期刊文献+

人工智能医疗器械软件生产质量管理体系特殊要求研究 被引量:5

Study on Special Requirement of Artificial Intelligence Medical Device Quality Management System
下载PDF
导出
摘要 目的人工智能医疗器械产品更新频率远高于传统医疗器械,因此需要建立动态稳健的医疗器械质量管理体系新模式,促进人工智能医疗器械产品健康发展。方法通过讨论人工智能医疗器械的质量管理体系框架,在此基础上,讨论了影响人工智能医疗器械质量的关键因素,设计变更和验证确认环节的控制思路。并对人工智能医疗器械在质量评价过程中需重点关注的内容进行了比较全面的讨论,包括软件可解释性、评价方法和验证及确认方法问题。结果影响人工智能医疗器械质量的关键因素包括设计变更和验证确认环节。同时,软件可解释性、评价方法和验证及确认也需要进行重点关注。结论人工智能医疗器械正处于蓬勃发展期,相应的技术和业态也在不断形成中,需要针对人工智能医疗器械企业需要建立动态稳健的质量管理新模式,在缩短产品迭代更新的研发与验证周期的同时,及时前瞻性地发现算法更新带来的质量风险。 Objective The update frequency of artificial intelligence(AI)medical devices is much higher than that of traditional medical devices.Therefore,it is necessary to establish a new dynamic and stable mode of medical device quality management system to promote the healthy development of AI medical devices.Methods By discussing the framework of quality management system of AI medical devices,the key factors affecting the quality of AI medical devices and the control ideas of design change and validation were discussed.In addition,the key points in the process of quality evaluation of AI medical devices were discussed comprehensively,including software interpretability,evaluation methods,verification and validation methods.Results The key factors affecting the quality of AI medical devices include design change and verification and validation.At the same time,software interpretability,evaluation method,verification and validation also need to be focused on.Conclusion AI medical devices are in a period of vigorous development,and the corresponding technologies and formats are also constantly forming.It is necessary to establish a new dynamic and robust quality management mode for AI medical device enterprises,so as to timely and prospectively discover the quality risks brought by algorithm update while shortening the research and development and verification cycle of product iterative update.
作者 李澍 王浩 王晨希 郝烨 李佳戈 李静莉 LI Shu;WANG Hao;WANG Chenxi;HAO Ye;LI Jiage;LI Jingli(Institute for Medical Devices Control,National Institutes for Food and Drug Control,Beijing 102629,China)
出处 《中国医疗设备》 2021年第9期15-18,22,共5页 China Medical Devices
基金 国家重点研发计划(2019YFC1711702)。
关键词 人工智能 医疗器械 质量管理体系 机器学习 可解释性 artificial intelligence medical devices quality management system machine learning interpretability
  • 相关文献

参考文献8

二级参考文献66

  • 1徐红,钱红兵,陈曦.Ada软件的动态测试技术研究[J].北京航空航天大学学报,1997,23(1):18-24. 被引量:2
  • 2Amato F,Lopez AM,Penamendez EM,et al.Artificial neural networks in medical diagnosis [J] .lAppl Biomed,2013,11 (2):47-58.
  • 3Cooper RA,Dicianno BE,Brewer BR,et al.A perspective on intelligent devices and environments in medical rehabilitation[J]. Med Eng Phys,2008,30(10): 1387-1398.
  • 4Dilsizian SE,Siegel EL.Artificial intelligence in medicine and cardiac imaging: harnessing big data and advanced computing to provide personalized medical diagnosis and treatment[J]. Curr Cardiol Rep,2013,16(1) : 1-8.
  • 5Carmena JM.Advances in neuroprosthetic learning and control[J] .Plos Biol,2013,11 (5):e 1001561.
  • 6Peng X,Lin P, Zhang T, et al.Extreme Learning Machine-based Classification of ADHD Using Brain Structural MRI Data[J]. PLoS One,2013,8( l l ):e794 76.
  • 7Food and Drug Administration.Guidance for Industry and Food and Drug Administration Staff: Computer-Assisted Detection Devices Applied to Radiology Images and Radiology Device Data - Premarket Notification,2012[S].
  • 8Submissions. Food and Drug Administration.Guidance for Industry and FDA Staff: Clinical Performance Assessment: Considerations for Computer-Assisted Detection Devices Applied to Radiology Images and Radiology Device Data-Premarket Approval (PMA) and Premarket Notification,2012[S].
  • 9Bishop CM,Nasrabadi NM.Pattern Recognition and Machine Leaming[J].J Elect imaging,2007,16(4):20-25.
  • 10Hastie T,Tibshirani R,Friedman JH,et al.The elements of statistical learning: data mining, inference, and prediction[J]. Math lntell,2001,27(2): 83-85.

共引文献102

同被引文献47

引证文献5

二级引证文献3

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部