Machine Learning Reveals Serum Sphingolipids as Cholesterol-Independent Biomarkers of Coronary Artery Disease

Background: Ceramides are sphingolipids that play causative roles in diabetes and heart disease, with their serum levels measured clinically as biomarkers of cardiovascular disease (CVD).

Methods: We performed targeted lipidomics on serum samples of individuals with familial coronary artery disease (CAD) (n = 462) and population-based controls (n = 212) to explore the relationship between serum sphingolipids and CAD, employing unbiased machine learning to identify sphingolipid species positively associated with CAD.

Results: Nearly every sphingolipid measured (n = 30 of 32) was significantly elevated in subjects with CAD compared with population controls. We generated a novel Sphingolipid Inclusive CAD risk score, termed SIC, that demarcates CAD patients independently and more effectively than conventional clinical CVD biomarkers including LDL-cholesterol and serum triglycerides. This new metric comprises several minor lipids which likely serve as measures of flux through the ceramide biosynthesis pathway, rather than the abundant deleterious ceramide species that are incorporated in other ceramide-based scores.

Conclusion: This study validates serum ceramides as candidate biomarkers of cardiovascular disease and suggests that comprehensive sphingolipid panels be considered as measures of CVD.