Monday, January 30, 2023

Artificial intelligence to calculate Alzheimer’s risk according to brain age

The human brain contains many clues about a person’s long-term health; In fact, research shows that a person’s brain age is a more useful and accurate predictor of future health risks and disease than their date of birth.

Now, a new artificial intelligence (AI) model analyzing magnetic resonance (MR) brain imaging developed by researchers at the University of Southern California (USC) can be used to accurately capture the cognitive decline associated with neurodegenerative diseases such as Alzheimer’s. Could previous methods.

Brain aging is considered a reliable biomarker of risk for neurodegenerative diseases. This risk increases when a person’s brain exhibits characteristics that appear elder More than expected for someone his age. Using the deep learning capabilities of a novel AI model developed by the team to analyze the scans, researchers have been able to detect subtle markers of brain anatomy that would otherwise be very difficult to detect and that correlate with cognitive decline . Their findings were published January 2 in the journal Proceedings of the National Academy of Scienceprovide unprecedented insight into human cognition.

“Our study harnesses the power of deep learning to identify areas of the brain that show cognitive decline in ways that aging can lead to Alzheimer’s,” he explains. Andrei Irimiaassistant professor of gerontology, biomedical engineering, quantitative and computational biology, and neuroscience at USC and corresponding author of the study.

“People age at different rates, and so do the types of tissues in the body. We know this colloquially when we say: ‘Such a person is 40, but he looks 30’ The same idea applies to the brain. The brain of a 40 year old might look like this young like 30, or so Viejo Like a 60″ one, comments the researcher.

Thanks to high precision artificial intelligence

Irimia and his team compared brain MRIs from 4,681 cognitively normal participants, some of whom developed cognitive decline or Alzheimer’s disease later in life.

Using this data, they built an artificial intelligence model called a neural network to predict the participants’ ages from their brain MRIs. First, the researchers trained the network to generate detailed anatomical maps of the brain that revealed specific aging patterns for each subject. They then compared the perceived (biological) brain ages with the actual (chronological) ages of the study participants. The greater the difference between the two, the worse the participants’ cognitive scores, indicating their risk of suffering from Alzheimer’s.

The results showed that the model developed by the team could predict the true (chronological) age of cognitively normal participants with a mean absolute error of 2.3 years, which is roughly comparable to models already recognized for brain age estimation. One year is more accurate. Used a different neural network architecture.

“Interpretable artificial intelligence could become a powerful tool for assessing risk for Alzheimer’s and other neurocognitive diseases,” says Irimia, who is also a professor in USC’s Viterbi School of Engineering and the USC College of Letters, Arts and Sciences. “The sooner we can identify people at high risk of Alzheimer’s, the sooner doctors can move forward with treatment, monitoring, and disease management options. What makes AI especially powerful is its ability to understand the subtle and subtle aspects of aging.” It has the potential to capture complex features that other methods might not, and which are important for identifying an individual’s risk many years before the disease develops.”

Brain ages differently by gender

The new model also reveals gender differences in the way different brain regions age. Some parts of the brain age faster in men than in women, and vice versa.

Men, who are at higher risk of motor impairment due to Parkinson’s disease, experience faster aging in the motor cortex of the brain. The findings also suggest that, in women, the rate of normal aging may be relatively slower in the right hemisphere of the brain.

A promising area of ​​study for personalized medicine

The applications of this work go well beyond disease risk assessment. Professor Irimia envisions a world where the novel deep learning methods developed as part of the study are used to help people understand how quickly they are aging normally. “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,” he highlighted.

“Many people would be interested in knowing the exact rate of their ageing. The information can give us clues about various lifestyle changes or interventions that a person can adopt to improve their overall health and well-being. Our The methods can be used to design patient-centered treatment plans and personalized maps of brain aging that may interest people with different health needs and goals,” the researchers concluded.

Scientific Reference:

,Physiologically interpretable deep learning captures domain-specific cognitive impairment of brain age. Proceedings of the National Academy of Sciences, 2023. DOI: 10.1073/pnas.2214634120

Nation World News Desk
Nation World News Desk
Nation World News is the fastest emerging news website covering all the latest news, world’s top stories, science news entertainment sports cricket’s latest discoveries, new technology gadgets, politics news, and more.
Latest news
Related news