A latest study by Cedars-Sinai investigators describes how ChatGPT, a synthetic intelligence (AI) chatbot, may help improve health outcomes for patients with cirrhosis and liver cancer by providing easy-to-understand details about basic knowledge, lifestyle and coverings for these conditions. 

A latest Cedars-Sinai study found ChatGPT—while it has limitations—may also help empower patients and improve health literacy for various populations. Image Credit: Getty.

The findings, published within the peer-reviewed journal Clinical and Molecular Hepatology, highlights the AI system’s potential to play a job in clinical practice.

Patients with cirrhosis and/or liver cancer and their caregivers often have unmet needs and insufficient knowledge about managing and stopping complications of their disease. We found ChatGPT—while it has limitations—may also help empower patients and improve health literacy for various populations.”

Brennan Spiegel, MD, MSHS, Director of Health Services Research, Cedars-Sinai and Co-corresponding Writer of the Study.

Patients diagnosed with liver cancer and cirrhosis, an end-stage liver disease that can also be a serious risk factor for probably the most common type of liver cancer, often require extensive treatment that will be complex and difficult to administer.

The complexity of the care required for this patient population makes patient empowerment with knowledge about their disease crucial for optimal outcomes.While there are currently online resources for patients and caregivers, the literature available is commonly lengthy and difficult for a lot of to know, highlighting the limited options for this group.”

Alexander Kuo, MD, Medical Director of Liver Transplantation Medicine, Cedars-Sinai and Co-corresponding Writer of the Study.

Personalized education AI models could help increase patient knowledge and education, noted Kuo.

Certainly one of those is ChatGPT, which stands for generative pre-trained transformer. It has quickly change into popular for its human-like text in chatbot conversations where users can input any prompt and it can generate a response based on the data stored in its database.

It has already shown some potential for medical professionals by writing basic medical reports and accurately answering medical student examination questions. 

ChatGPT has shown to have the opportunity to offer skilled, yet highly comprehensible responses. Nevertheless, that is one in all the primary studies to look at the power of ChatGPT to reply clinically oriented, disease-specific questions accurately and compare its performance to physicians and trainees.”

Yee Hui Yeo, MD, First Writer of the Study and A Clinical Fellow within the Karsh Division of Gastroenterology and Hepatology, Cedars-Sinai.

To confirm the accuracy of the AI model in its knowledge about each cirrhosis and liver cancer, investigators presented ChatGPT with 164 regularly asked questions in five categories. The ChatGPT answers were then graded independently by two liver transplant specialists. 

Each query was posed twice to ChatGPT and was categorized as either basic knowledge, diagnosis, treatment, lifestyle or preventive medicine. 

Study results include:

• ChatGPT answered about 77% of the questions accurately, providing high levels of accuracy in 91 questions from quite a lot of categories.  
• The specialists grading the responses said 75% of the responses for basic knowledge, treatment and lifestyle were comprehensive or correct, but inadequate.
• The proportion of responses that were “mixed with correct and incorrect data” was 22% for basic knowledge, 33% for diagnosis, 25% for treatment, 18% for lifestyle and 50% for preventive medicine. 

The AI model also provided practical and useful advice to patients and caregivers regarding the subsequent steps adjusting to a latest diagnosis. 

Still, the study left little doubt that advice from a physician was superior. 

“While the model was in a position to reveal strong capability in the essential knowledge, lifestyle and treatment domains, it suffered on the power to offer tailored recommendations in response to the region where the inquirer lived,” said Yeo. “That is most certainly on account of the numerous recommendations in liver cancer surveillance interval and indications reported by different skilled societies. But we’re hopeful that it can be more accurate in addressing the questions in response to the inquirers’ location.”

“More research continues to be needed to higher examine the tool in patient education, but we consider ChatGPT to be a really useful adjunctive tool for physicians—not a substitute—but adjunctive tool that gives access to reliable and accurate health information that is simple for a lot of to know,” Spiegel said. “We hope that this may also help physicians to empower patients and improve health literacy for patients facing difficult conditions equivalent to cirrhosis and liver cancer.”

Other Cedars-Sinai authors are Jamil Samaan, Hirsh Trivedi, Aarshi Vipani, Walid Ayoub, Ju Dong Yang and Omer Liran.

Source:

Journal reference:

Yeo, Y. H., et al. (2023). Assessing the performance of ChatGPT in answering questions regarding cirrhosis and hepatocellular carcinoma. Clinical and Molecular Hepatology. doi.org/10.3350/cmh.2023.0089.