Vanderbilt testing program that calculates risk scores for bedsores, readmissions

Vanderbilt University Medical Center is testing two statistical models to determine whether using predictive risk scores can improve care.

A computer program called Cornelius calculates two risk scores for each patient entering the hospital: one for developing bedsores and the other for readmission, according to an announcement. University biostatisticians tested more than 400 clinical and demographic variables for the two scenarios and based their models on analysis of some 30,000 patient records.

Cornelius's risk models rely on a handful of clinical and demographic factors documented in the electronic medical record within 24 hours of hospital admission.

In a randomized controlled trial, care teams don't know the risk scores for half of the patients, while they do for the other half and, as a result, might take extra preventive measures. Otherwise, both groups receive the same standards of care. The study, which began last year, is expected to continue for at least another year.

With Medicare discontinuing reimbursement for treatment of bedsores that develop in the hospital, organizations are looking at special mattresses and other ways to prevent them. And IT tools to predict risk of readmission have proliferated as penalties have been imposed.

In an adress at the CHIME13 fall forum this week, former national coordinator for health IT Farzad Mostashari, M.D., pointed out that there's a gap in terms of matching up supply and demand of predictive analytics tools and other new products.

Developers of such products such as readmission predictors need partners, clinical understanding and a place to try out their innovations, Mostashari said. And from the CIO's perspective, it's hard to evaluate and choose one product out of the thousand readmissions predictors floating around out there.

Research published recently in the American Journal of Managed Care analyzed the accuracy of various models.

"Use of any of the tools may provide some support for providers and health plans who undertake case management," the researchers wrote. "Focusing care-coordination efforts within the medical home on patients likely to benefit most requires appropriate identification of the highest risk, highest utilizing patients."

To learn more:
- find the announcement


The Real Payback of Healthcare Analytics

Tuesday, April 6 | 2pm ET / 11am PT

With the unpredictability of healthcare today, organizations are sharpening their focus on analytics to make more data-informed decisions. Join us for a roundtable session in which thought leaders will discuss how they are maximizing their analytics investments.