Artificial Intelligence development in precision dosing for dementia prevention

July 15, 2021

University of Florida researchers studying the use of a noninvasive brain stimulation treatment paired with cognitive training have found the therapy holds promise as an effective, drug-free approach for someday warding off Alzheimer’s disease and other dementias.

Yet determining optimal dosing for the treatment known as transcranial direct current stimulation, or tDCS, which is delivered by a safe and weak electrical current passed through electrodes placed on a person’s head, has been a challenge because of individual differences in anatomy.

Now, with the support of a $2.9 million grant from the National Institute on Aging, scientists in the UF colleges of Public Health and Health Professions and Engineering will use artificial intelligence technology, including advanced machine learning and deep-learning algorithms, to evaluate a large data set gleaned from a study of tDCS and cognitive training in older adults. The goal is to gain more insight into the mechanisms driving treatment response and individual variability so that researchers can design a customized method for providing tDCS with the best possible outcome.

The new study will use data derived from the National Institute on Aging-funded Augmenting Clinical Training in Older Adults: The ACT Study, an ongoing study of 360 older adults led by Adam Woods, PhD, an associate professor of clinical and health psychology in the UF College of Public Health and Health Professions, part of UF Health, and associate director of the Center for Cognitive Aging and Memory at UF’s Evelyn F. and William L. McKnight Brain Institute. The ACT study pairs tDCS with cognitive training designed to improve working memory and processing speed.

In a smaller pilot study of the treatment, Woods and his colleagues demonstrated that tDCS combined with cognitive training improved cognition and brain function after only two weeks. Treatment effects varied from person to person due to differences in anatomy, such as skull thickness.

The new study will leverage machine learning algorithms to evaluate data from behavioral outcomes, neuroimaging and physiological features captured from participants in The ACT Study. That will help researchers find patterns among the 16 million data points, said team member Aprinda Indahlastari, PhD, a research assistant professor of clinical and health psychology.

Visit UF for more