Tang Dandan, Jin Yuanyuan, Hu XuanJie, Lin Dandan, Kapar Abiden, Wang YanJie, Yang Fang, Li Huling
Medical Engineering College of Xinjiang Medical University, Urumqi, 830017, China.
Institute of Medical Engineering Interdisciplinary Research, Xinjiang Medical University, Urumqi, China.
BMC Public Health. 2025 Feb 25;25(1):780. doi: 10.1186/s12889-025-21982-3.
AIDS is a highly fatal infectious disease of Class B, and Xinjiang is a high-incidence region for AIDS in China. The core of prevention and control lies in early monitoring and early warning. This study aims to identify the best model for predicting the monthly AIDS incidence in Xinjiang, providing scientific evidence for AIDS prevention and control.
Monthly AIDS incidence data from January 2004 to December 2020 in Xinjiang were collected. Six different models, including the ARIMA (2,1,2) model, ARIMA (2,1,2)-EGARCH (2,2) combined model, ARIMA (2,1,2)-TGARCH (1,1) combined model, ETS (A, A, A) model, XGBoost model, and LSTM model, were used for fitting and forecasting.
All models were able to capture the overall trend of the monthly AIDS incidence in Xinjiang. In terms of RMSE and MAE, the ETS (A, A, A) model performed the best, achieving the smallest values. For the MAPE metric, the ARIMA (2,1,2)-TGARCH (1,1) model performed the best. Considering RMSE, MAE, and MAPE together, the ETS (A, A, A) model was the best-performing model in this study. The LSTM model also showed good predictive performance, while the XGBoost model and ARIMA (2,1,2) model performed relatively poorly.
The ETS (A, A, A) model is the best model for predicting the monthly AIDS incidence in Xinjiang. Deep learning models (such as LSTM) have significant potential in time series forecasting. The XGBoost model and ARIMA (2,1,2) model may have limitations when handling time series data, and future improvements or combinations could enhance prediction performance.
艾滋病是乙类高致死性传染病，新疆是我国艾滋病高发地区，防控核心在于早期监测与预警。本研究旨在探寻预测新疆艾滋病月发病率的最佳模型，为艾滋病防控提供科学依据。
收集新疆2004年1月至2020年12月的艾滋病月发病率数据。采用六种不同模型进行拟合与预测，包括ARIMA(2,1,2)模型、ARIMA(2,1,2)-EGARCH(2,2)组合模型、ARIMA(2,1,2)-TGARCH(1,1)组合模型、ETS(A,A,A)模型、XGBoost模型和LSTM模型。
所有模型均能捕捉新疆艾滋病月发病率的总体趋势。在均方根误差（RMSE）和平均绝对误差（MAE）方面，ETS(A,A,A)模型表现最佳，取得最小值。对于平均绝对百分比误差（MAPE）指标，ARIMA(2,1,2)-TGARCH(1,1)模型表现最佳。综合考虑RMSE、MAE和MAPE，ETS(A,A,A)模型是本研究中表现最佳的模型。LSTM模型也显示出良好的预测性能，而XGBoost模型和ARIMA(2,1,2)模型表现相对较差。
ETS(A,A,A)模型是预测新疆艾滋病月发病率的最佳模型。深度学习模型（如LSTM）在时间序列预测方面具有巨大潜力。XGBoost模型和ARIMA(2,1,2)模型在处理时间序列数据时可能存在局限性，未来改进或组合可能会提高预测性能。
