IPCI Project
Integrated Preventive Cardiology Initiative (IPCI)
 |
Team Members: Rod Hayward, MD (PI) Jeremy Sussman, MD, MSc Brahmajee Nallamothu, MD, MPH Tim Hofer, MD, MSc Wyndy Wiitala, PhD Stephanie Visnic, BA Rose Ignacio, MS Jenny Burns, MHSA John Colozzi, BA Douglas Bentley, BA, MPH Funding: 7/1/2018 – 6/30/2022 Partners: VA Office of Reporting, Analytics, Performance Improvement, and Deployment (RAPID); VA Office of Specialty Care Services |
Background: Cardio-cerebrovascular Disease (CVD) is the leading cause of both morbidity and mortality in VHA, the nation, and worldwide, while also remaining a leading cause of ethnic and socio-economic mortality disparities. CVD also has excellent evidence for benefit from multiple treatments, which influence multiple target conditions (including heart attacks, stroke, congestive heart failure, and renal disease). Further, the risk factors for the different conditions and the treatment effects on these conditions vary substantially. Yet treatment guidelines remain simplistic and are not integrated across risk factors or conditions. For a given patient, which condition should be targeted? When is the best time to intervene? Which of the available treatments should be tried first? The National Heart, Lung, and Blood Institute set out to resolve this challenge five years ago, but abandoned the effort to create integrated guidelines, mainly due to the absence of data needed to direct integrated CVD prevention and treatment. Sophisticated probabilistic, risk prediction models are needed to tackle this problem.
Objectives: This 4-year study is designed to substantively improve primary CVD treatment choices by dramatically advancing how we use existing historical clinical data to integrate the alternative treatment options. In Aim 1, we will analyze 13-years of longitudinal electronic health record (EHR) data on Veterans age 45 to 80 using data from national VA datasets and focused medical record reviews. We will test a series of hypotheses trying to quantify the relationships of risk factors to different CVD outcomes and to improve patients’ risk stratification, a key factor for estimating absolute risk reduction from treatment. In Aim 2, we will test the validity and possibility for improving the findings of Aim 1. In Aim 3, we will evaluate an approach to predict risk-reduction from integrating anti-hypertensive, lipid-lowering, and antiplatelet therapies simultaneously, based on treatment effects obtained from high-quality randomized trials on CVD prevention.
Besides producing guidelines for treatment that can reduce premature mortality from CVD, this work will serve as a model for how historical clinical data can be used to better predict risk and personalize care, not just for CVD but for other conditions. In particular, the methods can be used to optimize policy models/guidelines for sequential decision-making for other chronic diseases that have multiple candidate treatments with differential effects on multiple potential complications. 
