Structured neural ode model predicts brain development from sparse data
DevelopmentODE: Structured Neural ODEs for Early Brain Development Dynamics Across a Decade
Machine Learning
Summary
Predicting how a child's brain develops over many years is hard because doctors only see each child a few times and at irregular ages. The authors created DevelopmentODE, a new model that learns common brain development patterns for a whole group while also understanding individual differences. It accounts for how brain changes speed up or slow down with age, using limited observations to forecast future brain connectivity. This method performs better than previous models when tested on brain scans taken over time.
What this means in practice
- •For clinical data analysts: Forecast individual brain connectivity changes from limited early clinical MRI scans to support neurodevelopmental assessments.
- •For mental health technology developers: Improve personalized brain development tracking in apps or tools that monitor child cognitive growth over years using sparse brain data.
Authors
Kaiqiao Han, Haitao Chen, Bryan Quah, Xiaoda Wang, Janelle Liu, John H Gilmore, Wei Gao, Yizhou Sun
Abstract
Understanding how individual brain development unfolds over childhood requires modeling developmental trajectories from sparse longitudinal observations. Long-term neurodevelopmental forecasting is challenging because each child is typically observed at only a few irregularly spaced visits, while developmental dynamics vary across individuals and age. Generic continuous-time models accommodate irregular timing but often absorb these factors into a single flexible transition function, providing little structure for how population progression, individual variability, and developmental age shape the dynamics. We propose DevelopmentODE, a structured continuous-time framework that organizes population- and subject-specific variation within a shared developmental geometry while allowing the governing dynamics to evolve with age. The model builds this geometry around a developmental canal representing the population trajectory, whose local direction provides a reference for organizing subject-specific variation. Subject deviation velocities are constrained relative to this direction, while a shared nonlinear deviation field captures individual developmental motion without disrupting population-level progression. DevelopmentODE further models developmental non-stationarity through ordered age-dependent deformations of the shared vector field, progressively adapting a common dynamical structure as age changes, while elapsed time determines the integration horizon. This formulation uses population-level developmental structure to guide learning from sparse individual trajectories while allowing dynamics to evolve smoothly with age. We evaluate DevelopmentODE on longitudinal fMRI by predicting future functional connectivity of the same child from earlier observations. DevelopmentODE consistently outperforms competing baselines across short- and long-horizon predictions.