Detecting COPD Through Speech Analysis: A Dataset of Danish Speech and Machine Learning Approach

TL;DR

This study explores the use of speech analysis with machine learning to detect COPD in Danish speakers, demonstrating promising accuracy and highlighting its potential as a non-invasive screening tool.

Contribution

The paper introduces a new Danish speech dataset and evaluates machine learning models for COPD detection, addressing linguistic variability in speech biomarkers.

Findings

Achieved 67% accuracy with openSMILE features and logistic regression.

Speech analysis shows potential as a non-invasive COPD screening method.

Collected speech data from 96 Danish participants with and without COPD.

Abstract

Chronic Obstructive Pulmonary Disease (COPD) is a serious and debilitating disease affecting millions around the world. Its early detection using non-invasive means could enable preventive interventions that improve quality of life and patient outcomes, with speech recently shown to be a valuable biomarker. Yet, its validity across different linguistic groups remains to be seen. To that end, audio data were collected from 96 Danish participants conducting three speech tasks (reading, coughing, sustained vowels). Half of the participants were diagnosed with different levels of COPD and the other half formed a healthy control group. Subsequently, we investigated different baseline models using openSMILE features and learnt x-vector embeddings. We obtained a best accuracy of 67% using openSMILE features and logistic regression. Our findings support the potential of speech-based analysis as a non-invasive, remote, and scalable screening tool as part of future COPD healthcare solutions.