The human brain holds many clues about a person’s long-term health—in fact, research shows that a person’s brain age is a much more useful and accurate predictor of future health risks and diseases than when they were born. A new AI model that analyzes brain MRI scans developed by USC researchers could be used to capture cognitive decline associated with neurodegenerative diseases such as Alzheimer’s much earlier than previous methods.
Brain aging is a reliable biomarker of risk for neurodegenerative diseases. These risks increase when a person’s brain displays features that appear “older” than would be expected for someone of that person’s age. By leveraging the deep learning ability of the team’s new AI model to analyze scans, researchers can detect subtle, hard-to-detect brain anatomy markers that are associated with cognitive decline. Their findings, which were recently published in the journal Proceedings of the National Academy of SciencesOffers an unprecedented glimpse into human cognition.
“Our study harnesses the power of deep learning to identify regions of the brain that age in ways that reverse the cognitive decline that may lead to Alzheimer’s disease,” he said. Andrey Jeremiahassistant professor of gerontology, biomedical engineering, and neuroscience in the Leonard Davis School of Gerontology at USC and author of the study.
People age at different rates, as do the types of tissues in the body. We know this colloquially when we say, “So-and-so is 40, but it looks like 30.”
Andrey JeremiahUSC Leonard Davis
Gerontology School
“People age at different rates, and so do the types of tissues in the body,” Jeremiah said. “We know this colloquially when we say, ‘So-and-so is 40, but it looks like 30.'” The same idea applies to the brain. The brain of a 40-year-old might seem “small” like the brain of a 30-year-old, or “big” like The brain of a 60-year-old.
Brain aging: a more accurate alternative to current methods
The researchers collected MRI images of the brain of 4,681 cognitively normal participants, some of whom developed cognitive decline or Alzheimer’s disease later in life.
Using this data, they created an artificial intelligence model called a neural network to predict the participants’ ages from MRI scans of their brains. First, the researchers trained the network to produce detailed anatomical brain maps that reveal the aging patterns of a given subject. They then compared the (biological) ages of the brain with the actual (chronological) ages of the study participants. The greater the difference between the two, the worse the participants’ cognitive scores, reflecting their risk of developing Alzheimer’s disease.
The results show that the team’s model could predict the true (chronological) ages of cognitively normal participants with an average absolute error of 2.3 years, which is about one year more accurate than the current award-winning model for estimating brain age that used a different neural network architecture.
The researchers collected MRI images of the brain of 4,681 cognitively normal participants, some of whom developed cognitive decline or Alzheimer’s disease later in life. (Illustration/Courtesy of USC’s Leonard Davis School of Gerontology)
said Eremia, who also holds faculty positions at the USC Viterbi School of Engineering and the University of Southern California Dornsife College of Letters, Arts and Sciences.
“The earlier we can identify people at high risk of Alzheimer’s disease, the first clinicians can intervene in treatment and monitoring options.” and disease management.“
Brain aging: differences by sex
The new model also reveals the sex-specific differences in how aging varies across brain regions. Certain parts of the brain in males age faster than in females, and vice versa.
Males, who are more likely to develop motor impairment due to Parkinson’s disease, experience faster aging in the brain’s motor cortex, the region responsible for motor function. The results also show that in females, typical aging may be relatively slower in the right hemisphere of the brain.
A promising emerging field of study is personalized medicine
The applications of this work extend far beyond disease risk assessment. Irimia envisions a world in which new deep learning methods developed as part of the study are used to help people understand how fast they age in general.
“One of the most important applications of our work is its potential to pave the way for personalized interventions that address each individual’s unique aging patterns,” Jeremiah said.
“A lot of people would be interested to know their true rate of aging. The information can give us hints about different lifestyle changes or interventions a person can adopt to improve their overall health and well-being. Our methods can be used to design patient-centered treatment plans and personalized maps of brain aging that It may concern people with different health needs and goals.”
More stories about: Alzheimer’s diseaseAnd Artificial intelligenceAnd NeurosciencesAnd Search