ChatGPT as a New Tool to Select a Biological for Chronic Rhino Sinusitis with Polyps, “Caution Advised” or “Distant Reality”?

Researchers

Journal

Modalities

Models

Abstract

ChatGPT is an advanced language model developed by OpenAI, designed for natural language understanding and generation. It employs deep learning technology to comprehend and generate human-like text, making it versatile for various applications. The aim of this study is to assess the alignment between the Rhinology Board’s indications and ChatGPT’s recommendations for treating patients with chronic rhinosinusitis with nasal polyps (CRSwNP) using biologic therapy. An observational cohort study involving 72 patients was conducted to evaluate various parameters of type 2 inflammation and assess the concordance in therapy choices between ChatGPT and the Rhinology Board. The observed results highlight the potential of Chat-GPT in guiding optimal biological therapy selection, with a concordance percentage = 68% and a Kappa coefficient = 0.69 (CI95% [0.50; 0.75]). In particular, the concordance was, respectively, 79.6% for dupilumab, 20% for mepolizumab, and 0% for omalizumab. This research represents a significant advancement in managing CRSwNP, addressing a condition lacking robust biomarkers. It provides valuable insights into the potential of AI, specifically ChatGPT, to assist otolaryngologists in determining the optimal biological therapy for personalized patient care. Our results demonstrate the need to implement the use of this tool to effectively aid clinicians.