
浏览全部资源
扫码关注微信
四川大学华西医院医学工程科(成都 610041)
LIU Qilin (E-mail: cd610041@163.com)
Received:10 September 2025,
Revised:2025-12-09,
Published:20 April 2026
移动端阅览
奉楠馨,谢思源,刘麒麟.基于运营日志数据的CT扫描工作流程优化与需求预测研究[J].北京生物医学工程,2026,45(2):170-176.
FENG Nanxin,XIE Siyuan,LIU Qilin.Optimization of CT scanning workflow and demand forecasting based on operational log data[J].Beijing Biomedical Engineering,2026,45(2):170-176.
奉楠馨,谢思源,刘麒麟.基于运营日志数据的CT扫描工作流程优化与需求预测研究[J].北京生物医学工程,2026,45(2):170-176. DOI: 10.3969/j.issn.1002-3208.2026.02.008.
FENG Nanxin,XIE Siyuan,LIU Qilin.Optimization of CT scanning workflow and demand forecasting based on operational log data[J].Beijing Biomedical Engineering,2026,45(2):170-176. DOI: 10.3969/j.issn.1002-3208.2026.02.008.
目的
2
计算机断层扫描(computed tomography
CT)是现代医学诊断的核心工具,但其设备昂贵且运营流程复杂,普遍存在效率低下和患者等待时间长等问题。研究旨在基于医疗物联网(internet of medical things
IoMT)获取的运营日志数据,构建一套量化工作流程效率的评价体系,通过分析影响检查效率的关键因素,对未来需求进行精准预测,为放射科精细化管理、差异化排班及医疗资源优化提供科学的决策依据。
方法
2
本研究对5台CT设备在3个月内的运营日志数据进行了回顾性分析。首先基于数据驱动的方法论,提取并清洗出了包括设备利用率、扫描生产率、平均检查周转时间及平均患者间隔时间(turnaround time,TAT)等关键绩效指标(key performance indicators
KPIs)体系。然后,按检查类型对KPIs进行差异化对比,以识别影响设备生产效率的主要因素。最后,利用5月和6月的每日扫描量数据作为训练集,分别构建了季节性自回归积分移动平均(seasonal autoregressive integrated moving average,SARIMA)模型和随机森林(random forest)回归模型,对7月的每日扫描量进行预测。通过均方根误差(root mean square error
RMSE)、平均绝对误差(mean absolute error
MAE)、决定系数(
<math id="M1"><mi>R</mi><mo>²</mo></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109200037&type=
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109200050&type=
3.21733332
2.79399991
)和方向准确性(directional accuracy)4个指标全面评估了模型性能。
结果
2
研究共纳入5台设备共74 159次扫描记录。KPI分析显示,设备平均检查时间1.47 min±0.48 min,平均检查周转时间为7.76 min±3.6 min,设备平均利用率85.76%±16%。分层次分析量化了检查协议复杂度对效率的显著影响,数据表明,复合部位扫描的平均TAT显著高于单一部位,增强扫描的TAT约为平扫的1.5倍。在需求预测方面,随机森林模型所有评价指标优于SARIMA模型约15%,表明机器学习模型能更有效捕捉医院工作流中的非线性特性。
结论
2
研究基于CT设备运营日志数据构建的KPI体系能够有效量化工作流程,明确了复杂检查是限制CT设备运行效率的关键因素。相对于传统的时间序列模型,研究证明了随机森林模型在预测短期扫描需求方面具有高准确性和应用潜力。研究结果表明,医疗机构可通过实施差异化预约排班策略和应用机器学习预测模型,动态调配技师与耗材,缩短患者等待时间,从而显著提升放射科的整体运营效率和医疗服务质量。
Objective
2
Computed tomography (CT) is a cornerstone of modern medical diagnostics; however, the conflict between high equipment costs and complex operational workflows often leads to inefficiencies and prolonged patient waiting times. This study aims to construct a quantitative evaluation system for workflow efficiency based on operational log data obtained from the internet of medical things (IoMT). By analyzing key factors affecting examination efficiency and accurately predicting future demand, this study seeks to provide a scientific basis for decision-making regarding refined management, differentiated scheduling, and the optimization of medical resources in radiology departments.
