Sensitivity and inter-observer variability for capsule endoscopy image analysis in a cohort of novice readers

Abstract

sensitivity in detecting lesions on capsule endoscopy. A group of novice readers can pre-screen recordings to thumbnail potential areas of small bowel lesions for further review. These thumbnails must be reviewed to determine the clinical relevance. Further studies are ongoing to assess other cohorts. INTRODUCTIONCapsule endoscopy is a new diagnostic procedure developed for the complete examination of the small intestine through video images transmitted from an ingestible camera [1][2][3] . Briefly, the PillCam TM capsule endoscopy and diagnostic imaging system (GIVEN Imaging, Yoqneam, Israel) is a commercially available system consisting of three major components: PillCam TM capsule which captures images and transmits digital pictures (at 2 frames/s) over an 8-h period, sensor array and data recorder, which receives and records the data transmitted from the PillCam TM capsule and RAPID TM Workstation, which is used to initialize the data recorder and to download and process the raw data from the data recorder [4,5] . The processed information, composed of approximately 50 000 still images collected over an 8-h period, can be reviewed as a continuous video stream. The reported time range typically needed for a complete review of a single capsule endoscopy recording case is anywhere from 50 [6,7] to 120 min [8] . Numerous studies have now demonstrated that the sensitivity and specificity of capsule endoscopy are advantageous over the traditional diagnostic methods of small bowel lesions [5][6][7][9][10][11] . Capsule endoscopy may also reduce total medical utilization and costs as well as improve patient's quality of life in certain circumstances [12] . RAPID COMMUNICATION Sensitivity and inter METHODS:Ten capsule endoscopy cases of small bowel lesions were administered to the readers. Gold standard findings were pre-defined by gastroenterologists. Ten gold standard "targets" were identified among the 10 cases. Readers were given a 30-min overview of Rapid Reader software and instructed to mark any potential areas of abnormalities. A software program was developed using SAS to analyze the thumbnailed findings. RESULTS:The overall sensitivity for detecting the gold standard findings was 80%. As a group, at least 5 out of 10 readers detected each gold standard finding per recording. All the gold standard targets were identified when the readers' results were combined. Incidental finding/false positive rate ranged between 8.2-59.8 per reader. CONCLUSION:A panel of medical students with minimal endoscopic experience can achieve high

How Should We Train Capsule Endoscopy? A Pilot Study of Performance Changes During a Structured Capsule Endoscopy Training Program

“…However, there is increasing awareness within diagnostic and therapeutic specialties that proficiency should be based on competency rather than numbers performed, especially as lesion recognition skills are often neglected as part of endoscopic training. While published studies have demonstrated that non-experts without prior CE training (medical students, technicians, and endoscopy nurses) may identify 30-100% of lesions detected by an expert [18,22], there is no literature to date that outlines the appropriate type or amount of CE training required to achieve competent independent practice. This preliminary study is the first to assess changes in performance during a ''hands-on'' CE training program such as might be used in everyday practice.…”

American Gastroenterological Association (AGA) Institute Technical Review on Obscure Gastrointestinal Bleeding

“…The cost-effectiveness of the capsule endoscopy study in the evaluation of patients with obscure GI bleeding may be increased by the preview of the recordings by an endoscopy nurse or an assistant. [107][108][109] In a pilot study by Appleyard et al in 2000, radioopaque beads were sewn into canine small bowels to compare the diagnostic yield between push enteroscopy and capsule endoscopy. Capsule enteroscopy identified more beads overall (64%) compared with push enteroscopy (37%), although push enteroscopy was found to be more sensitive for bead detection in the first meter of the examination (94% compared with 53% for capsule).…”

Systematic review and meta‐analysis of the performance of nurses in small bowel capsule endoscopy reading

“…Six studies were excluded for the following reasons: two did not involve nurses; 18,19 one used a bowel model instead of actual patients; 20 two used QuickView to aid CE reading; 21,22 and one did not have an adequate reference standard to gauge performance of the nurse endoscopist, as an inexperienced nurse was compared to a physician also inexperienced in CE. 11…”