
浏览全部资源
扫码关注微信
1.浙江省医疗器械检验研究院有源器械检验研究所,浙江杭州
2.国家药品监督管理局生物医学光学重点实验室,浙江杭州
徐珂,浙江省医疗器械检验研究院有源器械检验研究所主检、工程师,全国外科植入物和矫形器械标准化技术委员会有源植入物分技术委员会(SAC/TC 110/SC4)委员,全国药品监管系统第2批“组团式”柔性援疆人才。先后从事电磁兼容(EMC)、有源医疗器械性能和电气安全、医疗器械可用性工程相关工作,建立了浙江省首个医疗器械可用性工程实验室。GB/T 17626.3-2023《电磁兼容 试验和测量技术 第3部分:射频电磁场辐射抗扰度试验》、YY/T 1992-2025《采用机器人技术的辅助手术设备总结性可用性测试方法》等标准主要起草人,参与多项国家和省级重点研发项目,主持厅局级项目2项。E-mail: xuke@mdst.org.cn
收稿:2026-04-10,
修回:2026-06-24,
录用:2026-07-13,
纸质出版:2026-09-15
移动端阅览
徐珂,王晓丽.脑机接口医疗器械的临床转化瓶颈:人机信任的生成、损耗与修复[J].陆军军医大学学报,2026,48(17):2390-2396.DOI:10.16016/j.2097-0927.202604031.
Xu K,Wang X L.Clinical translation bottlenecks for brain-computer interface medical devices: generation, loss, and repair of human-machine trust[J].J Army Med Univ,2026,48(17):2390-2396.DOI:10.16016/j.2097-0927.202604031.
徐珂,王晓丽.脑机接口医疗器械的临床转化瓶颈:人机信任的生成、损耗与修复[J].陆军军医大学学报,2026,48(17):2390-2396.DOI:10.16016/j.2097-0927.202604031. DOI:
Xu K,Wang X L.Clinical translation bottlenecks for brain-computer interface medical devices: generation, loss, and repair of human-machine trust[J].J Army Med Univ,2026,48(17):2390-2396.DOI:10.16016/j.2097-0927.202604031. DOI:
脑机接口(brain-computer interface,BCI)作为生物医学工程前沿技术,重塑了医疗器械人机交互模式,而人机信任则是制约BCI医疗器械临床转化、规模化落地的核心底层约束。现有研究存在“重硬件性能、轻人机交互信任”的偏向,缺少以人机信任为核心的系统性整合分析,无法解释实验室高性能方案难以长期临床落地的现实痛点。本文以人机信任“生成-损耗-修复”全链条为逻辑主线,分层梳理信号采集、解码算法、双向闭环三大底层技术对人机信任的支撑作用,系统剖析了神经隐私泄露、算法偏见、长期植入炎症、人机身份认同冲突等伦理安全风险对信任体系的破坏机制,归纳出当前技术与伦理治理存在的4类机制性短板,并提出多模态信号融合、自适应可解释学习框架、跨学科协同伦理治理是破解信任困境的3条核心路径。本文结合我国BCI产业“两步走”发展目标与标准化建设进程,提出分阶段中长期发展路线,为搭建覆盖设备全生命周期、兼顾技术可靠与伦理安全的BCI医疗器械人机信任保障体系提供理论支撑与行业监管治理参考。
Brain-computer interface (BCI)
a cutting-edge technology in biomedical engineering
has revolutionized the human-machine interaction paradigm in medical devices. Nevertheless
human-machine trust remains the fundamental constraint hindering the clinical translation and widespread adoption of BCI medical devices. Current research exhibits a bias towards “hardware performance at the expense of human-machine interaction trust”
lacking a systematic and integrated analysis centered on this crucial aspect. This shortcoming fails to elucidate the practical challenges encountered when high-performance laboratory solutions struggle to achieve sustained clinical implementation. In this article
we take the “generation-depletion-repair” lifecycle of human-machine trust as its logical framework
systematically examining the supportive roles of 3 underlying technologies—signal acquisition
decoding algorithms
and bidirectional closed-loop systems—in fostering human-machine trust. We also systematically analyze the disruptive mechanisms of ethical and safety risks
including neural privacy disclosure
algorithmic bias
long-term implantation-induced inflammation
and conflicts in human-machine identity recognition
on the trust system. We further summarize four types of institutional shortcomings in current technological and ethical governance. Three core strategies are proposed to address the trust dilemma: multimodal signal fusion
adaptive interpretable learning frameworks
and interdisciplinary collaborative ethical governance. Aligned with China's "two-step" development strategy and standardization efforts in the BCI industry
we outline a phased medium- to long-term development roadmap
providing theoretical underpinnings and regulatory governance references for establishing a comprehensive BCI medical device human-machine trust assurance system that spans the entire device lifecycle and balances technical reliability with ethical safety.
工业和信息化部 , 国家发展改革委 , 教育部 , 等 . 七部门关于推动脑机接口产业创新发展的实施意见 工信部联科 〔2025〕 164 号[EB/OL]. ( 2025-07-23 )[ 2026-07-24 ]. https://www.gov.cn/zhengce/zhengceku/202508/content_7035603.htm https://www.gov.cn/zhengce/zhengceku/202508/content_7035603.htm .
