AbstractThe neurobiology of heterogeneous neurodevelopmental disorders such as autism spectrum disorders (ASD) are still unclear. Despite extensive efforts, most findings are difficult to reproduce due to high levels of individual variance in phenotypic expression. To quantify individual differences in brain morphometry in ASD, we implemented a novel subject-level, distance-based method on subject-specific attributes. In a large multi-cohort sample, each subject with ASD (n=100; n=84 males; mean age: 11.43 years; mean IQ: 110.58) was strictly matched to a control participant (n=100; n=84 males; mean age: 11.43 years; mean IQ: 110.70). Intrapair Euclidean distance of MRI brain morphometry and symptom severity measures were entered into a regularised machine learning pipeline for feature selection, with rigorous out-of-sample validation and bootstrapped permutation testing. Subject-specific structural morphometry features significantly predicted individual variation in ASD symptom severity (19 cortical thickness features, p=0.01, n=5000 permutations; 10 surface area features, p=0.006, n=5000 permutations). Findings remained robust across subjects and were replicated in validation samples. Identified cortical regions implicate key hubs of the salience and default mode networks as neuroanatomical features of social impairment in ASD. Present results highlight the importance of subject-level markers in ASD, and offer an important step forward in understanding the neurobiology of heterogeneous disorders.
Quantifying individual differences in brain morphometry underlying symptom severity in Autism Spectrum Disorders
