Scientists at Weill Cornell Medical College have found that people with autism spectrum disorders can be classified into four different subtypes based on their brain activity and behavior. Research published in the journal nature neuroscience.
The scientists used machine learning to analyze brain scans of 299 autistic patients and 907 non-autistic people. They found patterns of brain connectivity associated with behavioral traits in people with autism: verbal abilities, communication skills, and repetitive behaviors. This made it possible to identify four patient groups.
Two groups had above-average verbal intelligence. In one, social violations were more common, but there were fewer manifestations of repetitive behavior, and in the second, the opposite was true.
The other two groups had severe social disorders and repetitive behaviors, but one had high verbal intelligence and the other low.
The scientists also identified genetic differences in patient groups that will enable more effective treatments to be selected in the future.
Previously, the study authors used similar methods to identify four biologically distinct subtypes of depression. They also showed that these subgroups responded differently to different treatments for depression and determined optimal treatment strategies.