Stratifying ASD and characterizing the functional connectivity of subtypes in resting-state fMRI.

Researchers studied brain scans from 415 autistic people and found two distinct groups: those with more severe autism symptoms and those with moderate symptoms. The severe group showed different brain connection patterns, while the moderate group looked more similar to non-autistic people's brains. The researchers created a computer program that could identify which group someone belonged to with 75% accuracy based on their brain scan.

This neuroimaging study examined brain connectivity patterns in two distinct autism subtypes using resting-state fMRI data from 415 autistic individuals and 574 neurotypical controls. Participants were classified into Cluster-1 (severe impairment) and Cluster-2 (moderate impairment) based on ADI-R scores. Cluster-1 showed increased local brain connectivity but decreased remote connectivity, with widespread connectivity differences compared to controls. Cluster-2 displayed connectivity patterns more similar to neurotypical individuals, except for specific impairments in midcingulate cortex connections.

A machine learning model achieved ~75% accuracy in identifying autism subtypes based on brain connectivity patterns, suggesting distinct neurological profiles underlying different clinical presentations of autism.

Findings support the concept of autism subtypes with distinct brain connectivity patterns, which may inform personalized approaches to assessment and intervention. However, the clinical utility of neuroimaging-based subtyping requires further validation and improved accuracy before implementation in practice.

Single neuroimaging study using retrospective data analysis. Machine learning accuracy of 75% may be insufficient for clinical application. Validation was conducted but generalizability to broader populations unclear. No information provided about intervention implications or longitudinal outcomes.

Although stratifying autism spectrum disorder (ASD) into different subtypes is a common effort in the research field, few papers have characterized the functional connectivity alterations of ASD subgroups classified by their clinical presentations. This is a case-control rs-fMRI study, based on large samples of open database (Autism Brain Imaging Data Exchange, ABIDE). The rs-MRI data from n = 415 ASD patients (males n = 357), and n = 574 typical development (TD) controls (males n = 410) were included. Clinical features of ASD were extracted and classified using data from each patient's Autism Diagnostic Interview-Revised (ADI-R) evaluation.

Each subtype of ASD was characterized by local functional connectivity using regional homogeneity (ReHo) for assessment, remote functional connectivity using voxel-mirrored homotopic connectivity (VMHC) for assessment, the whole-brain functional connectivity, and graph theoretical features. These identified imaging properties from each subtype were integrated to create a machine learning model for classifying ASD patients into the subtypes based on their rs-fMRI data, and an independent dataset was used to validate the model. All ASD participants were classified into Cluster-1 (patients with more severe impairment) and Cluster-2 (patients with moderate impairment) according to the dimensional scores of ADI-R. When compared to the TD group, Cluster-1 demonstrated increased local connection and decreased remote connectivity, and widespread hyper- and hypo-connectivity variations in the whole-brain functional connectivity.

Cluster-2 was quite similar to the TD group in both local and remote connectivity. But at the level of whole-brain functional connectivity, the MCC-related connections were specifically impaired in Cluster-2. These properties of functional connectivity were fused to build a machine learning model, which achieved ∼75% for identifying ASD subtypes (Cluster-1 accuracy = 81.75%; Cluster-2 accuracy = 76.48%). The stratification of ASD by clinical presentations can help to minimize disease heterogeneity and highlight the distinguished properties of brain connectivity in ASD subtypes.