Screening of COVID-19 cases through a Bayesian network symptoms model and psychophysical olfactory test
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 develope...
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Elsevier
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/a6d164bd43b94d57bcd4c1cc39e9e393 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:a6d164bd43b94d57bcd4c1cc39e9e393 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:a6d164bd43b94d57bcd4c1cc39e9e3932021-11-24T04:33:07ZScreening of COVID-19 cases through a Bayesian network symptoms model and psychophysical olfactory test2589-004210.1016/j.isci.2021.103419https://doaj.org/article/a6d164bd43b94d57bcd4c1cc39e9e3932021-12-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2589004221013900https://doaj.org/toc/2589-0042Summary: 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.Susana EyheramendyPedro A. SaaEduardo A. UndurragaCarlos ValenciaCarolina LópezLuis MéndezJavier Pizarro-BerdichevskyAndrés Finkelstein-KulkaSandra SolariNicolás SalasPedro BahamondesMartín UgartePablo BarcelóMarcelo ArenasEduardo AgosinElsevierarticleDiagnostic technique in health technologyDiagnosticsHealth technologyMathematical biosciencesScienceQENiScience, Vol 24, Iss 12, Pp 103419- (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Diagnostic technique in health technology Diagnostics Health technology Mathematical biosciences Science Q |
| spellingShingle |
Diagnostic technique in health technology Diagnostics Health technology Mathematical biosciences Science Q Susana Eyheramendy Pedro A. Saa Eduardo A. Undurraga Carlos Valencia Carolina López Luis Méndez Javier Pizarro-Berdichevsky Andrés Finkelstein-Kulka Sandra Solari Nicolás Salas Pedro Bahamondes Martín Ugarte Pablo Barceló Marcelo Arenas Eduardo Agosin Screening of COVID-19 cases through a Bayesian network symptoms model and psychophysical olfactory test |
| description |
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. |
| format |
article |
| author |
Susana Eyheramendy Pedro A. Saa Eduardo A. Undurraga Carlos Valencia Carolina López Luis Méndez Javier Pizarro-Berdichevsky Andrés Finkelstein-Kulka Sandra Solari Nicolás Salas Pedro Bahamondes Martín Ugarte Pablo Barceló Marcelo Arenas Eduardo Agosin |
| author_facet |
Susana Eyheramendy Pedro A. Saa Eduardo A. Undurraga Carlos Valencia Carolina López Luis Méndez Javier Pizarro-Berdichevsky Andrés Finkelstein-Kulka Sandra Solari Nicolás Salas Pedro Bahamondes Martín Ugarte Pablo Barceló Marcelo Arenas Eduardo Agosin |
| author_sort |
Susana Eyheramendy |
| title |
Screening of COVID-19 cases through a Bayesian network symptoms model and psychophysical olfactory test |
| title_short |
Screening of COVID-19 cases through a Bayesian network symptoms model and psychophysical olfactory test |
| title_full |
Screening of COVID-19 cases through a Bayesian network symptoms model and psychophysical olfactory test |
| title_fullStr |
Screening of COVID-19 cases through a Bayesian network symptoms model and psychophysical olfactory test |
| title_full_unstemmed |
Screening of COVID-19 cases through a Bayesian network symptoms model and psychophysical olfactory test |
| title_sort |
screening of covid-19 cases through a bayesian network symptoms model and psychophysical olfactory test |
| publisher |
Elsevier |
| publishDate |
2021 |
| url |
https://doaj.org/article/a6d164bd43b94d57bcd4c1cc39e9e393 |
| work_keys_str_mv |
AT susanaeyheramendy screeningofcovid19casesthroughabayesiannetworksymptomsmodelandpsychophysicalolfactorytest AT pedroasaa screeningofcovid19casesthroughabayesiannetworksymptomsmodelandpsychophysicalolfactorytest AT eduardoaundurraga screeningofcovid19casesthroughabayesiannetworksymptomsmodelandpsychophysicalolfactorytest AT carlosvalencia screeningofcovid19casesthroughabayesiannetworksymptomsmodelandpsychophysicalolfactorytest AT carolinalopez screeningofcovid19casesthroughabayesiannetworksymptomsmodelandpsychophysicalolfactorytest AT luismendez screeningofcovid19casesthroughabayesiannetworksymptomsmodelandpsychophysicalolfactorytest AT javierpizarroberdichevsky screeningofcovid19casesthroughabayesiannetworksymptomsmodelandpsychophysicalolfactorytest AT andresfinkelsteinkulka screeningofcovid19casesthroughabayesiannetworksymptomsmodelandpsychophysicalolfactorytest AT sandrasolari screeningofcovid19casesthroughabayesiannetworksymptomsmodelandpsychophysicalolfactorytest AT nicolassalas screeningofcovid19casesthroughabayesiannetworksymptomsmodelandpsychophysicalolfactorytest AT pedrobahamondes screeningofcovid19casesthroughabayesiannetworksymptomsmodelandpsychophysicalolfactorytest AT martinugarte screeningofcovid19casesthroughabayesiannetworksymptomsmodelandpsychophysicalolfactorytest AT pablobarcelo screeningofcovid19casesthroughabayesiannetworksymptomsmodelandpsychophysicalolfactorytest AT marceloarenas screeningofcovid19casesthroughabayesiannetworksymptomsmodelandpsychophysicalolfactorytest AT eduardoagosin screeningofcovid19casesthroughabayesiannetworksymptomsmodelandpsychophysicalolfactorytest |
| _version_ |
1718415995734851584 |