AI Machine Learning Reveals How the Brain’s Anatomy Changes With Autism
We have come a long way in our understanding of autism since it was first used as a clinical description in 1943. Scientists have identified several genes that seem to play a role play a role and have developed therapies that can improve the quality of a person with autism. life. Despite these remarkable achievements, modern science has only discovered the tip of the iceberg of neurodevelopmental disorders. For example, scientists have yet to identify all the parts of the brain that are affected and how these structural differences lead to a multitude of symptoms and behaviors.
A major challenge standing in the way is autism — there is a mountain of individual variation when it comes to the underlying biology of the disorder. However, a team of neuroscientists are aiming to find all the dots in the brain of autistic people and connect them with a little help from AI.
In one newspaper published on Thursday in the magazine Scienceresearchers at Boston University used machine learning – a type of AI that learns and improves from experience – to identify the types of anatomical variations in the brain that are caused by autism compared with other factors like age gender or gender.
“It’s a technological innovation,” James McPartland, a clinical psychologist and autism researcher at Yale University who was not involved in the study, told The Daily Beast. “It’s really hard to tell which is the autism signal in so many [noisy data]. The more ways you can meaningfully analyze that noise, the more power you have to uncover signals that make sense in understanding the neuroscience of autism. “
Aidas Aglinskas, a neuroscientist at Boston University and lead author of the paper, told The Daily Beast, when it comes to the neuroscience of autism.
“[There’s] “It’s a common idea in precision medicine to try and find subtypes of autism — say autism A and autism B — and maybe they’re characterized by different symptoms,” says Aglinskas. “That in itself would be informative because then you might think that different treatments work better for group A or B. Instead, what we found, surprisingly, is an absolute greater amount of variation than can be captured by these individual subtypes.”
To explore the vast variability of the brain, Aglinskas and his colleagues studied and compared functional MRI scans between autistic and non-autistic individuals, obtained from the Brain Imaging Data Exchange. Autism (ABIDE). The Boston University team’s AI learned to filter out common neural variations that all brains share (such as those associated with age and sex) and identified regions in the brain that are associated regarding autism.
“[Our machine learning] Aglinskas says a large number of brain regions are involved, many of which are associated with known autism symptoms. “So things like areas in the brain involved in social perception, thinking about others, motor and sensory organs, and areas in language.”
McPartland says the findings are a great first step in mapping out the brains of people with autism and providing a more detailed roadmap for future research. But he cautions that the study, while advanced, is unlikely to have any immediate clinical applications, largely due to the current lack of treatments that target a specific part of the brain.
“No matter how much we understand about potential neurological differences, we as clinicians working with neuroscientists have a long way to go when we are in a that we can say, ‘Aha, there’s a structural difference in this brain region and this McPartland said.
Aglinskas agrees and admits that in the future, his team wants to include a range of brain measurements, like electroencephalograms that record the brain’s electrical activity and genetic data to see if those complement each other. What their AI finds or can provide a new perspective.
While the use of machine learning to crack the black box of autism is still underway, Aglinskas hopes it could be of immense value and could have a more clinical impact on neurological disorders. Others need more nuanced understanding.
“Diversity is particularly evident in autism, but so far it is not the only heterogeneous disorder,” he said. “[There is] attention-deficit disorder or depression, where there’s a lot of variation there. These methods can also be applied to study variation in those fields. “