The Promise of Predictive Analysis

If hospitals could accurately predict which patients were going to experience complications down the road, they could intervene early with those patients, and perhaps prevent them from having to be rehospitalized. Reducing readmissions is one of the potential benefits of predictive analysis, and it’s a big one.

“We have 750 patients every day. Instead of looking at everybody, if we can look at 20 patients, that would be a great advantage,” said Jose Azar, M.D., of Indiana University Health, in an H&HN article.

Also highlighted in the Hospitals & Health Networks article is Christiana Care Health System, which has been using predictive analytics for about five years. The Wilmington, Delaware, nonprofit health system set up its homegrown analytics system in 2012 with $10 million in grant funding from the Centers for Medicare & Medicaid Innovation Center.

Predictive analytics has helped Christiana Care improve on financial and utilization metrics, but administrators cautioned that predictions are no help if an organization doesn’t have the resources to respond to them. That means everyone – from doctors and care managers to nurses and social workers, and even clerical staff – needs to be ready to intervene based on predictions about patients.

“You need to be able to respond to and receive information in real time,” said Terri Steinberg, M.D., chief health information officer at Christiana Care. “That’s the cost of entry,” Steinberg told H&HN. “Without a robust care-management program, there’s no point” in making predictions.

Complimentary webinar recording available

A recent LUMEDX/Christiana Care webinar is now available as an online download or on CD. "Delivering Clinical and Business Excellence — The Power of Data Transparency: How Christiana Care Leverages Cardiology Data to Improve Care Quality and Contain Costs" can be downloaded by clicking hereIf you prefer to have a CD mailed to you, please click here.

 

Comments

Comments are closed on this post.
  • RSS

Statistics

  • Entries (235)
  • Comments (1069)

Categories