindly responses. Aim: To examine the accuracy and reproducibility of ChatGPT in responding to questions regarding knowledge, management, and emotional support for cirrhosis and HCC. Method: ChatGPT's responses to 164 frequently asked questions were independently graded by two transplant hepatologists, with a third reviewer resolving any discrepancies. We also compared the performance of ChatGPT on two previously validated and published questionnaires to the physicians or trainees who were tested in the included publications. Furthermore, we formulated the 26 quality measures of cirrhosis management into questions and tested ChatGPT's knowledge in cirrhosis care. Finally, the capacity to provide emotional support to patients or caregivers was tested. Results: ChatGPT regurgitated extensive knowledge about both cirrhosis and HCC, but for questions with correct responses, only a small proportion was labelled 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 the cut-off values for making medical decisions and treatment durations. When compared to physicians/trainees, ChatGPT fell short in knowledge of guidelines varying across geographic regions, such as HCC screening criteria. The model also provided practical and multifaceted advice to patients and caregivers regarding the next steps and adjusting to a new diagnosis. Conclusion: In summary, 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.

ChatGPT Utility in Healthcare Education, Research, and Practice: Systematic Review on the Promising Perspectives and Valid Concerns

“…Thus, ChatGPT cannot be used currently as a reliable updated source of literature review [ 83 ]. Nevertheless, ChatGPT can be used as a motivation to organize the literature in a decent format, if supplemented by reliable and up-to-date references [ 28 , 74 ].…”

“…Moreover, ChatGPT showed moderate accuracy in determining the imaging steps needed in breast cancer screening and in the evaluation of breast pain, which can be a promising application in decision making in radiology [ 69 ]. ChatGPT in health care settings also has the prospects of refining personalized medicine and the ability to improve health literacy by providing easily accessible and understandable health information to the general public [ 30 , 32 , 59 , 73 , 74 ]. This utility was demonstrated by ChatGPT responses, highlighting the need to consult health care providers among other reliable sources on specific situations [ 16 , 54 ].…”

“…Other issues accompanying ChatGPT applications in health care include the lack of personal and emotional perspectives needed in health care delivery and research [ 30 , 55 ]. However, ChatGPT emulation of empathetic responses was reported in a preprint in the context of hepatic disease [ 74 ]. Additionally, the issue of devaluing the function of the human brain should not be overlooked; therefore, stressing the indispensable human role in health care practice and research is important to address any psychologic, economic, and social consequences that could accompany the application of LLM tools in health care settings [ 72 ].…”

The Utility of ChatGPT as an Example of Large Language Models in Healthcare Education, Research and Practice: Systematic Review on the Future Perspectives and Potential Limitations

“…Fourth, as it currently stands, the knowledge of ChatGPT is limited to the period prior to 2021 based on the training datasets used in ChatGPT training [6]. Thus, ChatGPT currently cannot be used as a reliable updated source of literature review; nevertheless, it can be used as a motivation to organize the literature in a decent format and if supplemented by reliable and up-to-date references [47,61].…”

“…Moreover, ChatGPT showed moderate accuracy to determine the imaging steps needed in breast cancer screening and evaluation of breast pain which can be a promising application in decision making in radiology [50]. There is also the prospects of personalized medicine and improved health literacy by providing easily accessible and understandable health information for the general public [52,54,59,61,72]. This utility was demonstrated by ChatGPT responses highlighting the need to consult healthcare providers among other reliable sources on specific situations [16,56].…”