Department of Epidemiology & Biostatistics, and Center for Clinical Big Data and Statistics, Second Affiliated Hospital, College of Medicine, Zhejiang University, Hangzhou, China.
Front Public Health. 2022 Aug 12;10:966813. doi: 10.3389/fpubh.2022.966813. eCollection 2022.
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.
The annual percentage changes in the incidence of AIDS, gonorrhea, and syphilis were estimated by 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. For 1-year prediction, the collected data from 2011 to 2020 were used for modeling to predict the incidence in 2021. For 5-year prediction, the collected data from 2011 to 2016 were used for modeling to predict the incidence from 2017 to 2021. The performance was evaluated based on four indices: mean square error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE).
The morbidities of AIDS and syphilis are on the rise, and the morbidity of gonorrhea has declined in recent years. The optimal ARIMA models were determined: ARIMA(2,1,2)(0,1,1), ARIMA(1,1,2)(0,1,2), and ARIMA(3,1,2)(1,1,2) for AIDS, gonorrhea, and syphilis 1-year prediction, respectively; ARIMA (2,1,2)(0,1,1), ARIMA(1,1,2)(0,1,2), and ARIMA(2,1,1)(0,1,0) for AIDS, gonorrhea and syphilis 5-year prediction, respectively. For 1-year prediction, the MAPEs of ARIMA, ERNN, ARIMA-ERNN, and LSTM for AIDS 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. For 5-year prediction, the MAPEs of ARIMA, ERNN, ARIMA-ERNN, and LSTM for AIDS are 12.86, 23.54, 14.74, and 25.43, respectively; For gonorrhea, the MAPEs are 17.07, 17.95, 16.46, and 15.13, respectively; For syphilis, the MAPEs are 21.88, 24.00, 20.18 and 11.20, respectively. In general, the performance ranking of the four models from high to low is LSTM, ARIMA-ERNN, ERNN, and ARIMA.
The time series predictive models show their powerful performance in forecasting STDs incidence and can be applied by relevant authorities in the prevention and control of STDs.
准确预测性传播疾病（性病）的发病率对于早期预防和更好的政府战略规划至关重要。本文提出了四种不同的预测模型，用于预测艾滋病、淋病和梅毒的发病率。
采用 Joinpoint 回归估计艾滋病、淋病和梅毒发病率的年变化百分比。评估和比较了四种方法的性能，即自回归综合移动平均（ARIMA）模型、Elman 神经网络（ERNN）模型、ARIMA-ERNN 混合模型和长短时记忆（LSTM）模型。对于 1 年预测，使用 2011 年至 2020 年收集的数据进行建模，以预测 2021 年的发病率。对于 5 年预测，使用 2011 年至 2016 年收集的数据进行建模，以预测 2017 年至 2021 年的发病率。基于四个指标评估了性能：均方误差（MSE）、平均绝对误差（MAE）和平均绝对百分比误差（MAPE）。
艾滋病和梅毒的发病率呈上升趋势，淋病的发病率近年来呈下降趋势。确定了最佳的 ARIMA 模型：用于艾滋病、淋病和梅毒 1 年预测的 ARIMA（2,1,2）（0,1,1）、ARIMA（1,1,2）（0,1,2）和 ARIMA（3,1,2）（1,1,2）；用于艾滋病、淋病和梅毒 5 年预测的 ARIMA（2,1,2）（0,1,1）、ARIMA（1,1,2）（0,1,2）和 ARIMA（2,1,1）（0,1,0）。对于 1 年预测，ARIMA、ERNN、ARIMA-ERNN 和 LSTM 对艾滋病的 MAPE 分别为 23.26、20.24、18.34 和 18.63；对于淋病，MAPE 分别为 19.44、18.03、17.77 和 5.09；对于梅毒，MAPE 分别为 9.80、9.55、8.67 和 5.79。对于 5 年预测，ARIMA、ERNN、ARIMA-ERNN 和 LSTM 对艾滋病的 MAPE 分别为 12.86、23.54、14.74 和 25.43；对于淋病，MAPE 分别为 17.07、17.95、16.46 和 15.13；对于梅毒，MAPE 分别为 21.88、24.00、20.18 和 11.20。总体而言，这四个模型的性能从高到低的排序为 LSTM、ARIMA-ERNN、ERNN 和 ARIMA。
时间序列预测模型在预测性病发病率方面表现出强大的性能，相关部门可用于性病的预防和控制。
