Vocal biomarker predicts fatigue in people with COVID-19: results from the prospective Predi-COVID cohort study 2022 Elbéji et al

Abstract

Objective
To develop a vocal biomarker for fatigue monitoring in people with COVID-19.

Design
Prospective cohort study.

Setting
Predi-COVID data between May 2020 and May 2021.

Participants
A total of 1772 voice recordings were used to train an AI-based algorithm to predict fatigue, stratified by gender and smartphone’s operating system (Android/iOS). The recordings were collected from 296 participants tracked for 2 weeks following SARS-CoV-2 infection.

Primary and secondary outcome measures
Four machine learning algorithms (logistic regression, k-nearest neighbours, support vector machine and soft voting classifier) were used to train and derive the fatigue vocal biomarker. The models were evaluated based on the following metrics: area under the curve (AUC), accuracy, F1-score, precision and recall. The Brier score was also used to evaluate the models’ calibrations.

Results
The final study population included 56% of women and had a mean (±SD) age of 40 (±13) years. Women were more likely to report fatigue (p<0.001). We developed four models for Android female, Android male, iOS female and iOS male users with a weighted AUC of 86%, 82%, 79%, 85% and a mean Brier Score of 0.15, 0.12, 0.17, 0.12, respectively. The vocal biomarker derived from the prediction models successfully discriminated COVID-19 participants with and without fatigue.

Conclusions
This study demonstrates the feasibility of identifying and remotely monitoring fatigue thanks to voice. Vocal biomarkers, digitally integrated into telemedicine technologies, are expected to improve the monitoring of people with COVID-19 or Long-COVID.

Open access, https://bmjopen.bmj.com/content/12/11/e062463

 

I have a feeling this will fall flat when they try to reproduce it. But if it doesn't, hey, it's a strange biomarker, but whatever works at this point.

 

Voice changes can also occur in thyroid conditions.

 

My partner gets croaky when she is becoming over-exerted. It's usually a good sign that she needs to go rest a bit.

 

Yes, I think changes in voice, amount, and detail given, and other aspects of voice maybe revealing to study in our community.

Some are too debilitated in a crash to carry on much of a conversation at all. Also, problems with word retrieval could be noted in such a study.

 

Another speaking problem I've noted with ME, is combining two words into one. I've done this when I have felt more unwell than usual.

I understand pwME may also slur their words when they are feeling very unwell. This has happened to me.

 

History of the profession in a nutshell.

 

Indeed, it's always struck me that typing would be a decent entry-level type of test, as keystrokes are easily analysed. But vocal testing is an interesting one, as I imagine a lot of us do notice changes. I routinely lose my voice, tonsillitis-fashion, when I've run out of energy.

I'm interested in eye-tracking research, too, as it has a good chance of being considered reliably objective if the protocol's right. It'd be very hard (if not impossible) for a patient or a researcher to control or influence that type of function.