[1]窦一峰,崔金广,蒙文涛,等.三种数学模型预测医院门急诊就诊人次数的价值比较[J].医学信息,2020,33(24):18-22.[doi:10.3969/j.issn.1006-1959.2020.24.006]
　DOU Yi-feng,CUI Jin-guang,MENG Wen-tao,et al.Comparison of the Value of Three Mathematical Models on Prediction in the Number of Outpatient and Emergency Patients[J].Medical Information,2020,33(24):18-22.[doi:10.3969/j.issn.1006-1959.2020.24.006]
点击复制

三种数学模型预测医院门急诊就诊人次数的价值比较()
分享到：

医学信息[ISSN:1006-1959/CN:61-1278/R]

卷:
33卷
期数:
2020年24期
页码:
18-22
栏目:
出版日期:
2020-12-15

文章信息/Info

Title:
Comparison of the Value of Three Mathematical Models on Prediction in the Number of Outpatient and Emergency Patients
文章编号:
1006-1959（2020）24-0018-05
作者:
窦一峰; 崔金广; 蒙文涛; 吴秀春
天津市宝坻区人民医院网络信息中心，天津 301800
Author(s):
DOU Yi-feng; CUI Jin-guang; MENG Wen-tao; WU Xiu-chun
Network Information Center,People’s Hospital of Baodi District,Tianjin 301800,China
关键词:
医院; 门急诊; 就诊人次; 预测; NARNN; LSTM; SARIMA
Keywords:
Hospital; Outpatient and emergency department; Visits; Prediction; NARNN; LSTM; SARIMA
分类号:
R19
DOI:
10.3969/j.issn.1006-1959.2020.24.006
文献标志码:
A
摘要:
目的 探索数学模型对医院门急诊就诊人次的预测效果，以期得到最佳的预测模型，更好的提升门急诊资源配置效能。方法 收集天津市某三级甲等综合性医院2009~2019年医院门急诊就诊数据，构建NARNN、LSTM和SARIMA模型，采用2009年1月~2018年12月的数据用于模型的训练和测试，以2019年1~12月数据为预测集，比较三种模型的预测效果。结果NARNN、LSTM和SARIMA模型在MAPE上的结果分别为8.22%，4.32%和3.55%，在SMAPE上的结果分别为8.37%，4.33%和3.58%，LSTM和SARIMA的预测效果优于NARNN，其中SARIMA模型在4个指标上的结果均优于LSTM和NARNN，对门急诊人次数拟合和预测效果较好。结论 三种数学模型均能对门急诊人次数据进行有效预测，其中SARIMA模型预测该院门急诊就诊人次的效果最优，可为决策提供预测数据支持。
Abstract:
Objective To explore the predictive effect of mathematical models on hospital outpatient and emergency visits, in order to obtain the best predictive model, and better improve the efficiency of outpatient and emergency resource allocation.Methods Collecting the outpatient and emergency department visit data of a tertiary A general hospital in Tianjin from 2009 to 2019, construct NARNN, LSTM and SARIMA models, and use the data from January 2009 to December 2018 for model training and testing. The data from January to December 2019 is a prediction set, and the prediction effects of the three models are compared.Results The results of the NARNN, LSTM and SARIMA models on MAPE were 8.22%, 4.32% and 3.55%, respectively, and the results on SMAPE were 8.37%, 4.33% and 3.58%, respectively. The prediction effects of LSTM and SARIMA were better than NARNN, of which SARIMA results of the model on the four indicators were better than LSTM and NARNN, and the effect of fitting and predicting the number of outpatient and emergency department was better.Conclusion The three mathematical models can effectively predict the number of outpatient and emergency department visits. The SARIMA model predicts the number of outpatient and emergency department visits in this hospital with the best effect, and can provide predictive data support for decision-making.

参考文献/References:

[1]Dudziak T,Gajewski P,Sniezynski B,et al.Neural network modelling studies of steam oxidized kinetic behaviour of advanced steels and Ni-based alloys at 800 ℃ for 3000 h[J].Corrosion Science,2018,133(APR):94-111. [2]傅裕,鲍迎秋,谢沂伯,等.人工智能技术在皮肤病辅助诊断的应用研究[J].中国数字医学,2018,13(10):29-31,38. [3]朱大奇,史慧.人工神经网络原理及应用[M].北京:科学出版社.2006. [4]Ren G,Gao J.Comparison of NARNN and ARIMA Models for Short-Term Metro Passenger Flow Forecasting[C]//19th COTA International Conference of Transportation Professionals.2019. [5]袁鲁山.基于NAR神经网络的车速预测及应用[D].大连理工大学,2016. [6]Gers FA,Schmidhuber J,Cummins F,et al.Learning to Forget:Continual Prediction with LSTM[J].Neural Computation,2000,12(10):2451-2471. [7]李琳,王哲,张学良,等.基于LSTM深度神经网络的月门诊量预测精度研究[J].中国数字医学,2019,14(1):14-17. [8]于畅,张羽.基于ARMA模型拟合分析方法的地磁监测数据研究--以长春地磁台观测数据为例[J].防灾减灾学报,2019,35(3):58-63. [9]孙娜,许小珊,冯佳宁,等.ARIMA与GM(1,1)模型对我国肺结核年发病人数预测情况的比较[J].中国卫生统计,2019,36(1):73-76. [10]言晨绮,王瑞白,刘海灿,等.ARIMA模型预测2018-2019年我国肺结核发病趋势的应用[J].中华流行病学杂志,2019,40(6):633-637. [11]李芷云,常薇,陈平,等.基于ARIMA模型结合回归分析在产科工作量预测中的应用[J].中国医学创新,2019,16(10):161-166. [12]左秀霞.带高次趋势项的ADF单位根检验[J].数量经济技术经济研究,2019,36(1):152-169.

