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

Effect of a deep learning-based automatic upper GI endoscopic reporting system: a randomized crossover study (with video)

BACKGROUND AND AIMS

EGD is essential for GI disorders, and reports are pivotal to facilitating postprocedure diagnosis and treatment. Manual report generation lacks sufficient quality and is labor intensive. We reported and validated an artificial intelligence-based endoscopy automatic reporting system (AI-EARS).

METHODS

The AI-EARS was designed for automatic report generation, including real-time image capturing, diagnosis, and textual description. It was developed using multicenter datasets from 8 hospitals in China, including 252,111 images for training, 62,706 images, and 950 videos for testing. Twelve endoscopists and 44 endoscopy procedures were consecutively enrolled to evaluate the effect of the AI-EARS in a multireader, multicase, crossover study. The precision and completeness of the reports were compared between endoscopists using the AI-EARS and conventional reporting systems.

RESULTS

In video validation, the AI-EARS achieved completeness of 98.59% and 99.69% for esophageal and gastric abnormality records, respectively, accuracies of 87.99% and 88.85% for esophageal and gastric lesion location records, and 73.14% and 85.24% for diagnosis. Compared with the conventional reporting systems, the AI-EARS achieved greater completeness (79.03% vs 51.86%, P < .001) and accuracy (64.47% vs 42.81%, P < .001) of the textual description and completeness of the photo-documents of landmarks (92.23% vs 73.69%, P < .001). The mean reporting time for an individual lesion was significantly reduced (80.13 ± 16.12 seconds vs 46.47 ± 11.68 seconds, P < .001) after the AI-EARS assistance.

CONCLUSIONS

The AI-EARS showed its efficacy in improving the accuracy and completeness of EGD reports. It might facilitate the generation of complete endoscopy reports and postendoscopy patient management. (Clinical trial registration number: NCT05479253.).

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.