Comparing the Efficiency of Software-Based Speech Recognition Versus Traditional Telephone Transcription in an Outpatient Physical Medicine and Rehabilitation Practice.

Abstract

Speech recognition (SR) uses computerized word recognition software that automatically transcribes spoken words to written text. Some studies indicate that SR may improve efficiency of electronic charting as well as associated cost and turnaround time1,2, but it remains unclear in the literature whether SR is superior to traditional transcription (TT). This study compared the impact of report generation efficiency of SR to TT at the Canadian Armed Forces Health Services Centre. Dragon Medical Dictation™ SR software and traditional telephone dictation TT were used for two prespecified clinical days per week. In order to adjust for note length, total transcription efficacy was calculated as follows: word count/[dictation time+correction time]. The means and standard deviations were then separately calculated for TT visits and for SR visits. Differences in transcription efficacy and in visit measures, including patient demographics, visit duration, number of issues raised during the visit, and interventions performed, were compared using ANOVA, with the significance level set to 0.05. A total of 340 consecutive visits were analyzed; 198 were dictated over the phone using TT and 142 were transcribed using SR software. Dictation efficacy was significantly higher (p<0.0001) for TT as compared to SR, while turnaround times were shorter for SR (0.12 versus 4.75days). In light of these results, the Canadian Forces Health Services Centre in Ottawa has returned to use of TT because the relative inefficiency of report generation was deemed to have a greater impact on clinical care when compared to slower dictation turnaround time.