Report generation using digital speech recognition in radiology

The aim of this study was to evaluate whether the use of a digital continuo us speech recognition (CSR) in the field of radiology could lead to relevan t ne savings in generating a report. A CSR system (SP6000, Philips, Eindhov en, The Netherlands) for German was used to transform fluently spoken sente nces into text. Two radiologists dictated a total of 450 reports on five ra diological topics. Two typists edited those reports by means of conventiona l typing using a text editor (WinWord 6.0, Microsoft, Redmond, ash.) instal led on an IBM-compatible personal computer (PC). The same reports were gene rated using CSR system and the performance of both systems las men evaluate d by comparing the time needed to generate the reports and the error rates of both systems. In addition, the error rate of the CSR system and the time needed to create the reports was evaluate. The mean error rate for the CSR system was 5.5%, and the mean error rate for conventional typing was 0.4%. Reports edited with the CSR, on average, were generated 19% faster compare d with the conventional text-editing method. However, the amount of error r ates and time savings were different and depended on topics, speakers, and typists. Using CSR the maximum time saving achieved was 28% for the topic s onography. The CSR system was never slower, under any circumstances, than c onventional typing on a PC. When compared with a conventional manual typing method, the CSR system proved to be useful in a clinical setting and saved time in generating radiological reports. The amount of time saved, however , greatly depended on the performance of the typist. the speaker, and on st ored vocabulary provided by the CSR system.