• The current study used unsupervised machine learning to identify behavioral subtypes of autism.
• Sixteen subgroups were identified, and the hierarchy of those subgroups suggest there may be two unique subtypes of autism, each with a spectrum of severity.
• The autism subgroups were found to have unique behavioral profiles as well as differentiated treatment response.
• These findings may lead to advancements in targeted treatments for autistic individuals based on subtype membership.
Stevens, E., Dixon, D. R., Novack, M. N., Granpeesheh, D., Smith, T., & Linstead, E. (2019). Identification and analysis of behavioral phenotypes in autism spectrum disorder via unsupervised machine learning. International Journal of Medical Informatics, 129, 29-36. https://doi.org/10.1016/j.ijmedinf.2019.05.006