Diagnosis-informed neuro-subtyping reveals subgroups of autism spectrum disorder with reliable and distinct functional connectivity profiles.

Scientists studied brain scans from about 2000 people to better understand autism differences. They found two main autism subtypes: one group has brain areas that are over-connected, while the other has areas that are under-connected. These different connection patterns relate to autism symptoms in different ways. This discovery could help doctors provide more personalized treatments in the future.

This study used advanced computational methods to identify distinct autism subtypes based on brain connectivity patterns in approximately 2000 participants. Researchers employed a semi-supervised clustering approach (HYDRA) that outperformed traditional methods. Two reliable subtypes emerged: a hyper-connectivity subtype showing increased connections within and between brain networks, and a hypo-connectivity subtype displaying opposite patterns. The hyper-connectivity group showed stronger connections between attention and default mode networks but weaker connections between default mode and sensory networks.

Each subtype demonstrated different relationships between brain connectivity and autism symptoms, suggesting potential for personalized approaches to diagnosis and treatment.

Findings suggest autism heterogeneity can be systematically characterized using brain connectivity patterns. This may enable development of subtype-specific biomarkers and personalized treatment approaches. However, clinical translation requires validation studies and standardized implementation protocols.

Sample demographic characteristics not reported. Study methodology details limited in abstract. Clinical validation of subtypes and longitudinal stability unclear. Generalizability across different populations unknown.

Autism Spectrum Disorder (ASD) is a complex neurodevelopmental disorder characterized by heterogeneous symptoms and neurobiological features, which hinders the identification of reliable biomarkers. Until recently, ASD neuro-subtyping has emerged to detect neural features in each subgroup. We implemented neuro-subtyping of ASD using a semi-supervised clustering method, HeterogeneitY through DiscRiminative Analysis (HYDRA), guided by the labeling information of ASD/controls, together with a multi-scale dimension reduction method of high-dimensional input features. Functional connectivity was estimated as neural features for subtyping subjects from a large dataset with ∼2000 subjects.

Systematic evaluation of clustering performance was conducted and the semi-supervised approach was compared with unsupervised K-means, commonly used for neuro-subtyping, combined with different types of feature reduction methods. We successfully detected two clusters, the hyper-connectivity subtype and hypo-connectivity subtype, each exhibiting distinct connectivity patterns between and within large networks, with high reliability. The semi-supervised clustering approach demonstrated superior performance compared to the unsupervised approach. We observed cluster effect on functional connectivities, for instance, the hyper-connectivity cluster shows hyper-connectivity within major large networks and hyper/hypo-connectivities between networks, such as hyper-connectivity between default mode and attention networks, and hypo-connectivity between default mode and visual/auditory networks.

In contrast, the hypo-connectivity cluster displayed the opposite connectivity patterns. Furthermore, we found varying correlations between connectivities and main symptoms of ASD across subtypes. Our findings indicate that the semi-supervised approach has the potential to subtype ASD into distinct and reliable clusters. The clusters effectively differentiate heterogeneous neural markers based on functional connectivity patterns, meanwhile establish distinct neurobehavioral relationships across each subtype, which is a critical step towards developing individualized diagnosis and treatment strategies in the future.