Progress and Challenges in the Clinical Translation of Invasive Brain-Computer Interfacesfor Rehabilitation of Neurological Dysfunction
Shen Zijian1, Hu Feng1*, Shu Kai1, Wu Dongrui2*
1(Department of Neurosurgery, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430030, China) 2(Hubei Key Laboratory of Brain-Inspired Intelligent Systems, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology,Wuhan 430074, China)
Abstract：Brain-computer interfaces(BCIs), a frontier interdisciplinary technology that connects the brain to external devices, have achieved breakthrough advances in the diagnosis, treatment, and rehabilitation of neurological diseases. In particular, invasive BCIs (iBCIs), with their exceptionally high spatiotemporal resolution and superior signal-to-noise ratio, have become a pivotal technological pathway for tackling severe neurological dysfunctions such as stroke, severe spinal cord injury, and amyotrophic lateral sclerosis(ALS). During the 2024—2026 critical window for global clinical translation of the BCI industry, China has achieved multiple significant breakthroughs in core minimally invasive hardware development, adaptive neural decoding algorithms, the establishment of multicenter clinical trial platforms, and the development of ethical and regulatory standards. Building on the foundational scientific discoveries and prospective clinical trial data from recent leading research teams at home and abroad, this review systematically surveys the latest progress in iBCI core hardware fabrication and the evolution of signal decoding theory; examines in depth the landmark achievements across the three key areas of clinical translation-motor function restoration, speech-assisted communication, and neural function modulation; and comprehensively assesses the evolution of current multicenter clinical research designs, the reconstruction of rehabilitation efficacy evaluation systems, and the ongoing development of a collaborative governance framework integrating technology, clinical practice, ethics, and regulation. This work aims to provide a systematic academic reference for future basic research and large-scale clinical application in this field.
通讯作者:*伍冬睿,华中科技大学卓越首席教授、博导,人工智能与自动化学院副院长、图像信息处理与智能控制教育部重点实验室副主任。2023年入选IEEE Fellow,2023年起担任中国科学院一区TOP、中国自动化学会A+期刊IEEE模糊系统汇刊(IF=11.9)主编。主持国家自然科学基金委员会青A项目及青年千人项目。主要研究迁移学习、深度学习、主动学习、集成学习等高级机器学习方法,及精准、安全、隐私保护的脑电信号解码。出版学术专著《Perceptual Computing》(Wiley-IEEE出版社),发表 Proceedings of the IEEE、IEEE TPAMI、NationalScience Review 等SCI论文100余篇,ESI高引13篇,谷歌学术总引用1.9万余次(H=72)。连续6年入选斯坦福大学全球前2%科学家榜单,入选ScholarGPS全球前0.05%科学家榜单。E-mail: drwu@hust.edu.cn。胡峰,现任华中科技大学同济医学院附属同济医院 神经外科癫痫外科与脑机接口中心负责人,脑机接口临床研究型病房主任、副教授、副主任医师、硕士生导师,从事神经外科临床及科研工作。擅长神经外科医工结合方向,完成湖北省内首例机器人辅助脑深部电极植入手术、首例磁共振引导颅内癫痫和肿瘤激光消融手术、首例运动皮层电刺激手术。于2025年6月完成华中地区首例植入式脑机接口手术。担任中国医师协会神经调控专业委员会癫痫学组组员、中国抗癫痫协会青年委员会委员、中国抗癫痫协会术前评估与手术技术专委会委员等职务。在Neuro-oncology等期刊发表第一及通讯作者SCI文章13篇,最高影响因子14.9分,被引300余次。E-mail: hufeng@tjh.tjmu.edu.cn
引用本文:
沈子健, 胡峰, 舒凯, 伍冬睿. 侵入式脑机接口在神经功能障碍康复中的临床转化进展与挑战[J]. 中国生物医学工程学报, 2026, 45(4): 405-415.
Shen Zijian, Hu Feng, Shu Kai, Wu Dongrui. Progress and Challenges in the Clinical Translation of Invasive Brain-Computer Interfacesfor Rehabilitation of Neurological Dysfunction. Chinese Journal of Biomedical Engineering, 2026, 45(4): 405-415.
