An ensemble model based on early predictors to forecast COVID-19 healthcare demand in France - Faculté de droit - unités de recherche Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2021

An ensemble model based on early predictors to forecast COVID-19 healthcare demand in France

Marc Lavielle

Résumé

Short-term forecasting of the COVID-19 pandemic is required to facilitate the planning of COVID-19 healthcare demand in hospitals. Here, we evaluate the performance of 12 individual models and 22 predictors to anticipate French COVID-19 related healthcare needs from September 7th 2020 to January 7th 2021, and build an ensemble model that outperforms all individual models. We find that inclusion of early predictors (epidemiological, mobility and meteorological predictors) can halve the relative error for 14-day ahead forecasts, with epidemiological and mobility predictors contributing the most to the improvement. Our approach facilitates the comparison and benchmarking of competing models through their integration in a coherent analytical framework, ensuring avenues for future improvements can be identified.
Fichier principal
Vignette du fichier
Paireau_et_al_Ensemble_model_20210222[1].pdf (2.27 Mo) Télécharger le fichier

Dates et versions

pasteur-03690824 , version 1 (22-02-2021)
pasteur-03690824 , version 2 (10-11-2021)
pasteur-03690824 , version 3 (08-06-2022)

Licence

Paternité - Pas d'utilisation commerciale - Pas de modification

Identifiants

  • HAL Id : pasteur-03690824 , version 1

Citer

Juliette Paireau, Alessio Andronico, Nathanaël Hozé, Maylis Layan, Pascal Crepey, et al.. An ensemble model based on early predictors to forecast COVID-19 healthcare demand in France. 2021. ⟨pasteur-03690824v1⟩

Collections

INSERM
3890 Consultations
1713 Téléchargements

Partager

Gmail Facebook X LinkedIn More