Slalom is participating in the Publix Marathon, Half Marathon and 5K as part of our Q1 Slalom Cares Health and Wellness campaign to raise money for the American Cancer Society. Please join Slalom employees, clients, friends and family in supporting lifesaving research by donating to the cause.
Sunday, March 17 in Centennial Olympic Park
About Project Smile:
Last year, a team of Slalom consultants partnered with Google to provide Machine Learning technology to the American Cancer Society to help with breast cancer research. The team’s groundbreaking research identified patterns in breast cancer tissue images for ACS to analyze. The implications of the findings are profound, ranging from clarifying risk factors for breast cancer to providing insight to patient survival rate. ACS is now performing follow-up research on the findings and plans to use the platform as a foundation for future analysis.
Further details about the research:
At the American Cancer Society, our research focuses on identifying risk factors for breast cancer. Breast cancer, however, is not just one disease. To identify breast cancer risk factors it is critical to first classify the subtypes of breast cancer. There are many ways to classify cancers. Historically cancers were classified based on which proteins are turned on or turned off. For example, the estrogen receptor is key protein in most but not all breast cancers. Breast cancer cells without the estrogen receptor, commonly referred to as ER negative, are more aggressive than ER positive cancers. Women diagnosed with ER negative breast cancers have a poorer prognosis in part because there are few specialized treatments for these cancers beyond surgery, chemotherapy and radiation. ER negative breast cancers also are more likely to be diagnosed in younger women or African American women and have different risk factors than ER positive breast cancers.
Breast cancers can also be classified based on the morphological features of the breast cancer cells or in other words how the cells look under the microscope (what type of cells are there, how are they arranged, etc). Recently we were able to expand this area of research by digitizing images of the breast cancer tissue and partnering with Slalom Consulting. With Slalom's machine learning expertise, we are able to classify tumors based on novel features that cannot be distinguished by the human eye. In the upcoming months, we will be comparing the clinical characteristics, survival time, and risk factors among these novel features.
We would like to expand our work in these areas to examine the tumor tissue of newly diagnosed breast cancer cases in the Cancer Prevention Study cohorts and to look at additional protein pathways and digital features. Money collected through our fundraising efforts will go directly to these breast cancer projects.
The results of these projects will reveal new risk factors that can inform women for breast cancer prevention and risk prediction models, as well as new biological pathways that could lead to new drug targets for treatment or chemoprevention.