Methods
2
A retrospective analysis was conducted on operational log data from five CT scanners over a three-month period. First, utilizing a data-driven methodology, a system of key performance indicators (KPIs) was extracted and cleaned, including equipment utilization rate, scanning productivity, mean examination turnaround time (TAT), and mean inter-patient interval time. Subsequently, a comparative analysis of KPIs stratified by examination type was performed to identify primary factors influencing equipment productivity. Finally, using daily scan volume data from May and June as a training set, seasonal autoregressive integrated moving average (SARIMA) and random forest regression models were developed to forecast daily scan volumes for July. Model performance was comprehensively evaluated using root mean square error (RMSE), mean absolute error (MAE), coefficient of determination (
<math id="M2"><msup><mrow><mi>R</mi></mrow><mrow><mn mathvariant="normal">2</mn></mrow></msup></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109200090&type=
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109200089&type=
3.38666677
2.79399991
), and directional accuracy.
Results
2
The study included over 74 159 scan records from the five devices. KPI analysis revealed a mean examination time of
<math id="M3"><mn mathvariant="normal">1.47</mn><mtext> </mtext><mi mathvariant="normal">m</mi><mi mathvariant="normal">i</mi><mi mathvariant="normal">n</mi><mo>±</mo><mn mathvariant="normal">0.48</mn></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109200092&type=
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109200078&type=
24.46866608
2.62466669
min, a mean examination TAT of
<math id="M4"><mtext> </mtext><mn mathvariant="normal">7.76</mn><mtext> </mtext><mi mathvariant="normal">m</mi><mi mathvariant="normal">i</mi><mi mathvariant="normal">n</mi><mo>±</mo><mn mathvariant="normal">3.6</mn><mtext> </mtext></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109200057&type=
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109200042&type=
24.12999916
2.62466669
min, and an average equipment utilization rate of
<math id="M5"><mn mathvariant="normal">85.76</mn><mi mathvariant="normal">%</mi><mo>±</mo><mn mathvariant="normal">16</mn><mi mathvariant="normal">%</mi></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109200082&type=
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109200081&type=
22.52133369
2.62466669
. Stratified analysis quantified the significant impact of examination protocol complexity on efficiency; data indicated that the mean TAT for multi-site combined scans was significantly higher than that for single-site scans, and the TAT for contrast-enhanced scans was approximately 1.5 times that of non-contrast scans. Regarding demand forecasting, the random forest model outperformed the SARIMA model by approximately 15% across all evaluation metrics, demonstrating that machine learning models more effectively capture the non-linear characteristics of hospital workflows.
Conclusions
2
The KPI system constructed based on CT operational log data effectively quantifies the workflow and identifies complex examinations as the key factor constraining CT operational efficiency. Compared to traditional time-series models, this study demonstrates the high accuracy and potential application of the random forest model in forecasting short-term scanning demand. The findings suggest that healthcare institutions can significantly enhance the overall operational efficiency and service quality of radiology departments by implementing differentiated appointment scheduling strategies and applying machine learning predictive models to dynamically allocate technicians and consumables, thereby reducing patient waiting times.
魏笑雨. 基于医学CT图像的自动诊断研究[D]. 成都:电子科技大学, 2025.
Wei XY. Research on automatic diagnosis based on medical CT images[D]. Chengdu: University of Electronic Science and Technology of China, 2025.
徐志扬, 杨玉志, 陈健, 等. 基于真实世界数据多维度评估CT设备应用价值的研究[J]. 中国医学装备, 2024, 21(8): 13-17.
Xu ZY, Yang YZ, Chen J, et al. Study on the assessment of application value of CT equipment from multi-dimension based on real world[J]. China Medical Equipment, 2024, 21(8): 13-17.
庄美俊,于丽华,李晓亮. CT增强扫描患者操作流程改进及效果评价[J]. 中国现代医生, 2021, 59(15): 109-112.
