Machine Learning for Longitudinal Brain-Age Prediction

Abstract

Cross-sectional brain age models have demonstrated high accuracy and reliability for predicting chronological age based on structural brain features derived from single MRI scans. However, these models cannot separate baseline variation from true aging-related changes or noise. Longitudinal models address this limitation by predicting inter-scan intervals from paired MRI scans, controlling for baseline factors through repeated measurements. Using OASIS-3 data, we compare a cross-sectional 3D CNN against three longitudinal architectures for predicting inter-scan intervals: LILAC (Siamese neural network), LILAC+ (enhanced Siamese network with multi-layer perceptron), and AM (variational autoencoder). Longitudinal models substantially outperformed the cross-sectional approach, with LILAC+ achieving best performance (MSE = 1.97 years^2, MAE = 0.99 years, r = 0.86, R^2 = 0.71). Our results suggest that direct modeling of longitudinal change is more effective at capturing individual aging trajectories than deriving intervals from cross-sectional predictions.