[1] Feigin VL, Nichols E, Alam T, et al. Global, regional, and national burden of neurological disorders, 1990-2016: a systematic analysis for the global burden of disease study 2016[J]. The Lancet Neurology, 2019, 18(5): 459-480. [2] Rubiano AM, Carney N, Chesnut R, et al. Global neurotrauma research challenges and opportunities[J]. Nature, 2015, 527(7578): S193-S197. [3] Wei Rongman. Application of Brain-computer interface in post-stroke disease rehabilitations[J]. Theoretical and Natural Science, 2025, 133(1): 9-14. [4] Zhang Hongyu, Jiao Le, Yang Songxiang, et al. Brain-computer interfaces: the innovative key to unlocking neurological conditions[J]. International Journal of Surgery, 2024, 110(9): 5745-5762. [5] Chaudhary U, Birbaumer N, Ramos-Murguialday A. Brain-computer interfaces for communication and rehabilitation[J]. Nature Reviews Neurology, 2016, 12(9): 513-525. [6] Schwartz AB, Cui XT, Weber DJ, et al. Brain-controlled interfaces: movement restoration with neural prosthetics[J]. Neuron, 2006, 52(1): 205-220. [7] 陈小刚, 杨晨, 陈菁菁, 等. 脑机接口技术发展新趋势—基于2019-2020年研究进展[J]. 科技导报, 2021, 39(19): 56-65. [8] Mokienko OA. Invasive brain-computer interfaces: 25 years of clinical trials, scientific and practical issues[J]. Annals of the Russian Academy of Medical Sciences, 2025, 79(5): 424-431. [9] Dubynin I, Zemlyanskov M, Shalayeva I, et al. Neural-computer interfaces: theory, practice, perspectives[J]. Applied Sciences, 2025, 15(16): 8900. [10] Lebedev MA, Nicolelis MA. Brain-machine interfaces: from basic science to neuroprostheses and neurorehabilitation[J]. Physiological Reviews, 2017, 97(2): 767-837. [11] 陈琪, 袁天蔚, 张丽雯, 等. 脑机接口医学应用的研发现状与趋势[J]. 生物医学工程学杂志, 2023,40(3): 566-572. [12] 田甜, 周泽峰, 张鑫衍, 等. 脑机接口技术在医疗器械领域的应用及发展思考[J]. 中国医疗器械信息, 2025, 31(21): 1-3. [13] Fang Runjiu, Tian Huihui, Du Yan, et al. Flexible kirigami microelectrode arrays for neuronal activity recordings in non-human primate brains[J]. Nature Electronics, 2026, 9(2): 112-124. [14] 耿挺. 上海团队完成侵入式脑机接口迭代跨越[N]. 上海科技报, 2025-12-18: 1. [15] 刘苏雅. 我国开展首例侵入式脑机接口临床试验[N]. 北京日报, 2025-6-14: 3. [16] 姚国章. 脑机接口发展进展与典型案例研究[J]. 南京医科大学学报(社会科学版), 2025, 25(2): 105-112. [17] Hochberg LR, Bacher D, Jarosiewicz B, et al. Reach and grasp by people with tetraplegia using a neurally controlled robotic arm[J]. Nature, 2012, 485(7398): 372-375. [18] Rubin DB, Ajiboye AB, Barefoot L, et al. Interim safety profile from the feasibility study of the BrainGate Neural Interface System[J]. Neurology, 2023, 100(11): e1177-e1185. [19] Hou Zhichao. Advancements in flexible electrode implantation for invasive brain-computer interfaces[J]. Highlights in Science, Engineering and Technology, 2025, 125: 55-65. [20] Jung T, Zeng N, Fabbri JD, et al. A wireless subdural-contained brain-computer interface with 65,536 electrodes and 1,024 channels[J]. Nature Electronics, 2025, 8(12): 1272-1288. [21] Benabid AL, Costecalde T, Eliseyev A, et al. An exoskeleton controlled by an epidural wireless brain-machine interface in a tetraplegic patient: a proof-of-concept demonstration[J]. The Lancet Neurology, 2019, 18(12): 1112-1122. [22] Mitchell P, Lee SCM, Yoo PE, et al. Assessment of safety of a fully implanted endovascular brain-computer interface for severe paralysis in 4 patients: the stentrode with thought-controlled digital switch (SWITCH) study[J]. JAMA Neurology, 2023, 80(3): 270. [23] He Qiheng, Yang Yi, Ge Peicong, et al. The brain nebula: minimally invasive brain-computer interface by endovascular neural recording and stimulation[J]. Journal of NeuroInterventional Surgery, 2024, 16(12): 1237-1243. [24] Putrino D, Majidi S, Harel N, et al. 47238 results of the command trial: an early feasibility