New discovery of mental illness indicators using AI

The brain-imaging data comes from scans using functional magnetic resonance imaging (fMRI), which measures brain activity by detecting small changes in blood flow, as one study reports. newly published on


“We’ve built artificial intelligence models to explain a large number of them,” said Sergey Plis, an associate professor of computer science and neuroscience at Georgia State and lead author of the study. information from fMRI.


He compared this type of animation to a film – as opposed to a snapshot like the more common structural X-ray or MRI – and noted that “the available data is much larger, more much richer than regular blood tests or MRIs. But that’s the challenge – that huge amount of data is hard to interpret.”

Using functional magnetic resonance imaging in artificial intelligence methods

In addition, fMRIs on these specific conditions are very expensive and not easily obtained. However, using artificial intelligence modeling, conventional fMRIs can be mined for data available in large quantities.

“There are large data sets available in people without known clinical disorders,” explains Vince Calhoun, founding director of the TReNDS Center, and one of the study’s authors. The use of these large but unrelated pre-existing data sets improved the performance of the model on smaller specific data sets.

“New patterns emerge that we can firmly associate with each of the three brain disorders,” says Calhoun.

The artificial intelligence models were first trained on a dataset consisting of more than 10,000 individuals to learn to understand basic fMRI imaging and brain function. The researchers then used multisite data sets of more than 1,200 individuals, including those with autism spectrum disorder, schizophrenia, and Alzheimer’s disease.

How do computer programs work?

It’s like Facebook, YouTube or Amazon learns about you from your online behavior and starts to be able to predict future behavior, likes and dislikes. Computer software can even access “times” when brain-imaging data is more likely to be related to the mental disorder in question.

To make these findings clinically useful, they will need to be applied before the disorder manifests. “If we can find the markers and predict the risk of Alzheimer’s in 40-year-olds, then we can do something about it,” Calhoun said.

Similarly, if the risk of schizophrenia can be predicted before there are actual changes in brain structure, there could be ways to better or more effective treatments.

“Even if we knew from other tests or family history that someone was at risk for a disorder like Alzheimer’s, we still couldn’t predict exactly when it would happen,” Calhoun said. . “Brain imaging can bridge that time period, by catching relevant patterns as they appear before clinical disease is apparent.”

“The vision is that we collect a large dataset of images, our AI models study it and show us what they learn about certain disorders,” says Plis. “We’re building systems to uncover new knowledge that we wouldn’t have discovered on our own.”

“Our goal,” said Md Mahfuzur Rahman, first author of the study and a doctoral student in computer science at Georgia State, “is to connect the big world and the big data set with small worlds and disease-specific data sets, and move towards markers of decisive clinical relevance.”

This research was supported by start-up funds for SMP and in part by NIH grants R01EB006841, R01MH118695, RF1MH121885 and NSF 2112455.

Source: Eurekalert

Source link


News5h: Update the world's latest breaking news online of the day, breaking news, politics, society today, international mainstream news .Updated news 24/7: Entertainment, the World everyday world. Hot news, images, video clips that are updated quickly and reliably

Related Articles

Back to top button