顾及样本随机变异与空间依赖的城市居民高血压时空分异研究

The World Health Organization has identified hypertension as the leading cause of cardiovascular and cerebrovascular mortality and the World’s most common chronic disease, as hypertension is a major risk factor for strokes, myocardial infarctions, heart failures and arterial disease. In China, hypertension has become an important risk factor affecting the health condition of urban residents, and the treatment of hypertension and its complicating diseases leads to heavy consumption of medical and social resources. Therefore, analysis of the spatio-temporal variability of hypertension disease has a very important realistic meaning and a significant academic value. In this research, we introduce a space-time model based on the framework of Bayesian statistics for analyzing the spatio-temporal variability of hypertension disease for urban residents. This research contains three aspects:.(1)In order to eliminate the statistical bias resulted from the small sample size and spatial dependence, we introduce a multi-level hierarchical Bayesian space-time model considering the space-time interaction and sample random variation;.(2)In order to explore the stability of the estimated spatial patterns of hypertension and detect the areas with atypical disease risk, we analyze the classification rule based on space-time interaction effect and posterior probability;.(3)Based on the historical dataset of hypertension admissions, we illustrate our approach in a case study of hypertension disease in Shenzhen, China..It is expected that the research findings are useful for the local public health department to understand the long term space-time trend of hypertension, which is valuable for detecting the geographic environmental risk factors, and hypertension control and prevention.

世界卫生组织将高血压定义为导致心脑血管疾病死亡的首要原因和最常见的慢性病，并且是导致脑卒中、心肌梗塞和心血管及动脉疾病的重要致病因素。高血压已成为我国城市居民身体健康的重要风险因素，其治疗与控制消耗大量的社会资源。因此，研究城市居民高血压的时空分布特征具有十分重要的现实意义和学术价值。本课题拟面向城市居民高血压，分析与构建基于贝叶斯统计的城市居民高血压时空分析模型。本项目的研究内容包括：首先构建了考虑时空交互与样本随机变异的多水平层次贝叶斯时空模型，用于分析城市居民高血压的时空变化特征，消除“小样本”与空间依赖导致的统计偏差；然后研究基于后验概率推断的城市居民高血压时空变化趋势分析方法，识别疾病风险异常变化的区域；最后结合典型城市高血压病例数据，对模型进行实验分析。课题研究成果可直接服务于深圳市公共卫生部门了解高血压的长期时空变化趋势，为高血压地理环境致病因子探测和防控提供科学依据。

世界卫生组织将高血压定义为导致心脑血管疾病死亡的首要原因和最常见的慢性病，并且是导致脑卒中、心肌梗塞和心血管及动脉疾病的重要致病因素。高血压已成为我国城市居民身体健康的重要风险因素，其治疗与控制消耗大量的社会资源。因此，研究城市居民高血压的时空分布特征具有十分重要的现实意义和学术价值。本课题拟面向城市居民高血压，分析与构建基于贝叶斯统计的城市居民高血压时空分析模型。本项目的研究内容包括：首先构建了考虑时空交互与样本随机变异的多水平层次贝叶斯时空模型，用于分析城市居民高血压的时空变化特征，消除“小样本”与空间依赖导致的统计偏差；然后研究基于后验概率推断的城市居民高血压时空变化趋势分析方法，识别疾病风险异常变化的区域；最后结合典型城市高血压病例数据，对模型进行实验分析。课题研究成果可直接服务于深圳市公共卫生部门了解高血压的长期时空变化趋势，为高血压地理环境致病因子探测和防控提供科学依据。