TY - JOUR
T1 - Screening of COVID-19 cases through a Bayesian network symptoms model and psychophysical olfactory test
AU - Eyheramendy, Susana
AU - Saa, Pedro A.
AU - Undurraga, Eduardo A.
AU - Valencia, Carlos
AU - López, Carolina
AU - Méndez, Luis
AU - Pizarro-Berdichevsky, Javier
AU - Finkelstein-Kulka, Andrés
AU - Solari, Sandra
AU - Salas, Nicolás
AU - Bahamondes, Pedro
AU - Ugarte, Martín
AU - Barceló, Pablo
AU - Arenas, Marcelo
AU - Agosin, Eduardo
N1 - Funding Information:
This work was funded by the Technological Adoption Fund SiEmpre from SOFOFA Hub ( CORFO ) and partially funded by ANID through the Millennium Science Initiative Program ICN17 002 to S.E., P.B., and M.A.; ANID Millennium Science Initiative Program NCN17 081 and ANID/FONDAP CIGIDEN 15110017 to EU; ANID FONDECYT 1200146 to S.E; and ANID FONDECYT de Iniciacion 11190871 to P.A.S. We would also like to acknowledge the support of the Center for Aromas and Flavors staff for helping in the collection of the data and Camila Pavesi for assisting in the organization and preliminary analysis of the latter.
Publisher Copyright:
© 2021 The Authors
PY - 2021/12/17
Y1 - 2021/12/17
N2 - 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.
AB - 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.
KW - Diagnostic technique in health technology
KW - Diagnostics
KW - Health technology
KW - Mathematical biosciences
UR - http://www.scopus.com/inward/record.url?scp=85123508355&partnerID=8YFLogxK
U2 - 10.1016/j.isci.2021.103419
DO - 10.1016/j.isci.2021.103419
M3 - Article
AN - SCOPUS:85123508355
SN - 2589-0042
VL - 24
JO - iScience
JF - iScience
IS - 12
M1 - 103419
ER -