Abstract: Objective Objective To study the endemic trend of schistosomiasis japonica in Hubei Province，so as to provide the theo? retical basis for surveillance and forecasting of schistosomiasis. Methods Methods The time?series auto regression integrated moving av? erage（ARIMA）model was applied to fit the infection rate of residents of Hubei Province from 1987 to 2013，and to predict the shot?term trend of infection rate. Results Results The actual values of infection rate of residents were all in the 95% confidence inter? nals of value predicted by the ARIMA model. The prediction showed that the infection rate of residents of Hubei Province would continue to decrease slowly. Conclusion Conclusion The time?series ARIMA model has good prediction accuracy，and could be used for the short?term forecasting of schistosomiasis.

Key words: Schistosomiasis；Forecasting； Time series； ARIMA model；Hubei Province

摘要： 目的 目的 研究湖北省血吸虫病流行的变化趋势， 为血吸虫病监测预警提供理论依据。 方法 方法 运用时间序列ARI? MA模型对1987-2013年湖北省居民血吸虫病感染率进行拟合， 并预测感染率的短期变化趋势。 结果 结果 居民血吸虫病 感染率的实际值均处于ARIMA模型预测值的95%可信区间内。预测结果显示未来5年湖北省居民血吸虫病感染率仍将 继续降低， 但下降幅度不大。 结论 结论 时间序列ARIMA模型预测精度较好， 可用于对血吸虫病感染率进行短期预测分析。

关键词: 血吸虫病； 预测； 时间序列； ARIMA模型； 湖北省