A novel graph neural network based approach for influenza-like illness nowcasting: exploring the interplay of temporal, geographical, and functional spatial features
Abstract Background Accurate and timely monitoring of influenza prevalence is essential for effective healthcare interventions. This study proposes a graph neural network (GNN)-based method to address the issue of cross-regional connectivity in predicting influenza outbreaks, aiming to achieve real-...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-02-01
|
| Series: | BMC Public Health |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12889-025-21618-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571238002720768 |
|---|---|
| author | Jiajia Luo Xuan Wang Xiaomao Fan Yuxin He Xiangjun Du Yao-Qing Chen Yang Zhao |
| author_facet | Jiajia Luo Xuan Wang Xiaomao Fan Yuxin He Xiangjun Du Yao-Qing Chen Yang Zhao |
| author_sort | Jiajia Luo |
| collection | DOAJ |
| description | Abstract Background Accurate and timely monitoring of influenza prevalence is essential for effective healthcare interventions. This study proposes a graph neural network (GNN)-based method to address the issue of cross-regional connectivity in predicting influenza outbreaks, aiming to achieve real-time and accurate influenza prediction. Methods We proposed a GNN-based approach with dual topology processing, capturing both geographical and socio-economic associations among counties/cities. The model inputs consist of weekly matrices of influenza-like illness (ILI) rates at city level, along with geographical topology and functional topology. The model construction involves temporal feature extraction through 1-dimensional gated causal convolution, spatial feature embedding through graph convolution, and additional adjustments to enhance spatiotemporal interaction exploration. Evaluation metrics include four commonly used measures: root mean square error (RMSE), mean absolute percentage error (MAPE), mean absolute error (MAE), and Pearson correlation (Corr). Results Our approach for predicting influenza outbreaks achieves competitive performance on real-world datasets (Corr = 0.8202; RMSE = 0.0017; MAE = 0.0013; MAPE = 0.0966), surpassing established baselines. Notably, our approach exhibits excellent capability in accurately and timely capturing short-term influenza outbreaks during the flu season, outperforming competitors across all evaluation metrics. Conclusion The incorporation of dual topology processing and the subsequent fusion mechanism allows the model to explore in-depth spatiotemporal feature interactions. Demonstrating superior performance, our approach shows great potential in early detection of flu trends for facilitating public health decisions and resource optimization. |
| format | Article |
| id | doaj-art-620559652a0043d7add4d03577fb8299 |
| institution | Kabale University |
| issn | 1471-2458 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Public Health |
| spelling | doaj-art-620559652a0043d7add4d03577fb82992025-02-02T12:46:25ZengBMCBMC Public Health1471-24582025-02-0125111610.1186/s12889-025-21618-6A novel graph neural network based approach for influenza-like illness nowcasting: exploring the interplay of temporal, geographical, and functional spatial featuresJiajia Luo0Xuan Wang1Xiaomao Fan2Yuxin He3Xiangjun Du4Yao-Qing Chen5Yang Zhao6School of Public Health (Shenzhen), Sun Yat-sen UniversitySchool of Public Health (Shenzhen), Sun Yat-sen UniversityCollege of Big Data and Internet, Shenzhen Technology UniversityCollege of Urban Transportation and Logistics, Shenzhen Technology UniversitySchool of Public Health (Shenzhen), Sun Yat-sen UniversitySchool of Public Health (Shenzhen), Sun Yat-sen UniversitySchool of Public Health (Shenzhen), Sun Yat-sen UniversityAbstract Background Accurate and timely monitoring of influenza prevalence is essential for effective healthcare interventions. This study proposes a graph neural network (GNN)-based method to address the issue of cross-regional connectivity in predicting influenza outbreaks, aiming to achieve real-time and accurate influenza prediction. Methods We proposed a GNN-based approach with dual topology processing, capturing both geographical and socio-economic associations among counties/cities. The model inputs consist of weekly matrices of influenza-like illness (ILI) rates at city level, along with geographical topology and functional topology. The model construction involves temporal feature extraction through 1-dimensional gated causal convolution, spatial feature embedding through graph convolution, and additional adjustments to enhance spatiotemporal interaction exploration. Evaluation metrics include four commonly used measures: root mean square error (RMSE), mean absolute percentage error (MAPE), mean absolute