Study evaluates transcription accuracy in men and women

May 4, 2007

There is a significantly higher rate of transcription error in women compared to men when using commercial voice recognition applications, according to a recent study.

"Our residency program and department recently made the transition to speech recognition from a digital dictation system," said Syed Ali, MD, lead author of the study. "This prompted us to ask research questions about how to increase our accuracy rates and what factors adversely impacted speech recognition," said Dr. Ali.

Ten radiology residents, five male and five female, were each trained on a commercial speech recognition application. Each resident was asked to dictate a standardized set of ten radiology reports containing a total of 2,123 words. Utilizing a commercial software solution, the generated reports were then compared with the original reports and error rates were calculated. The error rate was defined as the sum of the number of word insertions and deletions divided by the total word count for a given report.

According to the study, error rates in the male population ranged from 0.025 to 0.139 while the error rates in the females ranged from 0.015 to 0.206. The results show a higher rate of recognition error in the females compared to the males.

"The immediate impact of the study for radiologists is an increased level of awareness that women may need to spend more time training on the system than their male counterparts and may have to work somewhat harder to make the system successful," said Dr. Ali. "This could include using macros or actually altering dictation style to increase recognition rates," he said.

"Any efforts to improve recognition rates will have a positive impact on physicians and patients of course by reducing error rates and improving productivity," said Dr. Ali.

The full results of this study will be presented on Monday, May 7, 2007 during the American Roentgen Ray Society’s annual meeting in Orlando, FL.

Source: American Roentgen Ray Society

Explore further: Machines learn to understand how we speak

Related Stories

Machines learn to understand how we speak

June 12, 2015

At Apple's recent World Wide Developer Conference, one of the tent-pole items was the inclusion of additional features for intelligent voice recognition by its personal assistant app Siri in its most recent update to its ...

Recommended for you

French teen finds 560,000 year-old tooth (Update)

July 28, 2015

A 16-year-old French volunteer archaeologist has found an adult tooth dating back around 560,000 years in southwestern France, in what researchers hailed as a "major discovery" Tuesday.

Oldest known Koran text fragments discovered

July 23, 2015

Two pages of text written on parchment that are believed to be sections of the Koran (Chapters 18 and 20) have been discovered by a PhD student in a British university library and are believed to be the oldest ever found. ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.