Application of a long short-term memory neural network: a burgeoning method of deep learning in forecasting HIV incidence in Guangxi, China.

J. Huang,N. Zang,R. Chen,J. Lai,G. Wang,B. Liang,W. Wei,H. Chen,Y. Liao,J. Jiang,J. Han,O. Zhou,C. Ning,H. Liang,L. Ye

doi:10.1017/s095026881900075x

Abstract

Guangxi, a province in southwestern China, has the second highest reported number of HIV/AIDS cases in China. This study aimed to develop an accurate and effective model to describe the tendency of HIV and to predict its incidence in Guangxi. HIV incidence data of Guangxi from 2005 to 2016 were obtained from the database of the Chinese Center for Disease Control and Prevention. Long short-term memory (LSTM) neural network models, autoregressive integrated moving average (ARIMA) models, generalised regression neural network (GRNN) models and exponential smoothing (ES) were used to fit the incidence data. Data from 2015 and 2016 were used to validate the most suitable models. The model performances were evaluated by evaluating metrics, including mean square error (MSE), root mean square error, mean absolute error and mean absolute percentage error. The LSTM model had the lowest MSE when the N value (time step) was 12. The most appropriate ARIMA models for incidence in 2015 and 2016 were ARIMA (1, 1, 2) (0, 1, 2)12 and ARIMA (2, 1, 0) (1, 1, 2)12, respectively. The accuracy of GRNN and ES models in forecasting HIV incidence in Guangxi was relatively poor. Four performance metrics of the LSTM model were all lower than the ARIMA, GRNN and ES models. The LSTM model was more effective than other time-series models and is important for the monitoring and control of local HIV epidemics.

Highlights

HIV/AIDS has brought tremendous challenges to global public health and life quality of humankind worldwide [1]
From 2005 to 2011, the HIV incidence in Guangxi increased slowly, but the epidemic situation from 2011 to 2015 showed a slow and seasonal decline, which meant that the time series was not stationary
We found that the Long short-term memory (LSTM) model had better predictive ability than did autoregressive integrated moving average (ARIMA) and other models, which is largely consistent with the results reported by others in predicting the influenza outbreaks [32]

Summary

Introduction

HIV/AIDS has brought tremendous challenges to global public health and life quality of humankind worldwide [1]. As an HIV-hit region, Guangxi Zhuang Autonomous Region, a province in southwestern China, has seen an increasing HIV incidence in recent years, and it has become a major public health problem in Guangxi [3, 4]. Corresponding intervention strategies as well as methods against local HIV/AIDS epidemics need urgently to be explored and developed. As the World Health Organization (WHO) has advocated, effective disease surveillance is dependent on effective disease control [5]. The government needs an accurate prediction in HIV incidence to formulate targeted interventions. Establishing high-precision prediction models is important for the monitoring and control of local HIV epidemics

Objectives

Methods

Results

Conclusion