医学人工智能标准体系：历史与现状

郑欣雅; 黄运有; 张奕婷; 翁晟杰; 詹剑锋; 张知非

doi:10.12290/xhyxzz.2023-0428

医学人工智能标准体系：历史与现状

doi: 10.12290/xhyxzz.2023-0428

1.
首都医科大学基础医学院，北京 100069
2.
广西师范大学计算机科学与工程学院，广西桂林 541000
3.
中国科学院计算技术研究所先进计算机系统研究中心，北京 100086

基金项目:

中国科学院战略性先导科技专项 XDA0320000

中国科学院战略性先导科技专项 XDA0320300

广西科技计划项目-电力数据分析研究 GuiKe AD20297004

详细信息

通讯作者:
张知非, E-mail: zhifeiz@ccmu.edu.cn

中图分类号: R3; TP18
计量
- 文章访问数: 448
- HTML全文浏览量: 91
- PDF下载量: 191
- 被引次数: 0
出版历程
- 收稿日期: 2023-09-11
- 录用日期: 2023-10-30
- 刊出日期: 2023-11-30

Medical Artificial Intelligence Standard System: History and Current Status

1.
Capital Medical University School of Basic Medical Sciences, Beijing 100069, China
2.
School of Computer Science and Engineering, Guangxi Normal University, Guilin, Guangxi 541000, China
3.
Research Center for Advanced Computer Systems, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100086, China

Funds:

Strategic Priority Research Program of the Chinese Academy of Sciences XDA0320000

Strategic Priority Research Program of the Chinese Academy of Sciences XDA0320300

Guangxi Science and Technology Electric Power Data Analysis Research GuiKe AD20297004

More Information

Corresponding author: ZHAGN Zhifei, E-mail: zhifeiz@ccmu.edu.cn

摘要

摘要: 当前医学人工智能标准化进程尚处于萌芽阶段，难以满足医学人工智能产品在研发、部署、管控、评估以及指导等多方面的需求。这一方面导致人工智能产品的研发过程难以规范化，增加了研发成本，影响了产品质量；另一方面也造成了人工智能产品难以进行统一的交互、比较和评价，可能导致产品被错误评估，从而误导医学人工智能产品的研发方向，因此建立成熟统一的医学人工智能标准体系成为当务之急。为推动医学人工智能标准体系从萌芽阶段走向成熟，本文从医学数据标准、标准数据集、基准和规范/指南4个方面深入分析医学人工智能标准的发展历程，揭示当前医学人工智能标准中存在的问题，以期为相关研究提供参考和借鉴。
- 医学人工智能标准体系 /
- 数据标准 /
- 标准数据集 /
- 测试基准 /
- 规范
Abstract: The standardization of medical artificial intelligence (AI) is currently in its infancy and falls short of meeting the needs for the development, deployment, control, assessment, and guidance of medical AI products. This not only makes it difficult to standardize the research and development process and therefore increase the cost and affect the quality of the products, but also leads to challenges in achieving unified interaction, comparison, and evaluation of AI products. It may result in incorrect estimation and evaluation of products, thus misguiding the direction of medical AI development. Consequently, establishing a mature and unified standard system for medical AI has become an urgent priority. To facilitate the advancement of the medical AI standard system from its nascent stage to maturity, we conduct an in-depth analysis of the development history of medical AI standards from four aspects: medical data standards, standard datasets, benchmarks, and norms/guidelines. By revealing the problems in the current medical AI standards, we aim to provide a reference for related research.
- medical artificial intelligence standard system /
- data standards /
- standard datasets /
- testing bench-marks /
- guidelines
注释:

作者贡献：郑欣雅负责数据处理、撰写论文；黄运有负责论文修订；张奕婷、翁晟杰负责文献检索；张知非、詹剑锋提出选题思路、修订和审校论文。

利益冲突：所有作者均声明不存在利益冲突

HTML全文

参考文献(37)

