HIMSS11: Laying the Foundation for Data-Driven Applications

The HIMSS conference was in Orlando, the home of DisneyWorld, last week and it was indeed like an amusement park for health IT professionals.  So many attractions: vendor demos to view in the exhibit hall, concurrent education sessions, and so many colleagues, clients and prospects in one place that it’s difficult to not suffer information overload.  And, I didn’t even mention the receptions and parties (most of which I was too drained to attend).

Meaningful Use = Content + IT

Unlike some of the IT professionals at the conference who felt that HIMSS11 lacked the level of creative innovations on display in past years, I was excited by the progress made in building the infrastructure that will enable a new class of data-driven innovations.  Granted, it was a bit repetitive to have so many vendors touting their ability to help providers meet Meaningful Use requirements and demonstrating what looked like the same dashboard for reporting core quality measures.  But looking beneath the surface to consider how much progress has been made in the past 12 months in shifting the focus from the technology to what can be done once content flows through the technology platform gave this data geek reason to be optimistic about the future.  In fact, I use the word “exciting” twice in this video interview I did with Liza Sisler from Proficient at HIMSS.

Interoperability

Among the highlights for me at HIMSS11 was the Interoperability Showcase, which I found both extremely useful and rather mind-blowing.  The Showcase was useful in understanding a variety of use cases where standards are being applied—mostly in pilot programs—to exchange, aggregate, and analyze data.  The mind-blowing aspect relates to the sheer number of agencies and IT consulting firms working on pieces of the overall infrastructure and regulations, coupled with the realities of our not-so-united states that result in lack of nationwide master indexes and formats.  See Keith Boone’s post called Putting the Lego Together to get a sense of the current state of standards for HIE.

Translating research for clinical decision support tools

I was also pleased to attend the Elsevier press briefing at HIMSS11 where they demonstrated their Smart Content system that builds automated bridges between Elsevier’s extensive body of research information and their clinical decision support (CDS) tools.  Reconfiguring existing research knowledge that largely resides in textual formats for use in clinical applications is a major undertaking and it’s encouraging to see that the largest publisher of research journals has made significant progress in this regard.  On a wider scale, the research community is making progress in reporting results that can more easily be extracted for further analysis (e.g., ClinicalTrials.gov current reporting formats), but crosswalks between research specialties and different types of media will be needed for the foreseeable future, especially as more collaboration occurs between researchers.

Social, mobile, local

The HIMSS conference itself is a perfect use case for the value of social and mobile media. (See Jane Sarasohn-Kahn’s terrific presentation at HIMSS on this topic.)  Without my smart phone and Twitter, I would never have been able to connect with as many people as I did.  Even with these social, mobile and local tools, I managed to miss a few people due to meeting overruns and technical glitches (i.e., connectivity problems in the massive convention center).  But, being able to connect with dozens of people from my online community at an event that had over 31,000 attendees — and share information with the broader online community who weren’t at the conference—clearly demonstrated the value of social, mobile and local media. 

Needed: New Collaborative Models in Medical Research

In a talk I gave in 2009[1], I addressed the challenge of turning the enormous quantities of digital data that will be produced by EHR systems into “reliable, usable” information and emphasized the importance of creating new models of medical research and statistical techniques for dealing with these large universes of new outcomes data.   I went out on a limb at the time –since my training in statistics was in business school, not medical school—but have since found many who support my position among the best and brightest in the medical community. 

Weaknesses of current research methods

Currently we use the term “translational medicine” for the process of taking the results from research studies, typically Randomized Control Trials (RCTs), and transforming them into data that can be used in a clinical setting.  The process includes writing articles for publication to describe the research findings in medical journals (after peer review), which then get further interpreted by clinical teams at medical societies/associations/public health authorities to produce guidelines or other clinical applications.  At the same time, published research results get disseminated in the mass media by healthcare journalists.    Many of the difficulties and inadequacies of this approach have come to light as the health IT infrastructure in the US struggles with integrating clinical evidence into electronic health records (EHRs).   The two toughest issues are:  1) the difficulty of extracting data from journals (print or electronic format) because the journal format wasn’t designed for data extraction, integration or machine analysis and 2) the lack of collaboration between research institutions that leads to an enormous number of research results that don’t build on previous studies and are sometimes contradictory.   As a result, even elaborate data mining engines—or a redesign of journal formats—won’t by themselves solve core problems with our current research system. 

New Data, New Models

Beyond lack of collaboration, there is a more fundamental issue about the appropriateness of RCTs as a source of clinical guidance.   Marya Zilberberg, MD, MPH writes in JAMA that we have an “avalanche of published research” yet the “data generated in an RCT are frequently irrelevant because of their limited generalizability” [2].  The cause of the limited generalizability is the “hetereogeneous treatment effect” and I won’t go into details of what that means here; for that, read Dr. Zilberberg’s blog series on Reviewing Medical Literature, which is now at part 5 and is highly recommended reading.   But, as you can probably guess from the word “heterogeneous”, the problem relates to the fact that we don’t all respond to a specific treatment in the same way.

Another recent article published in New England Journal of Medicine (NEJM)[3] buttresses my position that we need new research models and new incentives for collaborating.  This article presents some stark data on how little emphasis – and financial support – has been placed on outcomes research, best practices, new care models, quality, comparative effectiveness or service innovations relative to total biomedical research (0.1% v. 4.5% of total health expenditures).   The 0.1% will increase to 0.3% in 2010 according to the authors, but that’s still a small percentage considering that we are facing a huge pool of new outcomes data that will be generated by EHRs and haven’t yet agreed upon the best statistical methods for organizing and analyzing these collections of data that hold so much promise for enhancing the clinical value of medical research. 

There are models that have been developed for analyzing outcomes data, especially within the payer segment.  Registries of patient data have existed for some time, but have been limited in scope or the  reliability of the data sources (e.g., claims data).   But, in order to achieve a “higher standard” of clinical value, more collaboration and “development of more robust analytical techniques for ascertaining clinical value”[4] are needed.  

This emerging field offers opportunities for data publishers that understand how to apply master data management (MDM) principles and data analytics/predictive analytics companies in biomedical research that can adapt their models for clinical applications. Perhaps the biggest opportunity is for standards organizations and data publishers to build a collaborative infrastructure for better aligning biomedical research and clinical decision support systems. 

---

[1] http://www.slideshare.net/janicemc/epatientconnections2009-health-content-for-epatients

[2] The Clinical Research Enterprise; Time to Change Course?, JAMA, February 9, 2001—Vol 305, No. 6, Marya D. Zilberberg, MD, MPH,: http://jama.ama-assn.org/content/305/6/604.short.

[3] Biomedical Research and Health Advances, NEJM, February 9, 2011, Hamilton Moses, III, MD, and Joseph B. Martin, MD, PhD: http://healthpolicyandreform.nejm.org/?p=13733.

[4] Ibid.