Translation Tool Deepens Data Pool

A partnership between the Mayo Clinic and the minds behind IBM's Watson technology is close to completing development of tools to mine data from electronic health records that speak different digital languages.

The goal is to "safely and securely convert stores of electronic health records into a bottomless pool of real-world clinical knowledge," the Mayo Clinic says in a news release. Reaching that goal requires the ability to glean information from a variety of EHRs that tag and store clinical information in different, often proprietary, digital formats.

So far, investigators with the Mayo-led team have used "natural language processing tools" to pull information from the records of 30 patients with diabetes and run it through computing systems developed with IBM's Watson Research Center, a process that transforms the data into 134 billion pieces of information, according to the clinic. (Watson is the language-recognition computer that recently won a Jeopardy! challenge against two of the game show's best human players.)

HHS believes that mining EHRs for clinical information can lead to improved care by allowing researchers to learn from trends and treatment successes across the country.

"This gets to the heart of meaningful use," says Lacey Hart, Mayo's SHARP administrator, in the news release. "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 one of four funded by the $60 million Strategic Health IT Advance Research Project (SHARP) program, an initiative of the U.S. Department of Health and Human Services through its Office of the National Coordinator for Health IT.