Long short-term memory-based forecasting of influenza epidemics using surveillance and meteorological data in Tokyo, Japan
BackgroundInfluenza remains a significant public health challenge worldwide, necessitating robust forecasting models to facilitate timely interventions and resource allocation. The aim of this study was to develop a long short-term memory (LSTM)-based short-term forecasting model to accurately predi...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-08-01
|
| Series: | Frontiers in Public Health |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpubh.2025.1618508/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849229414820216832 |
|---|---|
| author | Daiki Koge Daiki Koge Keita Wagatsuma Keita Wagatsuma |
| author_facet | Daiki Koge Daiki Koge Keita Wagatsuma Keita Wagatsuma |
| author_sort | Daiki Koge |
| collection | DOAJ |
| description | BackgroundInfluenza remains a significant public health challenge worldwide, necessitating robust forecasting models to facilitate timely interventions and resource allocation. The aim of this study was to develop a long short-term memory (LSTM)-based short-term forecasting model to accurately predict weekly influenza case counts in Tokyo, Japan.MethodBy using weekly time-series data on influenza incidence in Tokyo from 2000 to 2019, along with meteorological variables, we developed four distinct models to evaluate the impact of the external variables of mean temperature, relative humidity, and national public holidays. After model training, we assessed the predictive performance on an independent test dataset, using mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), and Pearson’s correlation coefficient.ResultsDuring the study period, 1,445,944 influenza cases were analyzed. The model incorporating all three external variables demonstrated superior predictive accuracy, with an MSE of 3,646,084, RMSE of 1,909, MAE of 849, and Pearson’s correlation coefficient of 0.924. These findings underscore the substantial contribution of these external factors to improving the prediction performance.ConclusionThis study highlighted the efficacy of LSTM-based models for short-term influenza forecasting and reinforces the importance of integrating meteorological variables and national public holidays into predictive frameworks. Our optimal model provided more precise forecasts of influenza activity in Tokyo, Japan. |
| format | Article |
| id | doaj-art-e52e2a7bb43b43cc8aacb8d14f971ec0 |
| institution | Kabale University |
| issn | 2296-2565 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Public Health |
| spelling | doaj-art-e52e2a7bb43b43cc8aacb8d14f971ec02025-08-22T04:10:39ZengFrontiers Media S.A.Frontiers in Public Health2296-25652025-08-011310.3389/fpubh.2025.16185081618508Long short-term memory-based forecasting of influenza epidemics using surveillance and meteorological data in Tokyo, JapanDaiki Koge0Daiki Koge1Keita Wagatsuma2Keita Wagatsuma3Division of Bioinformatics, Department of Information Science, Graduate School of Science and Technology, Niigata University, Niigata, JapanInstitute for Research Administration, Niigata University, Niigata, JapanInstitute for Research Administration, Niigata University, Niigata, JapanDivision of International Health (Public Health), Graduate School of Medical and Dental Sciences, Niigata University, Niigata, JapanBackgroundInfluenza remains a significant public health challenge worldwide, necessitating robust forecasting models to facilitate timely interventions and resource allocation. The aim of this study was to develop a long short-term memory (LSTM)-based short-term forecasting model to accurately predict weekly influenza case counts in Tokyo, Japan.MethodBy using weekly time-series data on influenza incidence in Tokyo from 2000 to 2019, along with meteorological variables, we developed four distinct models to evaluate the impact of the external variables of mean temperature, relative humidity, and national public holidays. After model training, we assessed the predictive performance on an independent test dataset, using mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), and Pearson’s correlation coefficient.ResultsDuring the study period, 1,445,944 influenza cases were analyzed. The model incorporating all three external variables demonstrated superior predictive accuracy, with an MSE of 3,646,084, RMSE of 1,909, MAE of 849, and Pearson’s correlation coefficient of 0.924. These findings underscore the substantial contribution of these external factors to improving the prediction performance.ConclusionThis study highlighted the efficacy of LSTM-based models for short-term influenza forecasting and reinforces the importance of integrating meteorological variables and national public holidays into predictive frameworks. Our optimal model provided more precise forecasts of influenza activity in Tokyo, Japan.https://www.frontiersin.org/articles/10.3389/fpubh.2025.1618508/fullinfluenzameteorological factorforecastingepidemiologyclimate changeJapan |
| spellingShingle | Daiki Koge Daiki Koge Keita Wagatsuma Keita Wagatsuma Long short-term memory-based forecasting of influenza epidemics using surveillance and meteorological data in Tokyo, Japan Frontiers in Public Health influenza meteorological factor forecasting epidemiology climate change Japan |
| title | Long short-term memory-based forecasting of influenza epidemics using surveillance and meteorological data in Tokyo, Japan |
| title_full | Long short-term memory-based forecasting of influenza epidemics using surveillance and meteorological data in Tokyo, Japan |
| title_fullStr | Long short-term memory-based forecasting of influenza epidemics using surveillance and meteorological data in Tokyo, Japan |
| title_full_unstemmed | Long short-term memory-based forecasting of influenza epidemics using surveillance and meteorological data in Tokyo, Japan |
| title_short | Long short-term memory-based forecasting of influenza epidemics using surveillance and meteorological data in Tokyo, Japan |
| title_sort | long short term memory based forecasting of influenza epidemics using surveillance and meteorological data in tokyo japan |
| topic | influenza meteorological factor forecasting epidemiology climate change Japan |
| url | https://www.frontiersin.org/articles/10.3389/fpubh.2025.1618508/full |
| work_keys_str_mv | AT daikikoge longshorttermmemorybasedforecastingofinfluenzaepidemicsusingsurveillanceandmeteorologicaldataintokyojapan AT daikikoge longshorttermmemorybasedforecastingofinfluenzaepidemicsusingsurveillanceandmeteorologicaldataintokyojapan AT keitawagatsuma longshorttermmemorybasedforecastingofinfluenzaepidemicsusingsurveillanceandmeteorologicaldataintokyojapan AT keitawagatsuma longshorttermmemorybasedforecastingofinfluenzaepidemicsusingsurveillanceandmeteorologicaldataintokyojapan |