Abstract
AbstractMetabolomic platforms using nuclear magnetic resonance (NMR) spectroscopy can now rapidly quantify many circulating metabolites which are potential biomarkers of cardiovascular disease (CVD). Here, we analyse ∼170,000 UK Biobank participants (5,096 incident CVD cases) without a history of CVD and not on lipid-lowering treatments to evaluate the potential for improving 10-year CVD risk prediction using NMR biomarkers in addition to conventional risk factors and polygenic risk scores (PRSs). Using machine learning, we developed sex-specific NMR scores for coronary heart disease (CHD) and ischaemic stroke, then estimated their incremental improvement of 10-year CVD risk prediction when added to guideline-recommended risk prediction models (i.e., SCORE2) with and without PRSs. The risk discrimination provided by SCORE2 (Harrell’s C-index = 0.718) was similarly improved by addition of NMR scores (ΔC-index 0.011; 0.009, 0.014) and PRSs (ΔC-index 0.009; 95% CI: 0.007, 0.012), which offered largely orthogonal information. Addition of both NMR scores and PRSs yielded the largest improvement in C-index over SCORE2, from 0.718 to 0.737 (ΔC-index 0.019; 95% CI: 0.016, 0.022). Concomitant improvements in risk stratification were observed in categorical net reclassification index when using guidelines-recommended risk categorisation, with net case reclassification of 13.04% (95% CI: 11.67%, 14.41%) when adding both NMR scores and PRSs to SCORE2. Using population modelling, we estimated that targeted risk-reclassification with NMR scores and PRSs together could increase the number of CVD events prevented per 100,000 screened from 201 to 370 (ΔCVDprevented: 170; 95% CI: 158, 182) while essentially maintaining the number of statins prescribed per CVD event prevented. Overall, we show combining NMR scores and PRSs with SCORE2 moderately enhances prediction of first-onset CVD, and could have substantial population health benefit if applied at scale.
Publisher
Cold Spring Harbor Laboratory