A machine learning approach to differentiate between COVID-19 and influenza infection using synthetic infection and immune response data

Suzan Farhang-Sardroodi; Mohammad Sajjad Ghaemi; Morgan Craig; Hsu Kiang Ooi; Jane M Heffernan; Suzan Farhang-Sardroodi; Mohammad Sajjad Ghaemi; Morgan Craig; Hsu Kiang Ooi; Jane M Heffernan

doi:10.3934/mbe.2022272

Mathematical Biosciences and Engineering

2022, Volume 19, Issue 6: 5813-5831. doi: 10.3934/mbe.2022272

Previous Article Next Article

Research article

A machine learning approach to differentiate between COVID-19 and influenza infection using synthetic infection and immune response data

1.
Modelling Infection and Immunity Lab, Mathematics Statistics, York University, Toronto, Canada
2.
Centre for Disease Modelling (CDM), Mathematics Statistics, York University, Toronto, Canada
3.
Digital Technologies Research Centre, National Research Council Canada, Toronto, ON, Canada
4.
Sainte-Justine University Hospital Research Centre and Department of Mathematics and Statistics, Université de Montréal, Montreal, Quebec, Canada

Received: 27 January 2022 Revised: 14 March 2022 Accepted: 28 March 2022 Published: 06 April 2022

Data analysis is widely used to generate new insights into human disease mechanisms and provide better treatment methods. In this work, we used the mechanistic models of viral infection to generate synthetic data of influenza and COVID-19 patients. We then developed and validated a supervised machine learning model that can distinguish between the two infections. Influenza and COVID-19 are contagious respiratory illnesses that are caused by different pathogenic viruses but appeared with similar initial presentations. While having the same primary signs COVID-19 can produce more severe symptoms, illnesses, and higher mortality. The predictive model performance was externally evaluated by the ROC AUC metric (area under the receiver operating characteristic curve) on 100 virtual patients from each cohort and was able to achieve at least AUC = $ 91\% $ using our multiclass classifier. The current investigation highlighted the ability of machine learning models to accurately identify two different diseases based on major components of viral infection and immune response. The model predicted a dominant role for viral load and productively infected cells through the feature selection process.
- biological systems,
- mechanistic model,
- infectious disease,
- Influenza (flu),
- COVID-19,
- machine learning,
- classification,
- Logistic regression,
- regularization,
- Lasso,
- Ridge,
- PLS-DA
Citation: Suzan Farhang-Sardroodi, Mohammad Sajjad Ghaemi, Morgan Craig, Hsu Kiang Ooi, Jane M Heffernan. A machine learning approach to differentiate between COVID-19 and influenza infection using synthetic infection and immune response data[J]. Mathematical Biosciences and Engineering, 2022, 19(6): 5813-5831. doi: 10.3934/mbe.2022272

Related Papers:

Abstract

Data analysis is widely used to generate new insights into human disease mechanisms and provide better treatment methods. In this work, we used the mechanistic models of viral infection to generate synthetic data of influenza and COVID-19 patients. We then developed and validated a supervised machine learning model that can distinguish between the two infections. Influenza and COVID-19 are contagious respiratory illnesses that are caused by different pathogenic viruses but appeared with similar initial presentations. While having the same primary signs COVID-19 can produce more severe symptoms, illnesses, and higher mortality. The predictive model performance was externally evaluated by the ROC AUC metric (area under the receiver operating characteristic curve) on 100 virtual patients from each cohort and was able to achieve at least AUC = $ 91\% $ using our multiclass classifier. The current investigation highlighted the ability of machine learning models to accurately identify two different diseases based on major components of viral infection and immune response. The model predicted a dominant role for viral load and productively infected cells through the feature selection process.

