Advancing influenza forecasting models by integrating key epidemiological features
Abstract
Accurate, real-time forecasting of influenza activity is critical for guiding public health responses and operational planning. Despite the development of diverse statistical, mechanistic, machine learning, and ensemble approaches, seasonal influenza epidemics remain challenging to predict due to their complex dynamics. We developed an ensemble model to forecast influenza-like-illness activity in emergency departments in metropolitan France at national and regional scales, addressing three key challenges to improve forecast accuracy: i) incorporating a "holiday effect" into mechanistic models to account for the reduced transmission during school holidays, ii) refining filtering methods to leverage similarities in epidemic onset timing across seasons, and iii) developing (sub)type-specific model variants to capture the co-circulation of multiple influenza (sub)types. In total, we integrated 65 statistical and mechanistic models into 140 ensemble configurations, exploring various ensemble-building strategies. Models were assessed retrospectively through cross-validation across eight seasons, and the best-performing model was further tested on four out-of-sample seasons. Over the validation period, incorporating a holiday effect and accounting for similarities in epidemic onset timing in mechanistic models improved forecast score by up to 13% and 10% respectively. Although ensemble models were not always the top performers, they provided the most consistent accuracy across regions and seasons. The (sub)type-specific ensemble showed no consistent advantage over the non-stratified model in test seasons. The best-performing ensemble model was implemented in real time in 2025-2026 to support public health decision-making, enabling prospective evaluation. It accurately anticipated epidemic dynamics and peak timing at the national level and across most regions, demonstrating strong predictive skills.
Related
- Advancing herbicide safeners: Integrating structure-guided design, pathway mechanism elucidation, and smart delivery
- A data-driven approach to hepatitis C forecasting using machine learning and epidemiological models
- A multi-scale immuno-epidemiological behavioral model for influenza-like illness: connecting scales through symptom scores
- Epidemiological characterization of avian influenza virus circulation in pigeons and quail across different production systems in Chattogram, Bangladesh
- A Multimodal Machine Learning Framework Integrating Genomic, Epidemiological, Environmental, and Clinical Imaging Data for Accelerated Measles Detection and Transmission Inference
BibTeX
@misc{paireau2026advancing,
title = {{Advancing influenza forecasting models by integrating key epidemiological features}},
author = {Juliette Paireau and Sibylle Bernard-Stoecklin and Isabelle Pontais and Vincent Enouf and Guillaume Spaccaferri and Danielle Perez-Bercoff and Marie-Anne Rameix-Welti and Harold Noël and Bruno Coignard and Simon Cauchemez},
howpublished = {HAL},
year = {2026},
month = oct,
url = {https://pasteur.hal.science/pasteur-05799592v1},
note = {CC BY-NC 4.0},
}
RIS
TY - UNPB
TI - Advancing influenza forecasting models by integrating key epidemiological features
AU - Juliette Paireau
AU - Sibylle Bernard-Stoecklin
AU - Isabelle Pontais
AU - Vincent Enouf
AU - Guillaume Spaccaferri
AU - Danielle Perez-Bercoff
AU - Marie-Anne Rameix-Welti
AU - Harold Noël
AU - Bruno Coignard
AU - Simon Cauchemez
PY - 2026
DA - 2026/10/14
PB - HAL
UR - https://pasteur.hal.science/pasteur-05799592v1
AB - Accurate, real-time forecasting of influenza activity is critical for guiding public health responses and operational planning. Despite the development of diverse statistical, mechanistic, machine learning, and ensemble approaches, seasonal influenza epidemics remain challenging to predict due to their complex dynamics. We developed an ensemble model to forecast influenza-like-illness activity in emergency departments in metropolitan France at national and regional scales, addressing three key challenges to improve forecast accuracy: i) incorporating a "holiday effect" into mechanistic models to account for the reduced transmission during school holidays, ii) refining filtering methods to leverage similarities in epidemic onset timing across seasons, and iii) developing (sub)type-specific model variants to capture the co-circulation of multiple influenza (sub)types. In total, we integrated 65 statistical and mechanistic models into 140 ensemble configurations, exploring various ensemble-building strategies. Models were assessed retrospectively through cross-validation across eight seasons, and the best-performing model was further tested on four out-of-sample seasons. Over the validation period, incorporating a holiday effect and accounting for similarities in epidemic onset timing in mechanistic models improved forecast score by up to 13% and 10% respectively. Although ensemble models were not always the top performers, they provided the most consistent accuracy across regions and seasons. The (sub)type-specific ensemble showed no consistent advantage over the non-stratified model in test seasons. The best-performing ensemble model was implemented in real time in 2025-2026 to support public health decision-making, enabling prospective evaluation. It accurately anticipated epidemic dynamics and peak timing at the national level and across most regions, demonstrating strong predictive skills.
ER -