With a data warehouse's foundational architecture in place as part of the University of Pittsburgh Medical Center's $100 million analytics effort, researchers recently were able to electronically integrate clinical and genomic information on 140 breast cancer patients.
The researchers are trying to determine whether there are differences between pre-menopausal and post-menopausal breast cancer. They started with just two types of data: gene expression and copy number variant data, measuring changes in the amount of DNA. But they expect to add many more, according to an announcement.
UPMC plans to mine and integrate massive amounts of data, including clinical, genomic, proteomic, imaging and financial that previously resided in separate information systems. Combining the different datasets will allow researchers to analyze dozens of variables.
"The integration of data, which is the goal of the enterprise data warehouse, allows us to ask questions that we just simply couldn't ask before," said Adrian Lee, a professor in the Department of Pharmacology and Chemical Biology and director of the Women's Cancer Research Center.
The de-identified information on the 140 patients chosen to test the data warehouse previously was submitted to the federally funded multi-center project called The Cancer Genome Atlas.
The first phase of the five-year project is expected to be completed in the spring of 2014.
Cancer researchers working toward offering personalized treatments increasingly turn to technology in their attempts to harness big data. For instance, researchers at Washington University in St. Louis, with algorithms created by computer scientists from Brown University, are cataloging genetic mutations that lead to acute myeloid leukemia.
The American Society of Clinical Oncology, as well as Public Health England, also have massive databases in the works as they strive to better understand how cancer develops and the best ways to fight it.
To learn more:
- read the announcement