study of the synchron endovascular brain-computer interface[J]. Neurosurgery, 2025, 71(Suppl 1): 281-281. [25] Li Sining, Liu Gan, Feng Fan, et al. An interventional brain-computer interface for long-term EEG collection and motion classification of a quadruped mammal[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2025, 33: 1633-1642. [26] Shaeri MA, Shin U, Yadav A, et al. 33.3 MiBMI: a 192/512-channel 2.46 mm2 miniaturized brain-machine interface chipset enabling 31-class brain-to-text conversion through distinctive neural codes[C]//2024 IEEE International Solid-State Circuits Conference (ISSCC). San Francisco, CA, USA: IEEE, 2024: 546-548. [27] Yang Jie, Sawan M. Systems-on-chips for invasive brain-computer interfaces: challenges and opportunities[C]//2024 IEEE 17th International Conference on Solid-State & Integrated Circuit Technology (ICSICT). Nanjing, China: IEEE, 2024: 1-3. [28] Davis KC, Wyse-Sookoo KR, Raza F, et al. 5-year follow-up of a fully implanted brain-computer interface in a spinal cord injury patient[J]. Journal of Neural Engineering, 2025, 22(2): 026050. [29] Hettick M, Ho E, Poole AJ, et al. Minimally invasive implantation of scalable high-density cortical microelectrode arrays for multimodal neural decoding and stimulation[J]. Nature Biomedical Engineering, 2026, 10(6): 1206-1221. [30] Ria N, Eladly A, Masvidal-Codina E, et al. Flexible graphene-based neurotechnology for high-precision deep brain mapping and neuromodulation in Parkinsonian rats[J]. Nature Communications, 2025, 16(1): 2891. [31] Coope D, Lodwick S, Bambrough J, et al. First-in-human study of a graphene cortical interface for high-precision, high-fidelity brain-to-tumor mapping reveals high gamma activity capability: interim analysis[J]. Neuro-Oncology, 2025, 27(Suppl 5): v415. [32] Gasimov H, Alibeyli T, Safarli M. Neural signal-based prosthetic control: current advances and challenges in brain-computer interface technologies[J]. ScienceRise, 2025(2): 39-43. [33] Pandarinath C, Nuyujukian P, Blabe CH, et al. High performance communication by people with paralysis using an intracortical brain-computer interface[J]. eLife, 2017, 6: e18554. [34] 代建华, 章怀坚, 张韶岷, 等. 大鼠运动皮层神经元集群锋电位时空模式解析[J]. 中国科学(C辑:生命科学), 2009, 39(8): 736-745. [35] Sakhavi S, Guan C, Yan S. Learning temporal information for brain-computer interface using convolutional neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(11): 5619-5629. [36] Ding Y, Robinson N, Tong C, et al. LGGNet: learning from local-global-graph representations for brain-computer interface[J]. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35(7): 9773-9786. [37] Zhao Wei, Zhang Baocan, Zhou Haifeng, et al. Multi-scale convolutional transformer network for motor imagery brain-computer interface[J]. Scientific Reports, 2025, 15(1): 12935. [38] Wilson GH, Stein EA, Kamdar F, et al. Long-term unsupervised recalibration of cursor-based intracortical brain-computer interfaces using a hidden Markov model[J]. Nature Biomedical Engineering, 2025, 9(12):2013-2028. [39] Sussillo D, Stavisky SD, Kao JC, et al. Making brain-machine interfaces robust to future neural variability[J]. Nature Communications, 2016, 7(1): 13749. [40] Lee JY, Lee S, Mishra A, et al. Brain-computer interface control with artificial intelligence copilots[J]. Nature Machine Intelligence, 2025, 7(9): 1510-1523. [41] Fahimi F, Dosen S, Ang KK, et al. Generative adversarial networks-based data augmentation for brain-computer interface[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(9): 4039-4051. [42] 陈琼漩, 李鑫. 非侵入性脑机接口在脑卒中手功能康复中的应用现状[J]. 