Zhuang MJ, Yu LH, Li XL. Process improvement and impact assessment of operation on patients undergoing enhanced CT scanning[J]. China Modern Doctor, 2021, 59(15): 109-112.
赵海鹏,沈宇杨,宋雪,等. 上海市某三甲综合医院大型医用CT设备使用综合效益分析[J]. 医学与社会, 2024, 37(8): 99-106.
Zhao HP, Shen YY, Song X, et al. The comprehensive benefit analysis of using medical CT equipment in a Grade-A tertiary general hospital in Shanghai[J]. Medicine and Society, 2024, 37(8): 99-106.
廖文婷,邱怡君. 关键绩效指标(KPI)在医院设立实验室的运用[J]. 临床医药文献电子杂志, 2020, 7(12): 184-187.
Liao WT, Qiu YJ. Key performance indicators for the evaluation of laboratory facilities in hospitals[J]. Electronic Journal of Clinical Medical Literature, 2020, 7(12): 184-187.
卫志刚. 基于工作量绩效考核的调控机制的实践探索[J]. 现代医院管理, 2025, 23(3): 40-42, 71.
张楚洋. 精细化管理在公立医院管理运营创新中的作用与实践[J]. 经济师, 2025(2): 240-241.
廖伟光,刘松峰,孙波,等. 基于真实动态数据的大型医疗设备合理配置决策系统开发及应用[J]. 现代仪器与医疗, 2024, 30(5): 40-45.
Liao WG, Liu SF, Sun B, et al. Development and application of a rational configuration decision system for large medical equipment based on real dynamic data[J]. Modern Instruments Medical Treatment, 2024, 30(5): 40-45.
修梦瑶. DA公司绩效考核体系优化[D]. 秦皇岛:燕山大学, 2021.
Xiu MY. Optimization on performance evaluation system of DA company[D]. Qinhuangdao: Yanshan University, 2021.
高崇铭, 万红. 基于关键绩效指标法(KPI)的医疗设备绩效评价指标构建及标准化应用效果[J]. 中国品牌与防伪, 2025(7): 223-225.
杨一童, 季兴东. 基于医院医学影像信息化管理对其CT设备的效益影响研究[J]. 生命科学仪器, 2023, 21(4): 88-92.
Yang YT, Ji XD. Based on the hospital medical image information management on the benefit of CT equipment[J]. Life Science Instruments, 2023, 21(4): 88-92.
环丽娜,石霄. S医院医用设备效益分析——以CT经济效益分析为例[J]. 经济师, 2025(4): 260-261, 274.
郑斯怡. 大型医疗设备效益管理与绩效评价策略探讨[J]. 上海商业, 2022(12): 172-174.
Zamzam AH, Al-Ani AKI, Wahab AKA, et al. Prioritisation assessment and robust predictive system for medical equipment: a comprehensive strategic maintenance management[J]. Frontiers in Public Health, 2021, 9: 782203.
杨涛. CT设备中球管维护及检测分析研究[J]. 中国医疗器械信息, 2022, 28(24): 173-175.
Yang T. Analysis and research on maintenance and inspection of ball tube in CT equipment[J]. China Medical Device Information, 2022, 28(24): 173-175.
Huang G, Luo Z, Xiao X, et al. An ARMA-based model of predictive maintenance for medical equipment suppliers[C]// The International Conference on Smart Manufacturing, Industrial Logistics Engineering (SMILE) 2023. Singapore: Springer, Singapore, 2024: 773-780.
Chen Z, Liu Y, Qin Z, et al. Dual-branch deep learning with dynamic stage detection for CT tube life prediction[J]. Sensors, 2025, 25 (15): 4790.
Sahu AR, Palei SK, Mishra A. Data-driven fault diagnosis approaches for industrial equipment: a review[J]. Expert Systems: The International Journal of Knowledge Engineering, 2024, 41(2): e13360.1-e13360.29.
Zhong J, Zhang H, Liu Q, et al. Prognosis for filament degradation of X-ray tubes based on IoMT time series data[J]. IEEE Internet of Things Journal, 2025, 12(7): 8084-8094.
0
Views
1
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621