In many of our Meaningful Use Monday series we focused on a lot of the details around the meaningful use regulations. In this post I want to highlight one of the strategies that I’ve seen a bunch of EHR vendors and other EHR related companies employing to meet Meaningful Use. It’s an interesting concept that will be exciting to see play out.
The idea is what many are calling clinical data abstraction. I’ve actually heard some people refer to it as other names as well, but clinical data abstraction is the one that I like most.
I’ve seen two main types of clinical data abstraction. One is the automated clinical data abstraction. The other is manual clinical data abstraction. The first type is where your computer or server goes through the clinical content and using some combination of natural language processing (NLP) or other technology it identifies the important clinical data elements in a narrative passage. The second type is where a trained medical professional pulls out the various clinical data elements.
I asked one vendor that is working on clinical data abstraction whether they thought that the automated, computer generated clinical abstraction would be the predominate means or whether some manual abstraction will always be necessary. They were confident that we could get there with the automated computer abstraction of the clinical data. I’m not so confident. I think like transcription the computer could help speed up the abstraction, but there might still need to be someone who checks and verifies the data abstraction.
Why does this matter for meaningful use?
One of the challenges for meaningful use is that it really wants to know that you’ve documented certain discrete data elements. It’s not enough for you to just document the smoking status in a narrative paragraph. You have to not only document the smoking status, but your EMR has to have a way to report that you have documented the various meaningful use measures. In comes clinical data abstraction.
Proponents of clinical data abstraction argue that clinical data abstraction provides the best of both worlds: narrative with discrete data elements. It’s an interesting argument to make since many doctors love to see and read the narrative. However, all indications are that we need discrete data elements in order to improve patient care and see some of the other benefits of capturing all this healthcare data. In fact, the future Smart EMR that I wrote about before won’t be possible without these discrete healthcare data elements.
So far I believe that most people who have shown meaningful use haven’t used clinical data abstraction to meet the various meaningful use measures. Although, it’s an intriguing story to tell and could be an interesting way for doctors to meet meaningful use while minimizing changes to their workflow.
Side Note: Clinical data abstraction is also becoming popular when scanning old paper charts into your EHR. Although, that’s a topic for a future post.
Huh.
I’ve not yet seen an EHR that tried to pull the CQM data from a non-structured element.
In fact, what I’m seeing is the need, in some cases, for dual input of data (or selecting multiple check boxes in various locations) in order for the EHR to properly count it – seems asinine I know.
The irony of pulling the data from a non-structured, or narrative area is…there will need to be some structure added to ensure the data is abstracted properly.
Medical data has a bunch of numbers. 35 can mean many things.
To indicate smoking, the system would need to have some sort of trigger to work properly, like:
Smoker: Yes
rather than: the patient has used tobacco for 10 years
One provider may write it differently than another, and therefore may come out with different data.
Yes, one can argue that data abstraction provides the best of both worlds…but when the provider goes to attest, and the system is pulling low compliance numbers…things are going to really stink.
There are certainly challenges with automating it, but you’ll be amazed at how good some of these systems do. I’m with you though that it’s likely that someone will need to check and verify some of the automated abstraction of data. At least that’s my belief.
The new Praxis 5 has this capability and more with its new “datum” feature that collects discreet data elements within narrative text combined with its new “data miner” and query engine on the back end. Zero check-boxes or additional clicking required. The key is using the power of the Praxis Concept Processor to set the system up quickly and efficiently while maintaining the speed of generating unique high quality notes. Clinics need good product training and to take a methodical approach to system setup and clinic work flow. When done correctly it is 100% automated with no need for additional human intervention.
John, I do agree that most of the EMRs out there will have problems with this. I believe this is one of the reasons why stage 2 MU has been delayed. For clinical data abstraction most EMRs are highly user dependent, thus prone to errors, and add extra clicks/charting time to each visit. Then on the back end it’s a case of “garbage in = garbage out”.
[…] the scanning to an outside company. They do amazing work really fast. They even offer services like clinical data abstraction so you can really enhance the value of your scanned […]