Benchmarking machine learning for bowel sound pattern classification from tabular features to pretrained models

TL;DR

This study evaluates various machine learning models, including pre-trained audio models, for classifying bowel sound patterns, demonstrating that pre-trained models significantly outperform traditional methods, especially with limited data.

Contribution

It introduces a comprehensive benchmarking of machine learning approaches, highlighting the effectiveness of pre-trained models for bowel sound pattern classification.

Findings

Pre-trained models achieve higher AUC scores than traditional models.

Pre-trained models are especially effective with small sample classes.

The study advances automated gastrointestinal diagnostics.

Abstract

The development of electronic stethoscopes and wearable recording sensors opened the door to the automated analysis of bowel sound (BS) signals. This enables a data-driven analysis of bowel sound patterns, their interrelations, and their correlation to different pathologies. This work leverages a BS dataset collected from 16 healthy subjects that was annotated according to four established BS patterns. This dataset is used to evaluate the performance of machine learning models to detect and/or classify BS patterns. The selection of considered models covers models using tabular features, convolutional neural networks based on spectrograms and models pre-trained on large audio datasets. The results highlight the clear superiority of pre-trained models, particularly in detecting classes with few samples, achieving an AUC of 0.89 in distinguishing BS from non-BS using a HuBERT model and an AUC of 0.89 in differentiating bowel sound patterns using a Wav2Vec 2.0 model. These results pave the way for an improved understanding of bowel sounds in general and future machine-learning-driven diagnostic applications for gastrointestinal examinations