With the push to value-based reimbursement, providers are rethinking their strategies for embedding analytics in their workflow, according to an article at Health Data Management.
Atrius Health, a Boston-based not-for-profit alliance of medical groups, for example, is using natural language processing software on unstructured text within the electronic health record to run risk analyses on patients who rarely come in to flag those at risk for issues such as diabetes and obesity.
What's more, the University of Mississippi Medical Center, after spending months trying to clean up its data to make it usable for analytics, now sends "raw dumps" of data to a vendor that feeds into its machine-learning network and adds numerous other clinical and socioeconomic variables to develop predictive risk scores for issues such as heart disease, hospital readmission and hospital-acquired infections.
"I think everyone is trying to figure out how to reduce the 'time to value' of their data," John Showalter, M.D., UMMC's chief health information officer, tells Health Data Management.
Organizations are focused on getting clinical analytics closer to caregivers, though many report a general dissatisfaction with their existing population health and analytics tools, according to the article.
Many organizations are building their own tools. Chicago-based NorthShore University HealthSystem, for example, says it has learned through trial and error that to be effective, analytic tools have to be visible--and visual. Rather than sending monthly reports, it's focused on creating visualization dashboards that let users explore the data themselves.
Providers are struggling under all the data, including how to aggregate and store information, as well as how to integrate data into daily workflows, according to a Chilmark Research report that concluded that robust advanced capabilities likely are several years away.
One recent survey on population health initiatives found a majority of hospitals are "still just testing the waters."
To learn more:
- read the article