相似文献/References:

[1]白丽娟,谭云龙,孙延囡.北京地区医院图书馆员职业倦怠与主观幸福感调查研究[J].医学信息,2018,31(02):60.[doi:10.3969/j.issn.1006-1959.2018.02.021]
　BAI Li-juan,TAN Yun-long,SUN Yan-nan.Investigation and Research on Job Burnout and Subjective Well - being ofHospital Librarians in Beijing Area[J].Medical Information,2018,31(24):60.[doi:10.3969/j.issn.1006-1959.2018.02.021]
[2]潘晓辉.医院科研兼职档案员队伍存在的问题及解决对策[J].医学信息,2018,31(06):25.[doi:10.3969/j.issn.1006-1959.2018.06.009]
　PAN Xiao-Hui.Problems and Solutions of Part-time Archivists in Hospital Scientific Research[J].Medical Information,2018,31(24):25.[doi:10.3969/j.issn.1006-1959.2018.06.009]
[3]刘 映,王媛媛,梁 萍,等.性化管理措施对医院形象提升的思考[J].医学信息,2018,31(08):25.[doi:10.3969/j.issn.1006-1959.2018.08.009]
　LIU Ying,WANG Yuan-yuan,LIANG Ping,et al.Reflections on the Improvement of Hospital Image with Humane Management Measures[J].Medical Information,2018,31(24):25.[doi:10.3969/j.issn.1006-1959.2018.08.009]
[4]潘晓辉,李 蓉.某三级甲等综合型医院国家自然科学基金管理策略探讨[J].医学信息,2018,31(11):31.[doi:10.3969/j.issn.1006-1959.2018.11.010]
　PAN Xiao-hui,LI Rong.Discussion on the Management Strategy of National Natural Science Fund of a Class A Comprehensive Hospital[J].Medical Information,2018,31(24):31.[doi:10.3969/j.issn.1006-1959.2018.11.010]
[5]赵 欣.医院临床中麻醉信息系统的应用分析[J].医学信息,2018,31(15):10.[doi:10.3969/j.issn.1006-1959.2018.15.005]
　ZHAO Xin.Application Analysis of Anesthesia Information System in Hospital Clinical Practice[J].Medical Information,2018,31(24):10.[doi:10.3969/j.issn.1006-1959.2018.15.005]
[6]刘禹良.基于Access的临床流感病例管理信息系统[J].医学信息,2019,32(01):25.[doi:10.3969/j.issn.1006-1959.2019.01.009]
　LIU Yu-liang.Access-based Clinical Influenza Case Management Information System[J].Medical Information,2019,32(24):25.[doi:10.3969/j.issn.1006-1959.2019.01.009]
[7]刘 超,吴姗姗,杨海波.大知识背景下医院图情档案一体化发展与工作创新[J].医学信息,2019,32(04):32.[doi:10.3969/j.issn.1006-1959.2019.04.012]
　LIU Chao,WU Shan-shan,YANG Hai-bo.Integrated Development and Work Innovation of Hospital Maps and Archives under the Background of Great Knowledge[J].Medical Information,2019,32(24):32.[doi:10.3969/j.issn.1006-1959.2019.04.012]
[8]王晓天.基于信息技术发展的医院信息化系统建设[J].医学信息,2019,32(06):25.[doi:10.3969/j.issn.1006-1959.2019.06.009]
　WANG Xiao-tian.Construction of Hospital Information System Based on Information Technology Development[J].Medical Information,2019,32(24):25.[doi:10.3969/j.issn.1006-1959.2019.06.009]
[9]张艳娟,李纪伟.门急诊处方点评与分析[J].医学信息,2019,32(13):123.[doi:10.3969/j.issn.1006-1959.2019.13.036]
　ZHANG Yan-juan,LI Ji-wei.Door Emergency Prescription Review and Analysis[J].Medical Information,2019,32(24):123.[doi:10.3969/j.issn.1006-1959.2019.13.036]
[10]丁志虎,胡光阔.智能机器人在医院消毒作业中的应用[J].医学信息,2020,33(05):28.[doi:10.3969/j.issn.1006-1959.2020.05.009]
　DING Zhi-hu,HU Guang-kuo.Application of Intelligent Robot in Hospital Disinfection[J].Medical Information,2020,33(24):28.[doi:10.3969/j.issn.1006-1959.2020.05.009]

更新日期/Last Update: 1900-01-01