Skip to main content

Advertisement

Can neural networks estimate parameters in epidemiology models using real observed data?

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

The primary objective of this study is to address the challenges associated with estimating parameters in mathematical epidemiology models, which are crucial for understanding the dynamics of infectious diseases within a population. The scope of this research includes the development and application of a two-phase neural network for parameter estimation, specifically within the context of epidemic compartmental models. This study presents a novel approach by integrating an extreme learning machine with a heuristic population-based optimization method within a two-phase neural network framework. The networks are driven by a heuristic population-based optimization method, enhancing the accuracy and efficiency of parameter estimation in mathematical epidemiology models. The effectiveness of the method is validated using actual COVID-19 data provided by the Turkish Ministry of Health. The data includes cases categorized as Susceptible, Exposed, Infected, Removed, and Deceased, which are crucial components of epidemic compartmental models. The obtained results highlight the capability of the proposed method to provide insights into the spread of infectious diseases by offering reliable estimates of model parameters. This, in turn, supports better understanding and forecasting of disease dynamics. The methodology provides a significant contribution to the field by offering a new, efficient technique for parameter estimation in epidemiological models.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data Availability

The data that were used to generate our results are gathered from the website of the Turkish Ministry of Health and are publicly available. All data can be downloaded from the website at General Coronavirus Table for Türkiye.

Code Availability

The source code and data used to produce the results for SIRD compartmental model presented in this manuscript are available from Github repository: https://github.com/kgunel/Mathematical-Epidemiology

Materials availability

Not applicable.

Abbreviations

ELM :

Extreme Learning Machine

MSE :

Mean Squared Error

ODE :

Ordinary Differential Equation

PSO :

Particle Swarm Optimization

SDE :

Stochastic Differential Equation

SEIRD :

Susceptible-Exposed-Infected-Removed-Deceased

SI :

Structural Identifiability

SIAN :

Structural Identifiability ANalyser

SIR :

Susceptible-Infected-Removed

SIRD :

Susceptible-Infected-Removed-Deceased

References

  1. Brauer F, Castillo-Chavez C, Feng Z (2019) Mathematical Models in Epidemiology, 1st edn. Texts in Applied Mathematics, vol 69. Springer, New York, NY. https://doi.org/10.1007/978-1-4939-9828-9

  2. Bernouilli D (1760) Essai dúne nouvelle analyse de la mortalite causee par la petite verole, et des avantages de línoculation pour la prevenir. Histoire de lÁcad., Roy. Sci. (Paris) avec Mem, 1–45

  3. Avram F, Adenane R, Ketcheson DI (2021) A review of matrix SIR Arino epidemic models. Math 9(13). https://doi.org/10.3390/math9131513

  4. Duan W, Fan Z, Zhang P, Gang G, Qiu X (2015) Mathematical and computational approaches to epidemic modeling: a comprehensive review. Front Comput Sci 9:806–826. https://doi.org/10.1007/s11704-014-3369-2

    Article  MATH  Google Scholar 

  5. Harjule P, Tiwari V, Kumar A (2021) Mathematical models to predict covid-19 outbreak: An interim review. J Interdiscip Math 24(2):259–284. https://doi.org/10.1080/09720502.2020.1848316

    Article  MATH  Google Scholar 

  6. Lang JC (2022) Use of mathematical modelling to assess respiratory syncytial virus epidemiology and interventions: a literature review. J Math Biol 84(4). https://doi.org/10.1007/s00285-021-01706-y

  7. Trejos DY, Valverde JC, Venturino E (2022) Dynamics of infectious diseases: A review of the main biological aspects and their mathematical translation. Appl Math Nonlinear Sci 7(1):1–26. https://doi.org/10.2478/amns.2021.1.00012

    Article  MathSciNet  MATH  Google Scholar 

  8. Yang H, Lin X, Li J, Zhai Y, Wu J (2023) A review of mathematical models of covid-19 transmission. Contemprary Math 4(1):75–98. https://doi.org/10.37256/cm.4120232080

