PET, AI Show Women's Brains Age Differently Than Men's
February 7, 2019 -- Are women's brains really that much different from men's? In a word, yes. A machine-learning algorithm applied to data from multiparametric PET brain scans showed that women's brains are more "youthful" than those of men of the same age, according to a study published February 4 in the Proceedings of the National Academy of Sciences.
When researchers at Washington University School of Medicine in St. Louis used an artificial intelligence (AI) algorithm to analyze medical images, they found that the female brain was metabolically three years younger than the age-matched male brain. This advantage could be the reason why women stay mentally sharper later in life.
"We find that throughout the adult life span the female brain has a persistently lower metabolic brain age -- relative to their chronological age -- compared with the male brain," wrote the group led by first author Dr. Manu Goyal. "The persistence of relatively younger metabolic brain age in females throughout adulthood suggests that development might in part influence sex differences in brain aging."
Goyal and colleagues analyzed data from 121 female and 84 male cognitively normal adults (age range, 20-82 years) participating in six different studies at the institution. All subjects underwent metabolic brain PET and structural 3-tesla MRI scans. PET images were coregistered to individual T1-weighed MR imaging sequences and regional measurements of total glucose and oxygen consumption in various brain regions. The glucose information is particularly key to the study because the brain runs on sugar, and how the brain uses that sugar changes as people age.
The researchers first trained the machine-learning algorithm by inputting data on the men's ages and brain metabolism. Next, they entered the women's brain metabolism data and directed the algorithm to calculate each woman's brain age. They found that the women's brains were an average of 3.8 years younger than their chronological ages. This relative youthfulness was observed even among study participants in their 20s.
When Goyal and colleagues reversed the analysis, training the algorithm on the women's data and applying it to the men's, they found the men's brains were 2.4 years older than their chronological ages.
Could the difference in brain aging be confounded by a few key brain regions and/or metabolic parameters? To circumvent that likelihood, the researchers repeated the use of the algorithm on a random selection of 60 of the study's brain regions in 1,000 AI permutations. In all scenarios, the women's brains were younger; the mean difference was 4.7 metabolic years (range, 1.4-7.9 years).
"Human brain aging is characterized by varying trajectories," the researchers wrote. "Some individuals succumb to rapid cognitive decline, whereas other individuals retain their cognitive abilities as they age beyond the typical human life span. Accordingly, it is important to understand the factors that influence brain aging, particularly in the context of an aging population."
Goyal and colleagues added that measuring metabolic brain age "might be useful in predicting the risk of cognitive decline and in identifying other factors that could potentially improve or worsen the trajectory of human brain aging."