Predicting breast cancer subtype outcomes and the driver mutations that lead to different subtypes

Started June 15, 2023

Abstract or project description

Breast cancer is most common type of cancer in women. There are several different subtypes of breast cancer and different subtypes have different prognosis and require different treatment. As routine breast exams and mammograms have become standard of care, the natural next step is now to improve the diagnosis to treatment process if a patient has an irregular breast exam and/or mammogram. One approach to fill this role may be using machine learning to predict patient prognosis and driver mutations. Driving mutations have become a very useful tool in helping determine treatment plan and as such, predictive tools that provide more information about patient's prognosis and better characterizes their subtype of breast cancer may help physicians provide better care. This project will cover both of these tasks. The first task will predict patient survival time and rates given subtype of breast cancer and patient demographics information. The second task will identify mutational drivers of these different subtypes to help determined the best treatment and help better understand how these cancers manifest, change, and drive pathology.