Breast cancer is the most commonly diagnosed cancer among women worldwide. Patients diagnosed with breast cancer face the important question of what treatments to choose. While treatment decisions have become more refined over time, they are not yet personalized. Patients may be over or undertreated. A new award from the National Institutes of Health to the University of Pittsburgh aims to support the development of AI models to improve treatment for breast cancer patients.
The AI models will integrate data from different scales and timepoints from patients’ experiences (clinical variables, medical images, and genomics assays, from individual, macro-scale, to micro-scale and longitudinal). It will be sourced from a multi-center collaboration network consisting of the University of Pittsburgh, Duke University, and MD Anderson Cancer Center. The varied data input into the AI model will build the capacity to systematically and accurately assess a patient’s individual data to guide precision, more personalized, treatments of breast cancer.
The project leader, Shandong Wu, PhD, Professor at University of Pittsburgh and researcher at UPMC Hillman Cancer Center says, “This is an example of successful collaboration of a multidisciplinary AI team with data scientists, radiologists, pathologists, oncologists, surgeons, biologists, bioethicists, and biostatisticians to address a significant clinical challenge using advanced and ethical AI methods.”
The project is co-led by Adam Brufsky, MD, PhD, Professor of Medicine at the University of Pittsburgh and member of UPMC Hillman Cancer Center. It is funded at nearly $1.7M in its first year by the National Institutes of Health under Project Number 1OT2OD037972-01.
