Modeling differences in neurodevelopmental maturity of the reading network using support vector regression on functional connectivity data

Read full text Summarise with VIRAT
Authors: Oliver H. M. Lasnick, Jie Luo, Brianna Kinnie, Shaan Kamal, Spencer Low, Natasza Marrouch, Fumiko Hoeft
Cited by: 0
References: 65

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Predicting chronological age from functional properties of the brain may be informative of children’s neurodevelopmental trajectories. Specifically, neurodevelopmental or learning disorders may be associated with atypical maturation of brain networks. In this study, we examine the relationship between reading disorder (RD) and maturation of functional connectivity (FC) in the brain using a cross-sectional sample of N = 742 participants aged 6-21 years. A support vector regression model was trained to predict chronological age from FC data derived from a whole-brain model as well as multiple ‘reduced’ models, which were trained on FC data generated from a successively smaller number of regions in the brain’s reading network. We hypothesized that the trained models would show systematic underestimation of brain network maturity for poor readers, particularly for the models trained with reading/language regions. Results showed that the most highly weighted regions/functional connections were derived from the default mode and frontoparietal control networks, in line with previous research. The trained whole-brain model implied that participants with RD have a larger brain-age gap (difference between real and predicted age) than controls with typical or advanced reading ability; however additional post-hoc testing only confirmed a tendency for relative over estimation of age in advanced readers in the older cohort. Overall, results suggest that while FC networks may be particularly susceptible to, or reflective of, variation/developmental deviation associated with reading ability, there is large individual variability in the examined population. • A machine learning model trained on functional data predicted participants’ ages • The model showed variability in age prediction accuracy based on reading skills • The model highly weighted data from frontoparietal and default mode regions • Neural markers of reading and language are diffusely represented in the brain

Fields of Study & Subjects

Functional Brain Connectivity Studies Reading and Literacy Development Developmental and Educational Neuropsychology

Publication details

Journal / source
Developmental Cognitive Neuroscience
Volume
79
Pages
101716–101716
Publication date
25 March 2026
Language
EN