CardioOnco-AI: AI-Empowered Cardiotoxicity Risk Prediction Among Breast Cancer Survivors Using Multi-Site Real-World Data

Problem and Need for the Study

While breast cancer treatments have dramatically improved the long-term survival of patients, more survivors have developed cardiovascular disease as a result of these treatment regimens. Existing cardiovascular risk prediction models rely on a limited number of variables and are not able to do individualized predictions.

There is a critical need to develop novel, AI-powered informatics frameworks to build, maintain, and enhance models that predict cardiovascular risk among breast cancer survivors across diverse health systems.

Innovation and Impact

The goal of this project is to develop a new, generalizable AI solution that uses multimodal real world data to improve cardiotoxicity risk prediction in breast cancer survivors.

The project will involve:

• Curating real world data sets that include information about the cancer and non-medical factors that impact health
• Developing and evaluating cardiotoxicity risk prediction models for breast cancer survivors across health systems
• Evaluating the generalizability of the framework at two large states