Abstract
Objective Endoscopic reports are conventionally written at the end of each procedure, and the endoscopist must complete the report from memory. To make endoscopic reporting more efficient, we developed a new speech recognition (SR) system that generates highly accurate endoscopic reports based on structured data entry. We conducted a pilot study to examine the performance of this SR system in an actual endoscopy setting with various types of background noise.
Methods In this prospective observational pilot study, participants who underwent upper endoscopy with our SR system were included. The primary outcome was the correct recognition rate of the system. We compared the findings generated by the SR system with the findings in the handwritten report prepared by the endoscopist. The initial correct recognition rate, number of revisions, finding registration time, and endoscopy time were also analyzed.
Results Upper endoscopy was performed in 34 patients, generating 128 findings of 22 disease names. The correct recognition rate was 100%, and the median number of revisions was 0. The median finding registration time was 2.57 [interquartile range (IQR), 2.33-2.92] seconds, and the median endoscopy time was 234 (IQR, 194-227) seconds.
Conclusion The SR system demonstrated high recognition accuracy in the clinical setting. The finding registration time was extremely short.
