API Offers Ability to Target Ebola with EHR App

A $15 million project, funded by the Office of the National Coordinator for Health IT to define an application programming interface for electronic health records, could turn EHRs into effective public health tools at the point of care in fighting Ebola.

Kenneth Mandl, M.D., professor at Harvard Medical School and chair of the informatics program at Boston Children's Hospital, led a four-year project to develop a SMART (Substitutable Medical Apps and Reusable Technologies) platform architecture that he argues is desperately needed in the current battle against Ebola to enable EHR systems to fill the gaps between public health and clinical care.

“You can actually implement the API based on existing old-fashioned electronic health records that were not designed to run apps or to have any kind of Internet capability,” Mandl told Health Data Management. “It turns out that you can retrofit these EHRs with the API and we’ve demonstrated it again and again and again.”

Critical to this effort is making EHRs work more flexibly so when workflows change and situations change, clinicians can modify the way data are displayed and entered, he says. The problem, according to Mandl, is that public health is largely locked out of the point of care that could provide clinical context for how to approach individual patients.  

“God forbid the Ebola virus mutates or we see that in certain populations it presents differently than others,” he warns. “We’ve never seen Ebola at the scale we’ve seen in West Africa. Hopefully, we don’t see it in any scale here. But, what we want to do is capture every patient no matter how they present right away.”

Mandl asserts that EHR-connected apps like the SMART platform can “connect the dots” between public health data and EHRs at the point of care, flagging patient characteristics that might not be important most of the time but which become critically important in emerging situations.

“What if, in the midst of a crisis in which workflows, policies, procedures, and operations must be altered, the Centers for Disease Control and Prevention (CDC) could distribute an app to emergency departments as easily as a software developer submits an app to the Apple App Store?,” asks Mandl in an Oct. 20 viewpoint article published online by JAMA. “The app could be updated, just as smartphone apps constantly are, as the CDC adapts to an evolving or different epidemic.”

Far from being science fiction, he makes the case that the standards-based SMART programming interface currently exists today to make this kind of CDC app a reality. The value of the SMART platform is that an app can be updated immediately, says Mandl. Because the web app would be based on HTML5, it can be developed rather simply in less than a week, he adds.

“The data that the CDC hangs on to very tightly and only publishes in JIFFS and JPEGS and summaries could really be used to drive a better understanding at the point of care about health and outbreaks,” says Mandl. “If you know that a patient is coming from a region that has a certain level of Ebola, you know a certain amount about their risk and that can be quantitatively transposed into decision support at the point of care for the clinician personalized to that patient for a contextualized approach based on real data.”

According to Mandl, SMART is currently being used in patient care—an app for patients with hypertension runs at Boston Children’s Hospital inside the Cerner EHR. And, multiple systems are running the API including Intermountain Healthcare’s longitudinal medical record, the core Cerner product, and a version of the Veterans Health Administration’s Vista EHR. In addition, an advisory committee has been convened to promote the adoption of SMART which includes the Centers for Medicare and Medicaid Services, major healthcare delivery systems like HCA, pharmaceutical companies such as Eli Lilly, and vendors like Surescripts.

(See also: EHR Vendors See Heightened Role in Ebola Fight)

“If you’re going to invest $48 billion in EHR adoption, reimagine EHRs as iPhone-like platforms,” advises Mandl. “Whether you’re using a Cerner or an Epic or an Allscripts, there should be an API that is standard that lets you run an app, add an app or delete an app—in other words run what we call a substitutable app on the electronic health record.”

“There is no way that a current stage electronic health record will be able to do this, but our EHR platform—this API—allows big data to be mashed up at the point of care,” he says.