AI-Enabled Echocardiographic Biomarkers and Real-World Data for Predicting Cancer Therapy-Related Cardiac Dysfunction

External Institution: Kaiser Foundation Research Institute

External Collaborators: Elizabeth Feliciano, ScD (co-PI); David Ouyang, MD (co-PI); Andrew Ambrosy, MD (co-PI); Raymond Liu, MD; Joshua Nugent, PhD; Samir Thadani, MD

FDA Collaborators: Laleh Amiri-Kordestani, MD; Mori Krantz, MD; Abhilasha Nair, MD; Vaibhav Kumar, MD, MS; Hee-Koung Joeng, PhD

Date Started: 9/22/25

Regulatory Science Challenge 

Patients with a cancer diagnosis are more likely to develop heart issues compared to people who have not had cancer, partly due to side effects from cancer therapy. These heart issues, known as cancer therapy–related cardiac dysfunction (CTRCD), are difficult to detect early, and current monitoring methods are limited by lack of sensitivity, consistency, and personalization. 

Project Goals and Objectives

The objective of this proposal is to improve how CTRCD is monitored by combining artificial intelligence (AI) tools and real-world patient data from electronic health records (EHRs). The goals are to 1) test how well AI enabled models can detect early signs of CTRCD and 2) build and test new models that combine AI and EHRs to predict a patient’s risk of developing CTRCD. This work aims to improve CTRCD monitoring and prediction for individual patients.

For more detailed information on this project, please see this link.