2010-2015年耐甲氧西林金黃色葡萄球菌醫(yī)院流行趨勢時間序列分析
發(fā)布時間：2018-08-15 15:38
【摘要】：目的探討應用時間序列求和自回歸滑動平均模型(ARIMA)進行耐甲氧西林金黃色葡萄球菌(MRSA)流行趨勢預測的可行性,為降低MRSA定植或感染提供理論依據。方法使用2010-2014年浙江醫(yī)院MRSA檢出率擬合ARIMA模型,以2015年1-12月MRSA實際檢出率作為預測模型的考核樣本,驗證模型的預測效果。結果 MRSA檢出率ARIMA模型為Xt=0.3807Xt-1+Xt-12-0.3807Xt-13-0.02725;模型預測的平均相對誤差為20.19%,預測的動態(tài)趨勢與實際值基本吻合。結論 ARIMA模型對MRSA檢出率擬合較為滿意,預測效果良好,可為臨床早期采取防控措施提供依據。
[Abstract]:Objective to explore the feasibility of predicting the trend of (MRSA) prevalence of methicillin-resistant Staphylococcus aureus by using time series summation autoregressive moving average model (ARIMA) and to provide a theoretical basis for reducing MRSA colonization or infection. Methods the MRSA positive rate of Zhejiang Hospital from 2010 to 2014 was used to fit the ARIMA model, and the actual detection rate of MRSA from January to December 2015 was used as the test sample to verify the prediction effect of the model. Results the ARIMA model of MRSA detection rate was Xt=0.3807Xt-1 Xt-12-0.3807Xt-13-0.02725, the average relative error of the model was 20.19, and the predicted dynamic trend was basically consistent with the actual value. Conclusion the ARIMA model is satisfactory in fitting the detection rate of MRSA, and can provide evidence for early clinical prevention and control.
【作者單位】： 浙江醫(yī)院醫(yī)院感染管理科;浙江醫(yī)院醫(yī)學檢驗科;
【基金】：浙江醫(yī)院醫(yī)藥衛(wèi)生科學研究基金項目(2015YJ008)
【分類號】：R446.5
，
本文編號：2184653
[Abstract]:Objective to explore the feasibility of predicting the trend of (MRSA) prevalence of methicillin-resistant Staphylococcus aureus by using time series summation autoregressive moving average model (ARIMA) and to provide a theoretical basis for reducing MRSA colonization or infection. Methods the MRSA positive rate of Zhejiang Hospital from 2010 to 2014 was used to fit the ARIMA model, and the actual detection rate of MRSA from January to December 2015 was used as the test sample to verify the prediction effect of the model. Results the ARIMA model of MRSA detection rate was Xt=0.3807Xt-1 Xt-12-0.3807Xt-13-0.02725, the average relative error of the model was 20.19, and the predicted dynamic trend was basically consistent with the actual value. Conclusion the ARIMA model is satisfactory in fitting the detection rate of MRSA, and can provide evidence for early clinical prevention and control.
【作者單位】： 浙江醫(yī)院醫(yī)院感染管理科;浙江醫(yī)院醫(yī)學檢驗科;
【基金】：浙江醫(yī)院醫(yī)藥衛(wèi)生科學研究基金項目(2015YJ008)
【分類號】：R446.5
，
本文編號：2184653
本文鏈接：http://sikaile.net/huliyixuelunwen/2184653.html
最近更新
教材專著
