Applications and Future Perspectives of Large Language Models in Otolaryngology-Head and Neck Surgery: A Comprehensive Survey.

Since the release of ChatGPT, large language models (LLMs) have rapidly expanded into professional domains, including the medical field. These models, trained on vast text corpora, including the medical literature, have demonstrated impressive capabilities in tasks such as clinical decision support, research assistance, and education. This review focuses on the applications of LLMs in otolaryngology and head and neck surgery (ENT). We analyzed 25 studies published between January 2022 and March 2025 in ENT journals ranked in the top 25% based on the 2023 edition of the Journal Citation Reports (Q1). Moreover, we categorized them by use case and examined the models, datasets, and evaluation methods employed. Despite the growing adoption of LLMs in the ENT field, several challenges remain, including limited model diversity, inconsistent evaluations, and insufficient accuracy and fairness. We also contextualized LLM research trends within a broader medical domain. We highlighted five key areas for advancing clinical-grade LLMs: robust evaluation frameworks, external source-based generation, multimodal integration, agent-based reasoning, and model explainability. Our findings provide ENT clinicians and researchers with a practical foundation for understanding, evaluating, and applying LLMs or advanced versions of LLMs (e.g., Large Multimodal Models, Agents) in clinical and research settings.