Risk Stratification of Patients with Atherosclerotic Cardiovascular Disease (ASCVD)
Approved Research ID: 81959
Approval date: May 23rd 2022
Patients with prior heart disease or stroke are at increased risk of having a repeat event, with approximately 1 in 5 patients experiencing or dying from repeat events. However, there is a range of risk for patients, and a clear need exists for identifying those who are at higher risk of events despite taking medication. We propose to apply new artificial intelligence methods to develop a free and publicly available computer program that will calculate each patient's long-term chance of having or dying from a repeat heart attack or stroke based on his or her individual risk profile.
Current Scope: "This study will address an important unmet need for better risk stratification tools for patients with ASCVD. This would aid in identifying higher risk ASCVD patients, more likely to suffer a recurrent event, and could be used to tailor novel and costly risk reduction strategies to higher risk patients. In this study, we will utilize advanced statistical and machine learning (ML) methods to develop a model for predicting cardiovascular risk among patients with ASCVD. Our aim is to use advanced computational methods to design and train an artificial neural network for predicting recurrent ASCVD events among patients with prior ASCVD. We hypothesize that these computational approaches could be used to develop and validate a personalized risk assessment for patients with ASCVD. This project will contribute clinically meaningful and readily applicable results to directly impact a common clinical problem with high morbidity and cost burden. We will assume participant has prior ASCVD if they had an a history of myocardial infarction, coronary artery disease. ischemic stroke, peripheral arterial disease, arterial revascularization or transient ischemic attack prior to baseline."
Added new scope: the scope of this project stays the same but we would like to add new predictors variables to it. We plan to integrate images into the prediction model of the recurrent ASCVD events. We will work with raw ("bulk") image data and this is why we request an upgrade to a new Tier (Tier 3).