Automated Bowel Sound Analysis: An Overview

Abstract

Despite technological progress, we lack a consensus on the method of conducting automated bowel sound (BS) analysis and, consequently, BS tools have not become available to doctors. We aimed to briefly review the literature on BS recording and analysis, with an emphasis on the broad range of analytical approaches. Scientific journals and conference materials were researched with a specific set of terms (Scopus, MEDLINE, IEEE) to find reports on BS. The research articles identified were analyzed in the context of main research directions at a number of centers globally. Automated BS analysis methods were already well developed by the early 2000s. Accuracy of 90% and higher had been achieved with various analytical approaches, including wavelet transformations, multi-layer perceptrons, independent component analysis and autoregressive-moving-average models. Clinical research on BS has exposed their important potential in the non-invasive diagnosis of irritable bowel syndrome, in surgery, and for the investigation of gastrointestinal motility. The most recent advances are linked to the application of artificial intelligence and the development of dedicated BS devices. BS research is technologically mature, but lacks uniform methodology, an international forum for discussion and an open platform for data exchange. A common ground is needed as a starting point. The next key development will be the release of freely available benchmark datasets with labels confirmed by human experts.

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

“…Recent increases in computer processing power and improvements in data analysis bring the potential to employ bowel sound computational analysis to improve evaluation of gastrointestinal conditions [2] or feeding status [3,4]. A number of computerized bowel sound-based monitoring and diagnosis systems have been developed [5,6]. The development stage of the various technologies varies.…”

“…Improved accuracy at this stage will improve to the accuracy of any subsequent signal processing or analysis. A recent overview of automatic bowel sound analysis methods, also suggested that the detection of the BS occurrence could be a starting point for building bowel sound analysis standards, as well as international forums for discussion and cooperation [6].…”

Graphene-based strain sensor with sandwich structure and its application in bowel sounds monitoring

“…In addition, we can also determine the recovery of the intestinal tract by monitoring bowel sounds, because bowel sounds are produced by the peristaltic movement of the intestinal tract to push the intestinal contents and cause the intestinal contents to hit each other or the intestinal contents to collide with the intestinal wall, which can reect the intestinal movement. 13,14 Currently, clinical auscultation of bowel sounds is mainly performed with a stethoscope, but the judgment of the results depends on the physician's level of experience, and diagnostic errors can occur. 15 Moreover, studies have shown that the correct rate of clinician auscultation of bowel sounds is less than 90%.…”

Analysis of Gastrointestinal Acoustic Activity Using Deep Neural Networks

“…They have not only proposed their own neural network-based approach to BS identification, but also studied irritable bowel syndrome and demonstrated a link between BS and migrating motor complexes in the large bowel [14]. For more historical context we refer to our recent review [15].…”

“…Machine learning methods are widely used in bowel sound analysis [15]. One solution using machine learning algorithms is the use of the parameters Jitter and Shimmer, i.e., parameters that determine the variation of the fundamental frequency in relation to the frequency of the fundamental tone and the variation of the amplitude in relation to the average amplitude.…”