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

iScience

Andrés Finkelstein-Kulka¹  Martín Ugarte²  Marcelo Arenas³  Carlos Valencia⁴  Luis Méndez⁵  Pedro A. Saa⁶  Javier Pizarro-Berdichevsky⁷  Nicolás Salas⁸  Sandra Solari⁸  Pablo Barceló⁹  Eduardo A. Undurraga^1,10  Eduardo Agosin^1,11  Pedro Bahamondes^1,12  Susana Eyheramendy^1,13  Carolina López^1,14 

[1] CIFAR Azrieli Global Scholars Program, Toronto, Canada;Department of Gastroenterology, Clínica Alemana de Santiago, Santiago, Chile;Department of Obstetrics and Gynecology, Faculty of Medicine, Pontificia Universidad Católica de Chile, Santiago, Chile;Institute for Mathematical and Computational Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile;Millennium Initiative for Collaborative Research in Bacterial Resistance (MICROB-R), Santiago, Chile;Millennium Institute for Foundational Research on Data (IMFD), Santiago, Chile;Research Center for Integrated Disaster Risk Management (CIGIDEN), Santiago, Chile;Center for Aromas and Flavors, DICTUC SA., Santiago, Chile;Center for Innovation in Pelvic Floor, Hospital Sótero del Río, Santiago, Chile;Department of Chemical and Bioprocess Engineering, School of Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile;Department of Otolaryngology, Clínica Alemana de Santiago, Santiago, Chile;Endoscopy Unit, Hospital Padre Hurtado, Santiago, Chile;Faculty of Engineering and Science, Universidad Adolfo Ibáñez, Santiago, Chile;School of Government, Pontificia Universidad Católica de Chile, Santiago, Chile;

关键词: Diagnostic technique in health technology;    Diagnostics;    Health technology;    Mathematical biosciences;   

DOI  :  

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown