Project 445780

Cardiovascular disease (CVD) remains the most common cause of death in patients with systemic lupus erythematosus (SLE), a multi-system autoimmune disease that disproportionately affects women and young people. The precise mechanism of heightened CVD risk in SLE is unknown; however, it is thought to be related to inflammation from the disease itself and medications used to treat the disease. Existing tools to predict CVD risk designed for the general population only consider traditional risk factors such as high blood pressure, so unsurprisingly, they perform poorly in SLE patients. While some specific SLE models have been developed using traditional statistical methods, they are not routinely used by doctors in practice due to poor accuracy, complex calculations, and have not been widely tested. Accurately identifying which SLE patients are at highest risk of CVD events is essential to correctly allocating preventive care. Our project, SLE-CALCULATOR, will be the first to develop and test a risk prediction tool for CVD that is specific to SLE using advanced computer algorithms to identify patterns using thousands of data points, a method known as machine learning. It will incorporate known traditional CVD and SLE risk factors and blood tests in a large international dataset of approximately 3,000 SLE patients from the Brigham and Women's Hospital and Systemic Lupus Erythematosus International Collaborating Clinics cohorts. We will also test for novel lupus blood tests associated with increased risk of clotting (anti-beta2-glycoprotein I Domain 1 and anti-phosphatidylserine/prothrombin antibodies) to determine whether they should be included in the tool. The study will provide greater insights into the pathogenesis of CVD in SLE and potentially identify novel treatment targets for inflammation and atherosclerosis. Our CVD risk calculator designed specifically for SLE will be made available and accessible online to doctors and patients in clinical care.