Machine-learning model can reliably predict cognitive performance based on lifestyle indicators

A new study offers insight into the health and lifestyle indicators—including diet, physical activity and weight—that align most closely with healthy brain function across the lifespan. The study used machine learning to determine which variables best predicted a person’s ability to quickly complete a task without becoming distracted.

Reported in The Journal of Nutrition, the study found that age, blood pressure and body mass index were the strongest predictors of success on a test called the flanker task, which requires participants to focus on a central object without becoming distracted by flanking information.

Diet and exercise also played a smaller but relevant role in performance on the test, the team found, sometimes appearing to offset the ill effects of a high BMI or other potentially detrimental factors.

“This study used machine learning to evaluate a host of variables at once to help identify those that align most closely with cognitive performance,” said Naiman Khan, a professor of health and kinesiology at the University of Illinois Urbana-Champaign who led the work with kinesiology Ph.D. student Shreya Verma. “Standard statistical approaches cannot embrace this level of complexity all at once.”

To build the model, the team used data collected from 374 adults 19 to 82 years of age. The data included participant demographics, such as age, BMI, blood pressure and physical activity levels, along with dietary patterns and performance on a flanker test that measured their processing speed and accuracy in determining the orientation of a central arrow flanked by other arrows that pointed in the same or opposite direction.

“This is a well-established measure of cognitive function that assesses attention and inhibitory control,” Khan said.

Previous studies have found that several factors are implicated in the preservation of cognitive function across the lifespan, Khan said.

“Adherence to the healthy eating index, a measure of diet quality, has been linked to superior executive function and processing speed in older adults,” he said. “Other studies have found that diets that are rich in antioxidants, omega-3 fatty acids and vitamins are associated with better cognitive function.”

The Dietary Approaches to Stop Hypertension, or DASH diet, the Mediterranean diet, and a diet that combines the two, called the MIND diet, all “have been linked to protective effects against cognitive decline and dementia,” the researchers wrote. Physical factors, such as BMI and blood pressure, along with increased physical activity also are strong predictors of cognitive health, or decline, in aging.

“Clearly, cognitive health is driven by a host of factors, but which ones are most important?” Verma said. “We wanted to evaluate the relative strength of each of these factors in combination with all the others.”

Machine learning “offers a promising avenue for analyzing large datasets with multiple variables and identifying patterns that may not be apparent through conventional statistical approaches,” the researchers wrote.

The team tested various machine learning algorithms to see which one best weighed the various factors to predict the speed of accurate responses in the flanker test. The researchers tested the predictive ability of each algorithm, using a variety of approaches to validate those that appeared to perform the best.

They found that age was the most influential predictor of performance on the test, followed by diastolic blood pressure, BMI and systolic blood pressure. Adherence to the healthy eating index was less predictive of cognitive performance than blood pressure or BMI but also correlated with better performance on the test.

“Physical activity emerged as a moderate predictor of reaction time, with results suggesting it may interact with other lifestyle factors, such as diet and body weight, to influence cognitive performance,” Khan said.

“This study reveals how machine learning can bring precision and nuance to the field of nutritional neuroscience,” he said. “By moving beyond traditional approaches, machine learning could help tailor strategies for aging populations, individuals with metabolic risks or those seeking to enhance cognitive function through lifestyle changes.”