Mr. Ramaswamy et al., Continuous speech recognition in MR imaging reporting: Advantages, disadvantages, and impact, AM J ROENTG, 174(3), 2000, pp. 617-622
Citations number
13
Categorie Soggetti
Radiology ,Nuclear Medicine & Imaging","Medical Research Diagnosis & Treatment
OBJECTIVE. Our objective was to describe our experience with a commercially
available continuous speech recognition system, highlighting the advantage
s, disadvantages, and costs compared with those of conventional transcripti
on for MR imaging reports.
MATERIALS AND METHODS. Data from 5072 reports generated in our MR imaging s
ection during a 9-month period after the implementation of a commercial con
tinuous speech recognition system were compared with 4552 reports produced
during the same period 1 year earlier. Information pertaining to the use of
continuous speech recognition, report turnaround time, word recognition ra
te, report appearance, and equipment costs was collected.
RESULTS. After its system installation, continuous speech recognition was u
sed to dictate 81.8% of all reports. The mean report turnaround time decrea
sed from 87.8 to 43.6 hr, and report availability at 24 hr increased from 1
0.5% to 62.5%. The system was found to have an average word recognition acc
uracy of 92.7% for spontaneous dictation. Mean report length declined from
95 to 60 words, with an increase in spacing errors from 0.3 to 8.0 per 1000
words and a decrease in spelling errors from 3.0 to 0.8 per 1000 words. In
itial hardware and software costs were approximately $10,000, compared with
a yearly cost of $12,000 for human transcription.
CONCLUSION. Although the technology is still evolving and was evaluated in
its earliest implementation stages, continuous speech recognition nonethele
ss markedly improved report turnaround time and proved cost-effective.