Predicting brain age in children aged 2-6 years with autism spectrum disorders using routine T1- and T2-weighted magnetic resonance imaging.
Authors
Affiliations (3)
Affiliations (3)
- Department of Radiology Beijing Children's Hospital Capital Medical University National Center for Children's Health China.
- School of Biomedical Engineering Faculty of Medicine Dalian University of Technology Dalian Liaoning China.
- School of Software Dalian University of Technology Dalian Liaoning China.
Abstract
Early childhood (ages 2-6 years) represents a dynamic phase of brain maturation and a critical window for the emergence of neurodevelopmental disorders, such as autism spectrum disorder (ASD). However, the maturational patterns of the brain during this period remain underexplored, especially regarding the utility of routine clinical imaging. To develop a brain age prediction model using routine magnetic resonance imaging (MRI) and characterize maturational deviations in children with ASD. We retrospectively collected MRI data from 2010 typically developing children (TDC) and 822 children with ASD (aged 2-6 years). A brain age prediction model based on T1- and T2-weighted MRI was developed using machine learning algorithms in the TDC cohort and subsequently applied to the ASD cohort. Model performance was assessed using the mean absolute error (MAE) and Pearson's correlation coefficient (PCC). Brain age difference (BAD) was compared between the two groups, followed by age-matched analyses and age-stratified comparisons. The Ridge regression model demonstrated a robust performance in the TDC testing set (MAE = 0.526 years, PCC = 0.812) and showed comparable predictive performance in the ASD cohort (MAE = 0.497 years, PCC = 0.775). Age-matched analysis revealed significantly delayed brain maturation in ASD patients compared with TDC patients (<i>P</i> < 0.001). Stratified analysis identified nominal delays in ASD subgroups aged 3-4 years and 4-5 years, with a trend toward relatively advanced predicted brain age by ages 5-6 years. This routine MRI-based brain age prediction model demonstrated good performance, with low prediction error and high correlation between predicted and chronological age, in estimating the brain age of TDC and ASD. It revealed a dynamic, age-related pattern in children with ASD, highlighting developmental heterogeneity across early childhood.