Healthcare organizations and providers are maturing in their ability to use clinical intelligence as a means to improve the care of patients, the business of providing care, and the process of reporting clinically-relevant medical information to public health agencies and other organizations charged with managing the health of whole populations. “The promise of meaningful use is that this data is going to be available for them to manage care, improve quality, and reduce cost,” says John McInally, former CIO and current Partner of Healthcare Big Data and Analytics Group CSC, in an interview prior to HIMSS13.
Harnessing the power of big data and healthcare analytics, however, first requires that clinical and patient information is documented and captured appropriately. And only recently have healthcare organizations and providers begun to understand the value of big data and analytics to their clinical and business initiatives.
“The marketplace in healthcare really wasn’t ready last year,” recalls McInally. “People were just struggling to get their data warehouses up and be able to do meaningful use reporting — that was the thing that was all-consuming last year. Then this new thing came along which was accountable care and readmission risk, and suddenly the answers that we wanted to come from our traditional data warehouses weren’t there.”
The new level of accountability for providers requires that they have a comprehensive and accurate picture of a patient’s care comprising both structured (e.g., demographics) and unstructured data (e.g., physician notes), which is only possible through a new approach to data mining.
“In a traditional data warehouse, it’s entirely structured data, and you have to have a report writer and some pretty sophisticated thinking behind your questions,” explains McInally. “What we’re doing in big data is applying analytics tools that come from other segments in the industry and allowing the merge of text and unstructured data with structured data and not only answer the question but also expose other questions you may not have thought of.”
In short, big data is the synthesis of data irrespective of the form it takes. That being said, its strength is based on its ability to incorporate components of the patient experience that fit neatly into drop-down menus, checklists, or form fields, with the most important of these being physician notes in free text.
Coupled with that is the capacity to help both the individual patient and patient population. “We begin to stitch together a community of data, structured and unstructured, and we’re able to very quickly using these non-SQL tools answer big questions across large population and we’re able to personalize it down to the individual patient in a bed at the same time,” adds McInally.
Although the healthcare industry has been slow to adopt the concept of big data, nearly all healthcare reform via health IT is looking to this source of information for insight, from accountable care to clinical decision support. In order for a provider to have access to this kind of support, his organization must have the necessary infrastructure in place (i.e., data warehouse) to support the merging and parsing of patient data.
“A lot of the answers that you’re looking for today don’t come out of a traditional relational database management system or if they’re possible, they just don’t come out fast enough,” argues McInally. “The notion here is to be able to mine the data so that the data itself exposes a new hypothesis for you, and that’s the horizon we’re taking people out on.”
With the close of Stage 1 Meaningful Use for early adopters and demonstrated users of certified EHR technology, an ample amount of data is now residing in data warehouses. Next in line is the need to realize the use of this valuable information in the form of primary, secondary, and tertiary applications.