基于INLA算法的肺结核发病时空分布特征分析

胡锡健; 别思羽

doi:10.13568/j.cnki.651094.651316.2020.10.08.0001

您当前的位置：

首页 >

文章列表页 >

基于INLA算法的肺结核发病时空分布特征分析

数理科学 | 更新时间：2026-01-21

- 基于INLA算法的肺结核发病时空分布特征分析
- 基于INLA算法的肺结核发病时空分布特征分析
- 新疆大学学报（自然科学版中英文） 2020年37卷第4期页码：428-434
- 作者机构：
  
  新疆大学数学与系统科学学院
- 作者简介：
- 基金信息：
  
  国家自然科学基金项目(11961065);新疆维吾尔自治区研究生科研创新项目(XJ2020G025)
- DOI：10.13568/j.cnki.651094.651316.2020.10.08.0001
  中图分类号： R521;R181.3
- 纸质出版：2020
- 稿件说明：
移动端阅览
[1]胡锡健,别思羽.基于INLA算法的肺结核发病时空分布特征分析[J].新疆大学学报(自然科学版)(中英文),2020,37(04):428-434.
[1]胡锡健,别思羽.基于INLA算法的肺结核发病时空分布特征分析[J].新疆大学学报(自然科学版)(中英文),2020,37(04):428-434. DOI： 10.13568/j.cnki.651094.651316.2020.10.08.0001.

DOI：10.13568/j.cnki.651094.651316.2020.10.08.0001.

摘要

文章分析了肺结核发病风险的影响因素与时空分布特征

建立了疾病时空分布模型

通过R-INLA包估计模型参数与时空效应.结果显示

平均相对湿度、月平均降水、月平均日照时长和月人均GDP对应的相对风险分别为1.018、1.014、1.026和1.025

平均温度和平均气压对应的相对风险分别为0.956和0.767.总体来看

全国肺结核相对风险时空差异明显

空间上呈南重北轻分布态势

时间上呈逐年递减趋势.表明INLA算法对分析肺结核的时空分布特征具有可行性

平均相对湿度、月平均降水、月平均日照时长和月人均GDP对肺结核发病风险有正向作用

平均温度与平均气压有负向作用

平均风速无显著作用.新疆、贵州、海南、广西、湖南、黑龙江、湖北和广东为高发病风险地区

今后要加强疫情防控.春季为高发期

应做好预防工作.

Abstract

The article analyzed influencing factors and spatial-temporal distribution characteristics of tuberculosis relative risk. A disease spatial-temporal distribution model was established

and the R-INLA package was used to estimate model parameters and spatial-temporal effects. The results showed that the relative risks corresponding to average relative humidity

monthly average precipitation

monthly average sunshine duration

and monthly per capita GDP were 1.018

1.014

1.026

and 1.025

respectively. The relative risks corresponding to average temperature and average pressure were 0.956 and 0.767

respectively. On the whole

the relative risk of tuberculosis across the country had obvious spatial-temporal differences

with a distribution trend of heavier in the south and lighter in the north in space

with a decreasing trend in time. It showed that the INLA algorithm was feasible for analyzing the spatial-temporal distribution characteristics of tuberculosis. Average relative humidity

monthly average precipitation

monthly average sunshine duration and monthly per capita GDP had a positive effect on the risk of tuberculosis. Average temperature and average air pressure had a negative effect. Average wind speed had no significant effect. Xinjiang

Guizhou

Hainan

Guangxi

Hunan

Heilongjiang

Hubei and Guangdong are high relative risk areas

and epidemic prevention and control will be strengthened in the future. Spring is the period of high incidence

so preventive work should be done.

关键词

Keywords

references

茆诗松,汤银才.贝叶斯统计[M].2版.北京：中国统计出版社,2012.MAO S S,TANG Y C.Bayes statistics[M].2nd.Beijing:China Statistics Press,2012.(in Chinese)

GILKS W R,RICHARDSON S,SPIEGELHALTER D,et al.Markov chain monte carlo in practice[M].Boca Raton,Florida:The Chemical Rubber Company Press,1995.

BROOKS S,GELMAN A,JONES G,et al.Handbook of markov chain monte carlo[M].Boca Raton,Florida:The Chemical Rubber Company Press,2011.

RUE H,MARTINO S,CHOPIN N.Approximate bayesian inference for latent gaussian models by using integrated nested laplace approximations[J].Journal of the Royal Statistical Society Series B,2009,71(2):319-392.

RUE H.Fast sampling of gaussian markov random fields[J].Journal of the Royal Statistical Society Series B,2001,63(2):325-338.

RUE H,HELD L.Gaussian markov random fields[M].Abingdon:Taylor and Francis,2005.

FONG YY,RUE H,WAKEFIELD J.Bayesian inference for generalized linear mixed models[J].Biostatistics,2010,11(3):397-412.

LINDGREN F,RUE H.Bayesian spatial modelling with R-INLA[J].Journal of Statistical Software,2015,63(19):1-25.

GOMEZ-RUBIO V,PALMI-PERALES F.Multivariate posterior inference for spatial models with the integrated nested Laplace approximation[J].Journal of the Royal Statal Society Series C,2019,68(1):199-215.

WANF X F,YUE Y R,FARAWAY J J.Bayesian regression modeling with INLA[M].Boca Raton,Florida:The Chemical Rubber Company Press,2018.

BERNARDINELLI L,CLAYTON D,PASCUTTO C,et al.Bayesian analysis of space-time variation in disease risk[J].Statistics in Medicine,1995,14(21-22):2433-2443.

BLANGIARDO M,CAMELETTI M.Spatial and spatio-temporal bayesian models with R-INLA[M].Chichester:John Wiley&Sons Ltd,2015.

Freeny A.Empirical model-building and response surfaces[J].Technometrics,1987,30(2):229-231.

KNORR-HELD L,BESAG J.Modelling risk from a disease in time and space[J].Statistics in Medicine,1998,17(18):2045-2060.

浏览量

424

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据