Seasonality and trend prediction of scarlet fever incidence in mainland China from 2004 to 2018 using a hybrid SARIMA-NARX model

PeerJ

article

Yongbin Wang¹  Chunjie Xu²  Zhende Wang¹  Juxiang Yuan¹ 

[1] School of Public Health, North China University of Science and Technology;School of Public Health, Capital Medical University

关键词: SARIMA model;    Scarlet fever;    NAR model;    Hybrid model;    Forecasting;    NARX model;    Incidence cases;    Seasonality;    Trend;    In mainland China;   

DOI  :  10.7717/peerj.6165

学科分类：社会科学、人文和艺术（综合）

来源: Inra

【 摘 要 】

BackgroundScarlet fever is recognized as being a major public health issue owing to its increase in notifications in mainland China, and an advanced response based on forecasting techniques is being adopted to tackle this. Here, we construct a new hybrid method incorporating seasonal autoregressive integrated moving average (SARIMA) with a nonlinear autoregressive with external input(NARX) to analyze its seasonality and trend in order to efficiently prevent and control this re-emerging disease.MethodsFour statistical models, including a basic SARIMA, basic nonlinear autoregressive (NAR) method, traditional SARIMA-NAR and new SARIMA-NARX hybrid approaches, were developed based on scarlet fever incidence data between January 2004 and July 2018 to evaluate its temporal patterns, and their mimic and predictive capacities were compared to discover the optimal using the mean absolute percentage error, root mean square error, mean error rate, and root mean square percentage error.ResultsThe four preferred models identified were comprised of the SARIMA(0,1,0)(0,1,1)12, NAR with 14 hidden neurons and five delays, SARIMA-NAR with 33 hidden neurons and five delays, and SARIMA-NARX with 16 hidden neurons and 4 delays. Among which presenting the lowest values of the aforementioned indices in both simulation and prediction horizons is the SARIMA-NARX method. Analyses from the data suggested that scarlet fever was a seasonal disease with predominant peaks of summer and winter and a substantial rising trend in the scarlet fever notifications was observed with an acceleration of 9.641% annually, particularly since 2011 with 12.869%, and moreover such a trend will be projected to continue in the coming year.ConclusionsThe SARIMA-NARX technique has the promising ability to better consider both linearity and non-linearity behind scarlet fever data than the others, which significantly facilitates its prevention and intervention of scarlet fever. Besides, under current trend of ongoing resurgence, specific strategies and countermeasures should be formulated to target scarlet fever.

【 授权许可】

CC BY