Data-analytics gap: How real-time strategies can improve care quality and efficiency
With the government moving full-throttle toward value-based care initiatives that tie reimbursement to quality, providers have an even greater reason to proactively manage their patient populations to reduce risks across the care continuum.
The U.S Department of Health and Human Services announced in March it had already reached its goal of tying 30 percent of Medicare payments to value-based models in 2016 - nearly a year ahead of schedule. So it seems likely to meet or exceed its mission of having more than half of such payments be value-based by 2018.
It will take more than just data collection and good intentions for providers to survive in the value-based world: they'll need to leverage analytics as a natural part of the IT strategy.
The problem is that although most healthcare executives see analytics as a tremendous opportunity, too many providers "don't know what to do with it," said Dave Dimond, chief technology officer at EMC's global healthcare business.
>> SPECIAL REPORT CASE STUDY: St. Joseph Healthcare sees dramatic improvement serving high-risk population with HealthInfoNet
For one thing, the industry as a whole hasn't yet been able to fully embrace analytics because many organizations are still struggling with the final implementation of meaningful use, he said.
For another, "consolidating organizations are struggling to align data across multiple applications," said Dimond.
"Patients are really demanding more personalized treatments," he added. "But it's something most organizations won't really take on until it's become the standard of care."
ZEROING IN ON STRATEGY
Although population health management initiatives are certainly increasing in prevalence, providers are still struggling with the best way to make use of population health tools.
According to HIMSS Analytics' 2015 Population Health Study, about 67 percent of organizations have population health programs in place. However, only a quarter of these providers use a vendor-provided platform to address these specific needs.
HIMSS Analytics surveyed about 200 healthcare executives on their pop health initiatives and asked about their approach to tackling their population health IT needs. About 60 percent of the respondents said they're without a population health consultant. But of the respondents without population health initiatives in place, more than half have plans to employ these types of programs in the future.
Having a well-considered strategy for how to put those analytics tools to work – how to use them, where, and, crucially, why – is essential, said Dimond.
"There's lot of data that focuses over all of the patients. But it's more about finding the patients we don't see enough to make better decisions on their care. You have to look at the trends for treatments and diagnostics of others patients to see what's working – and to engage them."
Another big hurdle to a more widespread use of pop health analytics is the effort being expended across the industry to keep that data safe.
"There's a tremendous amount of energy expended on finding the best way to secure data," said Dimond. "All of this time that could instead be used to discover ways to use data, such as precision medicine, population health and other research opportunities."
Workflow is another considerable challenge: 81 percent of healthcare leaders polled in a 2015 survey sponsored by EMC said they aren't able to act on data in real-time. Another 40 percent were unable to drive actionable results and almost half of the respondents are unaware of how to cope with all of the data within their organization.
One-quarter of the respondents said they were experiencing "data overload."
The amount of data is only going to increase. So healthcare organizations need to start developing strategies to manage it to their advantage.
Providers "jumpstart engagement" with data – not being shy about enlisting the help of vendor partners who can "come in with different tools" that can help, Dimond said. "While doing that, you need to look at all kinds of data. It goes beyond the healthcare data model; you need to get involved with data science. From there you can start to build confidence in data, like with predictive analytics. Healthcare is just getting started."
The Healthcare IT News Special Report: Bridging the big data-analytics gap
Case Study: St. Joseph Healthcare sees dramatic improvement serving high-risk population with HealthInfoNet
Case Study: UnityPoint Health connects providers and hospitals with predictive analytics to improve patient care
Case Study: Children's Hospital of Pittsburgh develops customized prediction indicator for children with PeriHealth
Next Step: Quality and depth important to develop predictive analytics solutions