ARPA-H Biomedical Data Fabric Toolbox


Biden-Harris Administration announces new ARPA-H program to make medical research findings easier to use to improve health outcomes for Americans

New ARPA-H project will allow biomedical research data to be more accessible for the development of advanced health innovations and breakthroughs

Today, the Biden-Harris Administration is announcing the launch of the ARPA-H Biomedical Data Fabric Toolbox, a project that will thread together research data across the country to help the scientific community find and share medical insights more easily, so that we break down data research siloes, learn from the experiences of more patients, and deliver health solutions to people more quickly. The ARPA-H Biomedical Data Fabric Toolbox will consolidate research from a variety of health disciplines into a common language to resolve the inconsistencies in how research data is currently stored and allow researchers to incorporate data in new ways that accelerate health innovations. Led by the Advanced Research Projects Agency for Health (ARPA-H), in partnership with additional agencies at the Department of Health and Human Services (HHS), this project supports the Biden Cancer Moonshot and the President’s Unity Agenda by modernizing America’s medical research capabilities to improve health outcomes for all.

“Our goal is to make biomedical research data easier for people to use,” said Jennifer Roberts, Ph.D., director of the ARPA-H Resilient Systems Office. “With the ARPA-H Biomedical Data Fabric Toolbox, we’re increasing the resolution of information that can be shared across the scientific community so that people can get the most from the wide array of existing research to find and share insights more quickly, more precisely, and more comprehensively. We aim to develop a single search engine that works for many types of data, with the hope that people can find answers to questions like ‘what causes cancer to spread quickly or slowly.’”

ARPA-H will initially partner with HHS agencies including the National Cancer Institute (NCI), National Center for Advancing Translational Sciences (NCATS), and the National Institute on Drug Abuse (NIDA) within the National Institutes of Health (NIH), Food and Drug Administration (FDA), and the Office of the National Coordinator (ONC) to guide the development and application of new approaches to incorporating unique data assets into emerging research that spans the entire health care sector.

“Currently, NCI’s data science activities focus on operationalizing data infrastructure platforms using established technologies to meet data sharing requirements,” said Dr. Erika Kim, Ph.D., NCI program lead on this effort. “The ARPA-H Toolbox will develop prototype technologies to minimize human effort needed to collect and explore data as well as opening opportunities to build a resource that spans a wide variety of health conditions.”

By pursuing intentionally aggressive goals, this effort will challenge the computer science and biomedical research communities to develop new search capabilities and uncover gaps that require further research, all while protecting patient privacy. For example, the ARPA-H Toolbox will make it easier to search across multiple types of data and retrieve more complete results, including by scoring how well the data represents the patient population.

“ARPA-H is committed to speeding solutions in health data science and building models that can be applied across disciplines, with the goal of getting better and faster solutions to the people that need them,” said ARPA-H Director Renee Wegrzyn, Ph.D. “Through our partnership across HHS and the broader health ecosystem, we aim to revolutionize the way we collect, analyze, and share biomedical research data.”

More information on the ARPA-H Biomedical Data Fabric including details about an upcoming solicitation will be available at the program's page.