可解释人工智能在疾病诊疗中的应用

doi:10.3969/j.issn.1673-8640.2021.09.019

检验医学 ›› 2021, Vol. 36 ›› Issue (9): 976-980.DOI: 10.3969/j.issn.1673-8640.2021.09.019

可解释人工智能在疾病诊疗中的应用

井杰, 王蓓蕾, 刘善荣()

海军军医大学第一附属医院实验诊断科,上海 200433

收稿日期:2021-02-05 出版日期:2021-09-30 发布日期:2021-09-24
通讯作者: 刘善荣
作者简介:刘善荣,E-mail： liushanrong01@126.com。
井杰,男,1992年生,硕士,技师,主要从事检验医学与人工智能相关研究。
基金资助:
上海市优秀学科带头人基金项目(18XD1405300)

Explainable artificial intelligence in disease diagnosis and treatment

JING Jie, WANG Beilei, LIU Shanrong()

Department of Clinical Laboratory,the First Affiliated Hospital of Naval Medical University,Shanghai 200433,China

Received:2021-02-05 Online:2021-09-30 Published:2021-09-24
Contact: LIU Shanrong

摘要/Abstract

摘要：

可解释人工智能（XAI）是基于人工智能（AI）原则构建的可被用户理解和信任的AI系统,在检验医学领域具有广阔的应用前景。文章立足于检验医学的研究现状,结合XAI的基本概念、重要性和实现方法,重点阐述基于知识图谱的XAI技术在检验医学领域的研究思路,并展望检验XAI在疾病诊疗中的应用前景,及其研发面临的挑战和应用局限性。

关键词: 可解释人工智能, 检验医学, 知识图谱

Abstract:

Explainable artificial intelligence（XAI） refers to an artificial intelligence（AI）system based on some AI principles that can be understood and trusted by users,and has broad application prospects in the field of laboratory medicine. This review is based on the research status of clinical laboratory medicine,combined with the basic concepts,importance and implementation methods of XAI,focuses on the research ideas of XAI technology based on knowledge graphs in the field of clinical laboratory medicine,and looks forward to the application prospects of XAI in disease diagnosis and treatment,research challenges and application limitations.

Key words: Explainable artificial intelligence, Clinical Laboratory medicine, Knowledge graph

中图分类号:

R446

井杰, 王蓓蕾, 刘善荣. 可解释人工智能在疾病诊疗中的应用[J]. 检验医学, 2021, 36(9): 976-980.

JING Jie, WANG Beilei, LIU Shanrong. Explainable artificial intelligence in disease diagnosis and treatment[J]. Laboratory Medicine, 2021, 36(9): 976-980.

