Leveraging Sensor-Algorithm Synergy for Advancing Muscle-Tracking Technology

Advanced technologies for muscle tracking provide easy access to identify and track muscle activity, to make therapeutics and rehabilitation personalizable, accurate, and proactive. However, existing muscle-tracking devices pick up muscular motions either indirectly from mechanoacoutic signatures on skin surface or via ultrasound waves that demand specialized skin adhesion. Here we present a wireless wearable system, named Laryngeal Health Monitor (LaHMo), that leverages a machine-learning algorithm and duo-modal sensors for measuring movements of laryngeal muscles continuously and accurately. The duo-modal sensors use near-infrared (NIR) light that features deep-tissue penetration and strong interaction with myoglobin, a protein richly contained in muscles, to capture muscular locomotion. The incorporated inertial measurement unit sensor further decouples the complex superposition of signals from NIR recordings. Integrating a multimodal AI-boosted algorithm based on recurrent neural network (RNN), the platform accurately classifies activities of laryngeal muscles and head motion events. An adaptive model enables fast individualization without enormous data sources from the target user, facilitating its broad applicability. Long-term tests and simulations validate the efficacy of the LaHMo for real-world applications, such as monitoring disease progression in neuromuscular disorders, evaluating treatment efficacy, and providing biofeedback for rehabilitation exercises. The core platform highlighted in the LaHMo may serve as a general non-invasive, user-friendly solution for assessing neuromuscular function beyond the anterior neck, potentially improving diagnostics and treatment of various neuromuscular disorders.