Automatic cough detection based on airflow signals for portable spirometry system
This provides a robust cough detection method for portable spirometry systems, benefiting patients and clinicians in varied environments, though it is incremental as it applies existing classifiers to a new signal type.
The paper tackled automatic cough detection using airflow signals instead of audio, achieving sensitivity of 0.86, specificity of 0.91, accuracy of 0.91, and F1 score of 0.88 on a test set.
We give a short introduction to cough detection efforts that were undertaken during the last decade and we describe the solution for automatic cough detection developed for the AioCare portable spirometry system. In contrast to more popular analysis of sound and audio recordings, we fully based our approach on airflow signals only. As the system is intended to be used in a large variety of environments and different patients, we trained and validated the algorithm using AioCare-collected data and the large database of spirometry curves from the NHANES database by the American National Center for Health Statistics. We trained different classifiers, such as logistic regression, feed-forward artificial neural network, support vector machine, and random forest to choose the one with the best performance. The ANN solution was selected as the final classifier. The classification results on the test set (AioCare data) are: 0.86 (sensitivity), 0.91 (specificity), 0.91 (accuracy) and 0.88 (F1 score). The classification methodology developed in this study is robust for detecting cough events during spirometry measurements. As far as we know, the solution presented in this work is the first fully reproducible description of the automatic cough detection algorithm based totally on airflow signals and the first cough detection implemented in a commercial spirometry system that is to be published.