Tuesday, July 12, 2011
ROCHESTER, Minn. - Investigators with the Mayo Clinic-led SHARP project are close to finishing a suite of computing tools that can identify and sort digital health information from any electronic medical record, regardless of file format and data organization. Seeking to safely and securely convert stores of electronic health records into a bottomless pool of real-world clinical knowledge, dozens of experts in informatics, computer science and medicine attended a two-day conference at the University of Minnesota Rochester to highlight milestones of the SHARP initiative and identify future projects.
"The nation is hoping the SHARP community will deliver a product that will transform the way health information technology is used and thought about," said Christopher Chute, M.D., Dr. P.H., a Mayo Clinic epidemiologist and the principal investigator for Mayo's SHARP grant.
Mayo plays a leading role in the $60 million Strategic Health IT Advanced Research Projects (SHARP) program, which is funded by the U.S. Department of Health and Human Services. SHARP supports three major goals of electronic health information: better care for patients, better health for specific populations and lower health care costs.
"There is a huge ocean of information that has the potential to significantly improve delivery of care," said Wil Yu, the federal agency's SHARP program coordinator.
The information exists in the millions of electronic medical records kept in hospitals and clinics across the United States, but it is inaccessible as a single body of knowledge because there is no standard format for medical records.
Different hospitals and health information technology vendors tag and store health information in different formats - many of them proprietary. Mayo Clinic and the three research institutions also funded by SHARP are working on software to mine the data for best practices and statistical trends.
"This gets to the heart of meaningful use," said Lacey Hart, Mayo's SHARP administrator. "It's one thing to meet the government requirement that you should have an electronic record & but it's another thing, once you have that record, to make meaning out of it."
The project is ambitious: Eighty-nine experts from dozens of research institutions and the federal government attended a conference in late June at the University of Minnesota's Rochester campus. Areas covered ranged from informatics and computer science to medicine and administration.
To date, investigators have used natural language processing tools to isolate health information from about 30 medical records from patients with diabetes. When run through computing systems developed in partnership with IBM's Watson Research Center, those 30 patient records explode into 134 billion individual pieces of information to be organized and stored.
When working with sensitive records like patient information, researchers say they recognize that data privacy and security is paramount to a successful end product.
"The privacy of patient data is something we must hold in sacred trust," Dr. Chute said. "We want to do this as we partner with the communities, rather than exploit them."
The three other research Areas funded by the ONC's SHARP grants are:
- University of Illinois at Urbana-Champaign, Area 1, security of health information technology
- University of Texas Health Science Center at Houston, Area 2, patient-centered cognitive support
- Harvard University, Area 3, health care application and network platform architectures