Forecasting Scrub Typhus Cases in Eight High-Risk Counties in China: Evaluation of Time-Series Model Performance

Xianyu Wei,Junyu He,Quan Qian,Wenwu Yin,Hailong Sun,Yuming Guo,Yuanyong Xu,Ricardo J Soares Magalhaes,Wenyi Zhang,Yong Wang

doi:10.3389/fenvs.2021.783864

Abstract

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.

Highlights

Scrub typhus (ST) is a mite-borne disease caused by the Orientia tsutsugamushi (O. tsutsugamushi)
Various seasonal autoregressive-integrated moving average (SARIMA) and SARIMA model with exogenous variables (SARIMAX) models were established with different model structures, and temporal lagged exogenous variables at the eight considered counties and the optimal model structure with the corresponding performance are presented in Supplementary Appendix Table A1
Atmospheric pressure, sunshine duration, wind speed, and multivariate El Niño/Southern Oscillation index (MEI) with various temporal lags were found to be correlated with the ST temporal variation in Yingyang County and Guangning County; precipitation and relative humidity were included in ST forecasting at Yingyang County, while normalized difference vegetation index (NDVI) was included in the model at Guangning County

Summary

Introduction

Scrub typhus (ST) is a mite-borne disease caused by the Orientia tsutsugamushi (O. tsutsugamushi). Machine learning techniques have been developing rapidly during the past decade; random forest, support vector machine, or gradient boost machine techniques are used to determine the relationship between the studied natural attribute and the related environmental variable in the field of public health (Carvajal et al, 2018; He et al, 2018a). These methodologies have certain limitations on forecasting the disease in the future. Such a study will benefit the public health managers on providing precise ST forecasting models, especially in the high-risk ST counties

Objectives

Methods

Results

Discussion

Conclusion