References

[1]	L. D. Manzanares-Meza, O. Medina-Contreras, SARS-CoV-2 and influenza: A comparative overview and treatment implications, Bol. Med. Hosp. Infant. Mex., 77 (2020), 262–273. https://doi.org/10.24875/bmhim.20000183 doi: 10.24875/bmhim.20000183
[2]	K. Subbarao, S. Mahanty, Respiratory virus infections: Understanding COVID-19, Immunity, 52 (2020), 905–909. https://doi.org/10.1016/j.immuni.2020.05.004 doi: 10.1016/j.immuni.2020.05.004
[3]	H. Faury, C. Courboulès, M. Payen, A. Jary, P. Hausfater, C. E. Luyt, et al., Medical features of COVID-19 and influenza infection: A comparative study in Paris, France, J. Infect., 82 (2021), e36–e39. https://doi.org/10.1016/j.jinf.2020.08.017 doi: 10.1016/j.jinf.2020.08.017
[4]	X. Zheng, H. Wang, Z. Su, W. Li, D. Yang, F. Deng, et al., Co-infection of SARS-CoV-2 and influenza virus in early stage of the COVID-19 epidemic in Wuhan, China, J. Infect., 81 (2020), e128–e129. https://doi.org/10.1016/j.jinf.2020.05.041 doi: 10.1016/j.jinf.2020.05.041
[5]	S. Azekawa, H. Namkoong, K. Mitamura, Y. Kawaoka, F. Saito, Co-infection with SARS-CoV-2 and influenza A virus, IDCases, 20 (2020), e00775. https://doi.org/10.1016/j.idcr.2020.e00775 doi: 10.1016/j.idcr.2020.e00775
[6]	H. Khorramdelazad, M. H. Kazemi, A. Najafi, M. Keykhaee, R. Z. Emameh, R. Falak, Immunopathological similarities between COVID-19 and influenza: Investigating the consequences of Co-infection, Microb. Pathog., 152 (2021), 104554. https://doi.org/10.1016/j.micpath.2020.104554 doi: 10.1016/j.micpath.2020.104554
[7]	P. K. Bhatraju, B. J. Ghassemieh, M. Nichols, R. Kim, K. R. Jerome, A. K. Nalla, et al., Covid-19 in critically ill patients in the Seattle region—case series, NEJM., 382 (2020), 2012–2022. https://doi.org/10.1056/NEJMoa2004500 doi: 10.1056/NEJMoa2004500
[8]	N. Yanamala, N. H. Krishna, Q. A. Hathaway, A. Radhakrishnan, S. Sunkara, H. Patel, et al., A vital sign-based prediction algorithm for differentiating COVID-19 versus seasonal influenza in hospitalized patients, NPJ Digit. Med., 4 (2021), 1–10. https://doi.org/10.1038/s41746-021-00467-8 doi: 10.1038/s41746-021-00467-8
[9]	M. Ackermann, S. E. Verleden, M. Kuehnel, A. Haverich, T. Welte, F. Laenger, et al., Pulmonary vascular endothelialitis, thrombosis, and angiogenesis in Covid-19, NEJM., 383 (2020), 120–128. https://doi.org/10.1056/NEJMoa2015432 doi: 10.1056/NEJMoa2015432
[10]	Q. Li, X. Guan, P. Wu, X. Wang, L. Zhou, Y. Tong, et al., Early transmission dynamics in Wuhan, China, of novel coronavirus–infected pneumonia, NEJM., 382 (2020), 1199–1207. https://doi.org/10.1056/10.1056/NEJMoa2001316 doi: 10.1056/10.1056/NEJMoa2001316
[11]	N. Zhu, D. Zhang, W.Wang, X. Li, B. Yang, J. Song, et al., A novel coronavirus from patients with pneumonia in China, 2019, NEJM., 382 (2020), 727–733. https://doi.org/10.1056/NEJMoa2001017 doi: 10.1056/NEJMoa2001017
[12]	M. S. Ciupe, J. M. Heffernan, In-host modeling, Infect. Dis. Model., 2 (2017), 188–202. https://doi.org/10.1016/j.idm.2017.04.002
[13]	D. Kyte, J. Ives, H. Draper, T. Keeley, M. Calvert, Inconsistencies in quality of life data collection in clinical trials: A potential source of bias? Interviews with research nurses and trialists, PLoS One, 8 (2013), e76625. https://doi.org/10.1371/journal.pone.0076625 doi: 10.1371/journal.pone.0076625
[14]	F. Jiang, Y. Jiang, H. Zhi, Y. Dong, H. Li, S. Ma, et al., Artificial intelligence in healthcare: Past, present and future, Stroke Vasc. Neurol., 2 (2017). http://dx.doi.org/10.1136/svn-2017-000101
