Skip to main content

Researchers are Developing Analytics to Combat Dementia Using Mobile Sensor Data

Edison Thomaz

Edison Thomaz of Texas ECE and fellow researchers from The University of Texas at Austin have received a 4-year R01 grant award from the National Institute of Health (NIH) to study "Digital Biomarkers and Analytics for Cognitive Impairment with Mobile and Wearable Sensing."

Jared Benge and Justin Rousseau from the Dell Medical School and Rosemary Lester-Smith of the UT Department of Speech, Language, and Hearing Sciences are collaborating on the project.

Alzheimer’s disease and related dementias (ADRD) is a growing epidemic, and in the absence of effective treatment, disease burden increases as the population ages. ADRDs are difficult and costly diseases to treat, affecting millions of people in the U.S alone. Advancing early detection and prediction of this devastating and highly-debilitating condition is essential to the future of treatment for these conditions. Harnessing the capabilities of sensors in personal devices, state-of-the art machine learning techniques, and visual analytics provides an unprecedented opportunity to redefine the paradigm of care and improve quality of life.

The researchers are attempting to advance new computational approaches and analytics to identify digital biomarkers for ADRD detection, prediction and monitoring outside the clinic. This technology-driven approach is based on sensor data passively acquired from smartphones and wearables, and provides the foundation for assessment through continuous monitoring.

The work builds on state-of-the-art research techniques in behavior and context recognition, speech analysis, and machine learning to identify digital biomarkers of Alzheimer’s disease and related disorders. A novel visual analytics interface will assist physicians and health practitioners in interacting with the acquired sensor data, validating the digital biomarkers, verifying model results, and forecasting the progression of disease.

“It is very difficult to monitor the trajectory of cognitive impairment and come up with effective and precise ways to intervene,” said assistant professor Edison Thomaz. “This research will let us develop a more objective and continuous measure of the disease without imposing an additional burden on patients."

"I am thrilled to be bringing Texas ECE together with a stellar group of colleagues from across campus to tackle this urgent problem," he added.

Ideally the research will have similar benefits to the treatment of other common neuro-cognitive conditions, such as stroke and Parkinson’s disease.

Edison Thomaz is an assistant professor and Fellow of the Jack Kilby/Texas Instruments Endowed Faculty Fellowship in Computer Engineering in the Department of Electrical and Computer Engineering at The University of Texas at Austin. He is a leading researcher in the emerging field of personal health informatics. His work has been featured in numerous publications such as MIT Tech Review, The Houston Chronicle, and The Wall Street Journal.

Jared F. Benge, Ph.D., ABPP, is a board-certified clinical neuropsychologist and associate professor with the Department of Neurology at Dell Medical School at The University of Texas at Austin and UT Health Austin’s Comprehensive Memory Center within the Mulva Clinic for the Neurosciences. He specializes in assessment of dementia, Alzheimer’s disease and related disorders and cognitive impairment in movement disorders. Benge has 52 publications and numerous international and national conference presentations focusing on technology in cognitive impairment, early detection of cognitive decline and understanding real-world functioning in older adults with neurodegenerative disease.

Justin Rousseau, M.D., M.M.Sc., is an assistant professor in the Department of Population Health and Department of Neurology. He is board certified in neurology and clinical informatics and is a fellow of the American Medical Informatics Association. His research and development focus is on accessing, integrating and using data in electronic health records and patient-generated data to improve clinical decision support, health care delivery and the monitoring of health outcomes.

Rosemary A. Lester-Smith, Ph.D., CCC-SLP, is an Assistant Professor in the Department of Speech, Language, and Hearing Sciences at The University of Texas at Austin and the Director of the UT Voice Lab.  Dr. Lester-Smith’s research aims to improve the diagnosis and treatment of neurogenic voice disorders including vocal tremor.  She studies voice production in individuals with neurological disorders, healthy speakers, and singers to understand factors that impair or improve vocal control.  She uses acoustical, perceptual, and physiological methods in her research.  In addition, she uses computational models to simulate vocal tremor and vibrato, perturbation of voice auditory feedback to study auditory-motor control, and single-case experimental designs to evaluate the effectiveness of voice therapy.