Artificial Intelligence in Rhinology.

Abstract

Objectives: This paper aims to review the application of artificial intelligence (AI) in rhinology.

Methods: A literature search was conducted using the PubMed and Medline databases from 2000 to 2025.

Results: Within AI, machine learning (ML) represents a distinct subset that utilizes historical data to improve decision-making regarding future data. Rhinology uses various machine learning algorithms, with "classification" serving as a representative example of a supervised system where the algorithm predicts the category or class of an item. Deep learning (DL) algorithms assist in diagnosing sinusitis and quantifying sinus volumes from radiographic imaging. Recent research in surgical phase assessment aims to anticipate steps, prevent complications, and provide surgeons with feedback. The evolution in rhinology may involve the use of flexible, miniature instruments, advanced machine learning (ML) algorithms, and image-guidance systems, potentially paving the way for the introduction of robotic sinonasal surgery featuring multiple automation capabilities.

Conclusions: AI is shaping the future of health care by enhancing its quality, reducing costs, and improving accessibility. Although many applications of AI necessitate well-equipped centers and environments, its unique capabilities extend even to the most underserved areas, where it can assume the diagnostic roles typically performed by health care professionals.