[15]	T. Davenport, R. Kalakota, The potential for artificial intelligence in healthcare, Future Healthc. J., 6 (2019), 94. https://doi.org/10.7861/futurehosp.6-2-94 doi: 10.7861/futurehosp.6-2-94
[16]	A. Bohr, K. Memarzadeh, The rise of artificial intelligence in healthcare applications, Artif. Intell. Med., (2020), 25–60. https://doi.org/10.1016/B978-0-12-818438-7.00002-2
[17]	M. Mirbabaie, S. Stieglitz, N. Nicholas RJ. Frick, Artificial intelligence in disease diagnostics: A critical review and classification on the current state of research guiding future direction, Health Technol., 11 (2021), 693–731. https://doi.org/10.1007/s12553-021-00555-5 doi: 10.1007/s12553-021-00555-5
[18]	P. Baccam, C. Beauchemin, C. A. Macken, F. G. Hayden, A. S. Perelson, Kinetics of influenza A virus infection in humans, Virol. J., 80 (2006), 7590–7599. https://doi.org/10.1128/JVI.01623-05 doi: 10.1128/JVI.01623-05
[19]	A. Gonçalves, J. Bertrand, R. Ke, E. Comets, X. De Lamballerie, D. Malvy, et al., Timing of antiviral treatment initiation is critical to reduce SARS-CoV-2 viral load, CPT Pharmacometrics Syst. Pharmacol., 9 (2020), 509–514. https://doi.org/10.1002/psp4.12543 doi: 10.1002/psp4.12543
[20]	A. W. Salehi, P. Baglat, G. Gupta, Review on machine and deep learning models for the detection and prediction of Coronavirus, PloS one, 33 (2020), 3896–3901. https://doi.org/10.1016/j.matpr.2020.06.245 doi: 10.1016/j.matpr.2020.06.245
[21]	A. Alimadadi, S. Aryal, I. Manandhar, B. P. Munroe, B. Joe, Xi. Cheng, Artificial intelligence and machine learning to fight COVID-19, Physiol. Genomics, 52 (2020), 200–202. https://doi.org/10.1152/physiolgenomics.00029.2020 doi: 10.1152/physiolgenomics.00029.2020
[22]	A. W. Salehi, P. Baglat, G. Gupta, Alzheimer's disease diagnosis using deep learning techniques, Int. J. Eng. Adv. Technol., 9 (2020), 874–880. https://doi.org/10.35940/ijeat.C5345.02 doi: 10.35940/ijeat.C5345.02
[23]	P. Cao, A. W. Yan, J. M. Heffernan, S. Petrie, R. G. Moss, L. A. Carolan, et al., Innate immunity and the inter-exposure interval determine the dynamics of secondary influenza virus infection and explain observed viral hierarchies, PLoS Comput. Biol., 11 (2015), e1004334. https://doi.org/10.1371/journal.pcbi.1004334 doi: 10.1371/journal.pcbi.1004334
[24]	A. L. Jenner, R. A. Aogo, S. Alfonso, V. Crowe, X. Deng, A. P. Smith, et al., COVID-19 virtual patient cohort suggests immune mechanisms driving disease outcomes, PLoS Pathog., 17 (2021), e1009753. https://doi.org/10.1371/journal.ppat.1009753 doi: 10.1371/journal.ppat.1009753
[25]	F. McNab, K. Mayer-Barber, A. Sher, A. Wack, A. O'garra, Type I interferons in infectious disease, Nat. Rev. Immunol., 15 (2015), 87–103. https://doi.org/10.1038/nri3787 doi: 10.1038/nri3787
[26]	N. Néant, G. Lingas, Q. Le Hingrat, J. Ghosn, I. Engelmann, Q. Lepiller, et al., Modeling SARS-CoV-2 viral kinetics and association with mortality in hospitalized patients from the French COVID cohort, Proc. Natl. Acad. Sci., 118 (2021), e2017962118. https://doi.org/10.1073/pnas.2017962118 doi: 10.1073/pnas.2017962118
[27]	L. B. Ivashkiv, L. T. Donlin, Regulation of type I interferon responses, Nat. Rev. Immunol., 14 (2014), 36–49. https://doi.org/10.1038/nri3581 doi: 10.1038/nri3581
[28]	K. A. Pawelek, G. T. Huynh, M. Quinlivan, A. Cullinane, L. Rong, A. S. Perelson, Modeling within-host dynamics of influenza virus infection including immune responses, PLoS Comput. Biol., 8 (2012), e1002588. https://doi.org/10.1371/journal.pcbi.1002588 doi: 10.1371/journal.pcbi.1002588
