Peer-reviewed research
Voice recognition versus transcriptionist: Error rates and productivity in MRI reporting
Rodney H. Strahan and Michal Elisabeth Schneider-Kolsky, Journal of Medical Imaging and Radiation Oncology, 2010 · DOI 10.1111/j.1754-9485.2010.02193.x
Read the originalRead on October 16, 2026
- What it is
- A retrospective audit of 50 MRI reports dictated with voice recognition and 50 finalised reports made by a transcriptionist, for two radiologists. It compared typographical errors and turnaround times.
- How much weight it carries
- Peer-reviewed but small, with two radiologists and retrospective sampling. It is an older voice recognition system, and it contradicts the Iowa practice findings that report lower error rates. Read it as evidence that error rates depend on the system and workflow.
Facts taken from this source
- In a 2010 MRI audit of 50 voice-recognition reports and 50 transcriptionist reports, 42 and 30 finalised voice-recognition reports for the two radiologists contained errors, against 6 and 8 transcriptionist reports.
“Forty-two and 30 of the finalised VR reports for each of the radiologists investigated contained errors. Only 6 and 8 of the transcriptionist-generated reports contained errors.”