A sparse proteomic risk score incorporating plasma MMP12 level improves prediction of abdominal aortic aneurysm.

Background: Screening criteria for abdominal aortic aneurysm (AAA) are based on clinical factors, such as age and smoking history, but do not include biological factors that may better reflect disease pathogenesis. Objectives: We sought to determine whether a proteomic risk score (ProRS) incorporating plasma protein abundance could improve prediction of AAA. Methods: We performed a cross-sectional analysis of nearly 37,000 participants in the UK Biobank Pharma Proteomics Project with plasma protein abundance data for 274 cardiometabolic proteins. ProRS models were developed using regularized regression. Results: The generated sparse ProRS contained well-established clinical risk factors as well as a single protein - matrix metalloproteinase 12 (MMP12). Overall performance and discriminatory utility of this model was higher than an identical model without MMP12 (difference in Brier score 2.1 × 10 Conclusions: A biologically-plausible ProRS incorporating a single matrix metalloproteinase improved prediction of AAA over clinical factors alone. These results may be used to enhance screening strategies for AAA.