Accuracy, Reliability, and Comprehensibility of ChatGPT-Generated Medical Responses for Patients With Nonalcoholic Fatty Liver Disease

Abstract

Nonalcoholic fatty liver disease (NAFLD) is an increasing global health problem and is expected to become the leading indication for liver transplantation.¹ There are no approved NAFLD-specific pharmacotherapies, and lifestyle modification is the primary recommended therapy.² Innovative approaches to facilitate the implementation and long-term maintenance of lifestyle changes are needed to address the challenging and complex nature of the management of NAFLD, which recently was renamed as metabolic dysfunction-associated steatotic liver disease, to overcome the limitations and stigma of the previous name.^3,4 Artificial intelligence (AI)-powered chatbots have been shown to provide effective personalized support and education to patients, with the potential to complement health care resources. The OpenAI Foundation's AI chatbot, Chat Generative Pretrained Transformer (ChatGPT), has attracted worldwide attention for its remarkable performance in question-answer tasks.^5-7 This study evaluated the accuracy, completeness, and comprehensiveness of chatGPT's responses to NAFLD-related questions, with the aim of assessing its performance in addressing patients' queries about the disease and lifestyle behaviors.

Ähnliche Arbeiten