NEW YORK, Nov. 21 (UPI) — A new artificial intelligence system could diagnose autism much earlier in children, according to research to be presented this week at the annual meeting of the Radiological Society of North America in Chicago.
The newly developed system that analyzes specialized MRIs of the brain accurately diagnosed children aged 24 to 48 months with autism with an accuracy rate of 98.5%, the researchers said.
A multidisciplinary team at the University of Louisville developed the three-step system for analyzing and classifying diffusion tensor MRI, or DT-MRI, of the brain. DT-MRI is a special technique that detects how water travels along white matter areas in the brain, according to a news release.
“The current tools for diagnosing autism are subjective, especially when considering individuals who come close to the boundary between autism and typical development,” said study co-author Ayman El-Baz, professor and chair of the department of bioengineering at the University Louisville, UPI. by email.
“Consequently, there is an urgent need to develop a new objective technology for the early diagnosis of autism.”
The AI system involves extracting brain tissue images from the DT-MRI scans and extracting imaging markers that indicate the level of connectivity between brain regions.
A machine learning algorithm compares the marking patterns in the brains of children with autism and those with normally developing brains.
“Autism is primarily a disease of improper connections within the brain,” co-author Dr. Gregory N. Barnes, professor of neurology at the University of Louisville and director of the Norton Children’s Autism Center in Louisville, said in the release.
“DT-MRI captures these abnormal connections that lead to the symptoms often experienced by children with autism, such as impaired social communication and repetitive behaviors.”
The researchers applied their methodology to the DT-MRI brain scans of 226 children aged 24 to 48 months from the Autism Brain Imaging Data Exchange-II. The dataset included scans of 126 children affected by autism and 100 typically developing children.
Therapeutic intervention before age three may lead to better outcomes, including the potential for individuals with autism to achieve greater independence and higher IQs, the researchers noted.
According to the CDC’s 2023 Community Report on Autism, less than half of children with an autism spectrum disorder received a developmental evaluation by age 3, and 30% of children who met criteria for an autism spectrum disorder did not. formal diagnosis by age 8.
“Early intensive behavioral intervention within the age range from one to three years can have a significant benefit due to the phenomenon called neuroplasticity in the infant’s brain,” said El-Baz.
Reduction of workload
An autism assessment would begin with the researchers’ AI system, followed by a brief session with a psychologist to confirm results and guide parents on next steps. It could reduce the psychologists’ workload by up to 30%.
The investigators want to commercialize and get clearance from the Food and Drug Administration for their AI software.
“I’m all for any diagnostic technology that can help us diagnose autism earlier and reliably to help children access evidence-based intervention earlier,” Dr. Leandra Berry, associate director of clinical services for the center autism at Texas Children’s Hospital in Houston. , UPI said in a telephone interview.
However, she said, “Many studies will need to replicate this finding before we really adopt this technology.”
With the patients in the study ranging in age from 24 to 48 months, she noted that the study cannot address whether the technology will be useful for younger children.
Berry also noted that in research studies, grants typically pay for MRIs and other scans, but insurers may not cover expensive imaging tests, adding that this technology is accessible, especially in rural areas. , limited.
Although these data can provide a diagnosis, a specialist will need to communicate this information to a family. “There’s still a human clinician component that’s going to be critical,” Berry said.
It is essential to detect it early
Diana Robins, professor and director of the AJ Drexel Autism Institute at Drexel University in Philadelphia, told UPI in a telephone interview that “early detection is essential to reduce autism-related disability and improve positive outcomes for autistic individuals. “
However, “before you draw conclusions about identifying autism, you need to include children with other developmental delays in your sample,” said Robins, who has a doctorate in psychology.
It’s “important to discuss together” commonly occurring diagnoses, Dr. Susan Hyman, a professor in the Department of Developmental and Behavioral Pediatrics at the University of Rochester Children’s Golisano Hospital in Rochester, NY, told UPI via email.
She also said that almost half of autistic children have attention deficit/hyperactivity disorder, 40% of autistic people with autism have intellectual disabilities and 25% of autistic people have seizures which usually start in early childhood. childhood or adolescence.
“MRIs ordered in the community for autistic children who do not have seizures or rare neurologic findings provide information that will inform care on an individual level,” Hyman said.
It is also difficult for young children to wait still for an MRI.
“You have to try multiple times, try to scan them at bedtime when they’re sleepy, or you have to sedate them, which comes with a medical risk,” Robins said, adding that parents may not give consent.
Robins noted that there is no data available to indicate how much this technology will reduce psychologists’ workload. “This [technology] far from being ready for the general public,” she said.