[1]陈旻洁 王嵇 李丽 樊翊凌 赵旭霁 陈敏 郑军华 沈璐.基于BP神经网络的门诊放射检查爽约影响因素分析[J].中国卫生质量管理,2025,32(05):021-25.[doi:10.13912/j.cnki.chqm.2025.32.5.06]
　CHEN Minjie,WANG Ji,LI Li.Analysis of Influencing Factors for No-Show in Outpatient Radiology Examinations Based on BP Neural Network[J].Chinese Health Quality Management,2025,32(05):021-25.[doi:10.13912/j.cnki.chqm.2025.32.5.06]
点击复制

基于BP神经网络的门诊放射检查爽约影响因素分析()
分享到：

《中国卫生质量管理》[ISSN:1006-7515/CN:CN 61-1283/R]

卷:
第32卷
期数:
2025年05期
页码:
021-25
栏目:
特别关注
出版日期:
2025-05-15

文章信息/Info

Title:
Analysis of Influencing Factors for No-Show in Outpatient Radiology Examinations Based on BP Neural Network
作者:
陈旻洁 王嵇 李丽 樊翊凌 赵旭霁 陈敏 郑军华 沈璐
上海交通大学医学院附属仁济医院
Author(s):
CHEN Minjie;  WANG Ji;  LI Li
Renji Hospital, Shanghai Jiao Tong University School of Medicine
关键词:
门诊; 放射检查预约; 放射检查爽约; BP神经网络; 影响因素
Keywords:
Outpatient Clinic;  Radiology Examination Appointment;  No-Show for Radiology Examination;  BP Neural Network;  Influencing Factors
分类号:
R197.323
DOI:
10.13912/j.cnki.chqm.2025.32.5.06
文献标志码:
A
摘要:
目的通过分析上海某大型三级综合医院门诊放射检查预约数据，识别爽约因素，并制订针对性策略。方法从医院医技一体化预约系统提取2023年门诊放射检查预约数据，经过预处理得到有效数据524 308条。采用文献研究和关键知情人访谈，并结合样本数据确定研究变量。使用SPSS 20.0软件进行单因素分析，利用BP神经网络模型预测患者爽约行为。结果9个变量单因素分析均具有统计学意义（P＜0.05）。BP神经网络模型在训练库和测试库上的预测准确率均超过96%，影响爽约率的主要因素依次为预约检查等候周期、检查类型、是否为增强检查、检查部位、预约渠道和年龄。结论BP神经网络模型对预测患者爽约行为具有一定实用性。可通过优化预约系统排班和患者线上预约管理界面，设计个性化预约提醒等策略降低门诊放射检查爽约率，从而提高医疗资源利用效率。
Abstract:
ObjectiveTo identify factors contributing to missed appointments for outpatient radiology examinations by analyzing appointment data from a large tertiary general hospital in Shanghai and to propose targeted strategies.MethodsOutpatient radiology appointment data from 2023 were extracted from the hospital’s integrated medical technology appointment system. After preprocessing, 524 308 valid data entries were obtained. Research variables were determined through literature review, interviews with key informants, and analysis of the sample data. Univariate analysis was conducted using SPSS 20.0 software, and a BP neural network model was employed to predict patient no-show behavior.ResultsUnivariate analysis showed statistical significance for all nine variables (P<0.05). The BP neural network model achieved prediction accuracies exceeding 96% in both the training and testing datasets. The primary factors influencing the no-show rate were, in order, the appointment waiting period, examination type, whether it was a contrast-enhanced examination, examination site, appointment channel, and age. Conclusion The BP neural network model demonstrates practical utility in predicting patient no-show behavior. Strategies such as optimizing appointment scheduling systems, enhancing the patient online appointment management interface, and designing personalized appointment reminders can be implemented to reduce the no-show rate for outpatient radiology examinations, thereby improving the efficiency of medical resource utilization.

