Prediction of the use of hospital blood products based on time series model
10.12025/j.issn.1008-6358.2016.20160697
- VernacularTitle:基于时间序列模型预测上海某三甲综合医院血制品使用量
- Author:
Zheng-Lei QIAO
1
;
Chen-Chen GU
;
Min-Feng CAO
;
Wei ZHU
;
Rui-Ming RONG
Author Information
1. 复旦大学附属中山医院输血科
- Keywords:
clinical use of blood;
Winters model;
blood products inventory;
expert modeler
- From:
Chinese Journal of Clinical Medicine
2016;23(5):640-643
- CountryChina
- Language:Chinese
-
Abstract:
Objective:To systematically analyze the clinical use of various blood components,and find out the rules of forecasting demand scientifically,to provide a scientific basis for forecasting reasonable blood inventory volume.Methods:The clinical use of red blood cells and plasma and the number of people who received transfusion in a general hospital in Shanghai from January 2013 to January 2016 were analyzed with IBM SPSS Statistics 23.0 software,and a time series model was established with the Expert Modeler.Results:All of the residuals were white noise sequence.The model extracted all the data in the original sequence,and passed the model diagnosis.Compared with the actual value,the average relative error was basically within 8%,and predictive values were within the 95% confidence interval,so the predicting precision of the model was fine,and the prediction results were good.Conclusions:The establishment of a more suitable time series model for clinical use of blood can overcome the weaknesses of empirical use of blood,develop a more scientific blood inventory plan and receive good effects.
