New report preparation system for endoscopic procedures using speech recognition technology

Speech Recognition System Generates Highly Accurate Endoscopic Reports in Clinical Practice

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.

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.

Preliminary assessment of two novel mechanical colonoscopic polypectomy simulators: Description, evaluation and validation

Background and study aims  Colonoscopic polypectomy is an essential endoscopic skill. The simulators available for training are limited and based on raw porcine colons. Animal intestines are inconvenient and offer limited advantages for polypectomy training. These limitations are avoided by two novel mechanical simulators - the magnetic system based simulator (MSPS) and the simulator for polypectomy with high frequency current (HFPS) - described here. They are equipped to demonstrate self-repair of polyps after making a cut and hybrid polyps. The aim of this study was to describe and establish face, content, and construct validity of the two simulators and to assess their perceived utility as training and assessment tools. Methods  Ten novice, seven intermediate, and 10 advanced endoscopists participated in this study. Each one performed two polypectomies in MSPS and then one polypectomy and polyp retrieval in HFPS. The median times were compared among the three groups to preliminarily assess construct validity as a primary outcome. To establish face validity, the novices and intermediates completed a questionnaire about the credibility of each simulator after finishing the tasks. For content validity, the experts completed a questionnaire grading different aspects of the simulators' realism and their usefulness for training. Results  All 27 participants completed the modules. Median times needed to complete the tasks in both simulators differed significantly between the participants with different levels of experience ( P  < 0.05). Both MSPS and HFPS received favorable scores regarding face and content validity. No technical problems were encountered. Conclusion  This study provides preliminary validation for MSPS and HFPS as useful training tools in a preclinical setting as well as during colonoscopy training. Moreover, we demonstrated the construct validity of both simulators, which confirms their use as a skill assessment tool during a colonoscopy training program.