Tweet
J Adv Res
. 2026 Apr 4:S2090-1232(26)00288-2.
doi: 10.1016/j.jare.2026.04.009. Online ahead of print.
Dynamic feature selection improves influenza forecasting accuracy and generalization across countries
Jingyi Liang 1 , Zhiqi Zeng 2 , Kai Liao 3 , Min Liao 4 , Zhonghao Fang 1 , Lesi Kong 5 , Jianlin Feng 1 , Na Yu 4 , Zhengshi Lin 6 , Chitin Hon 7 , Arlindo Oliveira 8 , Zifeng Yang 9
Affiliations
Introduction: The differentiation in epidemic patterns and multiple influencing factors pose significant challenges to influenza forecasting, highlighting the need for novel methods to improve predictive accuracy and cross-regional generalizability.
Objectives: This study aims to develop an adaptive feature selection model named AdaFluDR to address the time-varying nature of influenza transmission drivers across different periods and regions.
Methods: AdaFluDR integrates the SpaceTime and Crossformer models and utilizes a correlation-driven mechanism. This mechanism constructs a comprehensive score by integrating the temporal, frequency, and time domain information of features, and dynamically adjusts feature processing pathways based on this score. Subsequently, a multilayer perceptron (MLP) will be employed to model the nonlinear mapping relationship between the integrated features and the target variable for prediction generation.
Results: The AdaFluDR model outperforms traditional methods and other machine learning approaches, demonstrating robust predictive performance across multiple forecasting horizons (1-4 weeks), and strong generalization ability across the United States, Canada, and Portugal.
Conclusion: Our study provides a novel and practical framework for forecasting influenza activity with reliable accuracy and cross-national applicability, providing a valuable tool for improving global epidemic preparedness and response strategies.
Keywords: Adaptive decisionmodel; Dynamic featureextraction; Full-period modeling; Influenza forecasting; Multi-region and multi-periodforecasting.
. 2026 Apr 4:S2090-1232(26)00288-2.
doi: 10.1016/j.jare.2026.04.009. Online ahead of print.
Dynamic feature selection improves influenza forecasting accuracy and generalization across countries
Jingyi Liang 1 , Zhiqi Zeng 2 , Kai Liao 3 , Min Liao 4 , Zhonghao Fang 1 , Lesi Kong 5 , Jianlin Feng 1 , Na Yu 4 , Zhengshi Lin 6 , Chitin Hon 7 , Arlindo Oliveira 8 , Zifeng Yang 9
Affiliations
- PMID: 41942047
- DOI: 10.1016/j.jare.2026.04.009
Introduction: The differentiation in epidemic patterns and multiple influencing factors pose significant challenges to influenza forecasting, highlighting the need for novel methods to improve predictive accuracy and cross-regional generalizability.
Objectives: This study aims to develop an adaptive feature selection model named AdaFluDR to address the time-varying nature of influenza transmission drivers across different periods and regions.
Methods: AdaFluDR integrates the SpaceTime and Crossformer models and utilizes a correlation-driven mechanism. This mechanism constructs a comprehensive score by integrating the temporal, frequency, and time domain information of features, and dynamically adjusts feature processing pathways based on this score. Subsequently, a multilayer perceptron (MLP) will be employed to model the nonlinear mapping relationship between the integrated features and the target variable for prediction generation.
Results: The AdaFluDR model outperforms traditional methods and other machine learning approaches, demonstrating robust predictive performance across multiple forecasting horizons (1-4 weeks), and strong generalization ability across the United States, Canada, and Portugal.
Conclusion: Our study provides a novel and practical framework for forecasting influenza activity with reliable accuracy and cross-national applicability, providing a valuable tool for improving global epidemic preparedness and response strategies.
Keywords: Adaptive decisionmodel; Dynamic featureextraction; Full-period modeling; Influenza forecasting; Multi-region and multi-periodforecasting.