Volume 11, Issue 1 (January 2024), Pages: 207-216

----------------------------------------------

 Original Research Paper

Detection and risk assessment of COVID-19 through machine learning

 Author(s): 

 B. Luna-Benoso, J. C. Martínez-Perales *, J. Cortés-Galicia, U. S. Morales-Rodríguez

 Affiliation(s):

 Escuela Superior de Cómputo, Instituto Politécnico Nacional, Mexico City, Mexico

 Full text

  Full Text - PDF

 * Corresponding Author. 

  Corresponding author's ORCID profile: https://orcid.org/0000-0001-9421-5923

 Digital Object Identifier (DOI)

 https://doi.org/10.21833/ijaas.2024.01.025

 Abstract

COVID-19, also known as coronavirus disease, is caused by the SARS-CoV-2 virus. People infected with COVID-19 may show a range of symptoms from mild to severe, including fever, cough, difficulty breathing, tiredness, and nasal congestion, among others. The goal of this study is to use machine learning to identify if a person has COVID-19 based on their symptoms and to predict how severe their illness might become. This could lead to outcomes like needing a ventilator or being admitted to an Intensive Care Unit. The methods used in this research include Artificial Neural Networks (specifically, Multi-Layer Perceptrons), Classification and Regression Trees, and Random Forests. Data from the National Epidemiological Surveillance System of Mexico City was analyzed. The findings indicate that the Multi-Layer Perceptron model was the most accurate, with an 87.68% success rate. It was best at correctly identifying COVID-19 cases. Random Forests were more effective at predicting severe cases and those requiring Intensive Care Unit admission, while Classification and Regression Trees were more accurate in identifying patients who needed to be put on a ventilator.

 © 2024 The Authors. Published by IASE.

 This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

 Keywords

 Machine learning, Artificial neural networks, Decision trees, Random forests, COVID-19

 Article history

 Received 28 July 2023, Received in revised form 5 January 2024, Accepted 15 January 2024

 Acknowledgment 

The authors would like to thank the Instituto Politécnico Nacional (Secretaría Académica, COFAA, EDD, EDI, SIP, and ESCOM) and CONAHCYT for their financial support in developing this work.

 Compliance with ethical standards

 Conflict of interest: The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

 Citation:

 Luna-Benoso B, Martínez-Perales JC, Cortés-Galicia J, and Morales-Rodríguez US (2024). Detection and risk assessment of COVID-19 through machine learning. International Journal of Advanced and Applied Sciences, 11(1): 207-216

 Permanent Link to this page

 Figures

 Fig. 1 Fig. 2 Fig. 3 Fig. 4 Fig. 5 Fig. 6 Fig. 7 Fig. 8 Fig. 9 Fig. 10 Fig. 11 Fig. 12 Fig. 13 

 Tables

 Table 1 

----------------------------------------------   

 References (31)

