Workflow must be a priority when implementing predictive analytics tools in healthcare
For predictive analytics truly to have an impact in healthcare, addressing workflow issues with providers must be a priority, according to several speakers who participated in FierceHealthIT's executive breakfast panel discussion "Using Predictive Analytics to Improve Care & Efficiencies," held Wednesday morning in New Orleans.
Such technology, the panel members agreed, currently is in a state of experimentation, which means uncertainty, and often reluctance, in terms of adoption by providers.
"Predictive analytics represent a great opportunity right now in healthcare, but we're still really in a state somewhere in between adolescence and a mid-life crisis," Kaveh Safavi, M.D., managing director for Accenture Health Practice, said. He added that while organizations that want to use such tools should be building a culture around testing and management, they often fail to go from "insight to action" due to a lack of communication.
Benjamin Horne, director of cardiovascular and genetic epidemiology at Salt Lake City-based Intermountain Medical Center, talked about his experience both in creating predictive models for providers to use and in convincing those same providers of their importance. He said that the key was interweave such tools into everyday tasks to avoid interruptions.
"And once you convince physicians of the importance of such tools, they can't live without them," Horne said. "You can't do enough to get information to them fast enough."
Be sure to check out full coverage of our breakfast in an upcoming issue of FierceHealthIT.
Rush CIO Lac Tran on using predictive analytics to improve outcomes, efficiency
How predictive analytics data helps your patients--and your business
Predictive tool helps ID at-risk trauma patients
Predictive tool pinpoints heart patient readmissions
Online nurse support improves vascular disease risk factors
Tool predicts survival odds for cardiac-arrest patients
Hospitals cut readmissions with predictive modeling