Dynamic feature selection improves influenza forecasting accuracy and generalization across countries

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.

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.

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.

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.

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.