Subtyping Autism Spectrum Disorder With a Population Graph-Based Dual Autoencoder: Revealing Two Distinct Biotypes.

Researchers studied brain scans from 443 males with autism and found two distinct subtypes. One group (ASD1) had milder symptoms and weaker brain connections, especially in areas related to communication. The other group (ASD2) had different brain connection patterns linked to sensory and movement areas. This suggests autism isn't one condition but includes different subtypes with unique brain patterns, which could help develop more personalized treatments.

This study used advanced machine learning techniques to analyze brain scans and clinical data from 443 males with autism spectrum disorder (ASD). Researchers developed a novel graph-based dual autoencoder method to identify distinct ASD subtypes based on brain connectivity patterns. Two distinct biotypes were identified: ASD1 characterized by lower clinical symptom scores and reduced brain network integration with weaker connectivity, particularly affecting communication-related networks; and ASD2 showing greater network segregation with sensorimotor connectivity patterns linked to overall symptom severity. The study demonstrates that different autism subtypes have distinct brain network patterns, with biotype-specific relationships between brain connectivity and behavioral symptoms, potentially informing personalized treatment approaches.

Findings suggest autism assessment and intervention may benefit from subtype-specific approaches. Brain connectivity patterns could potentially guide treatment selection, with ASD1 requiring communication-focused interventions and ASD2 benefiting from sensorimotor-targeted therapies. However, clinical translation requires further validation studies.

Study limited to males only, reducing generalizability to females with ASD. Single-site study design may limit broader applicability. Cross-sectional design prevents understanding of subtype stability over time. Novel methodology requires validation in independent samples.

Autism spectrum disorder (ASD) is a neurodevelopmental disorder characterized by significant heterogeneity in clinical symptoms and underlying neurobiology. This study aimed to identify distinct ASD biotypes and uncover their neurobiological underpinnings using a novel graph-based subtyping approach. Resting-state fMRI and clinical data from 443 males with ASD (17.22 ± 8.63 years) were analyzed. We proposed a population graph-based dual autoencoder for subtyping (PG-DAS), a deep clustering framework that integrates imaging data and nonimaging data to extract deep features for biotype identification.

Statistical analyses were conducted to compare clinical scores and functional connectivity patterns between biotypes. Correlation analyses examined the associations between intra- and internetwork connectivity and clinical symptoms. Predictive modeling using support vector regression assessed the ability of network connectivity to predict clinical scores. Two distinct ASD biotypes were identified.

ASD1 exhibited significantly lower clinical scores and reduced network integration, characterized by weaker intra- and internetwork connectivity, particularly in core networks such as the cingulo-opercular network, linked to communication symptom scores. In contrast, ASD2 exhibited greater network segregation, with internetwork connectivity in sensorimotor-related networks correlating with total symptom scores. Predictive modeling further revealed biotype-specific brain-behavior associations, with ASD1 and ASD2 showing positive correlations with social and communication scores, respectively. This study underscores the critical role of biotype-specific brain network patterns in understanding ASD heterogeneity.

The proposed PG-DAS framework proved effective in ASD subtyping and holds promise for broader applications in exploring other neuroheterogeneous disorders.