The use of speech recognition software helped a community radiology practice improve radiology report turnaround times 24-fold, according to a study published recently 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. 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. The authors of the JACR study, led by Luciano Prevedello, M.D., of Brigham and Women's Hospital in Boston, wanted to see whether those results are applicable to community hospitals considering the major differences in workflow.
As reported in an article in AuntMinnie.com, the authors pointed out that slow turnaround times, even in community-based practices, can be barriers to coordination of care. "If report turnaround time is not optimized in the community setting, patients may be transferred with incomplete medical records," the authors wrote. "This approach can be detrimental to continuity of care during the patient hand off [between the transferring and receiving institutions]."
The authors looked at a 150-bed community hospital that implemented speech recognition software between May 2011 and July 2011, and analyzed turnaround time and radiologist productivity in the five months before and after implementation.
Turnaround times were defined as the time between image acquisition and signoff on the final radiology report. The researchers found that the median turnaround time decreased from 24 hours to just one hour after implementation of the software, 80th percentile report turnaround times decreased from 60 to 10 hours, and that 95th percentile from 165 hours to 33 hours.
"Speech recognition software can be successfully implemented in a community hospital that has no radiology trainees, and its implementation yields substantial, multifold improvements in radiology report turnaround time," Prevedello and colleagues wrote. "These improvements can be achieved rapidly and without significant adverse impact on radiologist productivity."