03 March 2014

The provider side of big data

We have entered the age of “Big Data.” I’m not certain how this age differs from the Information Age, but a statement by Dan Ariely, James B. Duke Professor of Psychology and Behavioral Economics at Duke University’s Fuqua School of Business and director of Duke’s Center for Advanced Hindsight, provides an interesting perspective: “Big Data is like teenage sex: everyone talks about it, no one really knows how to do it, and everyone thinks everyone else is doing it, so everyone claims they are doing it.”

So, if we are in the prepubescent stage of health care informatics, what does the future hold?

allanswart/iStock/Thinkstock
The focus of big-data analytics today is on what I like to refer to as “patient-side data.” Investments being made to analyze patient-side data, evidenced by IBM’s recent agreement to implement natural language processing (NLP) in Cerner’s electronic medical record (EMR), are staggering. These data analyses run the gamut from genomic deconstruction for the purpose of individualized chemotherapy intervention to population-based trending of indicators beyond imagination. If these analyses result in actionable information, which I have no doubt they will, the actions required will not take place in a vacuum. More data is needed if these new discoveries are to reach their full potential.

I am a believer in Occam’s razor, a principle of parsimony. To paraphrase, the solution with the least number of variables is usually the one that should be employed. The Synergy Model, just one such parsimonious exemplar, provides a framework that may help us think about the other side of the big-data coin—“provider-side data.” The Synergy Model tells us that both patient and provider have specific characteristics which, when aligned, optimize patient outcomes.

We’re just beginning to scratch the surface in capturing and interpreting patient-side data, but we’re even further behind the curve when it comes to the provider side of the equation. Not long ago, the most we knew about members of our staffs is that they had licenses and could fog mirrors. With the advent of learning management systems (LMS), we can now track employee education. However, this remains a highly compliance-driven function. 

With the advent of the EMR, we’ll be able to aggregate provider-patient interaction data, such as the number of specific procedures completed by a practitioner. Data like this can be used for purposes such as credentialing and certification—in other words, quantitative data generated to support compliance-driven activities. Will the holy grail of improved patient outcomes be found in the check boxes of an EMR or the compliance report of an LMS? I think not.

Just as patient characteristics described by the Synergy Model relate to data found in the patient narrative, so too provider characteristics relate to data found in the provider narrative. Whether the professional narrative be found in the EMR (through documentation of patient interactions) or the professional’s development record (a narrative resource as rich as the patient's narrative), they are equally important in influencing patient outcome.

So, as we mature in the age of big data, what will the role of provider-side data be? Will it be purely regulatory, or will it begin to capture today the qualitative provider-side data we need to influence patient outcomes in the future?

For Reflections on Nursing Leadership (RNL), published by the Honor Society of Nursing, Sigma Theta Tau International. Comments are moderated. Those that promote products or services will not be posted.

No comments:

Post a Comment