Non-invasive algorithm for bowel motility estimation using a back-propagation neural network model of bowel sounds
2011

Non-invasive Algorithm for Estimating Bowel Motility

Sample size: 18 publication Evidence: moderate

Author Information

Author(s): Kim Keo-Sik, Seo Jeong-Hwan, Song Chul-Gyu

Primary Institution: Chonbuk National University

Hypothesis

Can a non-invasive algorithm using bowel sounds effectively estimate bowel motility compared to traditional methods?

Conclusion

The algorithm shows promise for non-invasive monitoring of bowel motility, correlating well with traditional methods.

Supporting Evidence

  • The algorithm achieved a correlation coefficient of 0.89 with traditional methods.
  • Mean average error of the algorithm was 10.6 hours compared to conventional measurements.
  • Jitter and shimmer values were significantly different between healthy subjects and patients.

Takeaway

Doctors can use sounds from your belly to check how well your intestines are working without needing X-rays.

Methodology

The study involved recording bowel sounds from healthy males and patients, analyzing features like jitter and shimmer, and using a neural network to estimate colon transit time.

Potential Biases

Potential bias due to the small number of subjects and lack of diverse demographics.

Limitations

The study had a small sample size and did not account for physiological differences among subjects.

Participant Demographics

12 healthy males (average age 24.8 years) and 6 patients with spinal cord injury (average age 55.3 years).

Statistical Information

P-Value

p<0.01

Statistical Significance

p<0.01

Digital Object Identifier (DOI)

10.1186/1475-925X-10-69

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication