Does front-end speech recognition make for a smooth-running operation, or does it simply complicate documentation and patient care?
Doctors and researchers debate this question in the November 2013 issue of health information management magazine For the Record.
Gary David, Ph.D., an associate professor of sociology at Bentley University in Waltham, Mass., notes in the article that front-end speech recognition does not always save labor, but it does change workflow.
With voice recognition software, "the issue of quality assurance becomes paramount," David says.
"Who is doing the proofreading? he adds. "In the past, the transcriptionist would correct the errors that invariably came up when doctors dictate. Without the medical transcriptionist, you have no one in charge of quality assurance but the physicians themselves.
"These programs still make mistakes and, in my research, I found that physicians would sometimes let small errors go--substituting 'he' for 'she,' for instance," David continues. "At times, the errors can be very difficult to identify. So it doesn't make sense for doctors to spend their time proofreading transcriptions."
The review process is what costs doctors the most time, David says.
Tracy Lawrence, an emergency department physician and director of risk management at Henry Mayo Newhall Memorial Hospital in Valencia, Calif., meanwhile, tells For the Record that his hospital is happy with its use of voice-recognition software, and that it has improved workflow.
"Prior to [voice recognition software], we used standard dictation to update the medical records of approximately 50,000 patients per year. This translated into about $1.5 million spent on back-end transcription each year," Lawrence says. "Now, we're realizing a significant financial savings."
As FierceMedicalImaging reported in November, the use of speech recognition software helped a community radiology practice improve radiology report turnaround times 24-fold, according to research published in the Journal of the American College of Radiology.
Previous studies have shown that implementing speech recognition software can have important benefits for large academic practices, as well. For example, a study published in the American Journal of Radiology in July 2010, found that the introduction of voice recognition at one academic medical center helped the facility's radiology department decrease average report turnaround time from 28 hours to 12.7 hours.
Last month, a HIMSS Analytics report named voice recognition a market to watch, categorizing it as having an "aggressive" adoption rate in the U.S. hospital marketplace as compared to 20 other applications in their report.
Jennifer Horowitz, senior director of research for HIMSS Analytics, told FierceHealthIT that the report includes historical data from the HIMSS Analytics database, which itself includes a census of U.S. hospitals. She added that the report evaluates the trends they've seen in the past few years. Speech recognition had been implemented at 47 percent of the hospitals surveyed, and with its compounded annual growth rate (CAGR) still increasing, there's a lot of "upward room for growth," Horowitz said.
To learn more:
- read the article in For the Record
HIMSS Analytics: Virtualization, voice recognition markets to watch
Speech recognition helps rad practice cut turnaround times
Desktop virtualization infrastructure offers hospitals fast ROI
Worried about BYOD? Just wait for its cloud-based spin-off
Electronic tools help to lower image transfer costs
Put your health IT dollars in cloud computing, virtual apps
EHR security: Are providers better off going to the cloud?