Predictive analytics help hospital slash post-surgical infections

As the federal government continues to push for value over volume when it comes to healthcare, providers--like those at the University of Iowa Hospitals and Clinics--increasingly are turning to technology to bolster their efforts.

In particular, the Iowa City-based academic medical center now is reaping the rewards from predictive analytics tools deployed roughly two years ago, according to the Wall Street Journal. With the help of such software, infection rates for colon surgery patients have dropped 58 percent since the end of 2012.

The hospital, according to John Cromwell, associate chief medical officer and director of surgical quality and safety, first built a model of its environment based on surgical procedures, outcomes and surgical site infection risks for 1,600 patients. The hospital then loaded the model into analytics software that pulls in information from various sources, such as patient records and medical equipment.

Now, surgeons, during procedures, can compare that information to information for patients undergoing operations in real time; nurses enter the real-time patient data into the software, which then determines a patient's risk of suffering a surgical site infection.

The information helps surgeons develop distinct post-operation plans of attack for individual patients.

"Our goal has been to get that risk ... before the patient leaves the operating room, mainly because there are some therapies out there that don't make sense to apply to every patient," Cromwell told WSJ.

Personalizing care through predictive analytics poses the opportunity to significantly reduce healthcare costs, according to a Rock Health report published last fall, including $192 billion in overtreatment, $128 billion in failures of care delivery and $35 billion in lack of care coordination--figures attributed to the Journal of the American Medical Association.

Like the University of Iowa, Massachusetts General Hospital also uses a predictive analytics tool, including surgeon acceptance of its predictions on risk, according to David Ting, associate medical director for information systems at the hospital. The tool, known as the Queriable Patient Interface Dossier, was developed in 2007.

Last summer, IQ4I Research & Consultancy predicted that the health analytics market could see as much as 25 percent annual growth over the next five years.

To learn more:
- read the Wall Street Journal article