Veterans Health Administration: EMR Foundation for Gains Data-Mining Benefits

For an industry driven by advanced knowledge and technological innovation, American health care is shockingly behind the curve on adoption of information technology. Only 1.5% of U.S. hospitals have adopted comprehensive electronic medical records systems (Jha et al., 2009). As of 2006, only 20% of U.S. hospitals had implemented electronic medical records (Arnst, 2006). The U.S. is lags behind several OECD countries in per capita spending on health IT (eHealth101, 2006) and is perhaps more than a decade behind international leaders in health IT (Anderson et al., 2006). Without serious investment in health IT, most American hospitals can’t take advantage of data mining.

An exception to this absence of data-mining capability is found in the Veterans Health Administration. The VA began developing the nation’s first functioning electronic medical record system in the late 1970s (Longman, 2009) and computerized medical records in all of its approximately 1300 facilities by 2000 (Arnst, 2006). VA hospitals using  VistA—Veterans Health Information Systems and Technology Architecture—constitute nearly half of the hospitals in the U.S. that have implemented comprehensive electronic medical records (Jha et al., 2009). With VistA, the VA has become the “unlikely leader” in maintaining electronic records that can be mined for insights that produce significant improvements in care and cost efficiency.

The VA has used data mining to improve practices in a number of ways. VA researchers have mined VistA data to target rewards for surgical teams that beat quality and safety benchmarks (and to identify underperforming surgical teams) and to sift through 12,000 medical records to evaluate and improve treatments for diabetes (Longman, 2009). The VA’s Center for Imaging of Neurodegenerative Diseases has used Weka to apply Random Forest and Support Vector Machine algorithms to brain imaging studies (Young, 2009). VA data mining also helped discover the link between arthritis medication Vioxx and heart attacks (Longman, 2009).

One obstacle to optimal data mining in VistA is the diversity of local data dictionaries. Local users can customize data dictionaries to meet unique local needs. That flexibility is a significant part of the system’s success (Brown et al., 2003). However, those different data dictionaries complicate efforts to combine and analyze data across the nationwide system. The VA’s efforts to create national standard dictionaries to translate local dictionaries support not only better immediate transactions such as e-prescribing (Brown et al. 2003) but improved large-scale data mining. The VA’s system has been sufficiently successful that other government hospitals in the U.S. and abroad are adopting and adapting VistA for their facilities (Longman, 2009).


Anderson, G. F., Forgner, B. K., Johns, R. A., & Reinhardt, U. E. (2006). Health Care Spending and Use of Information Technology in OECD Countries. Health Affairs, 25(3), 819–831.

Arnst, C. (2006, July 17). The Best Medical Care in the U.S. BusinessWeek. Retrieved August 1, 2009, from

Brown, S. H., Lincoln, M. J., Groen, P. J., & Kolodner, R. M. (2003). VistA—U.S. Department of Veterans Affairs National-Scale HIS. International Journal of Medical Informatics, 69(2–3), 135–156.

eHealth 101: Electronic Medical Records Reduce Costs, Improve Care, and Save Lives. (2006). American Electronics Association. Retrieved August 1, 2009, from

Jha, A. K., DesRoches, C. M., Campbell, E. G., Donelan, K., Rao, S. R., Ferris, T. G., et al. (2009). Use of Electronic Health Records in U.S. Hospitals. New England Journal of Medicine, 360(16), 1628–1638. doi: 10.1056/NEJMsa0900592.

Longman, P. (2009, August). Code Red: How Software Companies Could Screw up Obama’s Health Care Reform. Washington Monthly. Retrieved August 1, 2009, from

Rundle, R. (2001, December 10) In the Drive to Mine Medical Data, VHA Is the Unlikely Leader. Wall Street Journal, New York, p. 1.

Young, K. (2009). Diagnostic Data Mining for Multi-modal Brain Image Studies. Veterans Health Administration Center for Imaging of Neurodegenerative Diseases. Retrieved August 2, 2009, from


VistA works. No, not Microsoft Vista, but VistA, the  Veterans Health Information Systems and Technology Architecture. VistA is an open-source collection of a hundred modules built by the Veterans Administration’s own doctors, nurses, and programmers over the last thirty years. It is a model of bottom-up innovation and local customization. It has also turned the VA from the object of media/movie horror stories to the best health care provider in America.

