Speech Recognition no Panacea to Change Work Habit

Study published at RSNA 2008 and reported on in Auntminnie: SR Technology no panacea for reporting work habit change (registration required) reviewed the implementation of speech recognition technology at University of North Carolina Hospitals in Chapel Hill. This was not a review of the effectiveness of Speech Recognition overall since:

It's a well-known fact that implementing speech recognition (SR) technology can revolutionize report turnaround time and dramatically enhance the workflow efficiency of radiology departments.

But the question for this study was "can it improve the work habits of individual radiologists?". Not surprisingly technology does not change work habits. Radiologists who were slow to report before the implementation of speech were slow to report after the implementation of speech. Installing technology that speeds up the overall process does not change reporting behavior. Rank order of turnaround times by radiologists did not change pre and post implementation

The learning point - using technology to change behavior tends not to be successful. Technology should adapt to individual behavior rather than trying to change the behavior. Providing tools and technology that does not require a change behavior is more likely to be successful. Often behavior has been refined over the course of time that is optimal for that individual and circumstance - change is not always better or more efficient.

Doctors in the Typing Pool

An interesting blog from Westby Fisher on the failures of EMR systems that what it has turned our clinical staff into:

"...the world's most expensive typing pool has been born"

As he notes

Each morning, without fail, there's one or two individuals circling the computer terminals waiting for access to these electronic monetary portals, like children waiting to grab the last chair when the music stops.

That's true but I think the missing comparison here is how it used to be before the advent of the EMR's.....I can remember the same scene on the wards I worked on but instead of waiting for a seat in front of a computer it was waiting to get access to the "notes trolley" and the wait and frustration was no different and in many respects worse since there was only one record and therefore only one person could access it and enter data into the record. Much of this could be fixed with more accessibility, more computers or even better mobile access to the clinical data (here's one example combining the latest user friendly gadget with EMR access - you can see a video of this in action here:

But the issue of canned content being generated in large quantities with shortcut codes and pulling information from other sources to create a document is a problem. To create my note I can type
.id .pmh .psh .cmed .all .soc ....... you get the picture. These commands pulling data from other sources that add little to the actual clincal value of the document:

....demographics from the Central Registration.....four pages of Past Medical History...the original work was completed by the patient's poor primary care physician, neatly organized, but never to be updated again

.......page and a half of the current medications, their dose, prescribing physician, half of which come from self-generated 'CYA' hypoglycemia orders are also self-generated in the interest of 'safety'.....

......."Mother died of CA" automatically spits out previously entered by the hospitalist - bless their soul - so that billing to Medicare can go from Level 4 to Level 5 for the rest of the health care team

When clinical documentation really was clinical documentation and not just an automatic regurgitation of previous clinical notes captured by other people, the process of documenting was part of the clinicians analytical process. Entering the details was important as it afforded an opportunity to think about the patient, their history, symptoms, and signs and provided real input to the diagnostic process to arrive at a differential diagnosis and plan for the next steps. Clinicians are still trying to do this but all the while working to satisfy the documentation requirements so they can bill for their services

The rest is for Medicare and has been added repetitively and
identically by countless other individuals, all whom enter the same
content to assure achieving the maximum amount billed by law for their
services. Not that any of it is read, mind you, but it'd better be
there, lest the Medicare auditors descend on your facility.

Technology has helped kill the richness and detail of clinical documents and turned detail rich
reports into dumbed down "fill in the blank" cookie cutter reports that do not
reflect the richness of the information that physicians wants to provide to the colleagues.

In a recent discussion with a busy radiologists he remarked that what the referring physician needs from him is "more detail". He wants to provide the referring physician
the clinical information they need to treat the patient giving them the confidence in the information they receive with a rich detailed report that speaks their language.

So as not to reach the destination for the future of medicine painted by Westby Fisher:

Will they (future doctors) actually process what is entered, or merely become
highly-efficient typists and plagiarists in the never-ending quest to
become more "efficient" health care providers?

we must provide the tools that allow for clinicians to document clinical information efficiently with the richness of medical language while still providing the computers and clinical systems with their bits and bytes of data that allows these tools to function and help support the clinicians in the delivery of clinical cared