Application research of R language-based autoregressive integrated moving average model for predicting short-term consumption of medical consumables
10.19745/j.1003-8868.2024199
- VernacularTitle:基于R语言的ARIMA模型在医用耗材消耗量短期预测中的应用研究
- Author:
Ze-Hua LIU
1
;
Hong-Tao LU
;
Wei LI
;
Fei WEI
;
Si-Si WANG
;
Xiao-Ning FU
;
Xin-Ming DONG
Author Information
1. 天津康复疗养中心,天津 300191
- Keywords:
medical consumables;
R language;
autoregressive integrated moving average model;
consumption of medical consumables;
management of medical consumables
- From:
Chinese Medical Equipment Journal
2024;45(10):84-87
- CountryChina
- Language:Chinese
-
Abstract:
Objective To explore the effect of a R language-based autoregressive integrated moving average(ARIMA)model for predicting the consumption of medical consumables.Methods The monthly consumption data of a certain type of pre-filled flush syringe from July 2018 to June 2023 was selected as the sample data,which underwent smoothness test and difference operation with R language.An ARIMA model was established and the optimal model was determined according to the Akaike and Bayesian information criteria.The corresponding data of the third quarter of 2023 was used as the validation set to predict the consumption,and the prediction result was compared with the actual values to evaluate the prediction effect of the ARIMA model.Results The ARIMA model with the best fitting was ARIMA(0,1,1)(1,0,0)12,all the predicted data were within 95％confidence interval,and its mean absolute percentage error MAPE was 9.92％.P-value proved to be higher than 0.05 when the residual series were tested using the Ljung-Box statistics,which meant the prediction result was satisfactory.Conclusion The R language-based ARIMA model behaves well in predicting the consumption of medical consumables,and provides references for demand planning,budgeting,purchasing and management of medical consumables.[Chinese Medical Equipment Journal,2024,45(10):84-87]
