Data Science to Optimize Cardiovascular Disease Prevention (2024-2025)

This project team investigated how large-scale electronic health record data can be used to improve the understanding of risk factors and treatment strategies for cardiovascular disease. Using databases such as Truveta, which includes records from more than 100 million patients, the team explored questions related to predicting and preventing cardiovascular disease, the role of medications in shaping cardiovascular risk and how causal inference methods can inform treatment guidelines and policy. By leveraging both structured data and free-text medical notes, the team sought to identify novel risk factors, assess medication interactions and evaluate real-world management strategies.

The team produced four detailed statistical analysis plans and created a robust data analysis pipeline to support this work. One study is nearing completion with a manuscript in preparation, and two additional analyses are also advancing toward publication. Their efforts contributed to a successful grant application from the American Heart Association, focused on determining which patients might benefit most from new anti-obesity medications such as semaglutide (Wegovy) and tirzepatide (Mounjaro). These outcomes establish a strong foundation for continued research, with future work set to deepen insights into how real-world data can inform strategies to treat obesity, cardiovascular disease, and their connections to brain health.

Timing

Summer 2024 – Spring 2025

Team Outputs

Peer-reviewed manuscripts in progress

Grant proposal for the American Heart Association

See related Data+ summer project, Data Science to Optimize Cardiovascular Disease Prevention (2024).

Image: Coronary CT angiography of coronary arteries, by Oxford Academic Cardiovascular CT Core Lab and Lab of Inflammation and Cardiometabolic Diseases at NHLBI, NIH Image Gallery, , licensed under CC BY-NC 2.0