Monday, October 10, 2016

Incidence of speech recognition errors in the emergency department

Speech recognition errors occurred in 71% of emergency department notes and 21.1% of notes with errors were judged as critical with potential implications for patient care says a recent study in the International Journal of Medical Informatics.

Investigators looked at a random sample of 100 dictated notes and found 128 errors or 1.3 errors per note.

More than half of the errors were ascribed to speaker mispronunciation. Although when I use speech recognition software, it sometimes does not accurately discern what I am clearly saying.

Other errors involved deleted and added words, nonsense, and homonyms.

An example of a nonsense error was "patient up been admitted for stable gait."

Some of the critical errors (with possible interpretations) were as follows:

Cardiac exam is regular regular (irregular irregular)
Temperature 12.9 (102.9)
Exposure was a pap (bat) was found in room the family house 

Cranial nerves II through XII intact, he is out of 5 motor strength (5 of 5 motor strength) Pulling (pooling) of secretions

The authors concluded, "As this was a pilot study, we did not evaluate whether the errors were associated with actual adverse events."

I have used speech recognition software for several years with occasional amusing results. I have seen numerous gaffes in hospital charts. No one proofreads dictated notes before electronically signing them.

Of the many such errors I have seen, I can't recall a single one that led to an adverse patient outcome.

Luck? Not enough subjects in my experience (Type II error)? Or as I speculated in a blog post about electronic medical records 5 years ago, could it be that no one is reading most of these notes anyway?

Here's what I said back then:

The ability to copy and paste coupled with the ease of dictation results in voluminous notes. As you may know, coding (directly linked to reimbursement) for visits is based on the extent of the care given. “If it’s not documented, it didn’t happen,” goes the saying. But now we have the inverse. It is so easy to document that notes are easily puffed up to “document” extensive encounters with every patient.

Because they are so long, they are difficult to read and the black-on-white appearance of the words on so many screens causes the reader to skim over most of the note and go straight to the plan or recommendations.

I think no one is reading the notes.


William Reichert said...

Yes. No one is reading the notes. Why read the notes when much of it is fabricated. I read an ER doc's note once that claimed the patient had a normal neuro exam but the patient was in fact paralyzed from the waist down.For 5 years.
But it gets more interesting. Pretty soon the EHR will be so thorough and dense with every bit of observation that no one will read it either .
Then we will be back with the patient filling out 2 sheets of info
( complete past HX)whenever he/she sees a new MD. I know this is true because recently when I went to a new MD for for a procedure I filled out the 2 sheets and no one who treated me
bothered to look at even those 2 sheets.The EHR will only be used by government bureaucrats to collect big data.

Skeptical Scalpel said...

William, I have seen similar entries especially about supposed neurologic exams. Some of them occur IN THE SAME NOTE thanks to "copy and paste."

Yes, the government will be collecting big data, most of which will be inaccurate due to much of it being made up.

Cutter said...

I wonder how long it will be before third party contractors are reviewing charts for these inaccuracies and using it to deny payment. Maybe that's started already...

Anonymous said...

be very afraid....a giant land mine of TORTuous data awaiting the legal beagle's nose
put that with the similar grenades left about in the nursing data spread sheets we can no longer read (if we could find them) and our defense attorneys have no hope

Anonymous said...

I'm here to tell you I am not the only one who has had doctor dictated Dragon software notes that has caused problems. Its there. They just hide it.

Even worse is trying to get them fixed. Talk about retaliation.

Did they have Dragon in Ireland?

Anonymous said...

Glad to see Dr. Reichert back posting ... someone call Artiger. :)

Blacksails said...

Ive seen normal abdominal exams documented on patients with frank peritonitis, rectal temps documented on patients s/p APR, "CTABL" on patients s/p pneumonectomy and once saw a normal exam documented on a patient with an open abdomen.

William Reichert said...

Apropos of deception:
When I was in residency in California, we presented a cardiac case to our attending who presented himself as an expert in the physical exam. He "heard a murmur" at the left side of the left side of the chest. He waxed on about this for a while and then we put up the CXR which showed dextrocardia.No one laughed but one guy it is said developed an abdominal hernia
in the effort to contain himself.
I later heard after I moved east that the attending had accepted a job in Oregon.
I think a lot of physical findings are due to the placebo effect.,
which I have observed is the number one cause of all good
fortune in love. war and business.

William Reichert said...

To Cutter:
Like the police, once you are no longer trusted to tell the real story,doctors will soon be required to record their actions on a camera attached to the tongue blades residing in the chest pocket of their white coats.Extra points will be given for providing musical scores to provide an appropriate mood for the action. Heart surgeons will rely on WAGNER and his heroic opera scores when they crack open the chest . Docs who accept medicaid will over use the tune "Pennies from Heaven".
Psychatrists will offer that old stand by as sung by Patsy
CLINE : "Crazy".

Skeptical Scalpel said...

Regarding third-party contractors reviewing charts for mistakes--I would not be surprised if that happened.

We've all seen many examples of poor charting with electronic medical records. I enjoyed the anecdote about the dextrocardia.

Some are already calling for doctors to wear cameras and microphones. It could happen.

artiger said...

Anon at 7:44pm yesterday, I am here at your command.

I would not be opposed to wearing a camera and/or mic. If you are truly spending time interviewing the patients and examining them, what is there to hide? It would also prove that you have explained a procedure, risks, complications, etc., and answered questions. No more he said/she said. I'll bet our legal colleagues would be against it, if they really thought about the unintended consequences.

frankbill said...

What I have found is what I say to my doctor isn't always what gets in the notes. Sometimes not even close

artiger said...

Frank, to be fair, from our perspective, what you told us is exactly what went in the chart. You just remember it differently. That's why I say cameras and microphones would help eliminate such differences in perspective.

Skeptical Scalpel said...

We might as well agree to wear the camera. It may be inevitable. I agree it could be protective to doctors just as it can protect cops from false accusations.

Post a Comment