中国康复医学杂志, 2022, 37(11): 1566-1571. [43] Biasiucci A, Leeb R, Iturrate I, et al. Brain-actuated functional electrical stimulation elicits lasting arm motor recovery after stroke[J]. Nature Communications, 2018, 9(1): 2421. [44] Cervera MA, Soekadar SR, Ushiba J, et al. Brain-computer interfaces for post-stroke motor rehabilitation: a meta-analysis[J]. Annals of Clinical and Translational Neurology, 2018, 5(5): 651-663. [45] Nojima I, Sugata H, Takeuchi H, et al. Brain-computer interface training based on brain activity can induce motor recovery in patients with stroke: a meta-analysis[J]. Neurorehabilitation and Neural Repair, 2021, 36(2): 83-96. [46] Li Dan, Li Ruoyu, Song Yunping, et al. Effects of brain-computer interface based training on post-stroke upper-limb rehabilitation: a meta-analysis[J]. Journal of NeuroEngineering and Rehabilitation, 2025, 22(1): 44. [47] Cheng N, Phua KS, Lai HS, et al. Brain-computer interface-based soft robotic glove rehabilitation for stroke[J]. IEEE Transactions on Biomedical Engineering, 2020, 67(12): 3339-3351. [48] Wang Zi, Du Yimin, Guo Debin, et al. Brain-computer interface and functional electrical stimulation: a novel approach to motor rehabilitation in CNS injury patients[J]. International Journal of Surgery, 2026, 112(3): 7925-7935. [49] Capogrosso M, Milekovic T, Borton D, et al. A brain-spine interface alleviating gait deficits after spinal cord injury in primates[J]. Nature, 2016, 539(7628): 284-288. [50] Angeli CA, Boakye M, Morton RA, et al. Recovery of over-ground walking after chronic motor complete spinal cord injury[J]. New England Journal of Medicine, 2018, 379(13): 1244-1250. [51] Minassian K, Mckay WB, Binder H, et al. Targeting lumbar spinal neural circuitry by epidural stimulation to restore motor function after spinal cord injury[J]. Neurotherapeutics, 2016, 13(2): 284-294. [52] Hu Xuantao, Li Na, Pang Mao, et al. Brain-computer interface-controlled exoskeleton training for lower-limb rehabilitation in spinal cord injury: a pilot randomized clinical trial[J/OL]. Annals of Neurology, 2026 [2026-01-02]. https://doi.org/10.1002/ana.78144. [53] Ren Yihang, Mo Lifen, Lu Junlin, et al. Epidural electrical stimulation for functional recovery in incomplete spinal cord injury[J]. Cyborg and Bionic Systems, 2025, 6:0314. [54] Romeni S, Losanno E, Emedoli D, et al. High-frequency epidural electrical stimulation reduces spasticity and facilitates walking recovery in patients with spinal cord injury[J]. Science Translational Medicine, 2025, 17(780): eadp9607. [55] Liu Penghao, Cheng Yuanchen, Xu Zhuofan, et al. Spatiotemporal spinal cord stimulation with real-time triggering exoskeleton restores walking capability: a case report[J]. Annals of Clinical and Translational Neurology, 2025, 12(3): 659-665. [56] Cajigas I, Davis KC, Meschede-Krasa B, et al. Implantable brain-computer interface for neuroprosthetic-enabled volitional hand grasp restoration in spinal cord injury[J]. Brain Communications, 2021, 3(4): fcab248. [57] Yao Ruwei, Zhou Wenjialong, Liu Dingkun, et al. Fine grained two-dimensional cursor control with epidural minimally invasive brain-computer interface[J/OL]. medRxiv, 2025 [2026-08-04]. https://doi.org/10.1101/2025.10.06.25337264. [58] Moses DA, Metzger SL, Liu JR, et al. Neuroprosthesis for decoding speech in a paralyzed person with anarthria[J]. New England Journal of Medicine, 2021, 385(3): 217-227. [59] Willett FR, Kunz EM, Fan C, et al. A high-performance speech neuroprosthesis[J]. Nature, 2023, 620(7976): 1031-1036. [60] Wairagkar M, Card N, Iacobacci C, et al. Towards a real-time speech neuroprosthesis to restore speech in a person with ALS[J]. Neurosurgery, 2025, 71(Suppl 1): 58. [61] Angrick M, Luo S, Rabbani Q, et al. Online