Breast Cancer Coverage From Every Angle
Advertisement
Advertisement

Machine-Learning Prognostic Risk Model for African American Women With Breast Cancer

By: Celeste L. Dixon
Posted: Friday, November 30, 2018

In combination, four proteins identified in a machine-learning model may help to stratify high-risk African American patients with breast cancer with 86% accuracy—although the individual proteins did not have significant prognostic value. Based on the findings presented in New Orleans at the 2018 American Association for Cancer Research (AACR) Conference on The Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved (Abstract C101), this model retained its prognostic ability when the investigators controlled for clinicopathologic variables such as stage, age, and positive lymph nodes.

Finding paths to better clinical decision-making, potentially saving the lives of more African American women with breast cancer, is urgent, because their age-adjusted mortality rates are currently 40% higher than those of European American women despite similar incidence rates, the investigators noted. ‘We are excited that our model has the potential to inform clinicians to prioritize African American breast cancer patients for appropriate clinical trials and also help patients make decisions about enrolling in specific clinical trials,” commented Ritu Aneja, PhD, of the Georgia State University, Atlanta, in an AACR press release.

To create the model, the team in Dr. Aneja’s laboratory used gene-expression data from The Cancer Proteome Atlas and identified the combination composed of BCL2-like protein (BAX); inositol polyphosphate-4-phosphatase, type II (INPP4B); x-ray repair cross-complementing protein 1 (XRCC1); and cleaved poly (ADP-ribose) polymerase (c-PARP). The model could identify African American women whose risk of death was multiplied 11-fold, after controlling for variables including age and cancer stage.

Relatively soon, predicted Dr. Aneja, researchers will be able to “identify very specific patterns for understudied demographic groups to find high-risk patients, so they can be recruited for additional therapies.”



By continuing to browse this site you permit us and our partners to place identification cookies on your browser and agree to our use of cookies to identify you for marketing. Read our Privacy Policy to learn more.