Machine Learning Times
Machine Learning Times
EXCLUSIVE HIGHLIGHTS
Survey: Machine Learning Projects Still Routinely Fail to Deploy
 Originally published in KDnuggets. Eric Siegel highlights the chronic...
Three Best Practices for Unilever’s Global Analytics Initiatives
    This article from Morgan Vawter, Global Vice...
Getting Machine Learning Projects from Idea to Execution
 Originally published in Harvard Business Review Machine learning might...
Eric Siegel on Bloomberg Businessweek
  Listen to Eric Siegel, former Columbia University Professor,...
SHARE THIS:

9 years ago
Survey Finds Only 15% of Hospitals Use Advanced Predictive Modeling

 

Despite the potential benefits and return on investment for their clinical and operational goals, just 15 percent of hospitals are using some kind of advanced predictive modeling, according to a new survey.

Of the 15 percent who do use some kind of advanced predictive modeling solution, 85 percent identified themselves as hospital, multi-hospital, integrated delivery organizations, while 15 percent were academic medical centers.

PA Times AD

However, the survey—conducted earlier this month by healthcare technology vendor Jvion—also found that of those hospitals that aren’t using advanced predictive modeling, 96 percent indicated that they would or may consider an advanced predictive modeling solution in the future. In the survey, advanced predictive modeling is defined as “the application of machine learning algorithms to find patterns within data to predict patient-level risk.”

The good news is that of those hospitals that do employ predictive solutions 92 percent are using the outputs to predict patient risk or illness. The illnesses and conditions most often targeted include: predicting hospital readmissions (27 percent), predicting sepsis (27 percent), predicting patient deterioration (18 percent), finalizing decisions (18 percent), and predicting general patient health (10 percent).

In addition, providers who use advanced predictive modeling are tackling the following operational challenges (which were evenly distributed across survey respondents):

*Target length of stay expectations,
* Project reimbursements,
* Target intervention activities,
* Improve patient safety outcomes,
* Meet nurse staffing goals,
* Reduce mortality,
* Reduce readmissions, or
* Currently defining/in process.

“The survey findings point to a growing need within the provider community for solutions that help prevent patient illness through real-time predictions,” said Todd Schlesinger, vice president at Jvion, which develops software designed to predict and prevent patient-level disease and financial losses. “With so much changing in the industry, providers are hungry for analytics that will help them improve health outcomes while reducing risk and waste across the system.”

A full copy of the survey results is available here (registration required).

By: Greg Slabodkin
Originally published at www.healthdatamanagement.com

Leave a Reply