A machine learning approach as an aid for early covid-19 detection

Roberto Martinez-Velazquez; Diana P. Tobón V.; Alejandro Sanchez; Abdulmotaleb El Saddik; Emil Petriu

doi:10.3390/s21124202

A machine learning approach as an aid for early covid-19 detection

Roberto Martinez-Velazquez, Diana P. Tobón V., Alejandro Sanchez, Abdulmotaleb El Saddik, Emil Petriu

ARKADIUS Research Group

Research output: Contribution to journal › Article › peer-review

16 Scopus citations

Abstract

The novel coronavirus SARS-CoV-2 that causes the disease COVID-19 has forced us to go into our homes and limit our physical interactions with others. Economies around the world have come to a halt, with non-essential businesses being forced to close in order to prevent further propagation of the virus. Developing countries are having more difficulties due to their lack of access to diagnostic resources. In this study, we present an approach for detecting COVID-19 infections exclusively on the basis of self-reported symptoms. Such an approach is of great interest because it is relatively inexpensive and easy to deploy at either an individual or population scale. Our best model delivers a sensitivity score of 0.752, a specificity score of 0.609, and an area under the curve for the receiver operating characteristic of 0.728. These are promising results that justify continuing research efforts towards a machine learning test for detecting COVID-19.

Original language	English
Article number	4202
Journal	Sensors
Volume	21
Issue number	12
DOIs	https://doi.org/10.3390/s21124202
State	Published - 2 Jun 2021

Keywords

COVID-19 detection
Machine learning
SARS-CoV-2
Symptoms-based test

Product types of Minciencias

A1 article - Q1

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.3390/s21124202

Cite this

@article{38737d69e4024a5490d7c33e73bd0e23,

title = "A machine learning approach as an aid for early covid-19 detection",

abstract = "The novel coronavirus SARS-CoV-2 that causes the disease COVID-19 has forced us to go into our homes and limit our physical interactions with others. Economies around the world have come to a halt, with non-essential businesses being forced to close in order to prevent further propagation of the virus. Developing countries are having more difficulties due to their lack of access to diagnostic resources. In this study, we present an approach for detecting COVID-19 infections exclusively on the basis of self-reported symptoms. Such an approach is of great interest because it is relatively inexpensive and easy to deploy at either an individual or population scale. Our best model delivers a sensitivity score of 0.752, a specificity score of 0.609, and an area under the curve for the receiver operating characteristic of 0.728. These are promising results that justify continuing research efforts towards a machine learning test for detecting COVID-19.",

keywords = "COVID-19 detection, Machine learning, SARS-CoV-2, Symptoms-based test",

author = "Roberto Martinez-Velazquez and {Tob{\'o}n V.}, {Diana P.} and Alejandro Sanchez and {El Saddik}, Abdulmotaleb and Emil Petriu",

note = "Funding Information: Especial acknowledgements to the National Council of Science and Technology (CONACyT) and the State Council of Science and Technology Colima (CECyTCOL), both in M?xico. Publisher Copyright: {\textcopyright} 2021 by the authors. Licensee MDPI, Basel, Switzerland.",

year = "2021",

month = jun,

day = "2",

doi = "10.3390/s21124202",

language = "Ingl{\'e}s",

volume = "21",

journal = "Sensors",

issn = "1424-8220",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "12",

}

TY - JOUR

T1 - A machine learning approach as an aid for early covid-19 detection

AU - Martinez-Velazquez, Roberto

AU - Tobón V., Diana P.

AU - Sanchez, Alejandro

AU - El Saddik, Abdulmotaleb

AU - Petriu, Emil

N1 - Funding Information: Especial acknowledgements to the National Council of Science and Technology (CONACyT) and the State Council of Science and Technology Colima (CECyTCOL), both in M?xico. Publisher Copyright: © 2021 by the authors. Licensee MDPI, Basel, Switzerland.

PY - 2021/6/2

Y1 - 2021/6/2

N2 - The novel coronavirus SARS-CoV-2 that causes the disease COVID-19 has forced us to go into our homes and limit our physical interactions with others. Economies around the world have come to a halt, with non-essential businesses being forced to close in order to prevent further propagation of the virus. Developing countries are having more difficulties due to their lack of access to diagnostic resources. In this study, we present an approach for detecting COVID-19 infections exclusively on the basis of self-reported symptoms. Such an approach is of great interest because it is relatively inexpensive and easy to deploy at either an individual or population scale. Our best model delivers a sensitivity score of 0.752, a specificity score of 0.609, and an area under the curve for the receiver operating characteristic of 0.728. These are promising results that justify continuing research efforts towards a machine learning test for detecting COVID-19.

AB - The novel coronavirus SARS-CoV-2 that causes the disease COVID-19 has forced us to go into our homes and limit our physical interactions with others. Economies around the world have come to a halt, with non-essential businesses being forced to close in order to prevent further propagation of the virus. Developing countries are having more difficulties due to their lack of access to diagnostic resources. In this study, we present an approach for detecting COVID-19 infections exclusively on the basis of self-reported symptoms. Such an approach is of great interest because it is relatively inexpensive and easy to deploy at either an individual or population scale. Our best model delivers a sensitivity score of 0.752, a specificity score of 0.609, and an area under the curve for the receiver operating characteristic of 0.728. These are promising results that justify continuing research efforts towards a machine learning test for detecting COVID-19.

KW - COVID-19 detection

KW - Machine learning

KW - SARS-CoV-2

KW - Symptoms-based test

UR - http://www.scopus.com/inward/record.url?scp=85108064294&partnerID=8YFLogxK

U2 - 10.3390/s21124202

DO - 10.3390/s21124202

M3 - Artículo

AN - SCOPUS:85108064294

SN - 1424-8220

VL - 21

JO - Sensors

JF - Sensors

IS - 12

M1 - 4202

ER -

A machine learning approach as an aid for early covid-19 detection

Abstract

Keywords

Product types of Minciencias

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this