Summary: Researchers created an AI-based technique based on EEG scans to calculate brain’s age, which could help prevent neurological diseases from developing. When compared to conventional MRI-based methods, this technology makes it easier to perform a less expensive and invasive analysis.
The AI uses a strategic approach to managing risks associated with age-related problems like dementia and Parkinson’s by evaluating EEGs to identify possible premature aging.
Important Facts:
1. Modern Use of EEG: The AI method uses EEG, a more attainable and less expensive method than MRIs, to estimate the age of an adult’s brain.
2. First Detection and Management: By detecting early maturity, the technology can help in the early treatment of disorders like mild cognitive impairment and Parkinson’s disease.
3. Application: The technology is suitable for standard public health screenings and evaluating the efficacy of health and lifestyle changes because it is affordable and effective.
As people age, their neurons do, too. But if a brain ages quickly, there is potential for age-associated diseases like slight cognitive impairment, dementia, or Parkinson’s disease. If “brain time” could be easily determined, then early mental aging could be prevented before serious health issues become a reality.
An artificial intelligence technique based on electroencephalogram (EEG) brain scans was created by Drexel University’s Creativity Research Lab, capable of accurately estimating a person’s age in the field. The advancement of earlier, regular screening for chronic mental illnesses may be beneficial.
Led by John Kounios, PhD, professor in Drexel’s College of Arts and Sciences and Creativity Research Lab chairman, the research team used a type of artificial intelligence called machine learning to calculate an individual’s brain age similar to the way one may estimate another person’s age based on their physical appearance.
“When you first meet someone, you might try to determine their age: Is their hair gray? Do they have wrinkles?” said Kounios. “When you learn how old they really are, you might be surprised how young or old they look for their age and think that they are aging more quickly or more slowly than you think.”
Currently, machine-learning algorithms can learn from MRI images of healthy people’s brains what features can predict the age of an individual’s brain.
A machine-learning algorithm can learn how to determine an individual’s brain age based on their MRI by feeding a number of MRIs of healthy brains to a machine-learning algorithm along with the chronological ages of each of those brains.
Kounios and his colleagues developed the technique for using EEGs instead of MRIs using this framework.
This can be thought of as a measure of general brain health, according to Kounios. There is no cause for concern if a person’s brain appears younger than that of other healthy people of the same age. However, there might be premature brain aging, or “brain-age gap,” if a brain looks older than the brains of similarly able-bodied healthy peers.
Kounios explained that this kind of brain-age gap can be caused by a history of diseases, toxins, bad nutrition, and/or injuries, and can make a person vulnerable to age-related neurological disorders.
Although brain-age estimates are considered a crucial health indicator, they have not been widely used in medical care.
“Brain MRIs are expensive and, until now, brain-age estimation has been done only in neuroscience research laboratories,” said Kounios. However, my coworkers and I have created a low-cost EEG system to estimate a person’s brain age.
Electroencephalography, or EEG, is a recording of a person’s brain waves. The patient simply wears a headset for a short while, which is a less expensive and less invasive procedure than an MRI. Therefore, Kounios believes a machine learning program that uses EEG scans to determine brain age could be a more useful screening tool for brain health.
It can be used as a relatively inexpensive method to screen a large number of people for aging-related vulnerability. A person can be screened regularly to check for changes over time because of its low cost, Kounios said.
This can help to evaluate the efficacy of medications and other treatments. And as part of a comprehensive plan to improve brain performance, healthy people could use this method to evaluate the effects of lifestyle changes.
For inclusion in a new digital health platform, Drexel University granted Canadian healthcare provider DiagnaMed Holdings a license to use this brain-age estimation technology.
In addition to Kounios, Fengqing Zhang, PhD, and Yongtaek Oh, PhD, of Drexel University and Jessica Fleck, PhD, of Stockton University contributed to this research.
Abstract
Brain-age estimation with a low-cost EEG-headset: effectiveness and implications for large-scale screening and brain optimization.
Over time, pathological, genetic, environmental, and lifestyle factors can age the brain and diminish its functional capabilities.
Although these conditions can cause disorders to be identified and treated once they start to manifest, treatment can be challenging or ineffective by the time serious, overt symptoms start to manifest.
One method for assessing general age-related brain health and function that can be widely and affordably used is one approach to this issue.
To achieve this goal, we developed a machine-learning algorithm based on resting-state EEG (RS-EEG) recordings from healthy people as the foundation of a brain-age estimation technique that uses an individual’s RS-EEG recorded with the low-cost, user-friendly EMOTIV EPOC X headset to calculate that person’s estimated brain age.
We compared the current version of our machine-learning model to a subset of healthy participants as independent tests, and we found that there was a correlation coefficient of 0.582 between the estimated and chronological brain ages (r = 0.963 after statistical bias correction). The test-retest correlation was 0.750 (0.939 after bias-correction) over a period of 1 week.
Given these promising outcomes and the simple and affordable cost of implementation, this method has the potential to become widely used in the clinic, workplace, and home as a tool to assess general brain function and the effectiveness of interventions over time.
