论文部分内容阅读
目的预测浙江省肾综合征出血热(HFRS)发病趋势,为卫生工作的决策和防病治病提供科学依据。方法根据浙江省2001-2009年HFRS发病率,建立灰色GM(1,1)与广义回归神经网络组合〔GM(1,1)-GRNN〕模型,与GM(1,1)模型对比,并进行预测。结果 2001-2010年HFRS年发病率组合模型拟合值与实际值的平均相对误差为2.47%,明显低于GM(1,1)模型的平均相对误差(11.19%),组合模型的预测精度相对单一GM(1,1)模型有较大的改善;组合模型预测2011年HFRS年发病率为0.8591/10万。结论浙江省2010-2011年HFRS的发病率呈下降趋势,组合模型的预测精度高,可以提供更为准确的预测数据,从而为防控决策提供可靠依据。
Objective To predict the incidence of hemorrhagic fever with renal syndrome (HFRS) in Zhejiang Province and provide a scientific basis for the decision-making and disease prevention and treatment of health work. Methods Based on the incidence of HFRS in Zhejiang Province from 2001 to 2009, a GM (1,1) -GRNN model combining gray GM (1,1) with generalized regression neural network was established and compared with the GM (1,1) model prediction. Results The average relative error between the fit and actual values of annual incidence rate of HFRS from 2001 to 2010 was 2.47%, which was significantly lower than that of the GM (1,1) model (11.19%). The prediction accuracy of the combined model was relatively The single GM (1,1) model has been greatly improved. The combined model predicts the annual incidence of HFRS in 2011 to be 0.8591 / 100,000. Conclusions The incidence of HFRS in Zhejiang Province in 2010-2011 shows a decreasing trend. The combined model has high prediction accuracy and can provide more accurate prediction data, so as to provide a reliable basis for prevention and control decision-making.