This Article Full Text Full Text (PDF) Submit a response View responses Alert me when this article is cited Alert me when eLetters are posted Alert me if a correction is posted Services Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via Google Scholar Google Scholar Articles by Devine, E. G. Articles by Curtis, A. C. Search for Related Content PubMed PubMed Citation Articles by Devine, E. G. Articles by Curtis, A. C.

Comparative Evaluation of Three Continuous Speech Recognition Software Packages in the Generation of Medical Reports

Affiliation of the authors: Boston Veterans Administration Medical Center, Boston, Massachusetts.

Correspondence and reprints: Eric Devine, PhD, Department of Psychology (116b), Boston Department of Veterans Affairs, 150 S. Huntington Avenue, Boston, MA 02130; e-mail: <devine.eric{at}boston.va.gov>.

Abstract Objective: To compare out-of-box performance of three commercially available continuous speech recognition software packages: IBM ViaVoice 98 with General Medicine Vocabulary; Dragon Systems NaturallySpeaking Medical Suite, version 3.0; and L&H Voice Xpress for Medicine, General Medicine Edition, version 1.2.

Design: Twelve physicians completed minimal training with each software package and then dictated a medical progress note and discharge summary drawn from actual records.

Measurements: Errors in recognition of medical vocabulary, medical abbreviations, and general English vocabulary were compared across packages using a rigorous, standardized approach to scoring.

Results: The IBM software was found to have the lowest mean error rate for vocabulary recognition (7.0 to 9.1 percent) followed by the L&H software (13.4 to 15.1 percent) and then Dragon software (14.1 to 15.2 percent). The IBM software was found to perform better than both the Dragon and the L&H software in the recognition of general English vocabulary and medical abbreviations.

Conclusion: This study is one of a few attempts at a robust evaluation of the performance of continuous speech recognition software. Results of this study suggest that with minimal training, the IBM software outperforms the other products in the domain of general medicine; however, results may vary with domain. Additional training is likely to improve the out-of-box performance of all three products. Although the IBM software was found to have the lowest overall error rate, successive generations of speech recognition software are likely to surpass the accuracy rates found in this investigation.

This article has been cited by other articles:

				A. D. Harris, J. C. McGregor, E. N. Perencevich, J. P. Furuno, J. Zhu, D. E. Peterson, and J. Finkelstein The Use and Interpretation of Quasi-Experimental Studies in Medical Informatics J. Am. Med. Inform. Assoc., January 1, 2006; 13(1): 16 - 23. [Abstract] [Full Text] [PDF]

				P. Rao, A. Andrei, A. Fried, D. Gonzalez, and D. Shine Assessing Quality and Efficiency of Discharge Summaries American Journal of Medical Quality, November 1, 2005; 20(6): 337 - 343. [Abstract] [PDF]

				D. N. Mohr, D. W. Turner, G. R. Pond, J. S. Kamath, C. B. De Vos, and P. C. Carpenter Speech Recognition as a Transcription Aid: A Randomized Comparison With Standard Transcription J. Am. Med. Inform. Assoc., January 1, 2003; 10(1): 85 - 93. [Abstract] [Full Text] [PDF]

				S. M. Borowitz Computer-based Speech Recognition as an Alternative to Medical Transcription J. Am. Med. Inform. Assoc., January 1, 2001; 8(1): 101 - 102. [Abstract] [Full Text]

eLetters: