摘要
目的运用ARIMA模型,对因急性心肌梗死住院的患者人数进行短期预测,期望为相关科室的管理决策提供依据。方法利用2011年1月1日-2017年12月31日沈阳市某三甲医院心内科因急性心肌梗死住院的患者人数的时间序列构建ARIMA模型,并对2018年1月1日-2018年3月31日的数据进行验证,评估模型的效果。最后,通过建立的模型预测2018年该医院因急性心肌梗死住院的患者人数。结果 2011年至2017年心内科累计收治8838名急性心肌梗死患者。采用ARIMA模型预测2018年1季度心肌梗死患者住院数量,平均相对误差3.35%,模型预测效果较好。预计2018年心内科急性心肌梗死住院患者数量将达到150人/月。结论 ARIMA模型能有效模拟预测急性心肌梗死住院患者人数,对心内科的科学管理和资源配置具有重要的应用价值。
Objectives Using the ARIMA model, to make short-term prediction of number of patients with AMI and provide a basis for departmental management and decisions. Methods We conducted ARIMA model by using the amout of AMI in a hospital in Shenyang from January 2011 to December 2017. Then we evaluated the model by comparing the predictive data with the actual data of inpatients with AMI from January 2018 to March 2018. Finally, we predicted the amount of inpatients with AMI in 2018 through the established model. Results A total of 8838 acute myocardial infarction patients were treated in the department of cardiology from 2011 to 2017. The number of patients increased annually from 2011 to 2017, and there was no significant change in the average age and gender ratio, and the average length of hospital stay and case fatality were decreased slightly. The average relative error of model prediction in the first quarter of 2018 was 3.35%, indicating that prediction effect of the model was better. The number of inpatients with AMI in 2018 predicted by the time series model will continue to increase by up to 150 people per month. Conclusions The ARIMA model could effectively simulate the number of patients with AMI and had important application value for the scientific management and resource allocation of the cardiology department.
作者
兰震
迟卫军
付凌雨
孟艳燕
Lan Zhen;Chi Weijun;Fu Lingyu;Meng Yanyan(Medical Records Management Center,The First Affiliated Hospital of China Medical University,Shenyang 110001,China)
出处
《中国病案》
2018年第10期41-43,共3页
Chinese Medical Record
