灰色马尔科夫模型在我国肺结核发病率预测中的应用

2019-06-11 11:55:46王雅文沈忠周严宝湖杨银
中国卫生产业 2019年6期
关键词:模型

王雅文 沈忠周 严宝湖 杨银

[摘要] 目的 探讨应用GM(1,1)灰色预测模型和GM-Markov模型在全国肺结核发病率预测中的可行性,为制定措施加快降低结核病发病率提供参考。方法 收集2007—2017年全国肺结核数据,建立模型拟合2007—2016年数据并预测2017年全国肺结核发病率,评價两个模型的拟合及预测效果。 结果 拟建立的GM(1,1)模型为x(1)(k+1)= -1 960.635 9e(-0.0441k) +2 049.185 9;GM(1,1)模型与GM-Markov模型的拟合平均相对误差分别为2.08%和1.11%;预测2017年全国肺结核发病率相对误差分别为6.06%和3.40%。GM-Markov模型的拟合和预测效果优于GM(1,1)模型。 结论 GM-Markov模型较GM(1,1)灰色预测模型更适用于预测我国肺结核发病率。可借助该模型预判我国肺结核流行趋势 ,指导相关卫生资源分配。

[关键词] 肺结核;GM(1,1);Markov;预测

[中图分类号] R19 [文献标识码] A [文章编号] 1672-5654(2019)02(c)-0176-04

Application of Grey Markov Model in Predicting the Incidence of Tuberculosis in China

WANG Ya-wen1, SHEN Zhong-zhou1, YAN Bao-hu1, YANG Yin2

1.School of Public Health, Peking Union Medical College, Beijing, 100730 China; 2.Department of Pathogenic Biology, Institute of Basic Medical Sciences, Chinese Academy of Medical Sciences, Peking Union Medical College, Beijing, 100005 China

[Abstract] Objective To explore the feasibility of applying GM(1,1) gray prediction model and GM-Markov model in the prediction of tuberculosis incidence rate in China, and provide reference for formulating measures to accelerate the reduction of tuberculosis incidence. Methods The national tuberculosis data from 2007 to 2017 were collected, the model was fitted to the data of 2007 to 2016 and the incidence of tuberculosis in 2017 was predicted. The fitting and prediction effects of the two models were evaluated. Results The proposed GM(1,1) model was x(1)(k+1)=-1 960.635 9e(-0.0441k)+2 049.185 9; the average of the GM(1,1) model was compared with the GM-Markov model errors were 2.08% and 1.11%, respectively; the relative errors of the national tuberculosis incidence in 2017 were predicted to be 6.06% and 3.40%, respectively. The fitting and prediction effects of the GM-Markov model were better than the GM(1,1) model. Conclusion The GM-Markov model is more suitable for predicting the incidence of tuberculosis in China than the GM (1,1) gray prediction model. This model can be used to predict the trend of tuberculosis in China and to guide the allocation of relevant health resources.

[Key words] Tuberculosis; GM (1,1); Markov; Prediction

结核病是世界传染病中致死率较高的一种慢性传染病,同时结核病也是艾滋病感染者死亡及因抗生素耐药所致死亡的主要原因[1]。2017年全球有160万人死于结核病,中国是全球30个结核病高负担国家之一,在2017年结核病发病人数达83.5万[2]。结合杆菌可累及人体全身各个器官,主要侵犯肺部,称肺结核。我国是结核病高发病国家,政府先后出台了《结核病防治管理办法》《“十三五”全国结核病防治规划》等一系列结核病管理规范文件,并取得了一定的成效。由于我国幅员辽阔,人口众多,即使较低的发病率也意味着庞大的发病人数,因此对结核病发病数进行有效的预测,为疾病管理部门制定策略提供依据,将有助于加速降低我国结核病发病率。……

登录APP查看全文

猜你喜欢
模型
一半模型
一种去中心化的域名服务本地化模型
适用于BDS-3 PPP的随机模型
函数模型及应用
p150Glued在帕金森病模型中的表达及分布
函数模型及应用
重尾非线性自回归模型自加权M-估计的渐近分布
3D打印中的模型分割与打包
FLUKA几何模型到CAD几何模型转换方法初步研究
一个相似模型的应用