A Novel Unsupervised You Only Listen Once (YOLO) Machine Learning Platform for Automatic Detection and Characterization of Prominent Bowel Sounds Towards Precision Medicine

TL;DR

This study introduces a new machine learning platform to automatically detect and classify bowel sounds using acoustic analysis, offering a non-invasive tool for gastrointestinal monitoring.

Contribution

A novel unsupervised YOLO-based machine learning platform for real-time, annotation-free detection and characterization of bowel sounds.

Findings

K-Means clustering identified five distinct acoustic patterns in bowel sounds with high cluster quality metrics.

Temporal modeling revealed unique dwell times and transition dynamics between different bowel sound states.

The method shows potential for clinical applications in conditions like postoperative ileus and inflammatory bowel disease.

Abstract

Phonoenterography (PEG) offers a non-invasive and radiation-free technique to assess gastrointestinal activity through acoustic signal analysis. In this feasibility study, 110 high-resolution PEG recordings (44.1 kHz, 16-bit) were acquired from eight healthy individuals, yielding 6314 prominent bowel sound (PBS) segments through automated segmentation. Each event was characterized using a 279-feature acoustic profile comprising Mel-frequency cepstral coefficients (MFCCs), their first-order derivatives (Δ-MFCCs), and six global spectral parameters. After normalization and dimensionality reduction with PCA and UMAP (cosine distance, 35 neighbors, minimum distance = 0.01), five clustering strategies were evaluated. K-Means (k = 5) achieved the most favorable balance between cluster quality (silhouette = 0.60; Calinski–Harabasz = 19,165; Davies–Bouldin = 0.68) and interpretability, consistently identifying five acoustic patterns: single-burst, multiple-burst, harmonic, random-continuous, and multi-modal. Temporal modeling of clustered events further revealed distinct sequential dynamics, with Single-Burst events showing the longest dwell times, random continuous the shortest, and strong diagonal elements in the transition matrix confirming measurable state persistence. Frequent transitions between random continuous and multi-modal states suggested dynamic exchanges between transient and overlapping motility patterns. Together, these findings demonstrate that unsupervised PEG-based analysis can capture both acoustic variability and temporal organization of bowel sounds. This annotation-free approach provides a scalable framework for real-time gastrointestinal monitoring and holds potential for clinical translation in conditions such as postoperative ileus, bowel obstruction, irritable bowel syndrome, and inflammatory bowel disease.

Figures