参考文献/References:

［1］任红霞. 推动老年健康服务高质量发展实现健康老龄化［J］.中国卫生质量管理,2024,31(8):前插2.［2］张宝华. 大型医院医技检查排程优化研究［D］. 天津：天津大学，2019.［3］梁 敏, 刘兴淮. 医技检查预约平台的设计与应用［J］. 电脑知识与技术（学术版）, 2020, 16(12):3.［4］FIORILLO CE，HUGHES AL，I-CHEN C，et al.Factors associated with patient no-show rates in an academic otolaryngology practice［J］. The Laryngoscope，2018，128(3): 626-631. ［5］ZHOU Y，DONG D，JIANG W. Influence factors of patient no show in a outpatient department［J］. IOP Conference Series: Materials Science and Engineering，2018，439: 032047.［6］徐桔密,黄伟娜,罗 莉,等.接送服务链视角下住院患者放射检查失约现象分析［J］.中国卫生质量管理, 2024, 31(1):44-48.［7］DU QY, NIE K, WANG ZS. Application of entropy-based attribute reduction and an artificial neural network in medicine: a case study of estimating medical care costs associated with myocardial infarction［J］. Entropy, 2014, 16(9):4788-4800.［8］JIANG S, CHIN KS, TSUI KL. A universal deep learning approach for modeling the flow of patients under different severities［J］. Computer Methods and Programs in Biomedicine,2018, 154：191-203.［9］朱 光,邓弘林.大数据背景下医院门诊挂号预约爽约行为预测研究［J］.医学信息,2020,33(22):13-15,21.［10］ZACHARIAS C,PINEDO M.Appointment scheduling with no-shows and overbooking［J］.Production and Operations Management，2014，23(5)：788-801． ［11］HAMILTON W，ROUND A，SHARP D. Patient，hospital，and general practitioner characteristics associated with nonattendance：a cohort study［J］. British Journal of General Practice，2002，52（477）：317-319. ［12］黄小维,刘 平,柏 杨,等. 利用精益工具提升磁共振检查运行效率［J］. 中国卫生质量管理,2024,31(1):65-69,74. ［13］吴晓燕.MRI最佳序列选择对育龄期女性乳腺筛查的价值及良恶性病变鉴别的研究［D］.上海：上海交通大学，2014.［14］胡 磊,王 琦,陈 亮.微信服务号在优化门诊放射检查流程的应用探讨［J］.中国卫生质量管理,2017,24(1):62-64.

相似文献/References:

[1]陈小玲.基层部队医院门诊处方点评与分析[J].中国卫生质量管理,2016,23(02):047.[doi:10.13912/j.cnki.chqm.2016.23.2.16]
[2]韩鹏,王燕森,贾存波.某院门诊服务满意度调查分析[J].中国卫生质量管理,2016,23(02):056.[doi:10.13912/j.cnki.chqm.2016.23.2.19]
[3]许春红朱诺.门诊不良事件报告对改进门诊管理与服务的作用[J].中国卫生质量管理,2016,23(05):034.[doi:10.13912/j.cnki.chqm.2016.23.5.10]
[4]陈厚森张蓉张麟李晓娜卢俊英龙宪连.门诊病历质量评价指标设计与应用[J].中国卫生质量管理,2017,24(02):028.[doi:10.13912/j.cnki.chqm.2017.24.2.09]
[5]王芳 刘训华 陈维进 黄娅娟.“先诊疗后结算”优化门诊就医流程的实践[J].中国卫生质量管理,2017,24(05):038.[doi:10.13912/j.cnki.chqm.2017.24.5.13]
[6]陈旻洁 张红 施颖华 余岚 姚荷英 孙晓凡.大型综合医院优化门诊服务人员配置的实践与探讨[J].中国卫生质量管理,2017,24(05):041.[doi:10.13912/j.cnki.chqm.2017.24.5.14]
[7]幸海鹰 王从容 陈军 黎文.让志愿者参与门诊优质护理服务[J].中国卫生质量管理,2018,25(01):070.[doi:10.13912/j.cnki.chqm.2018.25.1.24]
[8]陈旻洁 沈骏 朱华 张斌渊 孙晓凡.门诊电子病历的实践和思考[J].中国卫生质量管理,2018,25(04):050.[doi:10.13912/j.cnki.chqm.2018.25.4.16]
[9]朱婕 张葆康 徐淑华 牛爱荣.降低门诊血常规报告迟发率[J].中国卫生质量管理,2019,26(01):096.[doi:10.13912/j.cnki.chqm.2019.26.1.28]
[10]周松 谢仁炜 陈洁 乔田乐.基于云诊疗技术的门诊诊疗服务流程优化[J].中国卫生质量管理,2020,27(01):099.[doi:10.13912/j.cnki.chqm.2020.27.1.25]

更新日期/Last Update: 2025-05-15