“I want it all.” This sentiment is shared by nearly all of the clinicians we’ve met with, from the largest integrated health systems (IHS) to the smallest physician practices, in reference to what data they want access to once an aggregation solution like a data warehouse is implemented. From discussions with organizations throughout the country and across care settings, we understand a problem that plagues many of these solutions: the disparity between what clinical users would like and what technical support staff can provide.
For instance, when building a Surgical Data Mart, an IHS can collect standard patient demographics from a number of its transactional systems. When asked, “which ‘patient weight’ would you like to keep, the one from your OR system (Picis), your registration system (HBOC) or your EMR (Epic)?” and sure enough, the doctors will respond, “all 3”. Unfortunately, the doctors often do not consider the cost and effort associated with providing three versions of the same data element to end consumers before answering, “I want it all”. And therein lies our theory for accommodating this request: Leave No Data Behind. In support of this principle, we are not alone.
By now you’ve all heard that Microsoft is making a play in healthcare with its Amalga platform. MS will continue its strategy of integrating expertise through acquisition and so far, it seems to be working. MS claims an advantage of Amalga is its ability to store and manage an infinite amount of data associated with a patient encounter, across care settings and over time, for a truly horizontal and vertical view of the patient experience. Simply put, No Data Left Behind. The other major players (GE, Siemens, Google) are shoring up their offerings through partnerships that highlight the importance of access to and management of huge volumes of clinical and patient data.
Why is the concept of No Data Left Behind important? Clinicians have stated emphatically, “we do not know what questions we’ll be expected to answer in 3-5 years, either based on new quality initiatives or regulatory compliance, and therefore we’d like all the raw and unfiltered data we can get.” Additionally, the recent popularity of using clinical dashboards and alerts (or “interventional informatics”) in clinical settings further supports this claim. While alerts can be useful and help prevent errors, decrease cost and improve quality, studies suggest that the accuracy of alerts is critical for clinician acceptance; the type of alert and its placement and integration in the clinical workflow is also very important in determining its usefulness. As mentioned above, many organizations understand the need to accommodate the “I want it all” claim, but few combine this with expertise of the aggregation, presentation, and appropriate distribution of this information for improved decision making and tangible quality, compliance, and bottom-line impacts. Fortunately, there are a few of us who’ve witnessed and collaborated with institutions to help evolve from theory to strategy to solution.
Providers must formulate a strategy to capitalize on the mountains of data that will come once the healthcare industry figures out how to integrate technology across its outdated, paper-laden landscape. Producers and payers must implement the proper technology and processes to consume this data via enterprise performance management front-ends so that the entire value chain becomes more seamless. The emphasis on data presentation (think BI, alerting, and predictive analytics) continues to dominate the headlines and budget requests. Healthcare institutions, though, understand these kinds of advanced analytics require the appropriate clinical and technical expertise for implementation. Organizations, now more than ever, are embarking on this journey. We’ve had the opportunity to help overcome the challenges of siloed systems, latent data, and an incomplete view of the patient experience to help institutions realize the promise of an EMR, the benefits of integrated data sets, and the decision making power of consolidated, timely reporting. None of these initiatives will be successful, though, with incomplete data sets; a successful enterprise data strategy, therefore, always embraces the principle of “No Data Left Behind”.