SCH: collaborative research: rehabilitation evaluation of neurologic motor disorders using wearable sensors

The National Science Foundation Division of Civil, Mechanical, and Manufacturing Innovation awarded the University of Tennessee at Chattanooga $189,931 on October 1, 2026, under the Engineering program (CFDA 47.041) to develop wearable sensor systems and patient-specific artificial intelligence for rehabilitation monitoring outside clinical settings in individuals with traumatic brain injury, autism spectrum disorder, and other neurologic motor disorders.

The research will investigate fundamental methods for combining multimodal wearable sensors with patient-specific analysis of complex movement data, including energy-efficient sensing approaches, feature extraction from wearable sensor signals, and machine learning techniques for analyzing high-dimensional time-series data collected during rehabilitation. The project aims to identify movement patterns associated with neurologic motor disorders, develop quantitative biomarkers of rehabilitation progress, and improve patient-specific assessment of recovery through clinical studies examining relationships between wearable sensor measurements and established clinical evaluations. The research supports national priorities in artificial intelligence and digital health while providing research opportunities for undergraduate and graduate students and outreach engagement with high school students in engineering and health sciences.

Performance of work occurs in Chattanooga, Tennessee through September 30, 2030.

Abstract

Traumatic brain injury, autism spectrum disorder, and other neurologic motor disorders can affect movement, balance, and coordination. These changes can make daily life harder and reduce quality of life. Rehabilitation may last for months or years. However, recovery is often checked only during clinic visits. This makes IT hard to know how patients move and function at home. This smart and connected health (SCH) project studies wearable sensors and patient-specific artificial intelligence for rehabilitation monitoring outside the clinic. The research aims to create objective measures of recovery. These measures can add to current clinical evaluations and help guide individualized rehabilitation. The project may improve access to remote rehabilitation and help identify delayed recovery earlier. IT also supports national priorities in artificial intelligence and digital health. The project will provide research opportunities for undergraduate and graduate students and engage high school students through outreach in engineering and health sciences. The project will investigate fundamental methods for combining multimodal wearable sensors with patient-specific analysis of complex movement data. The research includes the development of energy-efficient sensing approaches, methods for extracting informative features from wearable sensor signals, and machine learning techniques for analyzing high-dimensional time-series data collected during rehabilitation. These methods will be studied to identify movement patterns associated with neurologic motor disorders, develop quantitative biomarkers of rehabilitation progress, and improve patient-specific assessment of recovery. Clinical studies involving individuals with traumatic brain injury and autism spectrum disorder will examine relationships between wearable sensor measurements and established clinical evaluations while assessing the feasibility of the proposed framework for rehabilitation monitoring. The expected outcomes include new knowledge in wearable sensing, patient-specific machine learning, rehabilitation science, and human biomechanics, providing a foundation for future smart and connected health technologies for personalized rehabilitation. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the foundation's intellectual merit and broader impacts review criteria.- subawards are not planned for this award.