论文部分内容阅读
目的应用马尔科夫模型对甘肃省2016年11月和12月疑似预防接种异常反应(Adverse events following immunization,AEFI)报告数进行预测。方法选取2015年1月-2016年10月甘肃省分月AEFI报告数,通过10折交叉验证将其划分为6个状态,通过时间与状态的转移概率矩阵预测2016年11月和12月AEFI报告数。结果通过转移概率矩阵得到甘肃省2016年11月和12月转移概率分别为(0.33,0.33,0.33,0.00,0.00)和(0.00,0.33,0.19,0.19,0.19,0.08),11月和12月预测数分别为663例和717例,预测误差分别为14.67%和-38.68%。结论马尔科夫模型进行AEFI报告趋势预测是可行的,需要收集较长的时间序列数据以提高预测精度。
Objective To predict the number of AEFI reported in November and December 2016 in Gansu Province by Markov model. Methods The monthly AEFI reports of Gansu from January 2015 to October 2016 were selected and divided into 6 states by 10 fold cross-validation. The AEFI report of November and December 2016 was predicted by the transfer probability matrix of time and state. number. Results The transfer probability of Gansu Province from November to December 2016 was (0.33,0.33,0.33,0.00,0.00) and (0.00,0.33,0.19,0.19,0.19,0.08) respectively, and the monthly average of November, December and December The predicted numbers were 663 and 717, respectively, with prediction errors of 14.67% and -38.68%, respectively. Conclusions It is feasible to forecast the trend of AEFI report by Markov model, which needs to collect longer time series data to improve the prediction accuracy.