Advancing Equitable Risk-based Breast Cancer Screening and Surveillance
in Community Practice
Breast cancer remains the second leading cause of cancer death in United States women, with racial and ethnic disparities in breast cancer stage at diagnosis, rates of second breast cancers, and mortality. Our program follows the premise that screening and surveillance are most effective and equitable when all women have access to high-quality risk assessment and breast imaging, and when screening and surveillance strategies are targeted to clinically meaningful outcomes. There are three parts to this study.
Project 1
The aim of this project is to develop equitable advanced breast cancer risk models that incorporate imaging features, artificial intelligence (AI) algorithms, and clinical factors. As well as compare the benefits and harms of targeted screening frequency and supplemental MRI based on advanced cancer risk.
Project 2
This project takes a multilevel approach to identify woman-, neighborhood-, radiologist-, and facility-level factors that drive inequities in breast cancer screening performance and outcomes, and to explore whether targeted AI use and other interventions can improve population outcomes with attention to health equity.
Project 3
The last piece of this study focuses on improving surveillance imaging in breast cancer survivors through equitably predicting women at high risk of a surveillance failure (i.e. interval 2nd breast cancer), improving surveillance performance through AI, and examining social determinants of health as multilevel drivers of surveillance failures and targets for future interventions.
To accomplish these aims the VBCSS, in collaboration with the Breast Cancer Surveillance Consortium (BCSC) and CISNET computer simulation models will perform secondary analyses of data from breast imaging registries. The VBCSS will extract limited data sets from our registry to be pooled with data from our collaborators.
Please click here to access publications associated with this study
This project is funded by grant P01 CA154292 from the National Cancer Institute (NCI).