Researchers are proposing using artificial intelligence technology to help diagnose autism spectrum disorder.
In a recent article published in Scientific Reports, researchers from Brazil, France and Germany reportedly used magnetic resonance imaging to train a machine learning algorithm.
The work – in which the “quantitative diagnostic method” is proposed – was based on brain imaging data for 500 people, with more than 240 that had been diagnosed with autism.
WHAT IS ARTIFICIAL INTELLIGENCE (AI)?
Machine learning techniques were applied to the data.
“We began developing our methodology by collecting functional magnetic resonance imaging [fMRI] and electroencephalogram [EEG] data,” Francisco Rodrigues, the last author of the article and a professor at the University of São Paulo’s Institute of Mathematics and Computer Science, explained in a statement.
AS AI SHOWS UP IN DOCTORS’ OFFICES, MOST PATIENTS ARE GIVING PERMISSION AS EXPERTS ADVISE CAUTION
“We compared maps of people with and without ASD and found that diagnosis was possible using this methodology,” he added.
The machine learning algorithm was fed with the maps, and the system was able to determine which brain alterations were associated with autism with above 95% mean accuracy.
While previous research proposes methods for diagnosing autism based on machine learning, the article notes it often uses a single statistical parameter that is not brain network organization.
CALIFORNIA MAN WITH SEVERE AUTISM BEATS RUBIK’S CUBE WORLD RECORD: ‘EXUBERANCE IN OUR HEARTS’
Analyzing the fMRI data showed changes in certain brain regions associated with cognitive, emotional, learning and memory processes, and the cortical networks of autism patients showed more segregation, less distribution of information and less connectivity compared to controls.
“Until a few years ago, little was known about the alterations that lead to the symptoms of ASD. Now, however, brain alterations in ASD patients are known to be associated with certain behaviors, although anatomical research shows that the alterations are hard to see, making diagnosis of mild ASD much harder. Our study is an important step in the development of novel methodologies that can help us obtain a deeper understanding of this neurodivergence,” Rodrigues said.
The methodology is under development and will take years to implement, according to the São Paulo Research Foundation, which supported the research.
About one in 36 children has been identified with autism spectrum disorder, according to the Centers for Disease Control and Prevention.
Diagnosing the developmental disability can be difficult because there is no medical test, like a blood test, to do so.
Read the full article here