Annual global dengue dynamics are related to multi-source factors revealed by a machine learning prediction analysis.
<h4>Background</h4>Dengue is a significant global health threat, transmitted by mosquitoes and influenced by multiple factors. A comprehensive analysis of the impact of these factors on dengue at a global scale is helpful for better understanding and effective control of dengue epidemics...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-06-01
|
| Series: | PLoS Neglected Tropical Diseases |
| Online Access: | https://doi.org/10.1371/journal.pntd.0013232 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850116728935153664 |
|---|---|
| author | Haoyu Long Yilin Chen Jingru Feng Jian Chen Xue Zhang Wenjie Han Min Kang Xiangjun Du |
| author_facet | Haoyu Long Yilin Chen Jingru Feng Jian Chen Xue Zhang Wenjie Han Min Kang Xiangjun Du |
| author_sort | Haoyu Long |
| collection | DOAJ |
| description | <h4>Background</h4>Dengue is a significant global health threat, transmitted by mosquitoes and influenced by multiple factors. A comprehensive analysis of the impact of these factors on dengue at a global scale is helpful for better understanding and effective control of dengue epidemics.<h4>Methods</h4>This study employed machine learning techniques to develop a global predictive model for forecasting annual dengue cases. A wide range of multi-source features, including historical cases, population, climate, air travel, forest, anemia, vector, serotype and socioeconomic features, were comprehensively considered. The impact of these features was revealed using the SHAP (Shapley Additive Explanations) framework.<h4>Results</h4>The global multi-variable model outperformed the baseline model, indicating the importance of considering multiple factors. Among the multi-source features, historical cases contribute the most, at about 73.63%. Risk factors associated to dengue were identified, including the occurrence of Aedes mosquitoes, changes in the predominant serotype, and the prevalence of anemia. Feature contribution pattern was different between hyperendemic and non-hyperendemic regions. In hyperendemic regions, historical cases and population were found to contribute more significantly, emphasizing the role of population immunity in dengue dynamics.<h4>Conclusions</h4>Dengue is influenced by a wide range of multi-source factors, and prevention and control measures should be specifically designed while taking into account regional differences for effective control of dengue. |
| format | Article |
| id | doaj-art-d7a565c332944f9c99093fe2ed6bb8fc |
| institution | OA Journals |
| issn | 1935-2727 1935-2735 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS Neglected Tropical Diseases |
| spelling | doaj-art-d7a565c332944f9c99093fe2ed6bb8fc2025-08-20T02:36:15ZengPublic Library of Science (PLoS)PLoS Neglected Tropical Diseases1935-27271935-27352025-06-01196e001323210.1371/journal.pntd.0013232Annual global dengue dynamics are related to multi-source factors revealed by a machine learning prediction analysis.Haoyu LongYilin ChenJingru FengJian ChenXue ZhangWenjie HanMin KangXiangjun Du<h4>Background</h4>Dengue is a significant global health threat, transmitted by mosquitoes and influenced by multiple factors. A comprehensive analysis of the impact of these factors on dengue at a global scale is helpful for better understanding and effective control of dengue epidemics.<h4>Methods</h4>This study employed machine learning techniques to develop a global predictive model for forecasting annual dengue cases. A wide range of multi-source features, including historical cases, population, climate, air travel, forest, anemia, vector, serotype and socioeconomic features, were comprehensively considered. The impact of these features was revealed using the SHAP (Shapley Additive Explanations) framework.<h4>Results</h4>The global multi-variable model outperformed the baseline model, indicating the importance of considering multiple factors. Among the multi-source features, historical cases contribute the most, at about 73.63%. Risk factors associated to dengue were identified, including the occurrence of Aedes mosquitoes, changes in the predominant serotype, and the prevalence of anemia. Feature contribution pattern was different between hyperendemic and non-hyperendemic regions. In hyperendemic regions, historical cases and population were found to contribute more significantly, emphasizing the role of population immunity in dengue dynamics.<h4>Conclusions</h4>Dengue is influenced by a wide range of multi-source factors, and prevention and control measures should be specifically designed while taking into account regional differences for effective control of dengue.https://doi.org/10.1371/journal.pntd.0013232 |
| spellingShingle | Haoyu Long Yilin Chen Jingru Feng Jian Chen Xue Zhang Wenjie Han Min Kang Xiangjun Du Annual global dengue dynamics are related to multi-source factors revealed by a machine learning prediction analysis. PLoS Neglected Tropical Diseases |
| title | Annual global dengue dynamics are related to multi-source factors revealed by a machine learning prediction analysis. |
| title_full | Annual global dengue dynamics are related to multi-source factors revealed by a machine learning prediction analysis. |
| title_fullStr | Annual global dengue dynamics are related to multi-source factors revealed by a machine learning prediction analysis. |
| title_full_unstemmed | Annual global dengue dynamics are related to multi-source factors revealed by a machine learning prediction analysis. |
| title_short | Annual global dengue dynamics are related to multi-source factors revealed by a machine learning prediction analysis. |
| title_sort | annual global dengue dynamics are related to multi source factors revealed by a machine learning prediction analysis |
| url | https://doi.org/10.1371/journal.pntd.0013232 |
| work_keys_str_mv | AT haoyulong annualglobaldenguedynamicsarerelatedtomultisourcefactorsrevealedbyamachinelearningpredictionanalysis AT yilinchen annualglobaldenguedynamicsarerelatedtomultisourcefactorsrevealedbyamachinelearningpredictionanalysis AT jingrufeng annualglobaldenguedynamicsarerelatedtomultisourcefactorsrevealedbyamachinelearningpredictionanalysis AT jianchen annualglobaldenguedynamicsarerelatedtomultisourcefactorsrevealedbyamachinelearningpredictionanalysis AT xuezhang annualglobaldenguedynamicsarerelatedtomultisourcefactorsrevealedbyamachinelearningpredictionanalysis AT wenjiehan annualglobaldenguedynamicsarerelatedtomultisourcefactorsrevealedbyamachinelearningpredictionanalysis AT minkang annualglobaldenguedynamicsarerelatedtomultisourcefactorsrevealedbyamachinelearningpredictionanalysis AT xiangjundu annualglobaldenguedynamicsarerelatedtomultisourcefactorsrevealedbyamachinelearningpredictionanalysis |