Abstract: Gunstad, Miller and Ostrand
Using automated speech analysis to predict cognitive decline and future Alzheimer’s disease
John Gunstad, Ph.D., Department of Psychological Sciences, Brain Health Research Institute, ºÚÁϳԹÏÍø
Lindsay Miller Scott, Ph.D., University Hospitals Cleveland Medical Center, Department of Neurology, Case Western Reserve University School of Medicine
Rachel Ostrand, Ph.D., IBM Research
With the aging of the baby boomer generation, the prevalence of Alzheimer’s disease (AD) will triple by 2050 and generate an estimated $1.1 trillion in annual health care costs in the United States. These trends highlight the urgent need to identify persons at risk for future AD to delay symptom onset and optimize treatment regimen. Speech analysis may provide an inexpensive, non-invasive, and scalable method for early detection of cognitive impairment. Our pilot study will examine the feasibility of using conversational speech to both identify those persons with cognitive impairment and those at risk for cognitive decline in the next year. If confirmed, findings from the proposed study would provide the insight needed to develop tools to predict, detect, and monitor cognitive decline in real world settings.