[29]	F. G. Hayden, R. Fritz, M. C. Lobo, W. Alvord, W. Strober, S. E. Straus, Local and systemic cytokine responses during experimental human influenza A virus infection. Relation to symptom formation and host defense, J. Clin. Investig., 101 (1998), 643–649. https://doi.org/10.1172/JCI1355 doi: 10.1172/JCI1355
[30]	N. K. Vaidya, A. Bloomquist, A. S. Perelson, Modeling Within-Host Dynamics of SARS-CoV-2 Infection: A Case Study in Ferrets, Viruses, 13 (2021), 1635. https://doi.org/10.3390/v13081635 doi: 10.3390/v13081635
[31]	L. Bordi, G. Sberna, E. Lalle, P. Piselli, F. Colavita, E. Nicastri, et al., Frequency and duration of SARS-CoV-2 shedding in oral fluid samples assessed by a modified commercial rapid molecular assay, Viruses, 12 (2020), 1184. https://doi.org/10.3390/v12101184 doi: 10.3390/v12101184
[32]	W. H. Mahallawi, A. D. Alsamiri, A. F. Dabbour, H. Alsaeedi, A. H. Al-Zalabani, Association of viral load in SARS-CoV-2 patients with age and gender, Front. Med., 8 (2021), 39. https://doi.org/10.3389/fmed.2021.608215 doi: 10.3389/fmed.2021.608215
[33]	K. Ejima, K. S. Kim, C. Ludema, A. I. Bento, S. Iwanami, Y. Fujita, et al., Estimation of the incubation period of COVID-19 using viral load data, Epidemics, 35 (2021), 100454. https://doi.org/10.1016/j.epidem.2021.100454 doi: 10.1016/j.epidem.2021.100454
[34]	R. Tibshirani, Regression shrinkage and selection via the lasso, J. R. Stat. Soc. B Stat. Methodol., 58 (1996), 267–288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x doi: 10.1111/j.2517-6161.1996.tb02080.x
[35]	X. Han, M. S. Ghaemi, K. Ando, L. S. Peterson, E. A. Ganio, A. S. Tsai, et al., Differential dynamics of the maternal immune system in healthy pregnancy and preeclampsia, Front. Immunol., 10 (2019), 1305. https://doi.org/10.3389/fimmu.2019.01305 doi: 10.3389/fimmu.2019.01305
[36]	T. Miller, Explanation in artificial intelligence: Insights from the social sciences, Artif. Intell., 267 (2019), 1–38. https://doi.org/10.1016/j.artint.2018.07.007 doi: 10.1016/j.artint.2018.07.007
[37]	B. Kim, R. Khanna, O. O. Koyejo, Examples are not enough, learn to criticize! criticism for interpretability, Adv. Neural Inf. Process. Syst., 29 (2016), 2288–-2296.
[38]	C. Molnar, Interpretable machine learning, Lulu. Com., (2020).
[39]	W. J. Murdoch, C. Singh, K. Kumbier, R. Abbasi-Asl, B. Yu, Definitions, methods, and applications in interpretable machine learning, Proceedings of the National Academy of Sciences, 116 (2019), 22071–22080. https://doi.org/10.1073/pnas.1900654116 doi: 10.1073/pnas.1900654116
[40]	O. Dogan, S. Tiwari, M. A. Jabbar, S. Guggari, A systematic review on AI/ML approaches against COVID-19 outbreak, Complex Intell. Syst., 7 (2021), 2655–2678. https://doi.org/10.1007/s40747-021-00424-8 doi: 10.1007/s40747-021-00424-8
[41]	M. A. Quiroz-Juárez, A. Torres-Gómez, I. Hoyo-Ulloa, R. d. J. León-Montiel, A. B. U'Ren, Identification of high-risk COVID-19 patients using machine learning, PLoS One, 16 (2021), e0257234. https://doi.org/10.1371/journal.pone.0257234 doi: 10.1371/journal.pone.0257234
[42]	M. M. Rahman, F. Khatun, A. Uzzaman, S. I. Sami, M. A. Bhuiyan, T. S. Kiong, A comprehensive study of artificial intelligence and machine learning approaches in confronting the coronavirus (COVID-19) pandemic, PLoS One, 51 (2021), 446–461. https://doi.org/10.1177/00207314211017469 doi: 10.1177/00207314211017469

Reader Comments

Your name:*

Email:*
© 2022 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)