ABSTRACT
PURPOSE: This study explores the potential of the Chat-Generative Pre-Trained Transformer (Chat-GPT), a Large Language Model (LLM), in assisting healthcare professionals in the diagnosis of obstructive sleep apnea (OSA). It aims to assess the agreement between Chat-GPT's responses and those of expert otolaryngologists, shedding light on the role of AI-generated content in medical decision-making. METHODS: A prospective, cross-sectional study was conducted, involving 350 otolaryngologists from 25 countries who responded to a specialized OSA survey. Chat-GPT was tasked with providing answers to the same survey questions. Responses were assessed by both super-experts and statistically analyzed for agreement. RESULTS: The study revealed that Chat-GPT and expert responses shared a common answer in over 75% of cases for individual questions. However, the overall consensus was achieved in only four questions. Super-expert assessments showed a moderate agreement level, with Chat-GPT scoring slightly lower than experts. Statistically, Chat-GPT's responses differed significantly from experts' opinions (p = 0.0009). Sub-analysis revealed areas of improvement for Chat-GPT, particularly in questions where super-experts rated its responses lower than expert consensus. CONCLUSIONS: Chat-GPT demonstrates potential as a valuable resource for OSA diagnosis, especially where access to specialists is limited. The study emphasizes the importance of AI-human collaboration, with Chat-GPT serving as a complementary tool rather than a replacement for medical professionals. This research contributes to the discourse in otolaryngology and encourages further exploration of AI-driven healthcare applications. While Chat-GPT exhibits a commendable level of consensus with expert responses, ongoing refinements in AI-based healthcare tools hold significant promise for the future of medicine, addressing the underdiagnosis and undertreatment of OSA and improving patient outcomes.
Subject(s)
Clinical Decision-Making , Sleep Apnea, Obstructive , Humans , Cross-Sectional Studies , Prospective Studies , Alanine Transaminase , Sleep Apnea, Obstructive/diagnosis , Sleep Apnea, Obstructive/therapyABSTRACT
(1) Background: This narrative review aims to explore the predictors of success for pharyngeal surgery in the treatment of obstructive sleep apnea (OSA). An extensive literature search was conducted, identifying relevant studies published up to June 2023, utilizing various databases and key search terms related to OSA, surgical interventions, and predictors of success. The review encompasses both retrospective and prospective studies, case series, and cohort studies to provide a broad understanding of the topic; (2) Methods: Review of English scientific literature on phenotypes of OSA related to predictors of success of pharyngeal surgery; (3) Results: Of 75 articles, 21 were included, in these the following were determined to be factors for surgical success: body mass index (BMI) (8 articles), apnea/hypopnea index (AHI) (8 articles), cephalometry (8 articles), palatine tonsil size (7 articles), Modified Mallampati score (2 articles), genioglossus electromyography (2 articles), Friedman score or upper airway anatomy (3 articles), nasopharyngolaryngoscopy (2 articles), drug-induced sleep endoscopy (DISE) (1 article), oral cavity anatomy (1 article) and oxygen desaturation index (ODI) (1 article); (4) Conclusions: The lack of standardized protocols for the indication of pharyngeal surgery is a reality, however identifying known predictors of surgical success may facilitate homogenizing indications.