Three autism subtypes based on single‐subject gray matter network revealed by semi‐supervised machine learning

• Published in: Autism research 2024-10, Vol.17 (10), p.1962-1973
• Main Authors: Xu, Guomei, Geng, Guohong, Wang, Ankang, Li, Zhangyong, Liu, Zhichao, Liu, Yanping, Hu, Jun, Wang, Wei, Li, Xinwei
• Format: Article
• Language: English
• Subjects: Autism; autism spectrum disorders; Brain; Frontal gyrus; Graph theory; gray matter network; Heterogeneity; Machine learning; Precentral gyrus; Semi-supervised learning; semi‐supervised machine learning; Social organization; Substantia grisea
• ISSN: 1939-3792; 1939-3806; 1939-3806
• DOI: 10.1002/aur.3183

Autism spectrum disorder (ASD) is a heterogeneous, early‐onset neurodevelopmental condition characterized by persistent impairments in social interaction and communication. This study aims to delineate ASD subtypes based on individual gray matter brain networks and provide new insights from a graph theory perspective. In this study, we extracted and normalized single‐subject gray matter networks and calculated each network's topological properties. The heterogeneity through discriminative analysis (HYDRA) method was utilized to subtype all patients based on network properties. Next, we explored the differences among ASD subtypes in terms of network properties and clinical measures. Our investigation identified three distinct ASD subtypes. In the case–control study, these subtypes exhibited significant differences, particularly in the precentral gyrus, lingual gyrus, and middle frontal gyrus. In the case analysis, significant differences in global and nodal properties were observed between any two subtypes. Clinically, subtype 1 showed lower VIQ and PIQ compared to subtype 3, but exhibited higher scores in ADOS‐Communication and ADOS‐Total compared to subtype 2. The results highlight the distinct brain network properties and behaviors among different subtypes of male patients with ASD, providing valuable insights into the neural mechanisms underlying ASD heterogeneity. Lay Summary Autism spectrum disorder (ASD) is a complex condition characterized by challenges in social interaction and communication. The study aimed to explore different types or subgroups within individuals with ASD. We found three distinct subtypes among males with ASD, each showing unique patterns in the brain structure and behavior. These findings highlight the diversity within the ASD population and contribute to our understanding of the underlying brain mechanisms involved in ASD. Knowing these subtypes could help tailor interventions and treatments to better suit the specific needs of individuals with ASD, moving us closer to more personalized and effective approaches for support.