summary: Researchers have developed an AI-based method to estimate brain age using EEG scans. This may lead to early detection of neurological diseases. This technique allows for a lower cost and less invasive evaluation compared to traditional HE MRI-based methods.
AI can assess brain waves to identify potential premature aging and provide a proactive approach to managing risks associated with age-related diseases such as dementia and Parkinson's disease.
Important facts:
- Innovative uses of EEG: This AI technology uses EEG, which is a more accessible and less costly method than MRI, to estimate the age of an individual's brain.
- Early detection and management: By detecting premature aging, this technology can aid in early intervention for diseases such as mild cognitive impairment and Parkinson's disease.
- Wide range of applications: The affordability and efficiency of this technology make it suitable for routine public health testing and monitoring the effectiveness of medical and lifestyle interventions.
sauce: drexel university
As people age, their brains also age. However, premature brain aging can lead to age-related diseases such as mild cognitive impairment, dementia, and Parkinson's disease. Easily calculating “brain age” could help address premature brain aging before it causes serious health problems.
Researchers at Drexel University's Institute for Creativity have developed an artificial intelligence technology that can effectively estimate an individual's brain age based on electroencephalogram (EEG) brain scans. This technology could help make early routine screening for degenerative brain diseases more accessible.
The research team, led by Dr. John Kunios, professor in Drexel University's College of Arts and Sciences and director of the Creativity Lab, is using a type of artificial intelligence called machine learning to predict someone's brain age based on their age. estimated the brain age of an individual. about their appearance.
“When you meet someone for the first time, you might try to estimate their age. Is their hair gray? Do they have wrinkles?” Kunios said.
“Once you know their actual age, you may be surprised at how young or old they look for their age, and you may conclude that they are aging faster or more slowly than you expected.”
Machine learning algorithms can now learn features from MRI images of healthy people's brains that can predict the age of an individual's brain.
By feeding a large number of MRIs of healthy brains into a machine learning algorithm, along with the actual age of each of those brains, the algorithm can learn how to estimate the age of an individual's brain based on the MRIs.
Using this framework, Kounios and his colleagues developed a method to use EEG instead of MRI.
According to Konios, you can think of this as a measure of general brain health. If your brain looks younger than the brains of other healthy people of the same age, there is no need to worry. But if your brain looks older than the brains of your healthy peers at the same age, premature brain aging, or the “brain age gap,” may exist.
Kunios explained that this kind of brain-age gap can be caused by a medical history of disease, toxins, malnutrition, injury, etc., and can make you more susceptible to age-related neurological disorders. .
Despite being an important health marker, brain age estimates are not widely used in medicine.
“Brain MRI is expensive, and until now, brain age estimation has only been done in neuroscience laboratories,” Kunios says. “However, his colleagues and I have developed a machine learning technique that uses low-cost EEG systems to estimate a person's brain age.”
Electroencephalography (EEG) is the recording of a person's brain waves. It's a cheaper and less invasive procedure than an MRI, and patients only need to wear a headset for a few minutes. Therefore, a machine learning program that can estimate brain age using EEG scans rather than MRI could become a more accessible tool for diagnosing brain health, Kounios said.
“This can be used as a relatively inexpensive way to test large numbers of people for age-related vulnerabilities. The low cost also makes it easier to get tested regularly to check for changes over time. We can,” Konios said.
“This can help test the effectiveness of drugs and other interventions. And healthy people can take advantage of this technology as part of an overall strategy to optimize brain performance. You can test the effects of lifestyle changes.”
Drexel University has licensed this brain age estimation technology to Canadian healthcare company DiagnaMed Holdings for inclusion in a new digital health platform.
In addition to Kounios, contributing to this study were Dr. Fengqing Zhang and Dr. Yongtaek Oh of Drexel University, and Dr. Jessica Fleck of Stockton University.
About this AI and neuroscience research news
author: Annie Cope
sauce: drexel university
contact: Annie Cope – Drexel University
image: Image credited to Neuroscience News
Original research: Open access.
“Brain Age Estimation with Low-Cost EEG Headsets: Efficacy and Implications for Large-Scale Screening and Brain Optimization” by John Kounios et al. Frontiers of neurogenomics
abstract
Brain age estimation using low-cost EEG headsets: effectiveness and implications for large-scale screening and brain optimization
Over time, pathological, genetic, environmental, and lifestyle factors can cause the brain to age and its functional capacity to decline.
These factors can lead to disorders that can be diagnosed and treated once symptoms appear, but treatment is often difficult or ineffective by the time significant overt symptoms appear.
One approach to this problem is to develop methods that are widely and inexpensively available to assess general brain health and function as we age.
To achieve this objective, we developed a method for resting-state electroencephalogram (RS-EEG) recordings obtained from healthy individuals as the core of a brain age estimation technique that uses recorded personal RS-EEG at low cost. I trained a machine learning algorithm. Her user-friendly EMOTIV EPOC X headset returns a person's estimated brain age.
We tested the current version of our machine learning model on an independent test set of healthy participants and obtained a correlation coefficient of 0.582 between chronological age and estimated brain age (r = 0.963 after statistical bias correction). The 1-week test-retest correlation was 0.750 (0.939 after bias correction).
Given these excellent results, as well as the ease and low cost of implementation, this technology could be used in clinics, workplaces, It has the potential to be widely adopted in households.
