Discovery and Analytical Validation of a Vocal Biomarker to Monitor Anosmia and Ageusia in Patients With COVID-19: Cross-sectional Study

Abstract

Background: The COVID-19 disease has multiple symptoms, with anosmia and ageusia being the most prevalent, varying from 75% to 95% and from 50% to 80% of infected patients, respectively. An automatic assessment tool for these symptoms will help monitor the disease in a fast and noninvasive manner.

Objective: We hypothesized that people with COVID-19 experiencing anosmia and ageusia had different voice features than those without such symptoms. Our objective was to develop an artificial intelligence pipeline to identify and internally validate a vocal biomarker of these symptoms for remotely monitoring them.

Methods: This study used population-based data. Participants were assessed daily through a web-based questionnaire and asked to register 2 different types of voice recordings. They were adults (aged >18 years) who were confirmed by a polymerase chain reaction test to be positive for COVID-19 in Luxembourg and met the inclusion criteria. Statistical methods such as recursive feature elimination for dimensionality reduction, multiple statistical learning methods, and hypothesis tests were used throughout this study. The TRIPOD (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis) Prediction Model Development checklist was used to structure the research.

Results: This study included 259 participants. Younger (aged <35 years) and female participants showed higher rates of ageusia and anosmia. Participants were aged 41 (SD 13) years on average, and the data set was balanced for sex (female: 134/259, 51.7%; male: 125/259, 48.3%). The analyzed symptom was present in 94 (36.3%) out of 259 participants and in 450 (27.5%) out of 1636 audio recordings. In all, 2 machine learning models were built, one for Android and one for iOS devices, and both had high accuracy-88% for Android and 85% for iOS. The final biomarker was then calculated using these models and internally validated.

Conclusions: This study demonstrates that people with COVID-19 who have anosmia and ageusia have different voice features from those without these symptoms. Upon further validation, these vocal biomarkers could be nested in digital devices to improve symptom assessment in clinical practice and enhance the telemonitoring of COVID-19-related symptoms.

Trial registration: Clinicaltrials.gov NCT04380987; https://ichgcp.net/clinical-trials-registry/NCT04380987.

Keywords: AI; COVID-19; ageusia; anosmia; artificial intelligence; biomarker; device; digital; digital assessment tool; digital health; disease; loss of smell; loss of taste; medical informatics; noninvasive; pandemic; symptoms; telehealth; telemonitoring; tool; vocal biomarker.

Conflict of interest statement

Conflicts of Interest: None declared.

©Eduardo Higa, Abir Elbéji, Lu Zhang, Aurélie Fischer, Gloria A Aguayo, Petr V Nazarov, Guy Fagherazzi. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 08.11.2022.

Figures

Figure 1

Learning pipeline to the discovery of biomarkers. (A) Data collection from Predi-COVID and exclusion criteria. (B) Data treatment of audio data and studied outcome. (C) Data analysis for both audio formats done in parallel.

Figure 2

Sample plot with linear separation between 3gp and m4a audio formats. Principal component analysis was used on the extracted features, and the first 2 dimensions were used to plot the samples.

Figure 3

Final models for each audio format. (A) Biomarkers and P values from two-sided student's t-test for the presence of anosmia and ageusia were calculated using the probability of classifying as positive. (B) Confusion matrix of the best model. (c) ROC AUC curve. Class 0 represents absence of symptoms and Class 1 the presence of it. ROC AUC: area under the receiver operating characteristic curve.