Evaluation of RAPID(®) 5 Access software for examination of capsule endoscopies and reading of the capsule by an endoscopy nurse.

Background: Since capsule endoscopy (CE) is time consuming, one possible cost-effective strategy could be the use of an expert endoscopic assistant and available software to select images. Aims were to examine the clinical utility of RAPID(®) 5 Access software and find the optimum setting mode for reading. We also evaluated whether a nurse could preview the CE video and detect significant lesions accurately.

Methods: The capsule images in 14 volunteers with known mucosal injury induced by low dose aspirin and in 30 patients who were known to have a variety of significant lesions were selected. Using three setting modes of RAPID(®) 5 Access software, the detection rate and reading time for CE images by two well-trained physicians and one expert nurse were compared.

Results: There was no significant difference in detection rate among the three readers. The detection rate using Quickview RAPID(®) 5 Access was significantly higher than that using RAPID(®) Reader version 4.1. Comparison among the three modes of RAPID(®) 5 Access showed that auto mode as well as displaying a single image at 12 fps was superior in the detection rate of denuded redness, while its reading time was longer compared to the other modes. Some significant lesions were not detected by using Quickview and Quadview modes.

Conclusions: RAPID(®) 5 Access improves diagnostic yield, reducing reading time; however, it is still unacceptable because of the diagnostic miss rate and may be useful as an ancillary reading tool. Developing further improved software and training expert assistants for reading capsule images are necessary.