Amira Claxton / Mathematics / Faculty Mentor: Alicia Prieto-Langarica
Breast cancer is the second most common cancer and the leading cause of death among women worldwide. To combat this, the United States Preventative Service Task Force (USPSTF) has suggested that women get biennial mammograms starting at age 40 and continue to do so until the age of 74. Despite these preventative measures however, mortality rates, particularly in women of color, remain high. This fact is due to the daunting cost of the procedure, which makes continuous access to them difficult for lower income communities whose residents either lack medical insurance or only have access to low-quality health care. Consequently, women of color, primary residents of the aforementioned communities, are less likely to seek medical attention relating to breast cancer which in turn leads to them being diagnosed with higher stages of the disease, ultimately leading to their death. Our research utilizes machine learning algorithms to determine how often women should receive a mammogram based on biological and lifestyle risk factors. We establish a point system to determine an individual patient’s inherent risk of getting breast cancer based on these risk factors and use unsupervised clustering algorithms to place the patients in different screening categories based on their accumulated points. It is our hope that the system will increase awareness by providing a free source of knowledge to all women on their inherent risk to contract the disease, reducing breast cancer related deaths and simultaneously decreasing unnecessary spending on mammographic procedures.
Leave a Reply