Improving outbreak forecasts through model augmentation
Proceedings of the National Academy of Sciences · 2025
DOI: 10.1073/pnas.2508575122 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, 2025. Verfasst von Graham C Gibson und 6 weiteren Autor:innen. Beteiligte Einrichtung: Computing and Artificial Intelligence Division, Los Alamos National Laboratory, Los Alamos, NM 87544. Hauptthemen laut MEDLINE: Disease Outbreaks, COVID-19, Influenza, Human, Epidemiological Models. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: CDC HHS, HHS | Centers for Disease Control and Prevention (CDC), Council of State and Territorial Epidemiologists.
Abstract (Originalsprache)
Accurate forecasts of disease outbreaks are critical for effective public health responses, management of healthcare surge capacity, and communication of public risk. There are a growing number of powerful forecasting methods that fall into two broad categories-empirical models that extrapolate from historical data, and mechanistic models based on fixed epidemiological assumptions. However, these methods often underperform precisely when reliable predictions are most urgently needed-during periods of rapid epidemic escalation. Here, we introduce epimodulation, a hybrid approach that integrates fundamental epidemiological principles into existing predictive models to enhance forecasting accuracy, especially around epidemic peaks. When applied to empirical and machine learning forecasting methods (Autoregressive Integrated Moving Average, Holt-Winters, gradient-boosting machines, Prophet, and spline models), epimodulation improved overall prediction accuracy by an average of 12.3% (range: 8.5 to 18.7%) for COVID-19 hospital admissions and by 32.9% (range: 24.2 to 43.7%) for influenza hospital admissions; accuracy during epidemic peaks improved even further, by an average of 27.9% and 43.8%, respectively. Epimodulation also substantially enhanced the performance of complex forecasting methods, including the COVID-19 Forecast Hub ensemble model, demonstrating its broad utility in improving forecast reliability at critical moments in disease outbreaks.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Computing and Artificial Intelligence Division, Los Alamos National Laboratory, Los Alamos, NM 87544.
- Department of Epidemiology and Biostatistics, University of Georgia, Athens, GA 30602.
- Institute of Bioinformatics, University of Georgia, Athens, GA 30602.
- Integrative Biology, University of Texas at Austin, Austin, TX 78712.
- Santa Fe Institute, Santa Fe, NM 87501.
- Beyond Center for Fundamental Concepts in Science, Arizona State University, Tempe, AZ 85287.
ORCID-Profile: Spencer J Fox, Emily Javan, Susan E Ptak, Oluwasegun M Ibrahim, Michael Lachmann, Lauren Ancel Meyers
Förderung
- CDC HHS
- HHS | Centers for Disease Control and Prevention (CDC)
- Council of State and Territorial Epidemiologists
Zitieren
APA
Gibson, G. C., Fox, S. J., Javan, E., Ptak, S. E., Ibrahim, O. M., Lachmann, M., & Meyers, L. A. (2025). Improving outbreak forecasts through model augmentation. Proceedings of the National Academy of Sciences. https://doi.org/10.1073/pnas.2508575122
Vancouver
Gibson GC, Fox SJ, Javan E, Ptak SE, Ibrahim OM, Lachmann M, et al. Improving outbreak forecasts through model augmentation. Proceedings of the National Academy of Sciences. 2025. doi:10.1073/pnas.2508575122
BibTeX
@article{Gibson2025,
author = {Gibson, Graham C and Fox, Spencer J and Javan, Emily and Ptak, Susan E and Ibrahim, Oluwasegun M and Lachmann, Michael and Meyers, Lauren Ancel},
title = {Improving outbreak forecasts through model augmentation},
journal = {Proceedings of the National Academy of Sciences},
year = {2025},
doi = {10.1073/pnas.2508575122}
}
EUVIMED