Researchers at Weill Cornell Medicine have identified four subtypes of autism spectrum disorder using machine learning analysis of neuroimaging data, potentially leading to more personalised treatments. The study found patterns of brain connections linked with behavioural traits in people with autism, and confirmed that the four autism subgroups could also be replicated in a separate dataset. Differences in regional gene expression and protein-protein interactions explained the brain and behavioural differences. The team will next study these subgroups and potential subgroup-targeted treatments in mice.

Autism spectrum disorder (ASD) is a complex neurodevelopmental condition that affects communication, social interaction, and behavior in varying degrees. Despite extensive research, the underlying causes and mechanisms of ASD are still not well understood. However, a recent brain study conducted by researchers at the University of California, Los Angeles (UCLA) has identified four distinct subtypes of ASD, which could help unlock the mystery of this condition and improve diagnosis and treatment outcomes. This article explores the key findings of the study, its implications for ASD research, and the potential impact on individuals and families affected by the disorder.


Researchers at Weill Cornell Medicine have identified four distinct subtypes of autism spectrum disorder through machine learning analysis of neuroimaging data. The study analysed newly available neuroimaging data from 299 people with autism and 907 neurotypical people, using machine learning to identify patterns of brain connections linked with behavioural traits in people with autism, such as verbal ability, social affect, and repetitive or stereotypic behaviours. They confirmed that the four autism subgroups could also be replicated in a separate dataset and showed that differences in regional gene expression and protein-protein interactions explain the brain and behavioural differences. Autism is a highly heritable condition associated with hundreds of genes that has diverse presentation and limited therapeutic options, but the diagnostic criteria are broad which make it difficult to identify the optimal therapy when everyone is treated as being the same, when they are each unique. The study highlights a new approach to discovering subtypes of autism that might one day lead to personalised therapies for individuals with autism, specific to their individual subtype. The next steps include studying these subgroups and potential subgroup-targeted treatments in mice and refining machine-learning techniques even further. The authors have said that a personalised therapy assignment for individuals diagnosed with depression could also help in selecting the best possible therapy.


In conclusion, the recent brain study that revealed four distinct subtypes of autism is a breakthrough moment in our understanding of this complex neurological disorder. The identification of these subtypes could pave the way for more targeted treatments that address the unique needs of individuals with autism. While there is still much research to be done, this study offers hope for a future where individuals with autism can lead fuller, more integrated lives. Let us continue to support and invest in autism research, so we can continue to uncover the mysteries of this condition and improve the quality of life for those affected by it.