Personalized functional topography–based multisite brain age prediction modeling reveals divergent neurodevelopment in major depression
- Chenxuan Pang
- Xiaoyi Sun
- Jianlong Zhao
- Xinyuan Liang
- Lianglong Sun
- Qixiang Lin
- Jinrong Sun
- Xiaowen Lu
- Qiangli Dong
- Liang Zhang
- Xiaoqin Wang
- Dongtao Wei
- Yuan Chen
- Bangshan Liu
- Chu-Chung Huang
- Yanting Zheng
- Yankun Wu
- Taolin Chen
- Yuqi Cheng
- Xiufeng Xu
- Qiyong Gong
- Tianmei Si
- Shijun Qiu
- Ching-Po Lin
- Jingliang Cheng
- Yanqing Tang
- Fei Wang
- Jiang Qiu
- Peng Xie
- Lingjiang Li
- Yong He
- Mingrui Xia
2026-03-11
Major depressive disorder (MDD) is associated with widespread alterations in functional brain networks across the lifespan. However, heterogeneity in atypical brain development among patients with MDD remains largely uncharacterized. Using a multisite resting-state functional MRI dataset consisting of 1,105 MDD patients and 1,065 healthy controls, we constructed a harmonized multicenter brain age prediction model based on individualized functional topography and identified two patient subgroups with positive or negative brain age gaps (BAGs). In patients with a positive BAG (BAG+), expansion of the salience network (SAL) into the dorsolateral prefrontal and ventrolateral prefrontal cortices, in addition to contraction of the sensorimotor and dorsal attention networks (DAN), contributes to accelerated brain aging. Conversely, in the negative BAG (BAG−) group, SAL expansion into the orbitofrontal cortex (OFC) and contraction of the visual and sensorimotor networks (SMN) were linked to delayed brain development. These subgroups also exhibited distinct neurodevelopmental trajectories. Clinically, BAG+ patients showed stronger associations between higher-order network topography and mood symptoms, whereas BAG− patients exhibited links between visual/default mode network topography and insomnia. At the molecular level, both groups showed enrichment of genes related to synaptic signaling but displayed distinct expression patterns and divergent expression trajectories in key neurodevelopmental gene sets. Notably, antidepressant treatment modulated the brain in ways that were specific to each subgroup. These findings reveal heterogeneous neurodevelopmental profiles in MDD with distinct biological and clinical signatures, offering insights into personalized precision medicine for this disorder.