Abstract
We tested on three occasions, with anesthetists as subjects, the accuracy of two voice-recognition systems designed for anesthetic record keeping. Initially, a prototype system was tested (10 subjects); several years later the resulting commercial system was tested in a quiet environment (11 subjects) and in noisy operating rooms (10 subjects). For each test an anesthetist first trained the system to recognize his or her voice by reading aloud a list of common anesthetic terms. To determinerecognition accuracy, the percentage of words recognized correctly by the computer, each subject repeated the vocabulary words ten times. Although accuracy was similar during the three tests, it was slightly higher with the laboratory test (mean percent of words recognized correctly, 96.5%; range of accuracy for individual anesthetists, 91.6 to 98.8%) than with the prototype test (95.9%; range, 89.1 to 99.6%). Accuracy was lowest with the operating room test (95.3%; range, 87.8 to 98.4%). Twenty-four words caused particular difficulty during the laboratory test and were eliminated from the vocabulary of the subsequent operating room test. Omitting these 24 words from the laboratory vocabulary list allowed a more nearly direct comparison with the results from the operating room list; recognition accuracy improved in the former to 97.5% (range, 92.1 to 98.9%). Two anesthetists—one each from the laboratory and operating room tests —performed poorly, and eliminating their scores changed the respective overall scores to 98.2% (range, 96.7 to 98.9%) and 96.5% (range, 94.3 to 98.4%). Thus, the corrected difference between the laboratory accuracy and the operating room accuracy was 1.7%. We conclude that about 90% of anesthetists can achieve usable recognition accuracy with the current voice-recognition system, even with no previous experience with the system.
Similar content being viewed by others
References
Smith N Ty. Quantitative anaesthesia management and optimization of machine-user interface. In: van Ackern K, Frankenberger H, Konecny E, Steinbcreithner K, eds. Quantitative anaesthesia. Berlin: Springer-Verlag, 1989: 120–139
Paulus DA, van der Aa J, McLaughlin G, et al. A more accurate anesthesia record: the electronic clipboard (Abstract). Anesthesiology 1984;61:A178
Smith N Ty, Quinn ML, Sarnat AJ. Speech recognition for the automated anesthesia record. In: Gravenstein JS, New-bower RS, Ream AK, Smith N Ty, eds. The automated anesthesia record and alarms systems. Boston: Butter-worths, 1987:115–134
Sarnat AJ, Quinn ML, Smith N Ty. A preliminary evaluation of computerized speech recognition for anesthesia (Abstract). Anesthesiology 1981;55:A128
Sarnat AJ, Quinn ML, Smith N Ty. A computerized speech recognition system for anesthesia record keeping (Abstract). Anesthesiology 1982;57:A165
Smith N Ty, Brien RA, Banke K. Performance of the voice recognition component of an automated record keeping system (Abstract). Anesthesiology 1987;67[3A]:A193
Brien RA, Smith N Ty, Quinn ML, et al. The accuracy of voice recognition in the operating room (Abstract). Anesthesiology 1988;68:A331.
Shapiro RA, Berlant T. Noise in the operating room. N Engl J Med 1972;287:1236–1238
Author information
Authors and Affiliations
Additional information
Supported in part by Diatek Patient Management Systems, Inc, San Diego, CA; University of California, San Diego; and the Veterans Administration Medical Center, San Diego, CA.
Annual meetings of the American Society of Anesthesiologists, New Orleans, LA, October 1981; Las Vegas, October 1982; Atlanta, GA, October 1987; and San Francisco, CA, October 1988.
Rights and permissions
About this article
Cite this article
Smith, N.T., Brien, R.A., Pettus, D.C. et al. Recognition accuracy with a voice-recognition system designed for anesthesia record keeping. J Clin Monitor Comput 6, 299–306 (1990). https://doi.org/10.1007/BF02842489
Received:
Revised:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF02842489