基于ARIMA模型的医用缝线使用数据预测与配置优化方案探讨

ARIMA model-based usage data prediction and configuration optimization scheme for medical sutures

目的:基于自回归积分滑动平均(autoregressive integrated moving average,ARIMA)模型探讨影响医疗机构使用医用缝线的相关因素,为医疗机构合理使用医用缝线提供依据与优化策略。方法:以2014年1月至2023年11月期间某院每月医用缝线使用金额作为研究对象。将2014年1月至2018年12月的医用缝线使用金额数据作为训练集,采用R语言建立ARIMA模型;将2019年1月至2019年12月的医用缝线使用金额数据作为验证集,以验证ARIMA模型的可靠性。利用验证通过后的ARIMA模型预测2021年1月至2023年11月医用缝线每月使用金额并比较预测值与实际值之间的差异,用于评估2021年1月执行医用缝线优化政策带来的效益。结果:建立的ARIMA模型通过了白噪声检验(P>0.05),且2019年全年预测值和实际值之间差异无统计学意义(P>0.05);执行医用缝线优化政策后,某院医用缝线实际使用金额有所下降,2021年1月至2023年11月实际值远小于预测值,差异有统计学意义(P<0.05)。结论:基于ARIMA模型的医用缝线使用数据预测与配置优化方案可以充分挖掘某院医用缝线的使用规律,为医用缝线配置合理优化和智能精细化管理提供决策参考。

Objective To explore the factors affecting the use of medical sutures in medical institutions based on the autore-gressive integrated moving average(ARIMA)model so as to provide basis and optimization strategy for the rational use of medical sutures in medical institutions.Methods The monthly usage amount of medical sutures in some hospital from January 2014 to November 2023 was used as the research subject.An ARIMA model was established by R language,with the data on medical suture usage amount from January 2014 to December 2018 used as the training set;the reliability of the ARIMA model was verified with the data on medical suture usage amount from January to December 2019 as the validation set.The monthly usage amount of medical sutures from January 2021 to November 2023 was predicted with the validated ARIMA model,then the predictive value was compared with the actual one to evaluate the benefits of implementing the medical suture optimization policy in January 2021.Results The established ARIMA model passed the white noise test(P>0.05),and the difference between the predicted and actual values for the whole year of 2019 was not statistically significant(P>0.05);after the implementation of the medical suture optimization policy,the actual usage amount of medical sutures in some hospital decreased.The actual value from January 2021 to November 2023 was much lower than the predicted value,and the difference was statistically significant(P<0.05).Conclusion The ARIMA model-based medical suture usage data prediction and configuration optimization scheme contributes to clarifying the law of medical suture usage in some hospital,and provides references for optimization and precision managment of medical suture configuration.