Retinal Lipidomics Associations as Candidate Biomarkers for Cardiovascular Health

2025-08-05

AI Summary

This study addresses the knowledge gap between lipidomics and retinal microvascular phenotypes by investigating associations between serum lipid subclasses—free fatty acids (FFAs), diacylglycerols (DAGs), triacylglycerols (TAGs), and cholesteryl esters (CEs)—and quantitative retinal microvascular structural features. Method: Leveraging a large-scale healthy population cohort, we integrated deep learning–derived retinal microvascular metrics—including tortuosity, arteriolar/venular width, and fractal dimension—with targeted lipidomic profiling, thereby minimizing confounding from disease status or pharmacotherapy. Multivariable associations were assessed via Spearman correlation with false discovery rate (FDR) correction. Results: Elevated FFAs correlated significantly with increased vascular tortuosity; CE enrichment associated with widened arterioles and venules; conversely, DAGs and TAGs exhibited robust negative associations with microvascular width and structural complexity (e.g., reduced fractal dimension). These findings establish the retinal microvasculature as a noninvasive, sensitive biomarker of systemic lipid metabolism dysregulation, offering a novel paradigm for early metabolic risk screening.

Technology Category

• Computer Vision: Medical and Biological Imaging
• Machine Learning: Kernel Methods
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Retinal microvascular imaging is increasingly recognised as a non invasive method for evaluating systemic vascular and metabolic health. However, the association between lipidomics and retinal vasculature remains inadequate. This study investigates the relationships between serum lipid subclasses, free fatty acids (FA), diacylglycerols (DAG), triacylglycerols (TAG), and cholesteryl esters (CE), and retinal microvascular characteristics in a large population-based cohort. Using Spearman correlation analysis, we examined the interconnection between lipid subclasses and ten retinal microvascular traits, applying the Benjamini-Hochberg false discovery rate (BH-FDR) to adjust for statistical significance. Results indicated that FA were linked to retinal vessel twistiness, while CE correlated with the average widths of arteries and veins. Conversely, DAG and TAG showed negative correlations with the width and complexity of arterioles and venules. These findings suggest that retinal vascular architecture reflects distinct circulating lipid profiles, supporting its role as a non-invasive marker of systemic metabolic health. This study is the first to integrate deep learning (DL)derived retinal traits with lipidomic subclasses in a healthy cohort, thereby providing insights into microvascular structural changes independent of disease status or treatment effects.

Problem

• Investigates lipidomics links to retinal microvascular traits
• Explores serum lipid subclasses and retinal vessel characteristics
• Uses deep learning to analyze lipid profiles in healthy individuals

Innovation

• Deep learning-derived retinal traits analysis
• Spearman correlation for lipid-retinal links
• Benjamini-Hochberg FDR for significance adjustment