Intraoperative neural monitoring (IONM) is a critical technique for the protection of recurrent laryngeal nerve (RLN) function during thyroid surgery. In recent years, continuous innovations in IONM have established it as a cornerstone of modern thyroid surgery. However, current methodologies still exhibit limitations in the accurate assessment of neural function, and guidelines have yet to provide clear strategies for managing patients with intraoperative signal loss who subsequently develop postoperative voice disorders. This article reviews representative advances in the application of deep learning to bioelectrophysiological signals and systematically summarizes the use of deep learning in the field of voice medicine, thereby exploring the feasibility of integrating IONM with deep learning technologies.

Intraoperative neural monitoring (IONM) is a critical technique for the protection of recurrent laryngeal nerve (RLN) function during thyroid surgery. In recent years, continuous innovations in IONM have established it as a cornerstone of modern thyroid surgery. However, current methodologies still exhibit limitations in the accurate assessment of neural function, and guidelines have yet to provide clear strategies for managing patients with intraoperative signal loss who subsequently develop postoperative voice disorders. This article reviews representative advances in the application of deep learning to bioelectrophysiological signals and systematically summarizes the use of deep learning in the field of voice medicine, thereby exploring the feasibility of integrating IONM with deep learning technologies.