Mediation Analysis for Sparse and Irregularly Spaced Longitudinal Outcomes with Application to the MrOS Sleep Study

2025-06-09

AI Summary

This paper addresses the challenge of mediation analysis involving high-dimensional mediators (e.g., lipidomic profiles) and sparsely, irregularly sampled longitudinal cognitive outcomes (e.g., cognitive decline in elderly men from the MrOS Sleep Study). Methodologically, it introduces a novel statistical framework integrating mixed-effects functional principal component analysis (to model longitudinal dependence), debiased Lasso (for high-dimensional mediator selection), and resampling-based false discovery rate (FDR) control (for multiplicity adjustment), enabling robust inference on mediation effects. Its contributions are threefold: (1) it overcomes key limitations of conventional mediation analysis—namely, assumptions of dense sampling and low-dimensional mediators; (2) applied to the MrOS data, it identifies significant lipid mediators (e.g., PC aa C34:2), revealing a novel biological pathway: “circadian disruption → dysregulated lipid metabolism → cognitive decline”; and (3) it substantially improves statistical power and mechanistic interpretability.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Kernel Methods
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Social Networks and Social Media: Analysis of web-mediated communications, communities, and crowds

Abstract

Mediation analysis has become a widely used method for identifying the pathways through which an independent variable influences a dependent variable via intermediate mediators. However, limited research addresses the case where mediators are high-dimensional and the outcome is represented by sparse, irregularly spaced longitudinal data. To address these challenges, we propose a mediation analysis approach for scalar exposures, high-dimensional mediators, and sparse longitudinal outcomes. This approach effectively identifies significant mediators by addressing two key issues: (i) the underlying correlation structure within the sparse and irregular cognitive measurements, and (ii) adjusting mediation effects to handle the high-dimensional set of candidate mediators. In the MrOS Sleep study, our primary objective is to explore lipid pathways that may mediate the relationship between rest-activity rhythms and longitudinal cognitive decline in older men. Our findings suggest a potential mechanism involving rest-activity rhythms, lipid metabolites, and cognitive decline, and highlight significant mediators identified through multiple testing procedures.

Problem

• Analyzing mediation with high-dimensional mediators and sparse longitudinal outcomes
• Identifying lipid pathways linking rest-activity rhythms to cognitive decline
• Addressing correlation in irregular cognitive measurements and high-dimensional mediators

Innovation

• Handles sparse irregular longitudinal data
• Manages high-dimensional mediator analysis
• Adjusts mediation effects for multiple testing