图/表 1

参考文献 37

[1]	周泉, 齐素文, 肖斌, 等. 人工智能助力检验医学发展[J]. 南方医科大学学报, 2020, 40(2):287-296.
[2]	ZHANG K, LIU X H, SHEN J, et al. Clinically applicable AI system for accurate diagnosis,quantitative measurements,and prognosis of COVID-19 pneumonia using computed tomography[J]. Cell, 2020, 181(6):1423-1433.e11. DOI URL
[3]	ANDRAS I, MAZZONE E, VAN LEEUWEN F W, et al. Artificial intelligence and robotics:a combination that is changing the operating room[J]. World J Urol, 2020, 38(10):2359-2366. DOI URL
[4]	MAK K K, PICHIKA M R. Artificial intelligence in drug development:present status and future prospects[J]. Drug Discov Today, 2019, 24(3):773-780. DOI URL
[5]	SAMEK W, WIEGAND T, MÜLLER K R. Explainable artificial intelligence:understanding,visualizing and interpreting deep learning models[J]. ITU Journal:ICT Discoveries, 2017(Special Issue Ⅰ):39-48.
[6]	DOSHI-VELEZ F, KIM B. Towards a rigorous science of interpretable machine learning[J]. arXiv, 2017.
[7]	DESAI P, MENCIA-TRINCHANT N, SAVENKOV O, et al. Somatic mutations precede acute myeloid leukemia years before diagnosis[J]. Nat Med, 2018, 24(7):1015-1023. DOI URL
[8]	THOMAS L, THOMAS C. Evidence-based laboratory medicine[J]. Clin Lab, 2001, 47(9-10):479-482.
[9]	BADRICK T. Evidence-based laboratory medicine[J]. Clin Biochem Rev, 2013, 34(2):43-46.
[10]	GREAVES R F, BERNARDINI S, FERRARI M, et al. Key questions about the future of laboratory medicine in the next decade of the 21st century:a report from the IFCC-Emerging Technologies Division[J]. Clin Chim Acta, 2019, 495:570-589. DOI URL
[11]	AHMADIAN L, ENGEN-VERHEUL M V, BAKHSHI-RAIEZ F, et al. The role of standardized data and terminological systems in computerized clinical decision support systems:Literature review and survey[J]. Int J Med Inform, 2011, 80:81-93. DOI URL
[12]	BAILEY A L, LEDEBOER N, BURNHAM C D. Clinical microbiology is growing up:the total laboratory automation revolution[J]. Clin Chem, 2019, 65(5):634-643. DOI URL
[13]	GENZEN J R, BURNHAM C D, FELDER R A, et al. Challenges and opportunities in implementing total laboratory automation[J]. Clin Chem, 2018, 64(2):259-264. DOI URL
[14]	HALLWORTH M J, EPNER P L, EBERT C, et al. Current evidence and future perspectives on the effective practice of patient-centered laboratory medicine[J]. Clin Chem, 2015, 61(4):589-599. DOI URL
[15]	LUO Y, SZOLOVITS P, DIGHE A S, et al. Using machine learning to predict laboratory test results[J]. Am J Clin Pathol, 2016, 145(6):778-788. DOI URL
[16]	ARRIETA A B, DÍAZ-RODRÍGUEZ N, SER J D, et al. Explainable artificial intelligence(XAI):concepts,taxonomies,opportunities and challenges toward responsible AI[J]. Information Fusion, 2020, 58:82-115. DOI URL
[17]	贾音, 孙婷婷, 刘海东, 等. 常规检验大数据在胃癌早期诊断中的应用[J]. 中华检验医学杂志, 2021, 44(3):197-203.
[18]	GUNAR G, KUKAR M, NOTAR M, et al. An application of machine learning to haematological diagnosis[J]. Sci Rep, 2018, 8(1):411. DOI URL
[19]	BASTANI O, KIM C, BASTANI H. Interpretability via model extraction[J]. arXiv, 2017.
[20]	FRIEDMAN J H. Greedy function approximation:a gradient boosting machine[J]. Ann Stat, 2001, 29(5):1189-1232. DOI URL
[21]	GOLDSTEIN A, KAPELNER A, BLEICH J, et al. Peeking inside the black box:visualizing statistical learning with plots of individual conditional expectation[J]. J Comput Graph Stat, 2015, 24(1):44-65. DOI URL
[22]	ZHANG Y, WALLACE B. A sensitivity analysis of(and practitioners' guide to) convolutional neural networks for sentence classification[J]. arXiv, 2015.
[23]	BACH S, BINDER A, MONTAVON G, et al. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation[J]. PLoS One, 2015, 10(7):e0130140. DOI URL
[24]	吴飞, 廖彬兵, 韩亚洪. 深度学习的可解释性[J]. 航空兵器, 2019, 26(1):39-46.
[25]	ADADI A, BERRADA M. Peeking inside the black-box:a survey on explainable artificial intelligence(XAI)[J]. IEEE Access, 2018, 6:52138-52160. DOI URL
[26]	GURUMOORTHY K S, DHURANDHAR A, CECCHI G. ProtoDash:fast interpretable prototype selection[J]. arXiv, 2017.
[27]	WACHTER S, MITTELSTADT B, RUSSELL C. Counterfactual explanations without opening the black box:automated decisions and the GDPR[J]. Harvard Journal of Law & Technology, 2018, 31(2):841-887.
[28]	LIN Y K, WANG C F, CHANG C Y, et al. An efficient framework for counting pedestrians crossing a line using low-cost devices:the benefits of distilling the knowledge in a neural network[J]. Multimed Tools Appl, 2021, 80:4037-4051. DOI URL
[29]	王华珍, 金雅妮, 何霆, 等. 一种基于LIS的医学检验知识图谱构建方法:201910284604.6[P]. 2019-07-26.
[30]	张钹, 朱军, 苏航. 迈向第三代人工智能[J]. 中国科学(信息科学), 2020, 50(9):1281-302.
[31]	姜国睿, 陈晖, 王姝歆. 人工智能的发展历程与研究初探[J]. 计算机时代, 2020, 38(9):7-10.
[32]	ESTEVA A, ROBICQUET A, RAMSUNDAR B, et al. A guide to deep learning in healthcare[J]. Nat Med, 2019, 25(1):24-29.
[33]	LOUIS D N, GERBER G K, BARON J M, et al. Computational pathology:an emerging definition[J]. Arch Pathol Lab Med, 2014, 138(9):1133-1138. DOI URL
[34]	NAUGLER C, CHURCH D L. Automation and artificial intelligence in the clinical laboratory[J]. Crit Rev Clin Lab Sci, 2019, 56(2):98-110. DOI URL
[35]	OOSTERHUIS W. Adding clinical utility to the laboratory reports:automation of interpretative comments[J]. Clin Chem Lab Med, 2019, 57(3):365-370. DOI URL
[36]	KESSEL K A, COMBS S E. Review of developments in electronic,clinical data collection,and documentation systems over the last decade-are we ready for big data in routine health care?[J]. Front Oncol, 2016, 6:75.
[37]	王蓓蕾, 刘善荣. 人工智能在检验医学的应用与展望[J]. 中华检验医学杂志, 2020, 43(12):1150-1155.

