Business intelligence dashboard software from Tableau helps Johns Hopkins Hospital reduce patients' emergency department stays from 11 hours to four.
5 Big Wishes For Big Data Deployments
(click image for larger view and for slideshow)
With 67 private exam rooms and six trauma rooms occupying 35,000 square feet, the emergency department (ED) at Baltimore's Johns Hopkins Hospitalis a big place.
To optimize the flow of patients out of the ED, the hospital has become a marquee user of a dashboard from Tableau Software, which updates its status every five minutes, pulling patient whereabouts and status from five or six departmental systems.
Doctors, nurses, administrators, shift coordinators, and even the nurse managers on the floors use the dashboard. But the system, which can be accessed via authenticated PCs or tablets, has done more than optimize the flow of patients out of the ED; it has helped overcome a "silo" view of hospital activity.
"Before this, staff would bring six or seven reports to a monthly meeting," Hetal Rupani, an MHA and senior project administrator in the hospital's department of medicine, told InformationWeekin a phone interview. "Actually, the dashboard has broken the Berlin Wall," she said. "It's common ground, and everybody is using it."
"We're seeing a mature market, growing 9% over the last five years," James Gaston, senior director of clinical and business intelligence at HIMSS Analytics told InformationWeek.
To help heathcare organizations navigate the IT landscape, HIMSS Analytics produces a guide, Essentials of the US Hospital IT Market, compiled from its own survey database of nearly every hospital in the United States.
Gaston said at least one catalyst for adoption has been healthcare reform, including the Affordable Care Act (ACA), which has put pressure on these institutions to use more sophisticated IT, both to run their business and clinical services.
General-purpose dashboards "are one type of BI report application that healthcare is beginning to embrace as it improves IT overall," Gaston said.
Now that she can monitor the supply and demand of beds, as well as predict how many admissions from the ED will happen, Rupani wants to create other predictive models, such as peak times for discharging patients. To get a more complete view, she wants to pull in non-ED admissions, such as referrals.
"Right now, we only have the number [of these admissions], not the five-minute updates," she explained.
The success of the dashboard is indicated by the fact that other departments at Johns Hopkins Hospital are approaching Rupani, asking for help to deploy their own Tableau dashboards.
InformationWeek Tech Digest, Nov. 10, 2014Just 30% of respondents to our new survey say their companies are very or extremely effective at identifying critical data and analyzing it to make decisions, down from 42% in 2013. What gives?