Artificial intelligence (AI) could be used to diagnose autism in thousands of children at an earlier age, significantly improving their quality of life, according to a study.
A newly developed artificial intelligence system that analyzes magnetic resonance imaging (MRI) scans of the brain identifies children with autism between 24 and 48 months of age with 98.5 percent accuracy, according to a University of Louisville study.
This opens up the prospect of much more general and accurate testing of young children, as diagnosis using traditional methods only becomes reliable at age three, a separate study found.
It says artificial intelligence techniques are being developed that can “predict diagnostic outcomes before the age of three and provide more accurate predictions.”
It is hoped that the use of AI could help detect autism in young children, especially those under three years of age.
“Our approach is a new advance that allows early detection of autism in infants under two years of age,” said Mohamed Khoudri, a visiting researcher at the University of Louisville in Kentucky who helped develop the system.
Celine El Baw of University College London, who was not involved in the study, said the findings suggest AI could be used to improve the lives of young children, but warned that the stigma of the diagnosis could be difficult for some.
“Early identification could be helpful if interventions could be developed to enable children with autism to understand themselves very early so that they can lead more meaningful lives and benefit from any adaptations they may need due to their neurodivergence when they will go into the school system. ,” She said.
“However, much remains to be done to combat stigma and discrimination against autistic children, and there is a risk that in some cases the situation will get worse,” she said.
Children diagnosed with autism may receive support at school and from local authorities, and may also be eligible for financial support from the government, and parents can receive advice on how to support their children.
It is estimated that between 1 and 3 percent of the UK population has autism, although a recent study from University College London suggests the figure may be twice as high as previously thought.
There are three million children under the age of three, suggesting that thousands could potentially benefit from an AI diagnosis.
Currently, when assessing autism, parents are usually asked about the child’s development, such as when the child started talking.
The expert also looks at how the parents and child interact with each other, how they play, and reads any reports from the doctor, kindergarten or school.
They will ask about your medical history and perform a physical examination.
The developed artificial intelligence system involves extracting images of brain tissue from MRI images and identifying “markers” indicating the level of connection between brain regions.
A machine learning algorithm compares marker patterns in the brains of neurodivergent children with neurotypical children.
Called DT-MRI, the technique uses a special technique to measure how water moves through the brain’s white matter pathways.
The researchers applied AI to DT-MRI brain scans of 226 children aged 24 to 48 months. The dataset included images of 126 autistic children and 100 neurotypical children.
The technology has demonstrated an overall accuracy of 98.5% in identifying children with autism.
“Imaging holds promise for rapid and objective detection of autism,” Dr. said. Barnes. “We envision that the autism study will begin with a DT-MRI, followed by an abbreviated session with a psychologist to confirm the results and guide parents through next steps. This approach can reduce the workload of psychologists by up to 30 percent.”
The artificial intelligence system produces a report detailing the affected neural pathways, expected effects on brain function, and severity that can be used to guide early therapeutic interventions.
The researchers are working to commercialize their artificial intelligence software in the United States and gain regulatory approval.
They will present their findings next week at the annual meeting of the Radiological Society of North America (RSNA).
Source: I News
With a background in journalism and a passion for technology, I am an experienced writer and editor. As an author at 24 News Reporter, I specialize in writing about the latest news and developments within the tech industry. My work has been featured on various publications including Wired Magazine and Engadget.