1. Abolfotouh MA, Musattat A, Alanazi M, Alghnam S, and Bosaeed M (2022). Clinical characteristics and outcome of COVID-19 illness and predictors of in-hospital mortality in Saudi Arabia. BMC Infectious Diseases, 22: 950. https://doi.org/10.1186/s12879-022-07945-8   [Google Scholar] PMid:36526994 PMCid:PMC9758036
2. Alhadi B, Khder MM, Rashid S, Taha K, and Manzour AF (2023). Health care workers’ perceptions of their hospitals’ preparedness during the COVID-19 virus pandemic in three different world regions. Clinical Epidemiology and Global Health, 21: 101278. https://doi.org/10.1016/j.cegh.2023.101278   [Google Scholar] PMid:37033720 PMCid:PMC10066860
3. Arvind V, Kim JS, Cho BH, Geng E, and Cho SK (2021). Development of a machine learning algorithm to predict intubation among hospitalized patients with COVID-19. Journal of Critical Care, 62: 25-30. https://doi.org/10.1016/j.jcrc.2020.10.033   [Google Scholar] PMid:33238219 PMCid:PMC7669246
4. Bakheet S and Al-Hamadi A (2021). Automatic detection of COVID-19 using pruned GLCM-Based texture features and LDCRF classification. Computers in Biology and Medicine, 137: 104781. https://doi.org/10.1016/j.compbiomed.2021.104781   [Google Scholar] PMid:34455303 PMCid:PMC8382592
5. Ballering AV, van Zon SKR, Olde TC, and Rosmalen JGM (2022). Persistence of somatic symptoms after COVID-19 in the Netherlands: an observational cohort study. Lancet, 400(10350): 452-461. https://doi.org/10.1016/S0140-6736(22)01214-4   [Google Scholar] PMid:35934007
6. Boussen S, Cordier PY, Malet A, Simeone P, Cataldi S, Vaisse C, Roche X, Castelli A, Assal M, Pepin G, Cot K, Denis JB, Morales T, Velly L, and Bruder N (2022). Triage and monitoring of COVID-19 patients in intensive care using unsupervised machine learning. Computers in Biology and Medicine, 142: 105192. https://doi.org/10.1016/j.compbiomed.2021.105192   [Google Scholar] PMid:34998220 PMCid:PMC8719000
7. Charbuty B and Abdulazeez A (2021). Classification based on decision tree algorithm for machine learning. Journal of Applied Science and Technology Trends, 2(01): 20-28. https://doi.org/10.38094/jastt20165   [Google Scholar]
8. Cisterna-García A, Guillén-Teruel A, Caracena M, Pérez E, Jiménez F, Francisco-Verdú FJ, Reina G, González-Billalabeitia E, Palma J, Sánchez-Ferrer A, and Botía JA (2022). A predictive model for hospitalization and survival to COVID-19 in a retrospective population-based study. Scientific Reports, 12: 18126. https://doi.org/10.1038/s41598-022-22547-9   [Google Scholar] PMid:36307436 PMCid:PMC9614188
9. Despotovic V, Ismael M, Cornil M, Mc Call R, and Fagherazzi G (2021). Detection of COVID-19 from voice, cough and breathing patterns: Dataset and preliminary results. Computers in Biology and Medicine, 138: 104944. https://doi.org/10.1016/j.compbiomed.2021.104944   [Google Scholar] PMid:34656870 PMCid:PMC8513517
10. Duong LT, Nguyen PT, Iovino L, and Flammini M (2023). Automatic detection of COVID-19 from chest X-ray and lung computed tomography images using deep neural networks and transfer learning. Applied Soft Computing, 132: 109851. https://doi.org/10.1016/j.asoc.2022.109851   [Google Scholar] PMid:36447954 PMCid:PMC9686054
11. Ferté T, Ramel V, Cazanave C, Lafon ME, Bébéar C, Malvy D, Georges-Walryck A, and Dehail P (2021). Accuracy of COVID-19 rapid antigenic tests compared to RT-PCR in a student population: The StudyCov study. Journal of Clinical Virology, 141: 104878. https://doi.org/10.1016/j.jcv.2021.104878   [Google Scholar] PMid:34134035 PMCid:PMC8178956
12. Feteira-Santos R, Camarinha C, Nobre MA, Elias C, Bacelar-Nicolau L, Silva A, Furtado C, and Nogueira PJ (2022). Improving morbidity information in Portugal: Evidence from data linkage of COVID-19 cases surveillance and mortality systems. International Journal of Medical Informatics, 163: 104763. https://doi.org/10.1016/j.ijmedinf.2022.104763   [Google Scholar] PMid:35461149 PMCid:PMC9012514
13. Firouzabadi N, Ghasemiyeh P, Moradishooli F, and Mohammadi S (2023). Update on the effectiveness of COVID-19 vaccines on different variants of SARS-CoV-2. International Immunopharmacology, 117: 109968. https://doi.org/10.1016/j.intimp.2023.109968   [Google Scholar] PMid:37012880 PMCid:PMC9977625
14. Hu Q, Nauber F, Costa R, Zhang L, Yin L, Magaia N, and Albuquerque VHC (2022). Explainable artificial intelligence-based Edge fuzzy images for COVID-19 detection and identification. Applied Soft Computing, 123: 108966. https://doi.org/10.1016/j.asoc.2022.108966   [Google Scholar] PMid:35582662 PMCid:PMC9102011
