Shared hidden-factor information framework for multiple behavioral tasks

2026-05-23

AI Summary

This study addresses the limitation of traditional cognitive-behavioral task analyses in major depressive disorder (MDD), which are typically conducted in isolation and overlook potential inter-task relationships. To overcome this, the authors propose the SHIFT framework, which introduces individual-specific shared latent factors into multi-task behavioral modeling for the first time. This approach jointly captures cross-task dependencies and temporal dynamics while accounting for individual heterogeneity and circumventing the computational burden of high-dimensional integration. Efficient parameter estimation is achieved through an expectation-maximization algorithm combined with variational approximation. Simulation studies demonstrate that the method substantially improves both estimation accuracy and computational efficiency. When applied to MDD data, the identified shared parameters exhibit treatment-modulated patterns, suggesting their potential as novel behavioral biomarkers.

Abstract

Understanding cognitive processes in major depressive disorder (MDD) often relies on behavioral tasks, which are typically analyzed separately, overlooking potential correlations and shared latent structure. To address this limitation, we propose the Shared Hidden-factor Information Framework for Multiple Behavioral Tasks (SHIFT), a joint modeling approach that leverages shared information across tasks, allowing each task to benefit from information learned by the others. SHIFT introduces subject-specific latent factors that capture cross-task dependencies while accommodating individual heterogeneity in decision-making, response times (RTs), and strategy switching. To address computational challenges without requiring high-dimensional integration, we develop an expectation-maximization with variational approximation algorithm that preserves both temporal structure and between-task dependencies. Through extensive simulation studies, we demonstrate that SHIFT substantially improves estimation accuracy and efficiency relative to single-task analyses. We then apply SHIFT to a study of MDD to jointly model the Probabilistic Reward Task (PRT) and the Flanker Task (FT). Results indicate that MDD participants show lower engagement in the PRT and reduced focus in the FT compared with healthy controls. Moreover, when individuals are engaged and focused, they exhibit longer RTs. Although observed RTs do not predict treatment response, the shared parameters recovered by SHIFT showed suggestive treatment-modulation patterns, indicating their potential as exploratory behavioral markers for therapeutic outcomes.

Problem

• major depressive disorder
• behavioral tasks
• shared latent structure
• cross-task dependencies
• cognitive processes

Innovation

• joint modeling
• shared latent factors
• variational EM algorithm
• cross-task dependencies
• behavioral biomarkers