Ministry of Industry and Information Technology , National Development and Reform Commission , Ministry of Education , et al . Implementation opinions on promoting the innovative development of the Brain-Computer interface industry . MIIT joint scien ce and technology〔2025〕No.164[EB/OL].( 2025-07-23 )[ 2026-07-24 ]. https://www.gov.cn/zhengce/zhengceku/202508/content_7035603.htm https://www.gov.cn/zhengce/zhengceku/202508/content_7035603.htm .
Clément C . Brain-computer interface technologies: accelerating neuro-technology for human benefit [M]. Cham : Springer International Publishing , 2019 . DOI: 10.1007/978-3-030-27852-6 http://dx.doi.org/10.1007/978-3-030-27852-6 .
Benabid A L . Deep brain stimulation for Parkinson’s disease [J]. Curr Opin Neurobiol , 2003 , 13 ( 6 ): 696 - 706 . DOI: 10.1016/j.conb.2003.11.001 http://dx.doi.org/10.1016/j.conb.2003.11.001 .
Della Flora E , Perera C L , Cameron A L , et al . Deep brain stimulation for essential tremor: a systematic review [J]. Mov Disord , 2010 , 25 ( 11 ): 1550 - 1559 . DOI: 10.1002/mds.23195 http://dx.doi.org/10.1002/mds.23195 .
Gouveia F V , Warsi N M , Suresh H , et al . Neurostimulation treatments for epilepsy: Deep brain stimulation, responsive neurostimulation and vagus nerve stimulation [J]. Neurotherapeutics , 2024 , 21 ( 3 ): e00308 . DOI: 10.1016/j.neurot.2023.e00308 http://dx.doi.org/10.1016/j.neurot.2023.e00308 .
Blomstedt P , Sjöberg R L , Hansson M , et al . Deep brain stimulation in the treatment of obsessive-compulsive disorder [J]. World Neurosurg , 2013 , 80 ( 6 ): e245 - e253 . DOI: 10.1016/j.wneu.2012.10.006 http://dx.doi.org/10.1016/j.wneu.2012.10.006 .
Cho N , Squair J W , Aureli V , et al . Hypothalamic deep brain stimulation augments walking after spinal cord injury [J]. Nat Med , 2024 , 30 ( 12 ): 3676 - 3686 . DOI: 10.1038/s41591-024-03306-x http://dx.doi.org/10.1038/s41591-024-03306-x .
Urbaite G . Advancements in neural implants: a systematic review of neuralink-enabled brain-machine communication [J]. Luminis Appl Sci Eng , 2025 , 2 ( 3 ): 46 - 65 . DOI: 10.69760/lumin.2025003004 http://dx.doi.org/10.69760/lumin.2025003004 .
Guger C , Grünwald J , Xu R . Noninvasive and invasive BCIs and hardware and software components for BCIs [M]. Handbook of neuroengineering . Singapore : Springer Singapore , 2020 : 1 - 32 . DOI: 10.1007/978-981-15-2848-4_34-2 http://dx.doi.org/10.1007/978-981-15-2848-4_34-2 .
Chen S G , Chen M Y , Wang X , et al . Brain-computer interfaces in 2023—2024 [J]. Brain-X , 2025 , 3 : e70024 . DOI: 10.1002/brx2.70024 http://dx.doi.org/10.1002/brx2.70024 .
Huang J H , Huang L L , Li Y , et al . A bibliometric analysis of the application of brain-computer interface in rehabilitation medicine over the past 20 years [J]. J Multidiscip Healthc , 2025 , 18 : 1297 - 1317 . DOI: 10.2147/JMDH.S509747 http://dx.doi.org/10.2147/JMDH.S509747 .
Foong R , Ang K K , Quek C , et al . Assessment of the efficacy of EEG-based MI-BCI with visual feedback and EEG correlates of mental fatigue for upper-limb stroke rehabilitation [J]. IEEE Trans Biomed Eng , 2020 , 67 ( 3 ): 786 - 795 . DOI: 10.1109/TBME.2019.2921198 http://dx.doi.org/10.1109/TBME.2019.2921198 .
Dai B , Wang Y J , Mou X Y , et al . A reliability-enhanced brain-computer interface via mixture-of-graphs-driven information fusion [J]. Inform Fusion , 2025 , 120 : 103069 . DOI: 10.1016/j.inffus.2025.103069 http://dx.doi.org/10.1016/j.inffus.2025.103069 .
Wu D R , Xu Y F , Lu B L . Transfer learning for EEG-based brain-computer interfaces: a review of progress made since 2016 [J]. IEEE Trans Cogn Dev Syst , 2022 , 14 ( 1 ): 4 - 19 . DOI: 10.1109/tcds.2020.3007453 http://dx.doi.org/10.1109/tcds.2020.3007453 .
国家药品监督管理局医疗器械技术审评中心 . 关于发布深度学习辅助决策医疗器械软件审评要点的通告(2019年第7号) [EB/OL].( 2019-07-03 )[ 2026-7-26 ]. https://www.cmde.org.cn//xwdt/shpgzgg/gztg/20190703141714991.html https://www.cmde.org.cn//xwdt/shpgzgg/gztg/20190703141714991.html .
