The implementation of voice recognition software decreased report turn-around time for the department of radiology at the University of North Carolina in Chapel Hill and for 28 of 30 individual faculty members, according to an article published in the July edition of the American Journal of Roentgenology.
"The improvement in report turn-around time does not correlate with workload but does correlate with work habits, suggesting human behavior may play a role in determining the outcome of adopting a productivity-enhancing technology,” stated Arun Krishnaraj, MD, of the department of radiology at the University of North Carolina Hospitals in Chapel Hill, N.C., and colleagues.
The researchers collected data for nine months before and after the implementation of Agfa HealthCare's TalkTechnology 3.0 after a six-month training period, and then they analyzed the effect of work habits and caseload on such variations.
According to the research team, the average report turn-around time for the department before implementation of voice recognition was 28 hours. After implementation of voice recognition, the average turn-around time was 12.7 hours, the study noted. The average number of verified reports per month during the study period before implementation was 16,561. During the study period after implementation of voice recognition, the department averaged 17,427 reports per month, a 5 percent increase in volume.
The improvement in report turn-around time for individual faculty members ranged from –33 percent to +93 percent, and the rank order did not change significantly, the authors wrote. Faculty members' ranks in report turn-around time did not correlate significantly with volume rank before and after implementation of voice recognition.
Thirteen radiology faculty members who had type 1 work habits--that is, reviewed, revised and finalized reports at the time of image review--benefited the most from use of voice recognition, posting an average of 66 percent improvement in report turnaround time, the study found.
The eight attending radiologists who had type 2 work habits--they reviewed images with the trainee and verified reports in several batches daily after the trainee had made appropriate corrections after each session--posted an average of 60 percent reduction in report turn-around time after implementation.
The nine attending radiologists who had type 3 work habits (similar to type 2, but verified reports less frequently, i.e., once daily to biweekly) posted an average 24 percent reduction in turn-around report time.
Although the team noted certain limitations to the study, such as the lack of data on the financial effect, Krishnaraj and colleagues did note that their results yielded the following observations:
- An individual’s work habits affect the effectiveness of voice recognition; and
- Caseload and change is caseload did not significantly affect report turnaround time.
“Our data confirm the results of previous studies that implementation of a voice recognition system can lead to a significant decrease in report turn-around time,” concluded the authors. “Our study, however, showed that although percentage improvement in report turnaround time after implementation of voice recognition varied a great deal among members of an academic department, the rank order of individual faculty members did not vary greatly."