"IT in Health Care: Voice Recognition

 

Tools Make Rounds at Hospitals"

CASE

The infamous doctor’s scrawl may finally be on the

 

way out.

 

Voice technology is the latest tool health care

 

providers are adopting to cut back on time-consuming

 

manual processes, freeing clinicians to spend more time

 

with patients and reduce costs.

 

At Butler Memorial Hospital, voice-assisted technology

 

has dramatically reduced the amount of time the Butler, Pa.,

 

hospital’s team of intravenous (IV) nurses spends recording information

 

in patients’ charts and on other administrative tasks.

 

And at the Cleveland Clinic’s Fairview Hospital, doctors

 

are using speech recognition to record notes in patients’

 

e-medical records.

 

Butler recently completed a pilot project where three IV

 

nurses used Vocollect’s AccuNurse hands-free, voice-assisted

 

technology along with Boston Software System’s workflow automation

 

tools. The nurses were able to cut the time they spent

 

on phone calls and manual processes, including patient record

 

documentation, by at least 75 percent. Now, Butler is rolling out

 

the voice technology for its full IV team of four nurses and seven

 

other clinicians to use for patient care throughout the facility.

 

The productivity boost from the voice-assisted tools also

 

helps with the hospital’s expansion plans, says Dr. Tom

 

McGill. Butler VP of quality and safety.

 

Butler will soon add about 70 beds—growing from 235

 

beds now to more than 300—but it won’t need to expand the

 

IV nursing team because of the time savings from the voiceassisted

 

technology, McGill says.

 

In the past, when a patient needed IV care, such as a

 

change in the intravenous medication being administered, an

 

IV nurse would be paged. The nurse would have to call the

 

patient’s nursing station or the doctor requesting the IV to obtain

 

details. The nurse then would prioritize the request with

 

all the existing IV orders. Once IV care was completed, nurses

 

would record what they did in the patient’s e-medical record.

 

With the AccuNurse, which combines the use of speech

 

recognition and synthesis for charting and communication,

 

Butler’s IV nurses wear lightweight headsets and small

 

pocket-sized wireless devices that enable them to hear personalized

 

care instructions and other information about

 

patients’ IV needs.

 

IV requests are entered into Butler’s computer system,

 

which sends them through the Vocollect system to the appropriate

 

headset. IV nurses listen to details about new orders

 

and use the system to prioritize IV orders.

 

When they finish caring for a patient, nurses record

 

what they did in the patient’s e-medical record using voice

 

commands. “The nurses can document as they’re walking to

 

the next patient’s room,” says McGill. Once they finish with

 

one patient, nurses say “next task” to obtain instructions for

 

the next patient, McGill says.

 

The system has shown itself to be capable of understanding

 

different accents, he said. Butler is evaluating expanding

 

use of the voice-assisted technology to other clinical areas,

 

including surgery. The technology could be used to help ensure

 

that surgical staff complete patient safety checklists.

 

McGill wouldn’t say how much Butler paid for the system,

 

but he expects the ROI will be realized in 12 to

 

18 months. “It’s very affordable,” he notes. Meanwhile,

 

Dr. Fred Jorgenson, a faculty physician at Cleveland Clinic’s

 

Fairview Hospital, is using Nuance’s Dragon Medical speech

 

recognition technology to speak patient notes into the hospital’s

 

Epic EMR (electronic medical records) system.

 

“I’m not a fast typist,” Jorgenson says. “Many doctors

 

over a certain age aren’t. If I had to type all the time, I’d be

 

dead.” And, at 13 cents to 17 cents per line, dictation transcription

 

services are expensive.

 

“In primary care, patient notes can be 30 to 40 lines.

 

That adds up,” he says. Fairview is saving about $2,000 to

 

$3,000 a month that might have otherwise been spent on

 

transcription, Jorgenson said. It cost about $3,500 to get

 

Dragon up and running.

 

With transcription services, the turnaround time is 24 to

 

36 hours before information is available in the EMR. Spoken

 

notes are available immediately.

 

Jorgensen describes the accuracy of Dragon Medical’s

 

speech-to-text documentation as “very good,” especially

 

with medical terms and prescriptions. “It rarely gets medical

 

words wrong,” he says. “If you see a mistake, it’s usually with

 

‘he’ or ‘she,’ and you can correct it when you see it.”

 

Mount Carmel St. Ann’s hospital in Columbus, Ohio,

 

has been among the early wave of health care providers

 

using electronic clinical systems bolstered with speech recognition

 

capabilities. About seven years ago, emergency

 

department doctors at Mount Carmel St. Ann’s hospital

 

began having access to Dragon’s speech recognition software

 

not long after an e-health record system from Allscripts was

 

rolled out there.