15. Huyut MT (2023). Automatic detection of severely and mildly infected COVID-19 patients with supervised machine learning models. Innovation and Research in BioMedical Engineering, 44(1): 100725. https://doi.org/10.1016/j.irbm.2022.05.006   [Google Scholar] PMid:35673548 PMCid:PMC9158375
16. Kanti T, Mishra S, Panda G, and Chandra S (2021). Detection of COVID-19 from speech signal using bio-inspired based cepstral features. Pattern Recognition, 117: 107999. https://doi.org/10.1016/j.patcog.2021.107999   [Google Scholar] PMid:33967346 PMCid:PMC8086594
17. Liu W, Zhang L, Xie L, Hu T, Li G, Bai S, and Yi Z (2023). Multilayer perceptron neural network with regression and ranking loss for patient-specific quality assurance. Knowledge-Based Systems, 271: 110549. https://doi.org/10.1016/j.knosys.2023.110549   [Google Scholar]
18. López-Úbeda P, Díaz-Galiano MC, Martín-Noguerol T, Luna A, Ureña-López LA, and Martín-Valdivia MT (2020). COVID-19 detection in radiological text reports integrating entity recognition. Computers in Biology and Medicine, 127: 104066. https://doi.org/10.1016/j.compbiomed.2020.104066   [Google Scholar] PMid:33130435 PMCid:PMC7577869
19. Nyber T, Bager P, Svalgaard IB, Bejko D, Bundle N, Evans J, Krause TG, McMenamin J, Mosson J, Mutch H, Omokanye A, Peralta-Santos A, Pinto-Leite P, Starrfelt J, Thelwall S, Veneti L, Whittaker R, Wood J, Peboy R, and Presanis AM (2023). A standardised protocol for relative SARS-CoV-2 variant severity assessment, applied to Omicron BA.1 and Delta in six European countries, October 2021 to February 2022. Eurosurveillance, 28(36): 2300048. https://doi.org/10.2807/1560-7917.ES.2023.28.36.2300048   [Google Scholar] PMid:37676146 PMCid:PMC10486193
20. Pahar M, Klopper M, Warren R, and Niesler T (2022). COVID-19 detection in cough, breath and speech using deep transfer learnig and bottleneck features. Computers in Biology and Medicine, 141: 105153. https://doi.org/10.1016/j.compbiomed.2021.105153   [Google Scholar] PMid:34954610 PMCid:PMC8679499
21. Panthakkan A, Anzar SM, Mansoori SA, and Ahmad HA (2021). A novel DeepNet model for the efficient detection of COVID-19 for symptomatic patients. Biomedical Signal Processing and Control, 68: 102812. https://doi.org/10.1016/j.bspc.2021.102812   [Google Scholar] PMid:34075316 PMCid:PMC8156912
22. Perez M, Saad NJ, Lucaccioni H, Costa C, McMahon G, Machado F, Balasegaram S, and Machado RS (2021). Clinical and hospitalisation predictors of COVID-19 in the first month of the pandemic, Portugal. PLOS ONE, 16(11): e0260249. https://doi.org/10.1371/journal.pone.0260249   [Google Scholar] PMid:34797879 PMCid:PMC8604361
23. Rufino J, Ramírez JM, Aguilar J, Baquero C, Champati J, Frey D, Lillo RE, and Fernández-Anta A (2023). Consistent comparison of symptom-based methods for COVID-19 infection detection. International Journal of Medical Informatics, 177: 105133. https://doi.org/10.1016/j.ijmedinf.2023.105133   [Google Scholar] PMid:37393765
24. Thousif M, Abdul M, and Vankdothu R (2022). COVID-19 detection and classification for machine learning methods using human genomic data. Measurement: Sensors, 24: 100537. https://doi.org/10.1016/j.measen.2022.100537   [Google Scholar] PMid:36466096 PMCid:PMC9595328
25. Valero-Carreras D, Alcaraz J, and Landete M (2023). Comparing two SVM models through different metrics base on the confusion matrix. Computers and Operations Research, 152: 106131. https://doi.org/10.1016/j.cor.2022.106131   [Google Scholar]
26. Van Kessel SAM, Olde HTC, Lucassen PLBJ, and van Jaarsveld CHM (2022). Post-acute and long-COVID-19 symptoms in patients with mild diseases: A systematic review. Family Practice, 39(1): 159-167. https://doi.org/10.1093/fampra/cmab076   [Google Scholar] PMid:34268556 PMCid:PMC8414057
27. WHO (2020). Weekly epidemiological update - 29 December 2020. World Health Organization. Geneva, Switzerland.   [Google Scholar]
28. WHO (2021). Weekly epidemiological update on COVID-19 - 21 December 2021. World Health Organization. Geneva, Switzerland.   [Google Scholar]
29. WHO (2022). Weekly epidemiological update on COVID-19 - 21 December 2022. World Health Organization. Geneva, Switzerland.   [Google Scholar]
30. WHO (2023). Weekly epidemiological update on COVID-19 - 13 April 2023. World Health Organization. Geneva, Switzerland.   [Google Scholar]
31. Zhang H, Quost B, and Masson MH (2023). Cautious weighted random forest. Expert Systems with Applications, 213: 118883. https://doi.org/10.1016/j.eswa.2022.118883   [Google Scholar]