AUTHOR=Zhu Zhixin , Zhu Xiaoxia , Zhan Yancen , Gu Lanfang , Chen Liang , Li Xiuyang 

TITLE=Development and comparison of predictive models for sexually transmitted diseases—AIDS, gonorrhea, and syphilis in China, 2011–2021

JOURNAL=Frontiers in Public Health

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2022.966813

DOI=10.3389/fpubh.2022.966813

ISSN=2296-2565

ABSTRACT=Background: Accurate incidence prediction of sexually transmitted diseases (STDs) is critical for early prevention and better government strategic planning. In this paper, four different forecasting models were presented to predict the incidence of AIDS, gonorrhea, and syphilis. Methods: We estimated the annual percentage change in the incidence of AIDS, gonorrhoea and syphilis using joinpoint regression. The performance of four methods, namely, the autoregressive integrated moving average (ARIMA) model, Elman neural network (ERNN) model, ARIMA-ERNN hybrid model and long short-term memory (LSTM) model, were assessed and compared. The collected data from 2011 to 2020 were used for modeling to predict the incidence in 2021. The performance was evaluated based on four indices: relative error (RE), mean square error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). Results: The incidence rate of AIDS and syphilis was on the rise, and the incidence rate of gonorrhea has declined in recent years. For AIDS, the MAPEs for ARIMA, ERNN, ARIMA-ERNN and LSTM are 23.26, 20.24, 18.34 and 18.63 respectively; For gonorrhea, the MAPEs are 19.44, 18.03, 17.77 and 5.09 respectively; For syphilis, the MAPEs are 9.80, 9.55, 8.67 and 5.79 respectively. In general, the performance ranking of the four models from high to low is LSTM, ARIMA-ERNN, ERNN, ARIMA. Conclusions: The time series predictive models show their powerful performance in forecasting the STDs incidence and can be applied by relevant authorities in the prevention and control of STDs.