机器学习对关键医疗器械备件可用性的影响:受监督的机器学习视角
F H P A Dattu1,2, S T Syed Shazali2, S J Tanjong2
1Faculty of Engineering and Technology, i-CATS University College, Kuching, Malaysia.
International journal of health care quality assurance
|December 15, 2025
概括
这项研究将故障模式和效应分析 (FMEA) 与机器学习 (ML) 结合起来,以预测医疗设备故障,改善备件管理和减少医院停机时间,以改善患者护理.
科学领域:
- 生物医学工程 生物医学工程
- 医疗保健管理的管理
- 可靠性工程可靠性工程
背景情况:
- 关键医疗设备需要强有力的维护策略,以确保患者安全和运营效率.
- 传统的维护方法往往难以预测故障和有效管理备件库存.
- 集成高级分析为优化医疗设备管理提供了潜在的潜力.
研究的目的:
- 通过预测性备件管理,提高关键医疗设备的可靠性和运行质量.
- 为了减少设备停机时间,并优化医院环境中的维护计划.
- 通过先进的决策支持系统,提高整体医疗保健服务质量.
主要方法:
- 一种混合方法,将故障模式和效应分析 (FMEA) 与监督机器学习 (ML) 模型 (随机森林,人工神经网络,支持矢量机器) 结合起来.
- 分析了来自六家医院的各种医疗设备的2800份维护记录.
- 由FMEA衍生出的风险优先级号码 (RPN) 用作ML模型的输入特征,具有严格的超参数调整和交叉验证.
主要成果:
- 机器学习模型表现出高性能,随机森林和人工神经网络达到1.00准确度,支持矢量机器显示回忆率为0.94.
- 综合的FMEA-ML模型将医院的备件可用性提高了约12-15%.
- 预测分析成功加强了维护可追溯性,并确保了患者护理设备的连续性.
结论:
- 混合FMEA-ML模型为生物医学工程部门的维护规划提供了数据驱动的方法.
- 实施导致尽量减少停机时间,增强患者安全,并改善对医疗保健质量标准的遵守 (ISO 13485,JCI).
- 这种方法与联合国"健康与福祉可持续发展目标" (SDG3) 和"负责任的消费与生产" (SDG12) 一致.
相关概念视频
Issues And Trends In Healthcare Delivery System
6.1K
The issues and trends in healthcare delivery are constantly changing. The COVID-19 pandemic is one recent issue that wreaked havoc on healthcare systems, causing a shortage of healthcare workers, high demand for medicines and supplies, and increased medical expenditure due to a lack of insurance. Other issues include rising healthcare costs and care fragmentation.
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
6.1K
Steps in Outbreak Investigation
468
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
468

