Peng Zhihang, Bao Changjun, Zhao Yang, Yi Honggang, Xia Letian, Yu Hao, Shen Hongbing, Chen Feng
Department of Epidemiology and Biostatistics, Nanjing Medical University School of Public Health, Nanjing 210029, Jiangsu Province, China.
J Biomed Res. 2010 May;24(3):207-14. doi: 10.1016/S1674-8301(10)60030-9.
This paper first applies the sequential cluster method to set up the classification standard of infectious disease incidence state based on the fact that there are many uncertainty characteristics in the incidence course. Then the paper presents a weighted Markov chain, a method which is used to predict the future incidence state. This method assumes the standardized self-coefficients as weights based on the special characteristics of infectious disease incidence being a dependent stochastic variable. It also analyzes the characteristics of infectious diseases incidence via the Markov chain Monte Carlo method to make the long-term benefit of decision optimal. Our method is successfully validated using existing incidents data of infectious diseases in Jiangsu Province. In summation, this paper proposes ways to improve the accuracy of the weighted Markov chain, specifically in the field of infection epidemiology.
本文首先基于传染病发病过程中存在诸多不确定性特征，应用序贯聚类方法建立传染病发病状态的分类标准。然后提出一种加权马尔可夫链，用于预测未来发病状态。该方法基于传染病发病率作为相依随机变量的特殊特征，将标准化自系数作为权重。还通过马尔可夫链蒙特卡罗方法分析传染病发病率特征，以使决策的长期效益达到最优。利用江苏省传染病现有发病数据成功验证了我们的方法。总之，本文提出了提高加权马尔可夫链准确性的方法，特别是在感染流行病学领域。
