Exploring traditional machine learning for identification of pathological auscultations

TL;DR

This study applies traditional machine learning techniques to digital auscultation data to distinguish normal from abnormal pulmonary sounds, demonstrating promising accuracy and highlighting the potential for improved diagnostic support in medical auscultation.

Contribution

It introduces a comprehensive analysis of machine learning models on auscultation data, utilizing various audio features and evaluation strategies to improve diagnostic accuracy.

Findings

Supervised models outperform unsupervised models in detection accuracy.

Achieved mean AUC ROC of 0.691 for side-based detection.

Achieved mean AUC ROC of 0.721 for patient-based detection.

Abstract

Today, data collection has improved in various areas, and the medical domain is no exception. Auscultation, as an important diagnostic technique for physicians, due to the progress and availability of digital stethoscopes, lends itself well to applications of machine learning. Due to the large number of auscultations performed, the availability of data opens up an opportunity for more effective analysis of sounds where prognostic accuracy even among experts remains low. In this study, digital 6-channel auscultations of 45 patients were used in various machine learning scenarios, with the aim of distinguishing between normal and anomalous pulmonary sounds. Audio features (such as fundamental frequencies F0-4, loudness, HNR, DFA, as well as descriptive statistics of log energy, RMS and MFCC) were extracted using the Python library Surfboard. Windowing and feature aggregation and concatenation strategies were used to prepare data for tree-based ensemble models in unsupervised (fair-cut forest) and supervised (random forest) machine learning settings. The evaluation was carried out using 9-fold stratified cross-validation repeated 30 times. Decision fusion by averaging outputs for a subject was tested and found to be useful. Supervised models showed a consistent advantage over unsupervised ones, achieving mean AUC ROC of 0.691 (accuracy 71.11%, Kappa 0.416, F1-score 0.771) in side-based detection and mean AUC ROC of 0.721 (accuracy 68.89%, Kappa 0.371, F1-score 0.650) in patient-based detection.