Forecasting Scrub Typhus Cases in Eight High-Risk Counties in China: Evaluation of Time-Series Model Performance
Scrub typhus (ST) is expanding its geographical distribution in China and in many regions worldwide raising significant public health concerns. Accurate ST time-series modeling including uncovering the role of environmental determinants is of great importance to guide disease control purposes. This...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-01-01
|
| Series: | Frontiers in Environmental Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenvs.2021.783864/full |
| _version_ | 1819364726319087616 |
|---|---|
| author | Junyu He Junyu He Xianyu Wei Wenwu Yin Yong Wang Quan Qian Hailong Sun Yuanyong Xu Ricardo J. Soares Magalhaes Ricardo J. Soares Magalhaes Yuming Guo Wenyi Zhang |
| author_facet | Junyu He Junyu He Xianyu Wei Wenwu Yin Yong Wang Quan Qian Hailong Sun Yuanyong Xu Ricardo J. Soares Magalhaes Ricardo J. Soares Magalhaes Yuming Guo Wenyi Zhang |
| author_sort | Junyu He |
| collection | DOAJ |
| description | Scrub typhus (ST) is expanding its geographical distribution in China and in many regions worldwide raising significant public health concerns. Accurate ST time-series modeling including uncovering the role of environmental determinants is of great importance to guide disease control purposes. This study evaluated the performance of three competing time-series modeling approaches at forecasting ST cases during 2012–2020 in eight high-risk counties in China. We evaluated the performance of a seasonal autoregressive-integrated moving average (SARIMA) model, a SARIMA model with exogenous variables (SARIMAX), and the long–short term memory (LSTM) model to depict temporal variations in ST cases. In our investigation, we considered eight environmental variables known to be associated with ST landscape epidemiology, including the normalized difference vegetation index (NDVI), temperature, precipitation, atmospheric pressure, sunshine duration, relative humidity, wind speed, and multivariate El Niño/Southern Oscillation index (MEI). The first 8-year data and the last year data were used to fit the models and forecast ST cases, respectively. Our results showed that the inclusion of exogenous variables in the SARIMAX model generally outperformed the SARIMA model. Our results also indicate that the role of exogenous variables with various temporal lags varies between counties, suggesting that ST cases are temporally non-stationary. In conclusion, our study demonstrates that the approach to forecast ST cases needed to take into consideration local conditions in that time-series model performance differed between high-risk areas under investigation. Furthermore, the introduction of time-series models, especially LSTM, has enriched the ability of local public health authorities in ST high-risk areas to anticipate and respond to ST outbreaks, such as setting up an early warning system and forecasting ST precisely. |
| first_indexed | 2024-12-24T23:03:31Z |
| format | Article |
| id | doaj.art-2dc857252b7c442a95c14692853712bb |
| institution | Directory Open Access Journal |
| issn | 2296-665X |
| language | English |
| last_indexed | 2024-12-24T23:03:31Z |
| publishDate | 2022-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Environmental Science |
| spelling | doaj.art-2dc857252b7c442a95c14692853712bb2022-12-21T16:35:03ZengFrontiers Media S.A.Frontiers in Environmental Science2296-665X2022-01-01910.3389/fenvs.2021.783864783864Forecasting Scrub Typhus Cases in Eight High-Risk Counties in China: Evaluation of Time-Series Model PerformanceJunyu He0Junyu He1Xianyu Wei2Wenwu Yin3Yong Wang4Quan Qian5Hailong Sun6Yuanyong Xu7Ricardo J. Soares Magalhaes8Ricardo J. Soares Magalhaes9Yuming Guo10Wenyi Zhang11Ocean Academy, Zhejiang University, Zhoushan, ChinaOcean College, Zhejiang University, Zhoushan, ChinaChinese PLA Center for Disease Control and Prevention, Beijing, ChinaChinese Center for Disease Control and Prevention, Beijing, ChinaChinese PLA Center for Disease Control and Prevention, Beijing, ChinaChinese PLA Center for Disease Control and Prevention, Beijing, ChinaChinese PLA Center for Disease Control and Prevention, Beijing, ChinaChinese PLA Center for Disease Control and Prevention, Beijing, ChinaSpatial Epidemiology Laboratory, School of Veterinary Science, The University of Queensland, Brisbane, QLD, AustraliaChild Health Research Center, The University of Queensland, Brisbane, QLD, AustraliaDepartment of Epidemiology and Preventive Medicine, School of Public Health and Preventive Medicine, Monash University, Melbourne, VIC, AustraliaChinese PLA Center for Disease Control and Prevention, Beijing, ChinaScrub typhus (ST) is expanding its geographical