ASSESSING THE ACCURACY AND CREDIBILITY OF CHATGPT: A COMPARATIVE STUDY ON NUTRITIONAL MANAGEMENT OF HYPERTENSION WITH EVIDENCE-BASED LITERATURE

Loading...
Thumbnail Image
Date
2023
Journal Title
Journal ISSN
Volume Title
Publisher
UMT Lahore
Abstract
In the realm of healthcare, the arrival of Artificial Intelligence (AI) has introduced a paradigm shift, redefining the ways medical information is generated. A notable AI application in this domain is ChatGPT, an advanced language model that offers information and assistance on a wide array of topics, including nutritional advice. As AI becomes increasingly linked with healthcare, there emerges a critical need to evaluate the accuracy and reliability of AI-generated data, particularly in contexts as complex as managing hypertension. This study conducts a thematic analysis to evaluate the alignment between ChatGPT-generated data and evidence-based literature. By investigating 15 questions about nutritional approaches for the management of hypertension, this study aims to reveal the similarities and differences between ChatGPT generated data and evidence-based data such as PEN knowledge pathways, PubMed, and Google Scholar.
Description
Keywords
Citation
Collections