Open AccessA dengue fever predicting model based on Baidu search index data and climate data in South China
Author(s) -
Dan Liu,
Songjing Guo,
Mingjun Zou,
Cong Chen,
Fēi Dèng,
Zhong Xie,
Sheng Hu,
Liang Wu
Publication year - 2019
Publication title -
plos one
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.99
H-Index - 332
ISSN - 1932-6203
DOI - 10.1371/journal.pone.0226841
Subject(s) - dengue fever , partial autocorrelation function , distributed lag , time series , statistics , generalized additive model , autoregressive integrated moving average , mathematics , geography , medicine , virology
With the acceleration of global urbanization and climate change, dengue fever is spreading worldwide. Different levels of dengue fever have also occurred in China, especially in southern China, causing enormous economic losses. Unfortunately, there is no effective treatment for dengue, and the most popular dengue vaccine does not exhibit good curative effects. Therefore, we developed a Generalized Additive Mixed Model (GAMM) that gathered climate factors (mean temperature, relative humidity and precipitation) and Baidu search data during 2011–2015 in Guangzhou city to improve the accuracy of dengue fever prediction. Firstly, the time series dengue fever data were decomposed into seasonal, trend and remainder components by the seasonal-trend decomposition procedure based on loess (STL). Secondly, the time lag of variables was determined in cross-correlation analysis and the order of autocorrelation was estimated using autocorrelation (ACF) and partial autocorrelation functions (PACF). Finally, the GAMM was built and evaluated by comparing it with Generalized Additive Mode (GAM). Experimental results indicated that the GAMM (R 2 : 0.95 and RMSE: 34.1) has a superior prediction capability than GAM (R 2 : 0.86 and RMSE: 121.9). The study could help the government agencies and hospitals respond early to dengue fever outbreak.