Abstract: Typically, dentists perform data entry in practice management systems (PMS) through dictation to an assistant. This prevents dentists from interacting directly with the PMS. Speech recognition can provide the solution to this problem. Existing speech interfaces of PMSs are cumbersome to use and poorly designed. In dentistry, there is a clear need for a usable natural language interface for clinical data entry.
In this presentation, we describe the development and evaluation of our speech-to-chart prototype which contained the following components: speech recognizer; post-processor for error correction; NLP application (ONYX) and; graphical chart generator. We evaluated the accuracy of the speech recognizer and the post-processor. We then performed a summative evaluation on the entire system. Our prototype charted 12 hard tissue exams. We compared the charted exams to reference standard exams charted by two dentists.
On manually transcribed exams, the system performed with an average 80% accuracy. The average time to chart a single hard tissue finding with the prototype was 7.3 seconds. An improved discourse processor will greatly enhance the prototype’s accuracy. This is an improvement over the speech interfaces of existing PMSs which are cumbersome, require using specific speech commands, and make several errors per exam. We successfully created a speech-to-chart prototype that charts hard tissue findings from naturally spoken dental exams.
Keywords: Speech Recognition Software; User-Computer Interface; Medical Informatics Applications; Practice Management; Dental Informatics; Electronic Dental Records; Natural Language Processing
This work is licensed under a Creative Commons Attribution-Noncommercial-Share Alike 3.0 United States License.