The open-source nature of VistA allowed it to win much easier acceptance from VA staff across the country because, if they found it was making their work more difficult, they could rip out the guts and make it work. If they discovered missing functionality, they could create it to suit their needs. One brilliant innovation, a bar-coding system that has cut medication errors and saved thousands of lives, was designed by Topeka VA nurse Sue Kinnick after she saw how slick the bar-coding system worked at a car rental place. Kinnick didn’t have to get approval from anyone outside her facility; she turned the idea into software, her facility tried it out, and it worked well enough to win converts throughout the system. No one had to force the bar-coding scheme on anyone; other VA hospitals gladly adopted it and adapted it to their own needs. That’s how open-source works: give folks the independence to try out diverse ideas in a decentralized system, maintain a mechanism that will allow you to aggregate those ideas, and the wisdom of crowds will often produce pretty good solutions.

Diversity of ideas, independence, decentralization, and aggregation: those don’t exactly sound like values consistent with the federal government. Indeed, when VistA’s predecessor code started bubbling up from ground-floor VA staff in the late 1970’s, the government tried to kill it. VA uppity-ups favored an official, centralized computerization program that was also in development. It took an act of Congress (thank you, Rep. Sonny Montgomery) to make VistA the official VA system in the early 1980s.

But now the VA appears bent on killing this golden goose. On May 26, the VA issued a memorandum ordering a moratorium on all “Class III” (i.e., local and collaborative) VistA development. Citing safety concerns, the VA declared that, bascially, all VistA development must be approved by Washington. Goodbye open source, hello centralization.

Rick Marshall sees this move as another step in a 15-year effort to squash the open-source, local-control programming that has served VA so well. Why would the VA give short shrift to the actual needs of its staff and patients?

This bureaucracy is under no obligation to listen to user requests. Instead, it listens to Congress, which listens to campaign contributors who lobby to replace VistA with their own software. And so the VistA bureaucracy has become obsessively focused on its own grand vision: replacing VistA with something more centralized and vendor-friendly. In the name of “modernization,” with Congress’ blessing, national development has poured most of its resources into a series of unwanted, unrealistic pork-barrel replacement projects that have squandered several billion dollars so far and left only failure, waste and demoralization behind.

With national development consumed by the replacement craze, users have relied on local developers to meet many of their actual VistA needs. Though most “local” developers have already been conscripted to assist in national development, many have continued to do local development on the side in an attempt to respond to the most urgent of their users’ requests.

This new memo puts an end to that. It puts doctors, nurses and other hospital staff in their new place—last. It unwittingly puts patient health outcomes down there with them. Turning hospitals into helpless consumers of national daydreams is all for their own good, of course—for their “safety.”

This is pure rationalization, but it’s nothing new. It is the culmination of a 15-year unwritten policy of dragging VistA away from the proven success of its user-driven model and toward the proven failure of a centralized model much like the one the creators of VistA rebelled against back in the 1970s. But the centralized model has one thing going for it: the big donors’ lobbyists want it, so Congress demands it [Frederick “Rick” Marshall, “Commentary: VA Memo Squashes VistA Innovation,”, 2009.07.29].

Moving to centralized proprietary software would be a disaster for the VA. Phillip Longman notes that proprietary health IT software doesn’t work specifically because it is designed by programmers removed from the working medical environment. They crank out code that makes doctors’ and nurses’ work more difficult. The proprietary vendors often impose license restrictions — more accurately called gag rules — that forbid hospitals from telling other facilities about bugs they discover in the code. And proprietary vendors are so worried about keeping customers locked into their purchase that they build systems that can’t talk to each other. As Longman puts it, “Patients might as well be schlepping around file folders full of handwritten charts.”

The democratic, participatory, grassroots nature of open source development helped the VA develop the first and best electronic medical record system in America, a system that has cut costs and saved thousands of lives. To abandon the open source model that has created “perhaps the greatest success story for government-developed information technology since the Internet itself” is a, to put it mildly, an enormous disappointment. The VA should cancel its May 26 memorandum and let its people do what they’ve been doing best for three decades: designing medical software that works for medical staff and the millions of veterans they serve.