 

When the e-health record was first rolled out—without

 

the voice capabilities—Mount Carmel St. Ann’s doctors

 

didn’t necessarily see the kind of productivity boost they

 

had been hoping for, in large part because they found themselves

 

spending a lot of time typing notes, says Dr. Loren

 

Leidheiser, chairman and director of emergency medicine at

 

Mount Carmel St. Ann’s emergency department. But as

 

more Mount Carmel St. Ann’s ER doctors began incorporating

 

the speech recognition capabilities into their workflow—

 

whether speaking notes into a lapel microphone or into a

 

computer in the patient room or hallway—the efficiency

 

picked up tremendously, says Leidheiser.

 

Also, before using the Dragon software, the ER department

 

spent about $500,000 annually in traditional dictation

 

transcription costs for the care associated with the hospital’s

 

60,000 to 70,000 patient visits yearly at the time. That was cut

 

down “to zero,” he says. The return on investment on the

 

speech recognition, combined with the use of the e-health

 

record system, was “within a year and a half,” notes Leidheiser.

 

Leidheiser also makes use of time stuck in traffic to dictate

 

notes that are later incorporated into patient records or

 

turned into e-mails or letters. Using a Sony digital recorder,

 

Leidheiser can dictate a letter or note while in his car, then

 

later plug the recorder into his desktop computer, where his

 

spoken words are converted to text.

 

Speech recognition technology is also helping U.S. military

 

doctors keep more detailed patients notes while cutting

 

the time they spend typing on their computers. By 2011, the

 

U.S. Department of Defense expects to have implemented its

 

integrated, interoperable electronic medical record system—

 

AHLTA—at more than 500 military medical facilities and

 

hospitals worldwide.

 

The system will be used for the care of more than 9 million

 

active military personnel, retirees, and their dependents.

 

Military doctors using the AHLTA system also have access

 

to Dragon NaturallySpeaking Medical speech recognition

 

technology from Nuance Communications’ Dictaphone

 

health care division, allowing doctors to speak “notes” into

 

patient records, as an alternative to typing and dictation.

 

Over the last year, the adoption of Dragon has doubled,

 

with about 6,000 U.S. military doctors using the software at

 

health care facilities of all military branches, including the

 

Air Force, Army, Navy, and Marine Corps.

 

The use of Dragon Naturally Speaking voice recognition

 

software with the AHLTA e-health record systems is

 

freeing doctors from several hours of typing their various

 

patient notes each week into the AHLTA, he said. Being able

 

to speak notes into an e-health record at the patient beside—

 

rather than staring at a computer screen typing—also helps

 

improves doctors’ bedside manner and allows them to narrate

 

more comprehensive notes, either while the patients are

 

there or right after a visit. That cuts down on mistakes

 

caused by memory lapses and boosts the level of details that

 

are included in a patient record, says Dr. Robert Bell

 

Walker, European Regional Medical Command AHLTA

 

consultant and a family practice physician for the military.

 

The voice capability “saves a lot of time and adds to the

 

thoroughness of notes from a medical and legal aspect,” says

 

Dr. Craig Rohan, a U.S. Air Force pediatrician at Peterson

 

Air Force base in Colorado. The ability to speak notes directly

 

into a patient’s electronic chart is particularly helpful

 

in complicated cases, where a patient’s medical history is

 

complex, he says. Text pops up on the computer screen immediately

 

after words are spoken into the system, so doctors

 

can check the accuracy, make changes, or add other details.

 

Also, because spoken words are immediately turned into

 

text, the medical record has “a better flow” to document patient

 

visits. Previously, “the notes that had been created by

 

[entering] structured text into the AHLTA system looks

 

more like a ransom note,” says Walker, with information

 

seemingly randomly pasted together.

 

Doctors can speak into a microphone on their lapels to

 

capture notes in tablet PCs during patient visits, or speak into

 

headsets attached to desktop or wall-mounted computers. The

 

storage requirement of voice notes is “small,” especially when

 

compared with other records, such as medical images, says

 

Walker. By adding spoken notes to medical records, e-mails,

 

and letters, “it’s easier to tell the story,” remarks Leidheiser.

 

CASE STUDY QUESTIONS:

 

1. What are some of the benefits afforded to organizations

 

implementing voice recognition technologies in these

 

settings? How can you quantify these benefits to assess

 

the value of the investment? Provide several examples

 

from the case.2. There is no margin for error when working in a health

 

care setting. How would you go about implementing

 

these technologies in this high-risk environment? What

 

precautions or approaches would you take to minimize

 

risks? Develop some recommendation.

 

3. In what other areas of medicine would you expect technology

 

to make inroads next? Where do you think it would

 

be most beneficial, and how would it change the way

doctors and nurses work today? Provide several examples