欧盟医疗器械法规对人工智能医疗器械产品的监管分析-国际医学与数据杂志-CSCIED科技核心评价数据库-手机版

欧盟医疗器械法规对人工智能医疗器械产品的监管分析

Regulatory analysis of EU medical device regulations on artificial intelligence medical device products

ES评分 0 浏览量：1203 下载量：5

DOI	10.12208/j.ijmd.20220205
刊名	国际医学与数据杂志 International Journal of Medicine and Data
年，卷(期)	2022, 6(5)
作者	王雅文,刘英慧*,郭兆君,梁宏,盛恒松,
作者单位	国家药品监督管理局医疗器械技术审评中心北京 ;
摘要	基于人工智能和机器学习（Artificial Intelligence and Machine Learning，AI/ML）医疗器械近年来发展迅速。然而，我们对基于AI/ML的医疗器械是如何在欧洲获得批准的情况知之甚少。新的欧洲医疗器械法规（European Medical Device Regulation，EU MDR）的发布实施日期为2021年5月26日，该法规提出了在人工智能软件产品应用于临床实践之前需要满足的相关要求。欧盟在该领域的发展尚处于起步阶段，自2015年以来，欧盟有80多种AI产品上市，临床试验和同品种临床数据分析是主要上市途径，本文从欧盟法规对人工智能医疗器械产品上市的相关要求进行阐述，总结前沿监管思路与方法，以期对我国人工智能产品的监督与管理提供参考。
Abstract	Medical devices based on artificial intelligence and machine learning (AI /ML) have developed rapidly in recent years. However, we know little about how Al /ML based medical devices are approved in Europe. The new European medical device regulation (EU MDR) is issued and implemented on May 26, 2021. The regulation puts forward the relevant requirements to be met before the application of artificial intelligence software products in clinical practice. The development of EU in this field is still in its infancy. Since 2015, more than 80 AI products have been launched in the EU. Clinical trials and clinical data analysis of the same variety are the main ways to launch AI products. This paper expounds the relevant requirements of EU regulations on the launch of AI medical devices, and summarizes the frontier regulatory ideas and methods, In order to provide reference for the supervision and management of artificial intelligence products in China.
关键词	人工智能；机器学习；医疗器械
KeyWord	Artificial intelligence; Machine learning; Medical devices
基金项目
页码	9-14

参考文献
相关文献

[1] Muehlematter U J, Daniore P, Vokinger K N. Approval of artificial intelligence and machine learning-based medical devices in the USA and Europe (2015-20): a comparative analysis[J].Lancet Digit Health,2021,3(3):e195-e203.

[2] Zechendorf E,Vassen P, Zhang J, et al. Heparan Sulfate Induces Necroptosis in Murine Cardiomyocytes: A Medical-In silico Approach Combining Invitro Experiments and Machine Learning[J]. Front Immunol,2018,9:393.

[3] Barragan-Montero A, Javaid U, Valdes G, et al. Artificial intelligence and machine learning for medical imaging: A technology review[J]. Phys Med,2021,83:242-256.

[4] Rahman R, Kodesh A, Levine S Z, et al. Identificationof newborns at risk for autism using electronic medical records and machine learning[J]. Eur Psychiatry,2020,63(1):e22.

[5] Pucchio A, Eisenhauer E A, Moraes F Y. Medical students need artificial intelligence and machine learning training[J]. Nat Biotechnol,2021,39(3):388-389.

[6] Watson J, Hutyra C A, Clancy S M, et al. Overcoming barriers to the adoption and implementation of predictive modeling and machine learning in clinical care: what can we learn from US academic medical centers?[J].JAMIA Open,2020,3(2):167-172.

[7] Beckers R, Kwade Z, Zanca F. The EU medical device regulation: Implications for artificial intelligence-basedmedical device software in medical physics[J]. Phys Med,2021,83:1-8.

[8] Gola M, Capasso L, Mondoni G, et al. From building regulations and local health rules to the new local building codes: a national survey in Italy on the prescriptive and performance requirements for a new performanceapproach[J]. Ann Ig,2020,32(5 Supple 1):36-51.

[9] Awaysheh A, Wilcke J, Elvinger F, et al. Review of Medical Decision Support and Machine-Learning Methods[J]. Vet Pathol,2019,56(4):512-525.

[10] Lo C M, Jack L Y. The use of multimedia medical data and machine learning for various diagnoses[J]. Comput Methods Programs Biomed,2018,165:A1.

[11] Fischer I, Steiger H J. Toward automatic evaluation of medical abstracts: The current value of sentiment analysis and machine learning for classification of the importance of PubMed abstracts of randomized trials for stroke[J]. J Stroke Cerebrovasc Dis,2020,29(9):105042.

[12] Png M E, Dritsaki M, Gray A, et al. Economic evaluation plan of a randomised controlled trial of intra-nodular injection of anti-TNF and placebo among patients with early Dupuytren's disease: Repurposing Anti-TNF for Treating Dupuytren's Disease (RIDD)[J]. Wellcome Open Res,2018,3:156.

[13] Sheppard L, Dewey H, Bernhardt J, et al. Economic Evaluation Plan (EEP) for A Very Early Rehabilitation Trial (AVERT): An international trial to compare the costs and cost-effectiveness of commencing out of bed standing and walking training (very early mobilization) within 24 h of stroke onset with usual stroke unit care[J]. Int J Stroke,2016,11(4):492-494.

[14] Ralbovsky N M, Lednev I K. Towards development ofa novel universal medical diagnostic method: Raman spectroscopy and machine learning[J]. Chem Soc Rev,2020,49(20):7428-7453.

[15] Borakati A. Evaluation of an international medical E-learning course with natural language processing and machine learning[J]. BMC Med Educ,2021,21(1):181.

[16] Monlezun D J, Carr C, Niu T, et al. Meta-analysis andmachine learning-augmented mixed effects cohort analysis of improved diets among 5,847 medical trainees, providers, and patients[J]. Public Health Nutr,2021:1-27

引用本文

王雅文,刘英慧*,郭兆君,梁宏,盛恒松. 欧盟医疗器械法规对人工智能医疗器械产品的监管分析 [J]. 国际医学与数据杂志. 2022; 6; (5). 9 - 14.

文献评论

相关学者

相关机构