distribution in China and in many regions worldwide raising significant public health concerns. Accurate ST time-series modeling including uncovering the role of environmental determinants is of great importance to guide disease control purposes. This study evaluated the performance of three competing time-series modeling approaches at forecasting ST cases during 2012–2020 in eight high-risk counties in China. We evaluated the performance of a seasonal autoregressive-integrated moving average (SARIMA) model, a SARIMA model with exogenous variables (SARIMAX), and the long–short term memory (LSTM) model to depict temporal variations in ST cases. In our investigation, we considered eight environmental variables known to be associated with ST landscape epidemiology, including the normalized difference vegetation index (NDVI), temperature, precipitation, atmospheric pressure, sunshine duration, relative humidity, wind speed, and multivariate El Niño/Southern Oscillation index (MEI). The first 8-year data and the last year data were used to fit the models and forecast ST cases, respectively. Our results showed that the inclusion of exogenous variables in the SARIMAX model generally outperformed the SARIMA model. Our results also indicate that the role of exogenous variables with various temporal lags varies between counties, suggesting that ST cases are temporally non-stationary. In conclusion, our study demonstrates that the approach to forecast ST cases needed to take into consideration local conditions in that time-series model performance differed between high-risk areas under investigation. Furthermore, the introduction of time-series models, especially LSTM, has enriched the ability of local public health authorities in ST high-risk areas to anticipate and respond to ST outbreaks, such as setting up an early warning system and forecasting ST precisely.https://www.frontiersin.org/articles/10.3389/fenvs.2021.783864/fullscrub typhustime-series modelingSARIMAX modelLSTM modelChinaenvironmental factors |
| spellingShingle | Junyu He Junyu He Xianyu Wei Wenwu Yin Yong Wang Quan Qian Hailong Sun Yuanyong Xu Ricardo J. Soares Magalhaes Ricardo J. Soares Magalhaes Yuming Guo Wenyi Zhang Forecasting Scrub Typhus Cases in Eight High-Risk Counties in China: Evaluation of Time-Series Model Performance Frontiers in Environmental Science scrub typhus time-series modeling SARIMAX model LSTM model China environmental factors |
| title | Forecasting Scrub Typhus Cases in Eight High-Risk Counties in China: Evaluation of Time-Series Model Performance |
| title_full | Forecasting Scrub Typhus Cases in Eight High-Risk Counties in China: Evaluation of Time-Series Model Performance |
| title_fullStr | Forecasting Scrub Typhus Cases in Eight High-Risk Counties in China: Evaluation of Time-Series Model Performance |
| title_full_unstemmed | Forecasting Scrub Typhus Cases in Eight High-Risk Counties in China: Evaluation of Time-Series Model Performance |
| title_short | Forecasting Scrub Typhus Cases in Eight High-Risk Counties in China: Evaluation of Time-Series Model Performance |
| title_sort | forecasting scrub typhus cases in eight high risk counties in china evaluation of time series model performance |
| topic | scrub typhus time-series modeling SARIMAX model LSTM model China environmental factors |
| url | https://www.frontiersin.org/articles/10.3389/fenvs.2021.783864/full |
| work_keys_str_mv | AT junyuhe forecastingscrubtyphuscasesineighthighriskcountiesinchinaevaluationoftimeseriesmodelperformance AT junyuhe forecastingscrubtyphuscasesineighthighriskcountiesinchinaevaluationoftimeseriesmodelperformance AT xianyuwei forecastingscrubtyphuscasesineighthighriskcountiesinchinaevaluationoftimeseriesmodelperformance AT wenwuyin forecastingscrubtyphuscasesineighthighriskcountiesinchinaevaluationoftimeseriesmodelperformance AT yongwang forecastingscrubtyphuscasesineighthighriskcountiesinchinaevaluationoftimeseriesmodelperformance AT quanqian forecastingscrubtyphuscasesineighthighriskcountiesinchinaevaluationoftimeseriesmodelperformance AT hailongsun forecastingscrubtyphuscasesineighthighriskcountiesinchinaevaluationoftimeseriesmodelperformance AT yuanyongxu forecastingscrubtyphuscasesineighthighriskcountiesinchinaevaluationoftimeseriesmodelperformance AT ricardojsoaresmagalhaes forecastingscrubtyphuscasesineighthighriskcountiesinchinaevaluationoftimeseriesmodelperformance AT ricardojsoaresmagalhaes forecastingscrubtyphuscasesineighthighriskcountiesinchinaevaluationoftimeseriesmodelperformance AT yumingguo forecastingscrubtyphuscasesineighthighriskcountiesinchinaevaluationoftimeseriesmodelperformance AT wenyizhang forecastingscrubtyphuscasesineighthighriskcountiesinchinaevaluationoftimeseriesmodelperformance |