AI-enabled multimodal and cardiovascular imaging biomarkers for precision cardiovascular care.
Section of Cardiovascular Medicine · Yale School of Medicine
We develop and clinically translate AI-enabled digital biomarkers — harnessing computer vision and statistical machine learning to advance precision phenotyping across the cardiovascular disease spectrum. Our goal is scalable, cost-effective tools that integrate seamlessly into routine clinical workflows to improve diagnosis, risk stratification, and therapeutic decision-making.
Building imaging-derived features from echocardiography, CT, and ECG that capture disease biology invisible to the human eye — and translating them into scalable clinical tools.
Decoding how epicardial and perivascular fat encode early cardiovascular risk through radiomic and deep learning analysis of routine CT scans.
Using data-driven subgroup discovery to identify who benefits most from therapy — reshaping how we design, enrich, and interpret cardiovascular trials.
Integrating imaging, electrophysiology, and the electronic health record into deployable AI systems that work at the point of care, at scale, and for everyone.
We are open to undergraduate and graduate students, medical students, residents, fellows, postdoctoral researchers, and faculty collaborators who want to build clinically grounded AI and digital phenotyping tools with clear translational potential. If our work resonates with you, we'd love to hear from you.