[1]	Shehab M, Abualigah L, Shambour Q, et al. Machine learning in medical applications: A review of state-of-the-art methods[J]. Comput Biol Med, 2022, 145: 105458. doi: 10.1016/j.compbiomed.2022.105458
[2]	Rajpurkar P, Chen E, Banerjee O, et al. AI in health and medicine[J]. Nat Med, 2022, 28: 31-38. doi: 10.1038/s41591-021-01614-0
[3]	Varma JR, Fernando S, Ting BY, et al. The Global Use of Artificial Intelligence in the Undergraduate Medical Curriculum: A Systematic Review[J]. Cureus, 2023, 15: e39701.
[4]	Grunhut1 J, Marques O, WyattNeeds ATM. Challenges, and Applications of Artificial Intelligence in Medical Education Curriculum[J]. JMIR Med Educ, 2022, 8: e35587. doi: 10.2196/35587
[5]	Sim JZT, Fong QW, Huang W, et al. Machine learning in medicine: what clinicians should know[J]. Singapore Med J, 2023, 64: 91-97.
[6]	国家药品监督管理局. 人工智能医疗器械质量要求和评价第4部分: 可追溯性[EB/OL]. (2023-09-05)[2023-11-10]. https://std.samr.gov.cn/hb/search/stdHBDetailed?id=05E9A95426E17056E06397BE0A0A1931.
[7]	史雪莲, 陈敏. 医疗人工智能标准体系研究[J]. 中国卫生信息管理杂志, 2019, 12: 759-762. https://www.cnki.com.cn/Article/CJFDTOTAL-WSGL201906027.htm
[8]	张知非, 杨郑鑫, 黄运有, 等. 医学大数据与人工智能标准体系: 现状、机遇与挑战[J]. 协和医学杂志, 2021, 12: 614-620. doi: 10.12290/xhyxzz.2021-0472
[9]	马琳, 邓宏勇. 国内外临床研究元数据标准: 特点及现状[J]. 中国循证医学杂志, 2023, 23: 478-484. https://www.cnki.com.cn/Article/CJFDTOTAL-ZZXZ202304009.htm
[10]	周晓梅, 李烁, 崇雨田, 等. 临床研究数据标准化工作的思考[J]. 临床内科杂志, 2022, 39: 790-792. https://www.cnki.com.cn/Article/CJFDTOTAL-LCLZ202211024.htm
[11]	Lee AJ, Kim KW, Shin Y, et al. CDISC-compliant clinical trial imaging management system with automatic verification and data Transformation: Focusing on tumor response assessment data in clinical trials[J]. J Biomed Inform, 2021, 117: 103782. doi: 10.1016/j.jbi.2021.103782
[12]	Duda SN, Kennedy N, Conway D, et al. HL7 FHIR-based tools and initiatives to support clinical research: a scoping review[J]. J Am Med Inform Assoc, 2022, 29: 1642-1653. doi: 10.1093/jamia/ocac105
[13]	Ayaz M, Pasha MF, Alzahrani MY, et al. The Fast Health Interoperability Resources (FHIR) Standard: Systematic Literature Review of Implementations, Applications, Challenges and Opportunities[J]. JMIR Med Inform, 2021, 9: e21929. doi: 10.2196/21929
[14]	张丽鑫, 钱庆, 唐明坤, 等. 人工智能医疗器械标准数据集构建现状[J]. 中华医学图书情报杂志, 2021, 30: 1-8. https://www.cnki.com.cn/Article/CJFDTOTAL-YXTS202108001.htm
[15]	Wu B, Fu L, Guo X, et al. Multi-omics profiling and digital image analysis reveal the potential prognostic and immunotherapeutic properties of CD93 in stomach adenocarcinoma[J]. Front Immunol, 2023, 25: 984816.
[16]	石镇维, 刘再毅. 重视医学影像人工智能数据库的标准化建设[J]. 协和医学杂志, 2021, 12: 599-601. doi: 10.12290/xhyxzz.2021-0507
[17]	马兆毅, 蒋薇, 宋超, 等. 肺部病变多模态影像和乳腺癌X线医学人工智能标准数据集研究[J]. 科技成果管理与研究, 2023, 18: 89-91.
[18]	王辉, 刘靖雅, 李哲, 等. 人工智能心电数据库的研究与应用[J]. 中国医疗设备, 2020, 35: 17-22. https://www.cnki.com.cn/Article/CJFDTOTAL-YLSX202010003.htm
[19]	Yoo H, Yum Y, Park SW, et al. Standardized Database of 12-Lead Electrocardiograms with a Common Standard for the Promotion of Cardiovascular Research: KURIAS-ECG[J]. Healthc Inform Res, 2023, 29: 132-144.
[20]	于伟泓, 张潇, 吴婵, 等. 糖尿病视网膜病变眼底彩照人工智能研究标准数据库的建立规范[J]. 协和医学杂志, 2021, 12: 684-688. doi: 10.12290/xhyxzz.2021-0613
[21]	中华医学会外科学分会外科手术学学组, 中华医学会器官移植学分会肝移植学组, 中国医师协会器官移植医师分会移植免疫学专业委员会. 肝脏移植标准数据集[J]. 器官移植, 2020, 11: 126-175. https://www.cnki.com.cn/Article/CJFDTOTAL-QGYZ202001021.htm
[22]	Zhou N, Yuan X, Du Q, et al. FerrDb V2: update of the manually curated database of ferroptosis regulators and ferroptosis-disease associations[J]. Nucleic Acids Res, 2023, 51: D571-D582.
[23]	Kaushal A, Altman R, Langlotz, C. Geographic distribution of US cohorts used to train deep learning algorithms[J]. J Am Med Assoc, 2020, 324: 1212-1213.
[24]	WHO. WHO Issues First Global Report on Artificial Intelligence (AI) in Health and Six Guiding Principles for Its Design and Use[EB/OL]. (2021-08-28)[2023-11-10]. https://www.who.int/news/item/28-06-2021-who-issues-first-global-report-on-ai-in-health-and-six-guiding-principles-for-its-design-and-use.
[25]	Blagec K, Kraiger J, Frühwirt W, et al. Benchmark datasets driving artificial intelligence development fail to capture the needs of medical professionals[J]. J Biomed Inform, 2023, 137: 104274.
[26]	Gao Y, Dligach D, Miller T, et al. DR. BENCH: Diagno-stic Reasoning Benchmark for Clinical Natural Language Processing[J]. J Biomed Inform, 2023, 138: 104286.
[27]	Karargyris A, Umeton R, Sheller MJ, et al. Federated benchmarking of medical artificial intelligence with MedPerf[J]. Nat Mach Intell, 2023, 5: 799-810.
[28]	Werdiger F, Visser M, Bivard A, et al. Benchmark dataset for clot detection in ischemic stroke vessel-based imaging: CODEC-Ⅳ[J]. Neuroimage, 2023, 271: 119985.
[29]	Wagner M, Müller-Stich BP, Kisilenko A, et al. Compara-tive validation of machine learning algorithms for surgical workflow and skill analysis with the HeiChole benchmark[J]. Med Image Anal, 2023, 86: 102770.
[30]	Singhal K, Azizi S, Tu T, et al. Large language models encode clinical knowledge[J]. Nature, 2023, 620: 172-180.
[31]	Walker HL, Ghani S, Kuemmerli C, et al. Reliability of Medical Information Provided by ChatGPT: Assessment Against Clinical Guidelines and Patient Information Quality Instrument[J]. J Med Internet Res, 2023, 25: e47479.
[32]	Biever C. The easy intelligence tests that AI chatbots fail[J]. Nature, 2023, 619: 686-689.
[33]	李志勇, 邱晓岚, 杨建龙, 等. WHO《为基于人工智能的医疗设备生成证据: 训练、验证和评估框架》解析及其对我国医学装备行业的启示[J]. 中国医学装备, 2022, 19: 157-167. https://www.cnki.com.cn/Article/CJFDTOTAL-YXZB202207034.htm
[34]	Niemiec E. Will the EU Medical Device Regulation help to improve the safety and performance of medical AI devices?[J]. Digit Health, 2022, 30: 20552076221089079.
[35]	国家标准化管理委员会. 信息技术人工智能平台计算资源规范[EB/OL]. (2022-10-12)[2023-11-10]. https://std.samr.gov.cn/gb/search/gbDetailed?id=EB58F4DA9161B2A2E05397BE0A0A7D33.
[36]	国务院. 关于加强科技伦理治理的意见[EB/OL]. (2022-03-20)[2023-11-10]. https://www.gov.cn/zhengce/2022-03/20/content_5680105.htm.
[37]	国务院. 生成式人工智能服务管理暂行办法[EB/OL]. (2023-07-10)[2023-11-10]. https://www.gov.cn/zhengce/zhengceku/202307/content_6891752.htm.