Center for Medical Device Evaluation . Notice on issuing the key review points fordeep learning-assisted decision-making medical device software(2019, No.7) [EB/OL].( 2019-07-03 )[ 2026-7-26 ]. https://www.cmde.org.cn//xwdt/shpgzgg/gztg/20190703141714991.html https://www.cmde.org.cn//xwdt/shpgzgg/gztg/20190703141714991.html .
Pan H G , Song H Q , Zhang Q , et al . Review of closed-loop brain-machine interface systems from a control perspective [J]. IEEE Trans Human-Mach Syst , 2022 , 52 ( 5 ): 877 - 893 . DOI: 10.1109/thms.2021.3138677 http://dx.doi.org/10.1109/thms.2021.3138677 .
Ho R T , Xue W , See M K , et al . Advances in clinical brain-computer interfaces for assistive substitution and rehabilitation: a rapid scoping review [J]. Surg Pract , 2025 , 29 ( 1 ): 35 - 49 . DOI: 10.1111/1744-1633.70002 http://dx.doi.org/10.1111/1744-1633.70002 .
李久辉 , 陈建俞 , 安婼娜 , 等 . 伦理审查视角下脑机接口技术和产品的伦理关切 [J]. 医学与哲学 , 2025 , 46 ( 22 ): 13 - 16 . DOI: 10.12014/j.issn.1002-0772.2025.22.03 http://dx.doi.org/10.12014/j.issn.1002-0772.2025.22.03 .
Li J H , Chen J Y , An R N , et al . Ethical dilemmas of brain-computer interface technologies and products from the perspective of ethical review [J]. Med Philos , 2025 , 46 ( 22 ): 13 - 16 . DOI: 10.12014/j.issn.1002-0772.2025.22.03 http://dx.doi.org/10.12014/j.issn.1002-0772.2025.22.03 .
Monti M M , Vanhaudenhuyse A , Coleman M R , et al . Willful modulation of brain activity in disorders of consciousness [J]. N Engl J Med , 2010 , 362 ( 7 ): 579 - 589 . DOI: 10.1056/NEJMoa0905370 http://dx.doi.org/10.1056/NEJMoa0905370 .
Du C D , Du C Y , Huang L J , et al . Reconstructing perceived images from human brain activities with Bayesian deep multiview learning [J]. IEEE Trans Neural Netw Learning Syst , 2019 , 30 ( 8 ): 2310 - 2323 . DOI: 10.1109/tnnls.2018.2882456 http://dx.doi.org/10.1109/tnnls.2018.2882456 .
Gao W H , Yan Z N , Zhou H , et al . Revolutionizing brain-computer interfaces: overcoming biocompatibility challenges in implantable neural interfaces [J]. J Nanobiotechnol , 2025 , 23 ( 1 ): 498 . DOI: 10.1186/s12951-025-03573-x http://dx.doi.org/10.1186/s12951-025-03573-x .
赵继宗 . 对21世纪网络神经外科临床实践的思考 [J]. 空军军医大学学报 , 2024 , 45 ( 4 ): 361 - 363 . DOI: 10.13276/j.issn.2097-1656.2024.04.001 http://dx.doi.org/10.13276/j.issn.2097-1656.2024.04.001 .
Zhao J Z . Reflections on the clinical practice of network neurosurgery in the 21st century [J]. J Air Force Med Univ , 2024 , 45 ( 4 ): 361 - 363 . DOI: 10.13276/j.issn.2097-1656.2024.04.001 http://dx.doi.org/10.13276/j.issn.2097-1656.2024.04.001 .
Luo S Y , Rabbani Q , Crone N E . Brain-computer interface: applications to speech decoding and synthesis to augment communication [J]. Neurotherapeutics , 2022 , 19 ( 1 ): 263 - 273 . DOI: 10.1007/s13311-022-01190-2 http://dx.doi.org/10.1007/s13311-022-01190-2 .
Cao L , Li H , Dong Y L , et al . Few-shot class-incremental learning with dynamic prototype refinement for brain activity classification [J]. IEEE J Biomed Health Inform , 2026 , 30 ( 1 ): 125 - 137 . DOI: 10.1109/JBHI.2025.3605108 http://dx.doi.org/10.1109/JBHI.2025.3605108 .
国家科技伦理委员会人工智能伦理分委员会 . 脑机接口研究伦理指引 [EB/OL].( 2024-02-02 )[ 2026-07-26 ] https://www.most.gov.cn/kjbgz/202402/t20240202_189582.html https://www.most.gov.cn/kjbgz/202402/t20240202_189582.html .
Artificial Intelligence Ethics Subcommittee of National Science and Technology Ethics Committee . Ethics guidelines for brain-computer interface research [EB/OL].( 2024-02-02 )[ 2026-07-26 ]. https://www.most.gov.cn/kjbgz/202402/t20240202_189582.html https://www.most.gov.cn/kjbgz/202402/t20240202_189582.html .
0
浏览量
14
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621