The machine learning model can reliably predict cognitive performance depending on lifestyle indicators

A new study offers an overview of health and lifestyle indicators – including diet, physical activity and weight – which are most closely aligning with a healthy brain function through life. The study used automatic learning to determine which variables best predicted a person’s capacity to quickly perform a task without being distracted.

Reported In The Journal of NutritionThe study revealed that age, blood pressure and body mass index were the strongest successful predictors during a test called the Flanker task, which forces participants to focus on a central object without being distracted by flanking information.

The diet and the exercise also played a smaller but relevant role in test performance, noted that the team sometimes seemed to compensate for the harmful effects of a high BMI or other potentially harmful factors.

“This study used automatic learning To assess a multitude of variables at the same time to help identify those who line up most closely with cognitive performance“Said Naiman Khan, professor of health and kinesiology at the University of Illinois Urbana-Champaign who led work with the student of the doctoral in Kinesiology Shreya Verma.” Standard statistical approaches cannot embrace this level of complexity at the same time. “

To build the model, the team used data collected from 374 adults from 19 to 82 years old. The data included the demography of the participants, such as age, BMI, blood pressure and physical activity levels, with Food regimes And the performance on a flanker test which measured their processing speed and their precision to determine the orientation of a central arrow flanked by other arrows which pointed out in the same direction or opposite.

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

Previous studies have shown that several factors are involved in preserving cognitive function through the lifespan, Khan said.

“Membership of the healthy food index, a measure of the quality of the food, has been linked to the higher executive function and the processing speed in the elderly,” he said. “Other studies have shown that regimes rich in antioxidants, omega-3 fatty acids and vitamins are associated with better cognitive function.”

Food approaches to stop hypertension, or the Dash regime, the Mediterranean diet, and a diet that combines both, called the mind regime, all “have been linked to protective effects against cognitive decline and dementia,” the researchers wrote. Physical factors, such as BMI and blood pressure, as well as increased physical activity are also strong predictors of cognitive health, or decline, in aging.

“Obviously, cognitive health is motivated by a multitude of factors, but which are the most important?” Said Verma. “We wanted to assess the relative force of each of these factors in combination with all the others.”

Automatic learning “offers a promising avenue to analyze large data sets with several variables and the identification of models that may not be apparent thanks to conventional statistical approaches”, wrote the researchers.

The team has tested various automatic learning algorithms to see which one weighed the various factors best to predict the speed of precise responses in the Flanker test. The researchers tested the predictive capacity of each algorithm, using a variety of approaches to validate those who seemed to work best.

They found that age was the most influential predictor of test performance, followed by Diastolic blood pressureBMI and Systolic blood pressure. Membership of the healthy food index was less predictive of cognitive performance than blood pressure or BMI but also correlated to better performance on the test.

“Physical activity has become a moderate reaction time predictor, with results suggesting that he can interact with other lifestyle factors, such as diet And body weightTo influence cognitive performance, “said Khan.

“This study reveals how automatic learning can provide precision and nuances in the field of nutritional neuroscience,” he said. “By going beyond traditional approaches, automatic learning could help adapt strategies for the aging of populations, individuals with metabolic risks or those who seek to improve cognitive function by lifestyle changes.”