  9. Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366. https://doi.org/10.1016/0893-6080(89)90020-8

    Article  MATH  Google Scholar 

  10. Zhou DX (2020) Universality of deep convolutional neural networks. Appl Comput Harmonic Anal 48(2):787–794. https://doi.org/10.1016/j.acha.2019.06.004

    Article  MathSciNet  MATH  Google Scholar 

  11. Yin S, Wu J, Song P (2023) Optimal control by deep learning techniques and its applications on epidemic models. J Math Biol 86(3). https://doi.org/10.1007/s00285-023-01873-0

  12. Schiassi E, De Florio M, D’Ambrosio A, Mortari D, Furfaro R (2021) Physics-informed neural networks and functional interpolation for data-driven parameters discovery of epidemiological compartmental models. Math 9(17). https://doi.org/10.3390/math9172069

  13. Kharazmi E, Cai M, Zheng X, Zhang Z, Lin G, Karniadakis GE (2021) Identifiability and predictability of integer- and fractional-order epidemiological models using physics-informed neural networks. Nat Comput Sci 1:744–753. https://doi.org/10.1038/s43588-021-00158-0

    Article  MATH  Google Scholar 

  14. Kummer L, Sidak K (2022) Neural Network Augmented Compartmental Pandemic Models

  15. Berkhahn S, Ehrhardt M (2022) A physics-informed neural network to model covid-19 infection and hospitalization scenarios. Adv Contin Discret Models 2022(1). https://doi.org/10.1186/s13662-022-03733-5

  16. Zhu X, Fu B, Yang Y, Ma Y, Hao J, Chen S, Liu S, Li T, Liu S, Guo W, Liao Z (2019) Attention-based recurrent neural network for influenza epidemic prediction. BMC Bioinforma 20(18, SI). https://doi.org/10.1186/s12859-019-3131-8. IEEE. Workshop on Biological Ontologies and Knowledge Bases at IEEE BIBM Workshop, Madrid, SPAIN, DEC 03-06, 2018

  17. Rao VSH, Kumar MN (2010) Estimation of the parameters of an infectious disease model using neural networks. Nonlinear Anal-Real World Appl 11(3):1810–1818. https://doi.org/10.1016/j.nonrwa.2009.04.006

    Article  MathSciNet  MATH  Google Scholar 

  18. Shaier S, Raissi M, Seshaiye P (2022) Data-driven approaches for predicting spread of infectious diseases through dinns: Disease informed neural networks. Lett Biomath 9(1):71–105. https://doi.org/10.30707/LiB9.1.1681913305.249476

  19. Nguyen L, Raissi M, Seshaiyer P (2022) Modeling, analysis and physics informed neural network approaches for studying the dynamics of covid-19 involving human-human and human-pathogen interaction. Comput Math Biophys 10(1):1–17. https://doi.org/10.1515/cmb-2022-0001

    Article  MathSciNet  MATH  Google Scholar 

  20. Gibbons CL, Mangen MJJ, Plass D, Havelaar AH, Brooke RJ, Kramarz P, Peterson KL, Stuurman AL, Cassini A, Fevre EM, Kretzschmar MEE, BCo BCDE, (2014) Measuring underreporting and under-ascertainment in infectious disease datasets: a comparison of methods. BMC Public Health 14. https://doi.org/10.1186/1471-2458-14-147

  21. Muhr D, Tripathi S, Jodlbauer H (2021) An adaptive machine learning methodology to determine manufacturing process parameters for each part. Procedia Comput Sc 180:764–771. https://doi.org/10.1016/j.procs.2021.01.325. Proceedings of the 2nd International Conference on Industry 4.0 and Smart Manufacturing (ISM 2020)

  22. Anand GSZLea G (2021) Exploiting machine learning in multiscale modelling of materials. J Inst Eng Chem Eng (India) Ser D 104:867–877. https://doi.org/10.1007/s40033-022-00424-z

