Study Shows Value of NLP in Pinpointing Quality Defects

For years, we’ve heard about how much clinical information is locked away in payer databases. Payers have offered to provide clinical summaries, electronic and otherwise, The problem is, it’s potentially inaccurate clinical information because it’s all based on billing claims. (Don’t believe me? Just ask “E-Patient” Dave de Bronkart.) It is for this reason that I don’t much trust “quality” ratings based on claims data.

Just how much of a difference there was between claims data and true clinical data hasn’t been so clear, though. Until today.

A paper just published online in the Journal of the American Medical Association found that searching EMRs with natural-language processing identified up to 12 times the number of pneumonia cases and twice the rate of kidney failure and sepsis as did searches based on billing codes—ironically called “patient safety indicators” in the study—for patients admitted for surgery at six VA hospitals. That means that hundreds of the nearly 3,000 patients whose were reviewed had postoperative complications that didn’t show up in quality and performance reports.

Just think of the implications of that as we move toward Accountable Care Organizations and outcomes-based reimbursement. If healthcare continues to rely on claims data for “quality” measurement, facilities that don’t take steps to prevent complications and reduce hospital-acquired infections could score just as high—and earn just as much bonus money—as those hospitals truly committed to patient safety. If so, quality rankings will remain false, subjective measures of true performance.

So how do we remedy this? It may not be so easy. As Cerner’s Dr. David McCallie told Bloomberg News, it will take a lot of reprogramming to embed natural-language search into existing EMRs, and doing so could, according to the Bloomberg story, “destabilize software systems” and necessitate a lot more training for physicians.

I’m no technical expert, so I don’t know how NLP could destabilize software. From a layman’s perspective, it almost sounds as if vendors don’t want to put the time and effort into redesigning their products. Could it be?

I suppose there is still a chance that HHS could require NLP in Stage 3 of meaningful use—it’s not gonna happen for Stage 2—but I’m sure vendors and providers alike will say it’s too difficult. They may even say there just isn’t enough evidence; this JAMA study certainly would have to be replicated and corroborated. But are you willing to take the chance that the hospital you visit for surgery doesn’t have any real incentive to take steps to prevent complications?

 

About the author

Neil Versel

Neil Versel

3 Comments

  • NLP is still “guess work”. The long-term solution is to correctly record the complete semantics of concepts based on a transportable information model. Then and only then will decision support be ubiquitous and measurable.

  • For quite a while I have been considering that perhaps billing file standards (X12) should merge with EHR interchange standards (HL7 and emerging standards). There are several reasons for this crazy idea, and quite a few against it too. However, for fun, a few interesting reasons for same are: 1) standardization of exchange types on one terminology, one format (X12, or HL7, or something, but just ONE), 2) the fact that to prove that services were reasonable and necessary, payers often request medical records ANYWAY, 3) integrated billing and EHR/clinical systems work better than separate ones (in my experience) and 4) most systems already produce one of the aforementioned formats and people have experience with them – why add something new.

    As for natural language processing, the graduate school I went to did a lot of research on the topic using things like SNOMED and clinic abstracts from scholarly papers. There is no reason NLP should destabilize anything – it is just another tool, another set of algorithms (albeit complicated and always under research) in the toolkit to analyze data, whether it be structured or unstructured in nature.

    I have no doubt that NLP can be a helpful tool, but it’s just another tool. Healthcare has been so behind the times when it came to IT, and has only so recently been coming up to speed, that it latches on to every technology that’s “new” to it as a silver bullet. Let’s calm down the “fad” machine!

  • Jon,
    Of course the biggest challenge with your suggestion I think would be getting the insurance companies to switch to the other standard. They would love the extra data if it was done right, but they would hate transitioning their systems to support the HL7 standard.

Click here to post a comment
   

Categories