Evaluation of the Applicability of ChatGPT in Patient Education on Obstructive Sleep Apnea

Abstract

ChatGPT (Chat-Generative Pre-trained Transformer) is an accessible and innovative tool for obtaining healthcare information. This study evaluates the quality and reliability of information provided by ChatGPT 4.0® regarding Obstructive Sleep Apnea (OSA), comparing it with responses from sleep medicine specialists. Thirty frequently asked questions about OSA were posed to ChatGPT 4.0® and two expert physicians. Responses from both sources (V1: AI and V2: Medical Experts) were blindly evaluated by a panel of six specialists using a five-point Likert scale across precision, relevance, and depth dimensions. The AI-generated responses (V1) achieved a slightly higher overall score compared to those from medical experts (V2), although the difference was not statistically significant (p > 0.08). These results suggest that both sources offer comparable quality and content. Additionally, ChatGPT’s responses were clear and easily understandable, providing an accessible explanation of OSA pathology.