error (MAE), and Pearson correlation (Corr). Results Our approach for predicting influenza outbreaks achieves competitive performance on real-world datasets (Corr = 0.8202; RMSE = 0.0017; MAE = 0.0013; MAPE = 0.0966), surpassing established baselines. Notably, our approach exhibits excellent capability in accurately and timely capturing short-term influenza outbreaks during the flu season, outperforming competitors across all evaluation metrics. Conclusion The incorporation of dual topology processing and the subsequent fusion mechanism allows the model to explore in-depth spatiotemporal feature interactions. Demonstrating superior performance, our approach shows great potential in early detection of flu trends for facilitating public health decisions and resource optimization.https://doi.org/10.1186/s12889-025-21618-6Influenza predictionSpatiotemporal interactionGraph neural network (GNN)Functional topologySocio-economic association |
| spellingShingle | Jiajia Luo Xuan Wang Xiaomao Fan Yuxin He Xiangjun Du Yao-Qing Chen Yang Zhao A novel graph neural network based approach for influenza-like illness nowcasting: exploring the interplay of temporal, geographical, and functional spatial features BMC Public Health Influenza prediction Spatiotemporal interaction Graph neural network (GNN) Functional topology Socio-economic association |
| title | A novel graph neural network based approach for influenza-like illness nowcasting: exploring the interplay of temporal, geographical, and functional spatial features |
| title_full | A novel graph neural network based approach for influenza-like illness nowcasting: exploring the interplay of temporal, geographical, and functional spatial features |
| title_fullStr | A novel graph neural network based approach for influenza-like illness nowcasting: exploring the interplay of temporal, geographical, and functional spatial features |
| title_full_unstemmed | A novel graph neural network based approach for influenza-like illness nowcasting: exploring the interplay of temporal, geographical, and functional spatial features |
| title_short | A novel graph neural network based approach for influenza-like illness nowcasting: exploring the interplay of temporal, geographical, and functional spatial features |
| title_sort | novel graph neural network based approach for influenza like illness nowcasting exploring the interplay of temporal geographical and functional spatial features |
| topic | Influenza prediction Spatiotemporal interaction Graph neural network (GNN) Functional topology Socio-economic association |
| url | https://doi.org/10.1186/s12889-025-21618-6 |
| work_keys_str_mv | AT jiajialuo anovelgraphneuralnetworkbasedapproachforinfluenzalikeillnessnowcastingexploringtheinterplayoftemporalgeographicalandfunctionalspatialfeatures AT xuanwang anovelgraphneuralnetworkbasedapproachforinfluenzalikeillnessnowcastingexploringtheinterplayoftemporalgeographicalandfunctionalspatialfeatures AT xiaomaofan anovelgraphneuralnetworkbasedapproachforinfluenzalikeillnessnowcastingexploringtheinterplayoftemporalgeographicalandfunctionalspatialfeatures AT yuxinhe anovelgraphneuralnetworkbasedapproachforinfluenzalikeillnessnowcastingexploringtheinterplayoftemporalgeographicalandfunctionalspatialfeatures AT xiangjundu anovelgraphneuralnetworkbasedapproachforinfluenzalikeillnessnowcastingexploringtheinterplayoftemporalgeographicalandfunctionalspatialfeatures AT yaoqingchen anovelgraphneuralnetworkbasedapproachforinfluenzalikeillnessnowcastingexploringtheinterplayoftemporalgeographicalandfunctionalspatialfeatures AT yangzhao anovelgraphneuralnetworkbasedapproachforinfluenzalikeillnessnowcastingexploringtheinterplayoftemporalgeographicalandfunctionalspatialfeatures AT jiajialuo novelgraphneuralnetworkbasedapproachforinfluenzalikeillnessnowcastingexploringtheinterplayoftemporalgeographicalandfunctionalspatialfeatures AT xuanwang novelgraphneuralnetworkbasedapproachforinfluenzalikeillnessnowcastingexploringtheinterplayoftemporalgeographicalandfunctionalspatialfeatures AT xiaomaofan novelgraphneuralnetworkbasedapproachforinfluenzalikeillnessnowcastingexploringtheinterplayoftemporalgeographicalandfunctionalspatialfeatures AT yuxinhe novelgraphneuralnetworkbasedapproachforinfluenzalikeillnessnowcastingexploringtheinterplayoftemporalgeographicalandfunctionalspatialfeatures AT xiangjundu novelgraphneuralnetworkbasedapproachforinfluenzalikeillnessnowcastingexploringtheinterplayoftemporalgeographicalandfunctionalspatialfeatures AT yaoqingchen novelgraphneuralnetworkbasedapproachforinfluenzalikeillnessnowcastingexploringtheinterplayoftemporalgeographicalandfunctionalspatialfeatures AT yangzhao novelgraphneuralnetworkbasedapproachforinfluenzalikeillnessnowcastingexploringtheinterplayoftemporalgeographicalandfunctionalspatialfeatures |