Noninvasive Diagnosis of Irritable Bowel Syndrome via Bowel Sound Features: Proof of Concept

Abstract

INTRODUCTION: Irritable bowel syndrome (IBS) is a common and debilitating disorder estimated to affect approximately 11% of the world's population. Typically, IBS is a diagnosis of exclusion after patients undergo a costly and invasive colonoscopy to exclude organic disease. Clinician's and researchers have identified a need for a new cost-effective, accurate, and noninvasive diagnostic test for IBS. METHODS: Using a diagnostic case-control study, we explored the use of bowel sounds to characterize IBS with a view to diagnostic use. We recruited participants with an existing clinical diagnosis of IBS or healthy (asymptomatic) digestive systems. We recorded bowel sounds for 2 hours after fasting and then for 40 minutes after a standard meal. RESULTS: We here report our results including our accuracy in characterizing IBS-related bowel sounds and differentiation between participants with IBS and healthy participants. Leave-one-out cross-validation of our model developed using the first 31 IBS and 37 healthy participants gave 90% sensitivity and 92% specificity for IBS diagnosis. Independent testing using the next 15 IBS and 15 healthy participants demonstrated 87% sensitivity and 87% specificity for IBS diagnosis. CONCLUSIONS: These preliminary results provide proof of concept for the use of bowel sound analysis to identify IBS. A prospective study is needed to confirm these findings. TRANSLATIONAL IMPACT: Our belt and model offer hope of a new approach for IBS diagnosis in primary practice. Combined with screening tests for organic disease, it would offer greater confidence to patients and could reduce the burden of unnecessary colonoscopies for health care systems and patients.

Automated Bowel Sound Analysis: An Overview

“…Moreover, the group proposed a mathematical model of BS generation [ 77 ], and a clinical application of the completed BS framework soon followed. The results of their proof-of-concept investigation of BS analysis for irritable bowel syndrome diagnosis are inspiring: 87% sensitivity and specificity were achieved in an independent cohort [ 78 ]. It would seem that the Australian team is heading towards the production of a medical device for BS recording and analysis.…”

Development of a bowel sound detector adapted to demonstrate the effect of food intake

“…Similar results have been reported previously and this consistency further validates our approach. Du et al [21] showed that the BS density and summed amplitude were significantly higher after food consumption. Recently, Horiyama et al [20] also reported that the density and length of BS significantly increased after coffee and soda intake.…”

“…Hence, we assume that a system analysing a shorter segment window would be better for identifying the majority of BS. In addition, the acoustic features obtained from BS, such as the duration and energy, have found to be useful for evaluating the bowel motility [12,20,21]. To accurately calculate these features, the start and end time point of each BS are required.…”

A CRNN System for Sound Event Detection Based on Gastrointestinal Sound Dataset Collected by Wearable Auscultation Devices

“…Next, we illustrate the reasons for selecting the six sound event classes for GI Sound Set. Bowel sounds can effectively screen out functional Gastrointestinal disease such as irritable bowel syndrome (IBS) [35], monitor whether postoperative intestinal paralysis POI and paralytic intestinal obstruction will occur [36], and it is possible to fine guide the feeding time and dose of enhanced recovery after surgery(ERAS). The patient's pain has always been an important observation index after the operation.…”