可解释人工智能在疾病诊疗中的应用

Explainable artificial intelligence in disease diagnosis and treatment

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 1

参考文献 37

相关文章 11

编辑推荐

Metrics

[1]	刘庆香, 张天娇, 龙琪琛, 周伟燕, 张传宝. 参考物质互通性评价方案[J]. 检验医学, 2021, 36(3): 245-249.
[2]	唐利萍, 刘明锦, 刘冠财, 鄢中华, 蔡华, 杨涛, 孙可其. 医学参考系统在我国IVD企业的应用与思考[J]. 检验医学, 2021, 36(3): 250-254.
[3]	李卿, 居漪, 金中淦, 虞啸炫, 欧元祝, 唐立萍, 王美娟, 刘文斌. 糖化血红蛋白IFCC参考方法及实验室网络比对[J]. 检验医学, 2016, 31(7): 607-609.
[4]	崔巍, 郭野. 从D-二聚体检测体系的变更谈检验与临床沟通[J]. 检验医学, 2015, 30(4): 311-313.
[5]	马硝惟, 秦娟秀, 何磊, 李敏. 建立以检验医师为核心的临床沟通制度[J]. 检验医学, 2015, 30(1): 64-67.
[6]	姜敏;储怡星;范基农;龚晓霖;陈悦. 《检验医学》2004至2007年载文被引分析[J]. 检验医学, 2009, 24(01): 81-84.
[7]	张芳;金仲品. 纳米材料与检验医学[J]. 检验医学, 2007, 22(04): 511-513.
[8]	吴茅;刘建栋;周永列. 新时期医学检验实习生综合管理办法及保证措施[J]. 检验医学, 2005, 20(06): 593-594.
[9]	曹秀华;王成英;刘克莉;崔秀明. 检验医学的发展现状及所面临的挑战[J]. 检验医学, 2004, 19(06): 566-568.
[10]	李萍;刘关键. 循证检验与诊断[J]. 检验医学, 2003, 18(03): 187-191.
[11]	李珉珉;孙蓓. DNA芯片与检验医学的发展[J]. 检验医学, 2001, 16(01): 51-53.