speech synthesis using a chronically implanted brain-computer interface in an individual with ALS[J]. Scientific Reports, 2024, 14: 9617. [62] Wang Yuchun, Tang Yurui, Wang Qianfeng, et al. Advances in brain computer interface for amyotrophic lateral sclerosis communication[J]. Brain-X, 2025, 3(1): e70023. [63] Zhang Daohan, Wang Zhenjie, Qian Youkun, et al. A brain-to-text framework for decoding natural tonal sentences[J]. Cell Reports, 2024, 43(11):114924. [64] Qian Youkun, Liu Changjiang, Yu Peixi, et al. Real-time decoding of full-spectrum Chinese using brain-computer interface[J]. Science Advances, 2025,11(45):eadz9968. [65] Carìa A. Towards predictive communication: the fusion of large language models and brain-computer interface[J]. Sensors, 2025, 25(13): 3987. [66] 田柳青. 侵入式脑机接口应用:记忆的解码与调控[J]. 心理科学进展, 2026, 34(2): 191-209. [67] Ramesh R, Azgomi HF, Louie KH, et al. At-home movement state classification using totally implantable cortical-basal ganglia neural interface[J]. Science Advances, 2026, 12(7): eadz4733. [68] Ehrlich SK, Tougas G, Bernstein J, et al. Brain-computer interface improves symptoms of isolated focal laryngeal dystonia: a single-blind study[J]. Movement Disorders, 2026, 41(2): 406-415. [69] Li Xiaodong, Wang Xin, Chen Shihao, et al. Gamma-band binaural beats neuromodulation enhances P300 classification in an auditory brain-computer interface paradigm[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2025, 33: 3455-3465. [70] Dohle E, Swanson E, Jovanovic L, et al. Toward the clinical translation of implantable brain-computer interfaces for motor impairment: research trends and outcome measures[J]. Advanced Science, 2025, 12(32): e2502876. [71] Luo Yu, Liu Xiaohu, Yang Miaomiao. Current status and future prospects of brain-computer interfaces in the field of neurological disease rehabilitation[J/OL]. Frontiers in Rehabilitation Sciences, 2026[2026-02-10]. https://doi.org/10.3389/fresc.2026.1666530. [72] Patrick-Krueger KM, Burkhart I, Contreras-Vidal JL. The state of clinical trials of implantable brain-computer interfaces[J]. Nature Reviews Bioengineering, 2024, 3(1): 50-67. [73] 王瑞平. 随机对照临床试验设计中的样本量估算方法[J]. 上海医药, 2023, 44(1): 48-52. [74] 潘岳松, 金奥铭, 王梦星. 临床研究样本量的估计方法和常见错误[J]. 中国卒中杂志, 2022, 17(1): 31-35. [75] Mansour S, Giles J, Nair KPS, et al. A clinical trial evaluating feasibility and acceptability of a brain-computer interface for telerehabilitation in patients with stroke[J]. Journal of NeuroEngineering and Rehabilitation, 2025, 22(1): 91. [76] 中华医学会神经外科学分会. 植入式脑机接口临床应用路径管理中国专家共识 (2026版)[J]. 中华神经医学杂志, 2026, 25(1): 2-10. [77] Satam IA, Szabolcsi R. Ethical and safety challenges of implantable brain-computer interface[J]. Interdisciplinary Description of Complex Systems, 2025, 23(2): 82-94. [78] 周程. 脑机接口领域中的伦理问题研究[J]. 人民论坛 学术前沿, 2024, 33(16): 44-55. [79] 顾心怡, 陈少峰. 脑机接口的伦理问题研究[J]. 科学技术哲学研究, 2021, 38(4): 79-85. [80] 李佩瑄, 薛贵. 脑机接口的伦理问题及对策[J]. 科技导报, 2018, 36(12): 38-45. [81] 叶岸滔. 脑机接口技术:伦理问题与研究挑战[J]. 昆明理工大学学报(社会科学版), 2016, 16(6): 8-14. [82] 金莎日娜, 翟晓梅. 侵入式脑机接口技术临床试验的伦理考量[J]. 医学与哲学, 2025, 46(2): 6-11. [83] Oxley TJ, Deo DR, Cernera S, et al. The “Brussels 4”: essential requirements for implantable brain-computer interface user autonomy[J]. Journal of Neural Engineering, 2025, 22(1): 013002. [84] 王高峰, 张志领. 脑机接口隐私风险治理[J]. 科技管理研究, 2022, 42(5): 204-209. [85] Song Cheng. Application and future prospects of brain-computer interface in neurological diseases[J]. MedScien, 2025, 1(1): MS004742. [86] 许未晴, 陈磊, 隋秀峰, 等. 脑机接口-脑信息读取与脑活动调控技术[J]. 科学通报, 2023, 68(8): 927-943. [87] 张学义, 潘平平, 庄桂山. 脑机融合技术的哲学审思[J]. 科学技术哲学研究, 2020, 37(6): 76-82. [88] 杨艺, 王昊. 脑机接口技术发展方略的分层评估与战略思考[J]. 医学与哲学, 2025, 46(24): 1-6,13.
