Speech recognition shortens the recording time of prehospital medical documentation

Effects of a novel endoscopic reporting system with voice recognition on the endoscopic procedure time and report preparation time: propensity score matching analysis

BACKGROUND

With the increase in endoscopic procedures, endoscopists are spending more time creating reports. Although medical reports have largely become electronic, most of the current reporting systems require manual operation. This study aimed to evaluate the efficacy of a novel endoscopic reporting system that uses voice recognition (VR) technology.

METHODS

We retrospectively reviewed consecutive patients who underwent esophagogastroduodenoscopy between September 2019 and March 2020 at a general hospital in Japan. The novel reporting system, used during endoscopic procedures, is equipped with VR and provides automatic responses by playing back recognized words. Differences in total time spent on the endoscopic procedure and report preparation between the manual entry (ME) and VR groups were evaluated using a propensity score matching method.

RESULTS

We enrolled 356 patients: 226 and 130 patients in the ME and VR groups, respectively. Propensity score matching created 101 matched pairs. After matching, the median report preparation time (311 vs. 383 s, P = 0.009) and median total time (765 vs. 842 s, P = 0.053) in the VR group were shorter than those in the ME group. The VR system independently shortened the total and report preparation times by 156 s (95% confidence interval, - 274 to - 37 s; P = 0.009) and 118 s (95% confidence interval, - 220 to - 15 s; P = 0.023), respectively, on multiple linear regression analysis.

CONCLUSIONS

The VR system could save the report preparation time and the total time. This novel system may improve the efficiency of endoscopy-related tasks.