Guest blogger: Karen Burton, Healthcare Business Development Manager
Healthcare is beginning to realize the many benefits of a big data collection and analytics tools. Hospitals have had business intelligence/data warehouse projects in finance for some time. With the advent of “meaningful use” clinical quality improvements reporting requirements, the need for clinical data warehouse is more pressing. Starting soon, Medicare will impose penalties on hospitals that don’t show improvement in 3 key areas:
- Reducing 30-day readmission rate of patients suffering from acute myocardial infarction, pneumonia or heart failure
- Increasing Meaningful adoption of electronic health record (EHR) systems
- Decreasing Hospital-acquired conditions, where patients contract a disease while they’re in hospital care
By 2017, these 3 factors will make up about 6% of an average hospital’s Medicare revenue, a significant sum considering that Medicare is the largest insurer in the country. To ensure meeting these standards—and to improve their overall quality of care—many healthcare systems are employing big data to deliver better care and stay in compliance with Medicare improvement requirements.
Many institutions are gaining benefits from collecting data from previously isolated sources. For example, the Ohio State University’s Wexner Medical Center developed their own business intelligence system to analyze their operations data to improve care. This project resulted in a 15% reduction in average length of stay, a 30% reduction in readmissions, a 60% reduction in days to resolve bill rejections and overall increased patient satisfaction. As a result of the many inquiries from their success, OSUMC decided to spin off a healthcare analytics company to extend those benefits to other healthsystems: Health Care DataWorks (HCD).
Today HCD offers health systems a proven, integrated clinical and financial analytics at a fraction of the cost and time required to build themselves. In partnership with Logicalis, HCD’s winning analytics are offered as a SaaS in the cloud – further reducing the investment and time to value. Features like a Readmissions dashboard allow users to easily analyze readmission rates by any number of attributes, including by discharging physician, clinical services, diagnosis-related group (DRG), and diagnosis. The dashboard’s overall hospital view shows all readmissions regardless of cause for all payers and specifically for the Medicare population. Quality and health information managers can drill down into specific details at the account level to understand why a readmission occurred and determine where processes can be improved, such as providing more clear discharge instructions. Administrators can also determine if there’s a specific nurse station, physician, or procedure that is affecting readmission rates.
The ultimate big data tool for clinical analytics so far has been IBM’s Watson, which last year was loaded with over 1.5 million patient records from Memorial Sloan-Kettering Cancer Center, as well as 600,000 pieces of published medical evidence and two million pages of text from medical journalists. With this immense amount of data, Watson became a sort of computerized oncologist, able to recommend treatment options to doctors.
Big data clearly has promise for healthcare, but do you think healthcare systems can quickly adopt clinical analytics tools? Or is this just hype, and we won’t see big data used in a meaningful way for some time? Tell us why in the comments.