Deep Learning Algorithm Identifies Differences in Brains of Boys and Girls with Autism

Functional brain organization differs between boys with autism and girls with autism, according to a deep learning study out of the Stanford University School of Medicine in California. Researchers reported their findings in The British Journal of Psychiatry.

“We detected significant differences between the brains of boys and girls with autism, and obtained individualized predictions of clinical symptoms in girls,” said study senior author Vinod Menon, PhD. “We know that camouflaging of symptoms is a major challenge in the diagnosis of autism in girls, resulting in diagnostic and treatment delays.”

The study focused on functional magnetic resonance imaging brain scans from 773 children with autism: 637 boys and 136 girls. Researchers used 678 scans to develop an artificial intelligence algorithm that was able to distinguish between the sexes with 86% accuracy. When the team tested the algorithm in the remaining 95 scans, it achieved the same level of accuracy.

RELATED: US Study Finds Disparities in Timing of Neurodevelopmental Disorder Diagnosis

When researchers tested the algorithm on 976 brain scans from neurotypical children, however, they found it could no longer distinguish between boys and girls. The finding suggests the identified gender differences in children with autism are different from normative gender differences.

In particular, the study showed different connectivity patterns in motor, language, and visuospatial attention systems in girls with autism. The largest differences between girls and boys with autism were in a group of motor areas, including the primary motor cortex, supplementary motor area, parietal and lateral occipital cortex, and middle and superior temporal gyri. Girls with brain patterns more like boys, the research team explained, tended to have more pronounced motor symptoms.

Language areas, too, differed between boys and girls with autism. Prior studies, researchers pointed out, have identified greater language impairments in boys with autism.

“We may need to have different tests for females compared with males,” said study lead author Kaustubh Supekar, PhD. “The artificial intelligence algorithms we developed may help to improve diagnosis of autism in girls.”

References

Supekar K, de Los Angeles C, Ryali S, Cao K, Ma T, Menon V. Deep learning identifies robust gender differences in functional brain organization and their dissociable links to clinical symptoms in autism. Br J Psychiatry. Published online February 15, 2022. doi: 10.1192/bjp.2022.13

Digitale E. Study finds differences between brains of girls, boys with autism. News release. Stanford Medicine. February 17, 2022. Accessed March 14, 2022.