Adaptive Shrinkage Estimation For Personalized Deep Kernel Regression In Modeling Brain Trajectories

2025-04-10

AI Summary

Longitudinal brain imaging studies face challenges in estimating regional volumetric trajectories due to sparse and irregularly sampled data, cross-scanner heterogeneity, and substantial inter-individual biological variability. To address these issues, we propose an uncertainty-aware personalized deep kernel regression framework. First, we introduce an adaptive Bayesian shrinkage mechanism that dynamically integrates population-level priors with subject-specific dynamics. Second, we employ a deep kernel Gaussian process to model nonlinear developmental or degenerative trajectories while enabling alignment and calibration of multi-source longitudinal data. Third, the framework delivers interpretable predictions with principled uncertainty quantification. Evaluated on three independent neuroimaging cohorts, our method significantly outperforms linear mixed-effects models, generalized additive models, and state-of-the-art deep learning approaches across MAE, RMSE, and calibration error metrics, demonstrating strong generalizability. The implementation is publicly available.

Technology Category

• Machine Learning: Kernel Methods
• Reasoning under Uncertainty: Relational Probabilistic Models
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Longitudinal biomedical studies monitor individuals over time to capture dynamics in brain development, disease progression, and treatment effects. However, estimating trajectories of brain biomarkers is challenging due to biological variability, inconsistencies in measurement protocols (e.g., differences in MRI scanners), scarcity, and irregularity in longitudinal measurements. Herein, we introduce a novel personalized deep kernel regression framework for forecasting brain biomarkers, with application to regional volumetric measurements. Our approach integrates two key components: a population model that captures brain trajectories from a large and diverse cohort, and a subject-specific model that captures individual trajectories. To optimally combine these, we propose Adaptive Shrinkage Estimation, which effectively balances population and subject-specific models. We assess our model's performance through predictive accuracy metrics, uncertainty quantification, and validation against external clinical studies. Benchmarking against state-of-the-art statistical and machine learning models -- including linear mixed effects models, generalized additive models, and deep learning methods -- demonstrates the superior predictive performance of our approach. Additionally, we apply our method to predict trajectories of composite neuroimaging biomarkers, which highlights the versatility of our approach in modeling the progression of longitudinal neuroimaging biomarkers. Furthermore, validation on three external neuroimaging studies confirms the robustness of our method across different clinical contexts. We make the code available at https://github.com/vatass/AdaptiveShrinkageDKGP.

Problem

• Estimates brain biomarker trajectories despite biological variability and measurement inconsistencies
• Balances population and individual models for personalized brain trajectory forecasting
• Validates robustness across diverse clinical contexts and neuroimaging studies

Innovation

• Personalized deep kernel regression framework
• Adaptive Shrinkage Estimation for balancing models
• Integration of population and subject-specific models