Ju Sun Part of $1.2M Grant to Study Role of AI in Breast Cancer Treatment

University of Minnesota-based researchers were recently awarded $1.2 million over the next four years from the National Cancer Institute (NCI). The funding will be used to help develop an innovative computational framework for artificial intelligence (AI)-driven healthcare research with imbalanced data. The general framework is expected to benefit most disease diagnoses and prognoses. In particular, it can be used to give a more precise and unbiased prediction of cardiotoxicity—any heart damage arising from cancer treatments—when treating breast cancer patients.

The study is led by Rui Zhang, a Masonic Cancer Center researcher and founding division chief of the Division of Computational Health Sciences at the U of M Medical School, and Ju Sun, computer science assistant professor in the University of Minnesota’s College of Science and Engineering, alongside Ying Cui, an assistant professor at University of California - Berkeley.

“The primary goal of the study is to solve an inevitable data problem with medical big data,” said Zhang. “The data we use in cancer research is often not balanced, meaning that there are not equal numbers of patients with different health outcomes,” he added. “This is problematic, as imbalances in these numbers can lead to inaccurate or biased results drawn during research.”

With this study, Zhang, Sun, and Cui aim to create innovative AI methods that will learn from this imbalanced data.

“Using different types of medical records from patients across clinics and health systems, we will derive novel AI solutions to mitigate biases and boost prediction accuracy in imbalanced biomedical data. We will particularly benchmark and optimize these developments on the prediction of cardiotoxicity among the patients with breast cancer,” said Sun.

If they succeed, doctors around the world will be able to more accurately predict heart issues in patients with breast cancer.  

“The technology at our disposal today is unprecedented. We’re excited and proud that the University of Minnesota is leading the way in using AI to anticipate post-treatment health challenges for breast cancer survivors,” Sun added.

The study team is currently collecting and pre-processing electronic health records for patients with breast cancer as well as developing novel optimization methods to deal with imbalanced data. Going forward, future research will examine foundational methods in multiple data modalities with the real-world data.