Related Experiment Video
Updated: May 30, 2026
07:41
Video Imaging and Spatiotemporal Maps to Analyze Gastrointestinal Motility in Mice
Published on: February 3, 2016
Non-invasive algorithm for bowel motility estimation using a back-propagation neural network model of bowel sounds
Keo-Sik Kim1, Jeong-Hwan Seo, Chul-Gyu Song
1School of Electronics and Information Engineering, Chonbuk National University, 664-14 1 Ga, Deokjin-dong, Jeonju, Republic of Korea.
Biomedical Engineering Online
|August 12, 2011
Summary
A new algorithm estimates bowel motility using bowel sounds, offering a non-invasive alternative to radiation-heavy colon transit time (CTT) tests. This method shows promise for continuous monitoring of digestive health.
Area of Science:
- Gastroenterology
- Biomedical Engineering
- Signal Processing
Background:
- Conventional colon transit time (CTT) assessments rely on radiography, involving radiation exposure and cumbersome equipment.
- There is a need for non-invasive methods to evaluate bowel motility.
Purpose of the Study:
- To develop and validate a non-invasive algorithm for estimating bowel motility using bowel sounds (BS).
- To utilize a back-propagation neural network (BPNN) model for analyzing BS and correlating it with CTT.
Main Methods:
- Bowel sound (BS) signals were recorded from three colonic segments in healthy males and patients with spinal cord injury.
- Acoustical features (jitter and shimmer) were extracted from BS signals.
- Six highly correlated features were used as input for a BPNN model to estimate CTT.
Main Results:
- Jitter and shimmer were significantly higher in patients compared to healthy subjects (p < 0.01), while CTT was lower in healthy individuals.
- The BPNN algorithm achieved a correlation coefficient of 0.89 and a mean average error of 10.6 hours when compared to conventional CTT measurements.
- The acoustical features of BS show potential for discriminating between different levels of bowel motility.
Conclusions:
- Jitter and shimmer of BS signals are clinically relevant parameters for assessing bowel motility.
- The developed algorithm offers a promising non-invasive approach for continuous bowel motility monitoring, potentially replacing or complementing conventional radiography.
