How VA Is Using Big Data to Keep Patients Out of the Hospital

Doctors combine assessment tools and analytics to address high-risk cases early.

The Partnership for Public Service and IBM Center for The Business of Government recently issued “From Data to Decisions III: Lessons from Early Analytics Programs,” which examines successful early government users of data to see how they got started, what sustained them and how the data was used to improve mission-critical programs.

The report identifies lessons learned to help federal leaders and managers avoid pitfalls, instill analytics faster and move more efficiently and effectively to create data-driven cultures.

The following case study, the second in a series of three excerpted from the report, examines how the Veterans Affairs Department uses data to minimize hospitalizations.

How VA Uses Data to Refine Patient Care

Outpatient care and services can keep patients out of the hospital and can keep them happier, healthier and alive longer, but doctors at the Veterans Health Administration did not always have the information they needed to make the most informed judgments.

Stephan Fihn, a primary care physician and head of VHA’s Office of Analytics and Business Intelligence, has begun to change this dynamic.

Fihn helped come up with the care assessments needs score, a predictive analytic tool intended to identify which of VHA’s 6.5 million primary care patients are at highest risk of hospitalization or death.

Now his office is creating an online care coordination tool, the patient care assessment system, which uses these assessment scores and hundreds of other data points to help 7,000 VHA medical teams coordinate 900 to 1,200 patients each.

“We have a [registered nurse] care coordinator. She’s got this list in front of her with patients who are at highest risk and she can go down it systematically now and say, ‘Oh I see Mr. So-and-So was in the hospital twice in the last month and he’s got a really high risk score and we’re not giving him any of these services. Maybe I will go talk with his primary care provider and figure out in our daily huddle which of his patients should be referred to one of these programs,’ ” Fihn says.

“It’s really changed the paradigm from a reactive one, where maybe in the end the only way we would see we were not doing it well was [high] hospitalization rates and we’d have to figure out why,” he says. “Now we’re looking at our patients at high risk of being in the hospital and saying, ‘What services can we provide to keep them out?’ ”

Both the scores and the assessment system draw from the 80 terabytes of patient statistics and other information collected in VHA’s corporate data warehouse, which sucks up data from electronic health records stored in the Veterans Health Information Systems and Technology Architecture at VHA medical facilities.

VISTA was created 20 years ago by rogue software tinkerers, many of them doctors, who saw in early personal computers an opportunity to improve how they managed and cared for patients.

The software they designed evolved into VISTA, which VHA offers free online. The electronic records system is one of the most widely used in the world. The presence of all that data has inspired VHA analysts to continue innovating and building tools to use it.

The data warehouse made the assessment scores and system possible, and helped VHA “do greater comparisons of our patients as they move across our system and as we see differences in treatment,” says Gail Graham, VHA’s deputy undersecretary for health for informatics and analytics, and Fihn’s boss.

She credits him with building the culture that makes data users out of VHA staffers at all levels. As a result, VHA employees refine and invent new uses for informatics products. The patient care assessment system, for example, was built for registered nurses in concert with registered nurses, who coordinate care for most teams, says clinical program manager Joanne Shear.

“Dr. Fihn’s office heard the hue and cry across the country: ‘How do we know exactly who we have to manage, how do we identify them? Where’s the tool that we can interact with the medical record?’ ”

System developers fully expect the assessment tool will morph as nurses use it, but only if they see it as a help, not a hindrance, says VHA health information technology lead Tami Box.

“The best and most optimized use remains be seen,” Box says. “We are trying to put tools in the hands of the people to use them and then find out how they use them in the best ways.”

To download the From Data to Decisions III: Lessons from Early Analytics Programs report, visit  

(Image via manaemedia/

NEXT STORY: A Federal Holiday Poem