Many have been keeping up to date on the pulse of ICD-10’s pending rollout with broadcasts such as Talk-Ten-Tuesday and other informative industry insider resources, many of which can be found at ICD10monitor.com. All these offerings provide clarity among the ICD-10 implementation fog.
With so many other healthcare changes happening simultaneously, however, one not talked about openly enough is big data. Just like with ICD-10, those familiar with this have foresight regarding what is to come. For those who might be less familiar with big data, a key point is this: the real revolution is not in the machines that calculate data, but in the data itself and how it’s being used.
ICD-10 is a very important component to all of this, largely because it is closely tied to recent movements to change models of care – going from fee-for-service to bundled payments, for example, plus the advent of electronic health records, focus on collaboration, accountable care organizations, reducing readmissions, and minimizing complications and infections.
According to the U.S. Department of Health and Senior Services (HHS), ICD-10 contains more than 155,000 codes and can be used to document far more complex diagnoses and procedures than the ICD-9 series, which has about 17,000 codes.
“All of the other priorities you’ve been working on require a thorough understanding of your patient population, including their diagnoses, risk factors and resource utilization in order to have the effective analytics that will help hospitals survive the changing health care environment,” American Hospital Association (AHA) Director of Coding and Classification Nelly Leon-Chisen recently explained.
Those words were echoed by Jayne Hart Chambers, senior vice president of strategic policy at the Federation of American Hospitals, as far back as 2008.
“We really need the robustness of ICD-10 to make some of the quality measures we want work,” she said at the time.
Fast-forward a few years, and Leon-Chisen predicts that “If you don’t have the clinical analytics to survive in the changing healthcare environment we’re facing (now), you may not survive until 2025 (the time ICD-11 is predicted to arrive in the U.S.) to find out.”
All of this is being built on what big data, with the help of ICD-10, will bring to the table. Data is no longer regarded as static or stale; rather, data has become a raw material of business, a vital economic input used to create a new form of economic value. The next challenge, once healthcare providers organize their information troves for population-based management, will be to bring relevant detail to the action level. Population health has a global feel to it, but basically it’s a means to think broadly in order to act pointedly.
“Analytics used to be the province of IT professionals who had to build preset analytical queries proposed by clinicians, but now such tools are becoming more flexible, allowing enterprises to dream up analyses on the fly and run follow-up queries over a matter of hours instead of the days or weeks it once took,” explained David Krueger, medical director for Bellin Health & ThedaCare Healthcare Partners in Green Bay, Wisc.
There currently are a slew of healthcare data-dicing firms stampeding into population-management market opportunity. A recent report on the state of IT readiness for accountable care listed a baker’s dozen of firms, specifically, each with its own sliver of market share.
“These firms tend to be turnkey approaches to pulling data together from various sources,” said Colin Buckley, strategic operations director at KLAS Enterprises, which co-authored the accountable care readiness report with Leavitt Partners. “They have their own data repository for creating registries, sorting data and guiding provider priorities. Some vendors incorporate built-in intelligence based on what they’ve learned offering services in such other areas of healthcare as financial reporting.”
This poses some interesting questions.
“Wouldn’t it be great, as you worked on reducing readmissions, if you could know that the readmissions were due to patients failing to take their medications, and why?” Leon-Chisen asked. “As you consider entering into collaborative arrangements, wouldn’t you want to know patient populations you are treating, what risk factors they have, what you can do about them, and what resources they are utilizing?”
Those types of questions and more can be answered at great speed using combined patient demographic data along with ICD-10 diagnosis codes, all of which are being collected within patients’ electronic medical records. Having a larger data set to search from, using ICD-10, offers clinical analysts added depths to drill down into and gain finer details regarding answers they may be looking for. Sometimes it’s what you find that you weren’t looking for that brings about answers as well.
In the end it’s also what brings about better patient care and produces the best patient outcomes. That’s what separates the good healthcare organizations from the great ones.
That’s why ICD-10 is a big piece in the big-data healthcare puzzle.
About the Author
Andrew Torres is a recent graduate from The College of St. Scholastica in Duluth, Minn, where he held a major in health information management and a minor in computer information systems. His healthcare experience comes from working as an analyst for the data warehouse in the information systems department of a major health system in Minnesota.
Contact the Author
To comment on this article please go to email@example.com
Mayer-Schonberger, Viktor, and Cukier, Kenneth. Big Data: A Revolution That Will Transform How We Live, Work, and Think. New York: Houghton Mifflin Harcourt, 2013. Print.
Leon-Chisen, Nelly. “If We Procrastinate Long Enough, Will ICD-11 Be Ready?” H&HN Hospitals & Health Networks. 03 2012: 12. Print.
Morrissey, John. “Concentrating on Data That Matter.” H&HN Hospitals & Health Networks. 04 2013: 22-23. Print.
Conn, Joseph. “Ready or not… HHS prepares for ICD-10; some say not so fast.” Modern Healthcare. 38.34 (2008): 16. Web. 24 Jun. 2013. <ISSN: 0160-7480>.