Use big data and analytics to slow health care costs and compete on outcomes

By: The Optum Risk & Quality Solutions Team

Health care is awash in data, so one might think that providers and payers would be on the forefront of the big data movement. While it’s true that claims data has been used for various purposes, including epidemiological research and predictive modeling, it doesn’t have the richness needed for what is truly needed in health care today: slowing the rapid rise of health care costs and competing on outcomes.

The reason: The vast majority of health care data is clinical data, most of which, until the turn of the century was virtually inaccessible to any sort of meta-analysis. Even with the rapid advancement of electronic medical records into the acute and outpatient environment, much of the data in EMRs remains siloed and inaccessible.

Despite limited accessibility of EMR data, because of greater clinical data availability the uses for health care data are changing. Driven primarily by the move toward new reimbursement and delivery models that require deeper insights from the existing data, payers, providers and policymakers in the United States and across the globe are exploring ways to utilize data. These organizations are utilizing clinical data, claims data and non-traditional data sources to analyze treatments as well as patient behaviors, genetics, risk factors and the environment. All this information helps organizations effect change in both financial and health outcomes. We can see what treatments are working, look at cost-to-benefit ratios and improve quality while subsequently improving costs.

In the RISKMATTERS article “Making Big Data Work,” written by Karalee Close, Stefan Larsson, John Luijs, Neil Soderlund and Anna Vichniakova of Boston Consulting, you’ll read about opportunity areas and related examples of how payers and providers from Australia, the Netherlands and the UK are utilizing big data and advanced analytics to make progress in transforming health care in their regions.

Optimizing care for patient populations: The state of Victoria in Australia comprehensively aggregated data and analyzed large populations to find out how they were spending health care dollars and, subsequently, find areas where care effectiveness could be improved.

Reducing the cost of care: A large payer in the Netherlands used data and analytics to reduce dependence on brand-name drugs when generics provided outcomes as good or better.

Reducing hospital readmissions: A government-run hospital trust in the UK analyzed provider and public data to identify factors that were associated with unusually large readmission rates, then developed interventions to improve care.

How can you begin to utilize big data for care and cost improvement in your organization? Click here to read the article in the latest edition of RISKMATTERS, and look for some recommendations on page 11.



Leave a Reply