基于“三年化疫”理论探讨百日咳发病与前期气象因素的相关性并建立预测模型.pdfVIP

论坛·傅士伦佑 Westem j,o urnal of Traditional Chinese Medici肘， 2015 Vol. 28 No.ll ~~m亘8倍白IDm@iB~白白喝o白 与臼ZE句@因昏倒也挺应前自0~翻@~* 张轩，贺娟A 北京中医药大学基础医学院，北京 100029 [摘 要]目的:探讨北京地区百日咳发病与前期(1-3 年前)气象因素的关联性，并建立即人工神经网 络医疗气象预测模型。方法:收集北京地区 1970-2004 年 35 年的气象资料和百日咳发病资料，采用 BP 人工 神经网络方法，分别从 1 年前、2 年前、3 年前 3 个不同时间维度，建立百日咳发病的气象预警模型。结果: 1) 百 日咳发病与前期(1-3 年前)气象因素具有相关性，其中关系最密切的气象因素是 1-3 年前的平均相对湿度; 2) 利用前期气象因素皆可成功建立百日咳发病的预测模型，以 1 年前气象因素建模的预测效果最佳。结论:1- 3 年前的气候可能会影响某些传染病的发病，今后对传染病发病的研究应注意考虑前期的气象变化. [关键词]百日咳; BP 人工神经网络;前期气象变化;三年化疫;五运六气 [中图分类号] R516. 7 [文献标识码] A [文章编号] 1004-6852(2015)11-0038-05 Exploration on the Correlation between the Incidence of Pertussis and Previous Meteorological Variables Based on the Theory of Plague Transformation in Three Years and Building Prediction Models ZHANG Xuan , HE luan Bωic Medicine School of Beiji咆 Universiη of Chinese Medicine , Beijing 1αJ02只 China Abstract Objective: To explore the correlation between pertussis incidence in Beijing and previous (one year to three years ago) meteorological variables , and estab!ish medical meteorological prediction models ofBP artificial neural network. Methods: The 由.ta of climate change 台om 1970 to 2004 and pertussis incidence in Beijing were col- lected and meteorological prediction models were estab !ished by adopting the method ofBP artificial neural network 仕om three different time dimensions including one year , two years and three years ago respectively. Results: 1) Per- tussis incidence is related to previous (one yearωthree years ago) meteorological variables among them , closely related meteorological factor was average relative humidit