Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Nov 17, 2022
Date Accepted: Feb 28, 2023
Date Submitted to PubMed: Mar 7, 2023
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Implementation and evaluation of a novel respiratory-responsive vocal biomarker to aid in the detection of COVID-19
ABSTRACT
Background:
We present results of a multi-site validation trial of a respiratory-responsive vocal-biomarker (RRVB) platform, originally developed using an asthma dataset, to detect active COVID-19 infection in patients presenting to hospitals in the US and India.
Objective:
The RRVB model under study utilizes a briefly held vowel elicitation captured on patients’ smartphones and produces a risk score calibrated to estimate whether the speaker likely belongs to a group with an asthma diagnosis or a healthy control group.
Methods:
To determine whether this RRVB model can also detect patients with active COVID-19 infection, a total of 497 participants (COVID-19 positive, symptomatic but COVID-19 negative, and healthy controls) were enrolled across 4 clinical sites (DMH, Pune India; Montefiore Medical Center, Bronx NY; Brigham & Women’s Hospital, Boston MA; UCSD Health, San Diego CA) and provided voice samples and symptom reports on their personal smartphones.
Results:
Compared with clinical diagnosis of COVID-19 confirmed by RT-PCR, the RRVB model performed with sensitivity of 73.2%, specificity of 62.9%, and odds ratio of 4.64 (p<0.0001). Patients experiencing respiratory symptoms were detected more frequently vs. those not experiencing respiratory symptoms and completely asymptomatic patients (78.4% vs. 67.4% vs. 68.0%). This RRVB model is not a COVID-19 test, but these results demonstrate its meaningful potential to serve as a pre-screening tool that could, in combination with temperature and symptom reports, be used to identify subjects at risk for COVID-19 infection and encourage targeted testing.
Conclusions:
The generalizability of this model for detection of possible disease state for multiple conditions having in common respiratory symptoms across different linguistic and geographic contexts suggests a potential path to development and validation of voice-based tools for broader disease surveillance and monitoring applications in the future
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.