Big Data and Population Health: The Power of Combining Clinical and Claims Data
As we continue to move toward a pay-for-performance healthcare model, big data as a strategic tool for population health goals to improve care, outcomes and costs remains front-and-center.
Up until recently, claims data was heavily relied upon to improve population health efforts. As a software data analytics company specializing in claims data, we know claims data has a big role to play in healthcare data analytics. However, we’re also very aware that the real power and benefit for health systems, patients and population health efforts lies in combining claims data with clinical data, namely from the electronic medical record (EMR) but lab and other data as well.
Neither clinical or claims data alone provides enough depth of information, yet they are natural complements. The power is in marrying them together for meaningful insights.
Claims data provides a retrospective look at what happened such as:
- Prescriptions filled
- Lab tests completed
- Treatment costs and outcomes
- Spans a patient’s full continuum of care
What claims data lacks, clinical data provides:
- Important clinical details about patients
- The process of care, which is key to improving quality of care
- Timeliness, as it’s collected in real time
Meaningful Insights for Population Health
According to an article in Healthcare IT News, health systems seeking to turn clinical and claims data into actionable insights should consider the following strategies for population health:
- Start with a broad data set that, at minimum, includes administrative data and clinical data. Ideally, the data will also include personal health record data, lab data, Continuity of Care Documents (CCD) data and consumer reported data such as health risk assessments and wearables data.
- Focus on insights to better coordinate care. Make sure data is bi-directional and real-time for the creation of dynamic care plans.
- Use the data to create a platform to drive patient engagement – a key to any successful population health effort.
Big Data Health System Collaborative
A fantastic example of big data in action can be seen In Michigan at one of the largest data-driven quality improvement efforts in surgery. The Michigan Surgical Quality Collaborative (MSQC) helps surgical teams across 73 Michigan hospitals improve patient care. The collaborative is funded by Blue Cross Blue Shield of Michigan, the state’s largest payer.
MSQC leverages 137 different types of data – including clinical and administrative data – that includes records from more than 420,000 operations performed at the MSQC participating hospitals. Operations initially focused on general surgery and now include specialty surgeries.
The data collected, analyzed and put into action has resulted in some impressive gains and programs:
- Infections for surgical infections post-colectomy surgery dropped the more often hospital teams followed a MSQC bundle of anti-infection protocols. Costs dropped as well.
- Data is currently being used to help patients reduce their risk of surgical complications by participating in a pre-surgery “prehabilitiation” that includes emotional factors, exercise and quitting smoking.
- MSQC is using its data to help improve opioid painkiller prescribing practices post-surgery.
With half of U.S. medical care related to surgical procedures, MSQC is on the right track with its focus on using big data to improve surgical outcomes and overall population health.
MSQC is a great example of transforming data into actionable insights to positively drive quality, costs and patient satisfaction goals. Such an approach also positions both health systems and patients for success in the changing healthcare system, where pay-for-performance and population health outcomes will matter most.
Trisha Young is Regional Vice President of Business Development at Intellimed.