SBIR Phase I: A Patient-Centered Wearable System to Enable Data-Driven Decisions in Neuromuscular Disorders

The broad impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project will benefit the members of the ALS community as this wearable technology and data collection enables greater independence for individual ALS patients allowing them to remotely communicate with caregivers and clinicians, and control environmental elements within their living spaces as well as being able to monitor their progression for self-care. Expanding the communication connection between and among the ALS patient, caregivers and clinical care team members creates a dynamic, multidisciplinary care environment, which can thoroughly address the changing needs of an ALS patient. The proposed technology could bring immediate and ongoing assistance to ALS patients and will remain functional as physical changes occur due to the progression of ALS, even when a patient has lost all movement ability. The immediate target market for this type of technology is individuals with severely impaired ability to move and speak. Neuromuscular conditions including multiple sclerosis, cerebral palsy, spinal cord injuries and severe stroke affect 1.5M people in the US and 30M people globally. This population has very limited options for effective communication and control and are largely underserved by existing technologies. The proposed project aims to create a technological platform to address communication and accessibility issues within care environments for patients affected by Amyotrophic Lateral Sclerosis (ALS). Patients with ALS develop a progressively reduced ability to communicate and interact with interface technology such as mice and keyboards. Each patient has dynamic needs due to the differing progression rates of the disease. This creates an opportunity to provide a personalized human-computer interface with data collection capabilities. The objectives of the proposal involve testing the effects of skin-electrode impedance and electromagnetic interference (EMI) from medical equipment such as ventilators and powered wheelchairs on the quality of biopotential signals. Furthermore, it involves personalizing signal classification models based on an individual's physical impairment. Advanced signal processing techniques, including Morlet wavelet and Hilbert transform, will be used to filter the data collected from multimodal sensor inputs. This will ensure a robust system design for multiple care environments, regardless of life support and technological equipment within that space. In addition, a human research study will be conducted with ALS participants in order to acquire a relevant data set.