  23. Daneker ZZKGELL M (2023) In: Nguyen, LKe (ed) Systems Biology: Identifiability Analysis and Parameter Identification via Systems-Biology-Informed Neural Network, 1st edn. Methods in Molecular Biology, pp 87–105. Humana New York, NY. https://doi.org/10.1007/978-1-0716-3008-2

  24. Alhazmi K, Sarathy SM (2023) Nonintrusive parameter adaptation of chemical process models with reinforcement learning. J Process Control 123:87–95. https://doi.org/10.1016/j.jprocont.2023.02.001

    Article  MATH  Google Scholar 

  25. Ali M, Jiang R, Ma H, Pan H, Abbas K, Ashraf U, Ullah J (2021) Machine learning - a novel approach of well logs similarity based on synchronization measures to predict shear sonic logs. J Pet Sci Eng 203:108602. https://doi.org/10.1016/j.petrol.2021.108602

    Article  Google Scholar 

  26. Ali M, Zhu P, Jiang R, Huolin M, Ehsan M, Hussain W, Zhang H, Ashraf U, Ullaah J (2023) Reservoir characterization through comprehensive modeling of elastic logs prediction in heterogeneous rocks using unsupervised clustering and class-based ensemble machine learning. Appl Soft Comput 148:110843. https://doi.org/10.1016/j.asoc.2023.110843

    Article  Google Scholar 

  27. Ali ZPHMea M (2023) A novel machine learning approach for detecting outliers, rebuilding well logs, and enhancing reservoir characterization 32:1047–1066. https://doi.org/10.1007/s11053-023-10184-6

  28. Rajula H.S.R, Verlato G, Manchia M, Antonucci N, Fanos V (2020) Comparison of conventional statistical methods with machine learning in medicine: Diagnosis, drug development, and treatment. Med 56(9). https://doi.org/10.3390/medicina56090455

  29. Neha Maharao MW, Victor Antontsev Varshney J (2020) Entering the era of computationally driven drug development. Drug Metab Rev 52(2):283–298. https://doi.org/10.1080/03602532.2020.1726944. (PMID: 32083960)

    Article  Google Scholar 

  30. Keutzer YHFANJWSGMEGVGMGKSEMMMPSUSHOBOTUTC L () Machine learning and pharmacometrics for prediction of pharmacokinetic data: Differences, similarities and challenges illustrated with rifampicin 14(8):1530. https://doi.org/10.3390/pharmaceutics14081530

  31. Miao H, Xia X, Perelson AS, Wu H (2011) On identifiability of nonlinear ode models and applications in viral dynamics. SIAM Rev 53(1):3–39. https://doi.org/10.1137/090757009

    Article  MathSciNet  MATH  Google Scholar 

  32. Massonis G, Banga JR, Villaverde AF (2021) Structural identifiability and observability of compartmental models of the covid-19 pandemic. Ann Rev Control 51:441–459. https://doi.org/10.1016/j.arcontrol.2020.12.001

    Article  MathSciNet  MATH  Google Scholar 

  33. Andersson M, Streb M, Ko JY, Klass VL, Klett M, Ekstrom H, Johansson M, Lindbergh G (2022) Parametrization of physics-based battery models from input-output data: A review of methodology and current research. J Power Sources 521. https://doi.org/10.1016/j.jpowsour.2021.230859

  34. Medianu S, Lefevre L (2021) Structural identifiability of linear port hamiltonian systems. Syst Control Lett 151. https://doi.org/10.1016/j.sysconle.2021.104915

  35. Wang Y, Delle Monache ML, Work DB (2022) Identifiability of car-following dynamics. Phys D-Nonlinear Phenom 430. https://doi.org/10.1016/j.physd.2021.133090

  36. Villaverde AF, Barreiro A, Papachristodoulou A (2016) Structural identifiability of dynamic systems biology models. PLOS Comput Biol 12(10):1–22. https://doi.org/10.1371/journal.pcbi.1005153

