荆门市脑出血发病与气象因子相关性分析及预测  

The Correlation Analysis of Cerebral Hemorrhage and Meteorological Factors and its Prediction Study in Jingmen City

作　　者：王欣[1] 肖玮钰[2] 肖会中[3] 

机构地区：[1]荆楚理工学院医学院,湖北省荆门448000 [2]南京信息工程大学 [3]湖北省气象局

出　　处：《中国慢性病预防与控制》2012年第5期557-559,共3页Chinese Journal of Prevention and Control of Chronic Diseases

摘　　要：目的探讨气象因子对脑出血发病的影响及其相关性,并建立基于气象因子的脑出血发病的预报模型,为预防和控制脑出血发病提供参考依据。方法收集2008-2010年荆门市脑出血逐日病例数和同期气象资料,应用SPSS 13.0软件,分析气象因子与脑出血发病的相关性,构建多元线性回归和前馈型神经网络(BP神经网络)模型预测脑出血发病人数,并对模型进行评价。结果气象因子与脑出血发病密切相关。线性回归模型为y赞=18.248-0.873x(1x1为气温,r=0.708,F=18.13,P<0.01),BP神经网络模型结构为7-6-1,2种模型预测的平均误差率分别为16.15%和8.08%,非线性相关系数分别为0.795和0.907。结论荆门市脑出血发病与气温呈显著负相关,BP神经网络模型有较好的预测效果。Objective To investigate the influence of the changes of meteorological factors on the occurrence of intracerebral hemorrhage（ICH） and its correlations,and establish the prediction model based on the correlations and impacts of meteorological factors on the occurrence of ICH.Methods The daily cases of ICH and the meteorological data over the same period during year 2008 to 2010 in Jingmen city in Hubei province were collected,and the correlation of meteorological factors and the incidence of ICH were analyzed with the SPSS13.0 software,and multiple linear regression and BP neural network model were built to predict the occurrence number of ICH,while the model was evaluated.Results The meteorological factors were closely related to intracerebral hemorrhage.Linear regression model was y^=18.248-0.873x1（x1 was the air temperature,r=0.708,F=18.13,P0.01）,the neural network model structure was 7-6-1,the average error rates of these two models＇ prediction were 16.15% and 8.08%,respectively,non-linear correlation coefficient was 0.795 and 0.907,respectively.Conclusion The occurrence of ICH and the temperature has significant negative correlation in Jingmen city,and neural network model has better prediction results.

关 键 词：脑出血 气象学 相关分析 预测 

分 类 号：R743.34[医药卫生—神经病学与精神病学]