EUVIMEDEUVIMED entdecken
Open Access

Physics-informed deep learning for infectious disease forecasting

Ying Qian iD, Kui Zhang iD, Eric Marty, Avranil Basu, Eamon B O'Dea iD, Xianqiao Wang iD, Spencer J Fox iD, Pejman Rohani iD, John M Drake iD, He Li

Journal of The Royal Society Interface · 2025-11 · 22 (232)

DOI: 10.1098/rsif.2025.0379 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of The Royal Society Interface, online erschienen am 26.11.2025. Verfasst von Ying Qian und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Chemical, Materials, and Biomedical Engineering, University of Georgia, Athens, GA, USA. Hauptthemen laut MEDLINE: Deep Learning, COVID-19, Neural Networks, Computer, SARS-CoV-2. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 80 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIH, NSF SCH.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate forecasting of contagious illnesses has become increasingly important to public health policymaking and better prediction could prevent the loss of millions of lives. To better prepare for future pandemics, it is essential to improve forecasting methods and capabilities. In this work, we implement physics-informed neural networks (PINNs), a popular tool in the area of scientific machine learning, to perform infectious disease forecasting. The used PINNs model incorporates dynamical systems representations of disease transmission into the loss function, thereby assimilating epidemiological theory and data using neural networks. Our approach is designed to prevent model overfitting, which often occurs when training deep-learning models with observation data alone. In addition, we use an additional sub-network to account for mobility, cumulative vaccine doses and other covariates that influence the transmission rate, a key parameter in the compartmental model. To demonstrate the capability of the proposed model, we examine the performance of the model using state-level COVID-19 data in California. Our simulation results show that predictions of the PINNs model on the number of cases, deaths and hospitalizations are consistent with existing benchmarks. In particular, the PINNs model outperforms naive baseline forecasts and various sequence deep-learning models, such as recurrent neural networks, long short-term memory networks, gated recurrent units and transformer models. We also show that the performance of the PINNs model is comparable with that of a sophisticated Gaussian infection state forecasting model that combines the compartmental model, a data observation model and a regression model for inferring parameters in the compartmental model. Nonetheless, the PINNs model offers a simpler structure and is easier to implement. In summary, we perform a systematic study of the predictive capability of the PINNs model in forecasting the dynamics of infectious diseases and our results showcase the potential of the proposed model as an efficient computational tool to enhance the current capacity of infectious disease forecasting.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningCOVID-19Neural Networks, ComputerSARS-CoV-2Communicable DiseasesHumansForecastingCalifornia

Stichwörter der Autor:innen

epidemiological modellinginfectious disease forecastingmachine learningphysics-informed neural networks (PINNs)

Autor:innen und Institutionen

  • School of Chemical, Materials, and Biomedical Engineering, University of Georgia, Athens, GA, USA.
  • Odum School of Ecology and Center for the Ecology of Infectious Diseases, University of Georgia, Athens, GA, USA.
  • School of Environmental, Civil Agricultural and Mechanical Engineering, College of Engineering, University of Georgia, Athens, GA, USA.
  • Department of Epidemiology and Biostatistics, University of Georgia, Athens, GA, USA.
  • Department of Infectious Diseases, College of Veterinary Medicine, University of Georgia, Athens, GA, USA.
  • Center for Influenza Disease and Emergence Research, University of Georgia, Athens, GA, USA.

ORCID-Profile: Ying Qian, Kui Zhang, Eamon B O'Dea, Xianqiao Wang, Spencer J Fox, Pejman Rohani, John M Drake

Förderung

  • NIH
  • NSF SCH

Zitieren

APA

Qian, Y., Zhang, K., Marty, E., Basu, A., O'Dea, E. B., Wang, X., Fox, S. J., Rohani, P., Drake, J. M., & Li, H. (2025). Physics-informed deep learning for infectious disease forecasting. Journal of The Royal Society Interface, 22(232). https://doi.org/10.1098/rsif.2025.0379

Vancouver

Qian Y, Zhang K, Marty E, Basu A, O'Dea EB, Wang X, et al. Physics-informed deep learning for infectious disease forecasting. Journal of The Royal Society Interface. 2025;22(232). doi:10.1098/rsif.2025.0379

BibTeX
@article{Qian2025,
  author = {Qian, Ying and Zhang, Kui and Marty, Eric and Basu, Avranil and O'Dea, Eamon B and Wang, Xianqiao and Fox, Spencer J and Rohani, Pejman and Drake, John M and Li, He},
  title = {Physics-informed deep learning for infectious disease forecasting},
  journal = {Journal of The Royal Society Interface},
  year = {2025},
  volume = {22},
  number = {232},
  doi = {10.1098/rsif.2025.0379}
}
Kostenlos starten →