Application of grey prediction model to the prediction of medical consumables consumption. Issue 2 (1st April 2019)

• Record Type: Journal Article
• Authors: Shen, Xuejun; Yue, Minghui; Duan, Pengfei; Wu, Guihai; Tan, Xuerui
• Is Part Of: Grey systems. Volume 9:Issue 2(2019)
• Page Start: 213
• Page End: 223
• Publication Date: 2019-04-01
• Subjects: GM (1, 1) model -- Medical materials -- Medical materials ABC classification; Cybernetics -- Periodicals; Systems engineering -- Periodicals; 003.5
• DOI: 10.1108/GS-11-2018-0059
• Languages: English
• ISSNs: 2043-9377

Abstract

Abstract : Purpose: Based on the prediction of the consumption of medical materials, the purpose of this paper is to study the applicability of the grey model method to the field and its predicted accuracy. Design/methodology/approach: The ABC classification method is used to classify medical consumables and select the analysis objects. The GM (1, 1) model predicts the annual consumption of medical materials. The GM (1, 1) modeling of the consumption of the selected medical materials in 2006~2017 was carried out by using the metabolite sequence and the sequence topology subsequence, respectively. The average rolling error and the average rolling accuracy are calculated to evaluate the prediction accuracy of the model. Findings: The ABC classification results show that Class A projects, which account for only 9.79 percent of the total inventory items, occupy most of the inventory funds. Eight varieties with varying purchases and usages and complete historical data were selected for further analysis. The subsequence GM(1, 1) model group constructed by two different methods predicts and scans the annual consumption of eight kinds of medical materials, and the rolling precision can reach more than 90 percent. Originality/value: The metabolic GM (1, 1) model is an ideal predictive model that can meet the requirements for a short-term prediction of medical material consumption (Zhang et al., 2014 ). The GM (1, 1) model is more suitable for a short-term prediction of medical material consumption with less data modeling.