Blog Post

Harnessing data to improve clinical performance

Share this post:

Sally Akers, RN, MSN, CNS is a Managing Partner, Provider Consulting and Analytics at IBM Watson Health

Hospitals and health systems are awash in data. Every patient admission, diagnosis, treatment decision, and outcome becomes a data point that is stored somewhere.

Too often, though, that data is fragmented in an assortment of hospital information systems that are either not universally accessible or not interoperable with one another. This keeps clinicians and administrators from accessing meaningful insights they could use to improve the cost and quality of the care they provide.

Thanks to innovations in healthcare data analytics, notably in the development of the data lake approach to clinical data storage, hospitals and health systems are increasingly able to unlock these disparate data sets to harness actionable information. Many leading organizations have already begun relying on that information for major quality improvement initiatives.

Take, for example, Jordan Valley Medical Center, a physician-owned, three-campus medical center in Utah’s southwest Salt Lake Valley, which developed a data-driven clinical performance initiative focused on reducing complications and treatment costs associated with sepsis.

Even though the center had implemented a protocol that followed national guidelines, case costs and length of stay for its sepsis patients were rising. It was time to consider a new approach, focused on aggressively intervening and treating sepsis in its earliest stages—before symptoms became critical.

To do this, Jordan Valley needed timely, granular clinical data that allowed hospital staff to monitor and track the entire process of care, from initial diagnosis to treatment patterns of different physicians’ practices to length-of-stay to readmissions to mortality.

The hospital turned to one of the most robust hospital performance benchmarking solutions available to start tracking detailed clinical information and outcomes data related to sepsis case cost, mortality, readmission, and complications and more. This data was analyzed both for Jordan Valley’s own facilities and for peer group hospitals. By continually monitoring this data set while making changes to improve its existing sepsis protocol, the hospital began to see improvements.

Over the course of just one year of careful tweaking based on benchmark performance data, Jordan Valley was able to reduce its average cost per sepsis case by 6.5% and outperform the top 25% of hospitals in the nation for length of stay, mortality, complications and readmissions related to sepsis cases.

While Jordan Valley’s performance marks a breakthrough in sepsis care, the hospital is hardly alone in this approach to tapping clinical data as a source of performance improvement insight.

Tackling system-wide performance

DeKalb Medical, a 627-bed, not-for-profit health system, with three campuses located throughout the state of Georgia, achieved a similar data-driven turnaround.

In 2012, DeKalb Medical underwent a fundamental shift in organizational strategy. Reeling in the wake of executive turnover, and saddled with financial set-backs that limited resources, the health system was looking for a way to improve operational and clinical outcomes, reduce administrative and clinical inefficiencies, and develop system-wide key performance metrics.

With the assistance of the same performance improvement solution Jordan Valley used, the DeKalb team fundamentally changed the way it measured system-wide performance. The team monitored key quality measures such as length of stay, mortality and readmissions, and compared the health system’s performance on each metric to national peer group standards each month.

The team then organized these industry best practices under the new DeKalb Quality Institute (DQI) banner, creating a center of excellence for understanding process of care at the most granular level and helping to improve physician efficiency and patient outcomes.

Overall, by continually tracking performance across these key measures and using that information to guide adjustments along the way, the system saw a reduction of complications and patient length of stay, resulting in savings of more than $12 million. Over a three year period, the health system decreased complications 58% and saved 55 additional lives annually. For its efforts, DeKalb received the 2016 Truven Health Advantage Award for Performance Improvement and Efficiency.

Achieving such a large shift in culture is not easy. Reorienting major administrative and clinical decisions around data requires an organization-wide commitment from care managers and business practice leads. But as we’ve seen at both Jordan Valley and DeKalb, unlocking the right data sets and aligning clinical and administrative teams so they can act on that information can drive real performance improvement.

For more examples of clients using data to improve their processes, visit our case study library.

More Blog Post stories

7 population health management strategies that reduce risk in performance-based contracts

Written by Maria Balderas, PhD | Blog Post, Value-Based Care

As healthcare providers transition to value-based care models, PHM plays a critical role in financial risk arrangements with public and private payers. ...read more


Discover “Discovery”

Written by Louisa Roberts | Blog Post, Drug Discovery, Life Sciences

I have worked with various flavors of Watson in the last 4 years, and it has taught me a lot about the need to understand bias, both in data and the interpretation of it.  In the spirit of transparency, I will be honest about my own bias – my favorite Watson Health product is Watson ...read more


What it takes to win with bundled payments

Written by Maria Balderas, PhD | Blog Post, Value-Based Care

To succeed with these bundled payments requires winning over physicians, coordinating post-discharge care and keeping close tabs on post-acute care providers. ...read more