Monday, April 13, 2009

MORE Reasons To Avoid Speech Recognition

A recent JACR article by Quint, et. al., noted that "More than 20% of our reports contained potentially confusing errors, and most radiologists believed that report error rates were much lower than they actually were." In response, Peter Marcovici, M.D., a radiology resident at UCSD writes about his own in-house survey. On a scale from 1-5, with 1 being "strongly disagree" and 5 being "strongly agree," his results were as follows:

1. I am satisfied with our VR software: 2.2
2. Our VR software increases my productivity/efficiency at work: 1.9
3. Our VR software decreases my productivity / efficiency at work: .2
4. Using our VR software introduces errors in communication: 4.2
5. I have seen errors in prior reports that I attribute to our VR software (not diagnostic errors): 4.4
6. I have been notified by a clinician because of an error due to our VR software: 3.8
7. I have seen an error attributable to our VR software that has significant clinical implication: 3.8
8. I have had to addend a report because of an error generated by our VR software: 4.1
9. Macros in our VR software increase completeness: 2.9
10. Macros in our VR software decrease accuracy: 3.6
11. Using our VR software enhances patient care and safety: 2.3
12. Our VR software increases potential for malpractice: 3.8
13. Our VR software allows for more time for teaching, learning, and attending conferences: 2.0
14. When reviewing reports generated by our VR software (before finalizing them), I notice errors which need correcting: 4.1
15. When comparing alternative systems (i.e., human transcription services), our VR software is . . .
a. Faster: 1.8
b. More accurate: 1.8
c. Leads to more confusing reports: 3.6
He concludes:

Does it make sense for radiologists to divert their gaze and attention to a third screen to edit thousands of words of text daily?
I conclude: NO! Which is no surprise to anyone.


Anonymous said...

Dr Dalai,

From a Rad's stand-point what do you see becoming of Medical Transcibers? Will they eventually become proof readers or will Speech Rec flop amongst most Rad's and keep the perpetual machine going as it is today?


Anonymous said...

I'm one of Dr. Marcovici's resident colleagues at UCSD and wholeheartedly agree with all of his comments. Speech recognition software seems to be particularly prevalent at academic centers (for obvious reasons, it is a lot cheaper to keep a resident after hours doing corrections than pay a transcriptionist). I fear SR/VR is creating an entire generation of residents who are A. less educated (they spend all their time transcribing, not looking at the studies or reading) and B. can't dictate on their own without a template someone else has created for them. Thank God 1 of the institutions we rotate through uses good ole transcriptionists so we won't dictate like complete fools when we finish our training.

Unknown said...

Your conclusion of 'No' is inarguable by your fellow radiologists (IMO anyway). But so what? VR is forced down our throats by the hospitals ('or shall we put your contract out for bid?'). Can this possibly change unless we (radiologists) are willing to pay for our own transcriptionists?