    Article  MATH  Google Scholar 

  37. Thomaseth K, Saccomani MP (2018) Local identifiability analysis of nonlinear ode models: How to determine all candidate solutions. IFAC-PapersOnLine 51(2):529–534. https://doi.org/10.1016/j.ifacol.2018.03.089. 9th Vienna International Conference on Mathematical Modelling

  38. Rey Barreiro X, Villaverde AF (2023) Benchmarking tools for a priori identifiability analysis. Bioinform 39(2):065. https://doi.org/10.1093/bioinformatics/btad065

    Article  MATH  Google Scholar 

  39. Kreutz C (2018) An easy and efficient approach for testing identifiability. Bioinforma 34(11):1913–1921. https://doi.org/10.1093/bioinformatics/bty035

    Article  MATH  Google Scholar 

  40. Browning AP, B.K.B.R.E. Warne DJ, J. SM (2020) Identifiability analysis for stochastic differential equation models in systems biology 17. https://doi.org/10.1098/rsif.2020.0652

  41. Hong H, Ovchinnikov A, Pogudin G, Yap C (2019) SIAN: software for structural identifiability analysis of ODE models. Bioinforma 35(16):2873–2874. https://doi.org/10.1093/bioinformatics/bty1069

    Article  MATH  Google Scholar 

  42. Hong H, Ovchinnikov A, Pogudin G, Yap C (2020) Global identifiability of differential models. Commun Pur Appl Math 73(9):1831–1879. https://doi.org/10.1002/cpa.21921

    Article  MathSciNet  MATH  Google Scholar 

  43. Kennedy J, Eberhart RC (1995) Particle swarm optimization. In: 1995 IEEE International Conference on Neural Networks Proceedings, vols 1-6, pp. 1942–1948. https://doi.org/10.1109/icnn.1995.488968. IEEE, Neural Networks Council. 1995 IEEE International Conference on Neural Networks (ICNN 95), UNIV W AUSTRAIA, PERTH, AUSTRALIA, NOV 27-DEC 01, 1995

  44. Ahmad MJ (2021) On the Neural Network Solutions of Some Mathematical Epidemiological Models. https://doi.org/10.13140/RG.2.2.12427.46884

  45. Clement JC, Ponnusamy V, Sriharipriya KC, Nandakumar R (2022) A survey on mathematical, machine learning and deep learning models for covid-19 transmission and diagnosis. IEEE Rev Biomed Eng 15:325–340. https://doi.org/10.1109/RBME.2021.3069213

    Article  MATH  Google Scholar 

Download references

Acknowledgements

We thank the anonymous referees for their constructive comments, which helped us to improve the manuscript. This study is the result of the thesis research conducted by Mr. Ahmad under the supervision of Dr. Günel.

Funding

K. Günel expresses gratitude for the assistance provided by the Aydın Adnan Menderes University Scientific Research Projects (BAP) through Grant No. ADU-FEF-22026. The authors extend their appreciation to the BAP commission and staff for their valuable support.

Author information

Authors and Affiliations

Authors

Contributions

The data was collected and verified by M.J. Ahmad. The proposed idea was conceived by K. Günel, who also supervised the project. Together, M.J. Ahmad and K. Günel developed the theory and implemented the corresponding codes. M.J. Ahmad conducted the numerical simulations. Both authors were involved in analyzing the experimental results and writing this manuscript.

Corresponding author

Correspondence to Korhan Günel.

Ethics declarations

Conflict of interest

The author declares that I have no conflict of interest.

Ethics approval and consent to participate

The conducted research is not related to either human or animal use.

Consent for publication

Not applicable.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ahmad, M.J., Günel, K. Can neural networks estimate parameters in epidemiology models using real observed data?. Appl Intell 55, 133 (2025). https://doi.org/10.1007/s10489-024-06012-w

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10489-024-06012-w

Keywords