施引文献

资源附件(0)

访问统计

点击查看大图

计量

文章访问数: 448
HTML全文浏览量: 91
PDF下载量: 191
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

地址：	北京市东城区帅府园1号北京协和医院老楼7号楼 3层302室《协和医学杂志》编辑部
电话：	010-69154261/4262
E - mail：	medj@pumch.cn mjpumch@126.com
期刊网站版权所有：	《协和医学杂志》编辑部京ICP备 11002662

留言板

医学人工智能标准体系：历史与现状

doi: 10.12290/xhyxzz.2023-0428

通讯作者:
张知非, E-mail: zhifeiz@ccmu.edu.cn

计量

Medical Artificial Intelligence Standard System: History and Current Status

Corresponding author: ZHAGN Zhifei, E-mail: zhifeiz@ccmu.edu.cn

计量

目录

留言板

医学人工智能标准体系：历史与现状

doi: 10.12290/xhyxzz.2023-0428

通讯作者: 张知非, E-mail: zhifeiz@ccmu.edu.cn

计量

出版历程

Medical Artificial Intelligence Standard System: History and Current Status

Corresponding author: ZHAGN Zhifei, E-mail: zhifeiz@ccmu.edu.cn

计量

出版历程

目录

通讯作者:
张知非, E-mail: zhifeiz@ccmu.edu.cn