EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A dynamic ensemble model for short-term forecasting in pandemic situations

Jonas Botz iD, Diego Valderrama iD, Jannis Guski iD, Holger Fröhlich iD

PLOS Global Public Health · 22.08.2024 · 4 (8) · e0003058

DOI: 10.1371/journal.pgph.0003058 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Global Public Health, online erschienen am 22.08.2024. Verfasst von Jonas Botz und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, Germany. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: French State and the German Federal Ministry for Economic Affairs and Climate Action, French Ministry of Economy and Finance in the context of the France 2030 initiative, Franco-German call on Artificial Intelligence Technologies.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

During the COVID-19 pandemic, many hospitals reached their capacity limits and could no longer guarantee treatment of all patients. At the same time, governments endeavored to take sensible measures to stop the spread of the virus while at the same time trying to keep the economy afloat. Many models extrapolating confirmed cases and hospitalization rate over short periods of time have been proposed, including several ones coming from the field of machine learning. However, the highly dynamic nature of the pandemic with rapidly introduced interventions and new circulating variants imposed non-trivial challenges for the generalizability of such models. In the context of this paper, we propose the use of ensemble models, which are allowed to change in their composition or weighting of base models over time and could thus better adapt to highly dynamic pandemic or epidemic situations. In that regard, we also explored the use of secondary metadata—Google searches—to inform the ensemble model. We tested our approach using surveillance data from COVID-19, Influenza, and hospital syndromic surveillance of severe acute respiratory infections (SARI). In general, we found ensembles to be more robust than the individual models. Altogether we see our work as a contribution to enhance the preparedness for future pandemic situations.

Autor:innen und Institutionen

  • Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, Germany.
  • Bonn-Aachen International Center for IT, University of Bonn, Bonn, Germany.

ORCID-Profile: Jonas Botz, Diego Valderrama, Jannis Guski, Holger Fröhlich

Förderung

  • French State and the German Federal Ministry for Economic Affairs and Climate Action
  • French Ministry of Economy and Finance in the context of the France 2030 initiative
  • Franco-German call on Artificial Intelligence Technologies
  • German Federal Ministry for Economic Affairs and Climate Action

Zitieren

APA

Botz, J., Valderrama, D., Guski, J., & Fröhlich, H. (2024). A dynamic ensemble model for short-term forecasting in pandemic situations. PLOS Global Public Health, 4(8), e0003058. https://doi.org/10.1371/journal.pgph.0003058

Vancouver

Botz J, Valderrama D, Guski J, Fröhlich H. A dynamic ensemble model for short-term forecasting in pandemic situations. PLOS Global Public Health. 2024;4(8):e0003058. doi:10.1371/journal.pgph.0003058

BibTeX
@article{Botz2024,
  author = {Botz, Jonas and Valderrama, Diego and Guski, Jannis and Fröhlich, Holger},
  title = {A dynamic ensemble model for short-term forecasting in pandemic situations},
  journal = {PLOS Global Public Health},
  year = {2024},
  volume = {4},
  number = {8},
  pages = {e0003058},
  doi = {10.1371/journal.pgph.0003058}
}
Kostenlos starten →