By Christine Kern, contributing writer
Predictive analytics are just starting to take a foothold in the healthcare industry.
A Jvion survey has found only 15 percent of healthcare providers are currently using some kind of predictive modeling and 92 percent of them are using the outputs to predict patient risk or illness. Eighteen percent are focusing on patient deterioration and 27 percent predicting sepsis.
Additionally, more than one quarter are using predictive analytics to prevent readmissions, one of the most significant items of concern when it comes to penalties, payment adjustments, and patient outcome reporting.
Conducted in March, the study queried the hospital community regarding their use of advanced predictive modeling to support their clinical and operational goals. For the study, advanced predictive analytics/modeling was defined as the application of machine learning algorithms to find patterns within data to predict patient-level risk.
Todd Schelinger, VP at Jvion, explains “the survey findings point to a growing need within the provider community for solutions that help prevent patient illness through real-time predictions. With so much changing in the industry,” he said, “providers are hungry for analytics that will help them improve health outcomes while reducing risk and waste across the system.”
According to the study, the majority of predictive analytics users are mid-size, non-academic hospitals or hospital systems, debunking the conventional assessment that healthcare analytics is currently an option only for the largest hospitals with the deepest pockets.
The study also found providers prefer vendor solutions (82 percent) for their predictive analytics over developing their own in-house solutions (18 percent). And 96 percent of those providers who are not presently using advanced predictive analytics stated that they are considering or plan to adopt them in the future. Among the operational goals identified by respondents were:
- targeting length of stay expectations
- project reimbursements
- target intervention activities
- improve patient safety outcomes
- meet nurse staffing goals
- reduce mortality
- reduce readmissions
- currently defining/in process
As Health IT Outcomes pointed out earlier, predictive analytics may still be in its infancy for healthcare but holds great potential for transforming the landscape for the future. “There are already many implementations across many hospitals in the country and across the world,” says study co-author Bin Xie in Modern Healthcare. “It could grow into a big, giant adult, so, when we compare it to its potential, it's still in its infancy.”