JMIR Publications

ABSTRACT

Background:

Recent work has shown the potential of using audio data in the screening for COVID-19. However, very little exploration has been put forward to monitor disease progression, especially recovery, in COVID-19, through audio. Tracking disease progression characteristics and patterns of recovery could lead to tremendous insights and more timely treatment or treatment adjustment, as well as better resource management in healthcare systems.

Objective:

The primary objective of this study is to explore the potential of longitudinal audio dynamics for COVID-19 monitoring using sequential deep learning techniques, focusing on prediction of disease progression and, especially, recovery trend prediction.

Methods:

Crowdsourced respiratory audio data including breathing, cough, and voice from 212 individuals over 5 days to 385 days were analysed, alongside their self-reported COVID-19 test results. We developed and validated a deep learning-enabled tracking tool using Gated Recurrent Units (GRUs) to detect COVID-19 disease progression, by exploring the audio dynamics of individuals’ historical audio biomarkers. The investigation is composed of two parts: i) COVID-19 detection in terms of positive and negative (healthy) using sequential audio signals, which was primarily assessed in terms of area under the receiver operating characteristic curve (AUC-ROC), sensitivity, and specificity, with 95% Confidence Intervals (CIs); ii) the longitudinal disease progression prediction over time in terms of probability of positive, which was evaluated using the correlation between the predicted probability trajectory and self-reported labels.

Results:

We first explored the benefits of capturing longitudinal dynamics of audio biomarkers for COVID-19 detection. The strong performance, yielding an AUC-ROC of 0.79, sensitivity of 0.75 and specificity of 0.70, supports the effectiveness of the approach compared to methods that do not leverage longitudinal dynamics. We further examined the predicted disease progression trajectory, which displays high consistency with the longitudinal test results with a correlation of 0.75 in the test cohort, and 0.86 in a subset of the test cohort with 12 participants who report disease recovery. Our findings suggest that monitoring COVID-19 evolution via longitudinal audio data has enormous potential in the tracking of individuals’ disease progression and recovery.

Conclusions:

An audio-based COVID-19 disease progression monitoring system was developed using deep learning techniques, with strong performance showing the high consistency between the predicted trajectory and the test results over time, especially for recovery trend predictions. This provides great potential in the post-peak and post-pandemic era that can help guide medical treatment and optimise hospital resource allocations. This framework provides a flexible, affordable and timely tool for COVID-19 disease tracking, and more importantly, it also provides a proof of concept of how telemonitoring could be applicable to respiratory diseases monitoring, in general.