
人工智能辅助诊疗发展现状与战略研究
AI Assisted Clinical Diagnosis & Treatment, and Development Strategy
医疗健康数据的融合、开放共享,利用人工智能对碎片化医学信息进行整理分析,对医疗诊断过程提供辅助,可改善医疗健康服务,促进政府决策合理化,缓解医疗卫生资源配置不均衡问题。本文选取健康医疗信息人机交互、数据智能中的语义理解与医学影像分析等方面,简要阐述了人工智能在辅助诊疗问题上的发展方向与现状,讨论了智能诊疗技术发展与应用的问题与挑战:一是医学信息的标准化表征和结构化整合构建术语标准是关键;二是利用海量医学知识,构建多模态数据采集分析与结构化知识推理相结合的智能诊疗模型是重要的影像智能发展点。建议建立国家级的健康医疗开放大数据云平台,开辟新的数据、信息整合、知识发现及服务市场;构建医疗健康信息的一些基础行业标准,加强国产高端医疗器械的研发力度,推动智能化医疗器械和智能可穿戴式设备的研发,引导产业在人工智能与高端医疗器械的结合上开辟新的市场。
The integration, open accessing of healthcare data, and the use of artificial intelligence to organize and analyze fragmented medical information can improve medical and health services, promote the level of rational government decision-making, and reduce the inequality in the allocation of medical and health resources. This paper summarizes the current status of technologies and applications of artificial intelligence in the field of medical information semantic fusion and in the field of image analysis, and analyzes current problems and challenges. The first is the standardized representation and structural integration of medical information to merge national and widely-used clinical terminologies, which is key to realizing auxiliary diagnosis based on ‘big data’ artificial intelligent. The second is the use of massive medical knowledge to construct an intelligent diagnosis and treatment model with the ability to combine multimodal data analysis and structured knowledge reasoning. Thus, we propose a national-level healthcare open data cloud platform that can help open up new data markets, improve the integration of healthcare data, and provide the new service of knowledge discovery and services. We also suggest to establish some basic industry standards for medical and health information, to strengthen the research and development of domestic medical devices, to promote the development of intelligent medical devices and smart wearable devices, and to guide the industry to open up new markets on the combination of artificial intelligence and medical devices.
人工智能 / 辅助诊疗 / 知识图谱 / 医学本体 / 医学影像分析
artificial intelligence / assisted diagnosis and treatment / knowledge graph / medical ontology / medical image analysis
[1] |
Chen Y, Argentinis J E, Weber G. IBM Watson: How cognitive computing can be applied to big data challenges in life sciences research [J]. Clinical Therapeutics, 2016, 38(4): 688–701.
|
[2] |
Dilsizian S E, Siegel E L. Artificial intelligence in medicine and cardiac imaging: Harnessing big data and advanced computing to provide personalized medical diagnosis and treatment [J]. Current Cardiology Reports, 2014, 16(1): 441.
|
[3] |
Stoitsis J, Valavanis I, Mougiakakou S G, et al. Computer aided diagnosis based on medical image processing and artificial intel-ligence methods [J]. Nuclear Instruments & Methods in Physics Research, 2006, 569(2): 591–595.
|
[4] |
Rotmensch M, Halpern Y, Tlimat A, et al. Learning a health knowledge graph from electronic medical records [J]. Scientific Reports, 2017, 7(1): 5994.
|
[5] |
袁凯琦, 邓扬, 陈道源, 等. 医学知识图谱构建技术与研究进展[J]. 计算机应用研究, 2018, 35(7): 1–11.
|
[6] |
徐增林, 盛泳潘, 贺丽荣, 等. 知识图谱技术综述 [J]. 电子科技大学学报, 2016, 45(4): 589–606.
|
[7] |
Crasto C J, Marenco L N, Liu N, et al. SenseLab: New develop-ments in disseminating neuroscience information [J]. Briefings in Bioinformatics, 2007, 8(3):150–162.
|
[8] |
Donnelly K. SNOMED-CT: The advanced terminology and cod-091中国工程科学 2018 年 第 20 卷 第 2 期ing system for eHealth [J]. Studies in Health Technology & Infor-matics, 2006(121): 279–290.
|
[9] |
Bodenreider O. The Unified Medical Language System (UMLS): Integrating biomedical terminology [J]. Nucleic Acids Research, 2004(32): 267–270.
|
[10] |
阮彤, 孙程琳, 王昊奋, 等. 中医药知识图谱构建与应用 [J]. 医学信息学杂志, 2016, 37(4): 8–13.
|
[11] |
Long E P, Lin H T, Liu Z Z, et al. An artificial intelligence plat-form for the multihospital collaborative management of congenital cataracts [J]. Nature Biomedical Engineering, 2017, 1(2): 0024.
|
[12] |
Xu K, Ba J, Kiros R, et al. Show, attend and tell: Neural image caption generation with visual attention [J]. Computer Science, 2015: 2048–2057.
|
[13] |
Jing B Y, Xie P T, Xing E. On the automatic generation of med-ical imaging reports. 2017 November 22. arXiv preprint arX-iv:1711.08195.
|
[14] |
Turan M, Pilavci Y Y, Jamiruddin R, et al. A fully dense and glob-ally consistent 3D map reconstruction approach for GI tract to en-hance therapeutic relevance of the endoscopic capsule robot. 2017 May 18. arXiv preprint arXiv:1705.06524.
|
[15] |
Turan M, Almalioglu Y, Konukoglu E, et al. A deep learning based 6 degree-of-freedom localization method for endoscopic capsule robots. 2017 May 15. arXiv preprint arXiv:1705.05435.
|
[16] |
Wu G, Kim M, Wang Q, et al. Scalable high performance image registration framework by unsupervised deep feature represen-tations learning [J]. Deep Learning for Medical Image Analysis, 2017, 63(7): 245–269.
|
[17] |
程京, 邢婉丽. 医疗器械与新型穿戴式医疗设备的发展战略研究 [J]. 中国工程科学, 2017, 19(2): 68–71.
|
[18] |
Jha S, Topol E J. Adapting to artificial intelligence: Radiolo-gists and pathologists as information specialists [J]. Jama, 2016, 316(22): 2353.
|
/
〈 |
|
〉 |