University of Iowa Hospitals and Clinics Transforms the O.R.
Accessible, predictive analytics results in 74% reduction in surgical infections
In the US, roughly one in 20 patients admitted to a hospital develops an infection, putting patients at risk for illness, prolonged hospitalization, and death. Additionally, the total cost of hospital-acquired infections in the US is estimated at $10 billion per year.
Associate Chief Medical Officer at the University of Iowa (UI) Hospitals and Clinics Dr. John Cromwell believed that the use of predictive analytics could prevent a high percentage of surgical site infections and decrease healthcare costs.
"We had the hypothesis that if we had the interventions to improve patient outcomes, and could identify at-risk patients using information from the medical record, we could create a very systematic approach to applying those interventions," said Dr. Cromwell.
The division's desktop analytics environment, however, could not handle large distributed data volumes. UI Hospitals and Clinics needed a way to connect multiple data sources and enable deployment of valuable analytics to frontline staff. The team needed a flexible, enterprise-grade, advanced analytics platform that encompassed the entire analytics lifecycle—from data aggregation and preparation to model development, deployment, and monitoring.
With TIBCO® Data Science, UI Hospitals and Clinics connected disparate enterprise systems and created a common dataset with embedded analytics. Moving from desktop to enterprise analytics, the organization turned prediction theory into a life-enhancing reality.
Reduced Infections and Cost of Care
TIBCO Data Science is using patient healthcare and historical data to create predictive models in a real-time environment, enabling faster, more accurate decision-making. With a 74 percent reduction in surgical site infections in three years, the University of Iowa proved its hypothesis and successfully implemented predictive analytics into the hospital workflow, reducing costs during hospitalization by $2.2 million at scale.
"We take information from electronic medical records and other sources, including real-time O.R. data, to determine whether patients are likely to get a surgical site infection," said Dr. Cromwell. "This allows us to modify and individualize the type of preventive care we're delivering, in real time."
Reduced Surgical Complications
TIBCO Data Science helped simplify deployment, execution, model sharing, and data analysis, making it easy for physicians to take data driven action in real time.
In addition to infection, the team used TIBCO Data Science to identify patients that should receive additional surgery preparation to avoid costly blood transfusions—and to identify those at high risk for delirium, a form of brain failure, saving nurses from a time-consuming, manual process and improving patient care.
"Predictive analytics is allowing us to manage ever-increasing data types and sources," said Dr. Cromwell. "And tools like TIBCO Data Science allow us to keep track of the various models we need for that type of exercise."
UI Hospitals and Clinics is now collaborating with the Center for Disease Control (CDC) to test the technology for wider use. Use of real-time risk-related data will hopefully be disseminated across hospitals around the country and the world. National adoption of the technology could save the healthcare system hundreds of millions of dollars annually.
"Big data and predictive analytics are transforming outcomes at virtually every point in patient care," Cromwell said. "We see so many other areas where this could be useful, including drug delivery, population health, managing patient flow, and every other aspect of medicine that allows us to deliver high-quality healthcare."