iScience
Volume 24, Issue 12, 17 December 2021, 103419
Journal home page for iScience

Article
Screening of COVID-19 cases through a Bayesian network symptoms model and psychophysical olfactory test

https://doi.org/10.1016/j.isci.2021.103419Get rights and content
Under a Creative Commons license
open access

Highlights

  • Total or partial loss of sense of smell is among the most prevalent COVID-19 symptoms

  • Partial olfactory impairment is seldom self-recognized, so a rapid test is developed

  • Bayesian net predicts COVID-19 status based on olfactory test and symptoms data

  • Results confirm measured olfactory loss as the most predictive COVID-19 symptom

Summary

The sudden loss of smell is among the earliest and most prevalent symptoms of COVID-19 when measured with a clinical psychophysical test. Research has shown the potential impact of frequent screening for olfactory dysfunction, but existing tests are expensive and time consuming. We developed a low-cost ($0.50/test) rapid psychophysical olfactory test (KOR) for frequent testing and a model-based COVID-19 screening framework using a Bayes Network symptoms model. We trained and validated the model on two samples: suspected COVID-19 cases in five healthcare centers (n = 926; 33% prevalence, 309 RT-PCR confirmed) and healthy miners (n = 1,365; 1.1% prevalence, 15 RT-PCR confirmed). The model predicted COVID-19 status with 76% and 96% accuracy in the healthcare and miners samples, respectively (healthcare: AUC = 0.79 [0.75–0.82], sensitivity: 59%, specificity: 87%; miners: AUC = 0.71 [0.63–0.79], sensitivity: 40%, specificity: 97%, at 0.50 infection probability threshold). Our results highlight the potential for low-cost, frequent, accessible, routine COVID-19 testing to support society's reopening.

Subject areas

Diagnostic technique in health technology
Diagnostics
Health technology
Mathematical biosciences

Data and code availability

De-identified human data for model training and validation have been deposited at Mendeley Data and are publicly available as of the date of publication. DOIs are listed in the key resources table. This paper does not report original code. Any additional information required to reanalyze the data reported in this paper is available from the lead contact upon request.

Cited by (0)

18

These authors contributed equally

19

Lead contact