脑机接口技术在孤独症谱系障碍干预训练中的研究进展

Research advances in brain-computer interface-based intervention training for autism spectrum disorder

摘要

孤独症谱系障碍（ASD）是儿童期常见的神经发育障碍之一，主要表现为社交沟通受损、兴趣范围局限及重复刻板行为。现有研究认为，其发生发展与社会脑相关功能网络发育异常密切相关。目前常用的行为训练、言语治疗及家庭干预对部分症状具有一定改善作用，但在实际应用中，疗效评估仍较多依赖行为观察，缺少可实时反映脑功能状态的客观指标，反馈滞后和患儿配合度不稳定也会影响干预效果的判断。脑机接口（BCI）通过采集并反馈脑活动信号，为ASD 干预提供了基于神经状态实时调节的新思路。近年来，随着可穿戴脑电设备、虚拟现实、社交机器人和智能算法的发展，BCI在ASD 领域的研究重点已由早期可行性验证逐渐转向临床探索。闭环反馈、多模态融合和个体化训练正在成为这一领域较受关注的发展方向。本文系统综述BCI干预ASD 的研究进展，重点阐述其技术原理、神经机制、主要应用模式、临床应用现状、疗效机制、现实挑战及未来发展方向，并进一步讨论BCI与其他神经调控技术的相对优势及互补性，旨在为该领域的后续研究与临床转化提供参考。

Abstract

Autism spectrum disorder (ASD) is one of the common neurodevelopmental disorders in childhood and it is mainly characterized by impairments in social communication, restricted interests, and repetitive stereotyped behaviors. Current evidence suggests that its onset and progression are closely associated with abnormal development of functional networks related to the social brain. Behavioral training, speech therapy, and family-based interventions currently in common use can improve some symptoms to a certain extent. However, in practice, efficacy assessment still relies heavily on behavioral observation, with a lack of objective indicators that can reflect brain functional states in real time. Delayed feedback and inconsistent cooperation from affected children may also affect the assessment of intervention effects. By acquiring and providing feedback on brain activity signals, brain-computer interface (BCI) technology provides a new approach to ASD intervention based on real-time adjustment of neural states. In recent years, with advances in wearable electroencephalography devices, virtual reality, social robots, and intelligent algorithms, the focus of BCI in ASD has gradually shifted from early feasibility validation to clinical exploration. Closed-loop feedback, multimodal integration, and individualized training are becoming increasingly prominent research directions in this field. This review systematically summarizes the research progress in BCI-based intervention for ASD, with a focus on its technical principles, neural mechanisms, major application paradigms, current clinical applications, therapeutic mechanisms, practical challenges, and future directions. In addition, the relative advantages of BCI and its complementarity with other neuromodulation techniques are further discussed, with the aim of providing a reference for future research and clinical translation in this field.

关键词

脑机接口 / 孤独症谱系障碍 / 干预训练 / 神经可塑性

Key words

Brain-computer interface / Autism spectrum disorder / Intervention training / Neuroplasticity

参考文献

[1] CHEN H, LIANG Q, WANG B, et al. Sports game intervention aids executive function enhancement in children with autism-An fNIRS study[J]. Neurosci Lett, 2024, 822: 137647.

[2] KUO N, YAO Y, MA C, et al. Efficacy of non-wearable VR-based behavioral training for preschool children with high-functioning autism spectrum disorder: A protocol for an upcoming randomized clinical trial[J]. Front Psychiatry, 2025, 16(16): 1575695.

[3] LONG J, LIAO X, HAN K, et al. A case report of high-dose repetitive transcranial magnetic stimulation-induced excessive laughing in a 6-year-old boy with autism spectrum disorder[J]. Clin Case Rep, 2025, 13(8): e70731.

[4] SANTOMAURO D F, ERSKINE H E, MANTILLA HERRERA A M, et al. The global epidemiology and health burden of the autism spectrum: Findings from the global burden of disease study 2021[J]. Lancet Psychiatry, 2025, 12(2): 111-121.

[5] ZHU H, GAN Y, YE J, et al. Effectiveness of brain-computer interface interventions in autism spectrum disorder rehabilitation: A systematic review and meta-analysis protocol[J]. BMJ Open, 2026, 16(1): e102277.

[6] BRUNNER I, LUNDQUIST C B, PEDERSEN A R, et al. Brain computer interface training with motor imagery and functional electrical stimulation for patients with severe upper limb paresis after stroke: A randomized controlled pilot trial[J]. J Neuroeng Rehabil, 2024, 21(1): 10.

[7] ZHAO Y, ZHAO L, YANG F, et al. Assessing visual motor performance in autistic children based on Kinect and fNIRS: A case study[J]. Neuroscience, 2024, 563: 10-19.

[8] ROJAS D C, MAHARAJH K, TEALE P, et al. Reduced neural synchronization of gamma-band MEG oscillations in first-degree relatives of children with autism[J]. BMC Psychiatry, 2008, 8(1): 66.

[9] TILWANI D, BRADSHAW J, SHETH A, et al. ECG recordings as predictors of very early autism likelihood: A Machine learning approach[J]. Bioengineering, 2023, 10(7): 827.

[10] MEKKAWY L. Efficacy of neurofeedback as a treatment modality for children in the autistic spectrum[J]. Bull Natl Res Cent, 2021, 45(1): 45.

[11] BI F, JIA Z, LV L, et al. Analysis of brain functional connectivity in children with autism spectrum disorder and sleep disorders: A fNIRS observational study[J]. Front Psychol, 2025, 16: 1544798.

[12] WAN L, LI Y, ZHU G, et al. Multimodal investigation of dynamic brain network alterations in autism spectrum disorder: Linking connectivity dynamics to symptoms and developmental trajectories[J]. NeuroImage, 2024, 302: 120895.

[13] WON K, KWON M, AHN M, et al. EEG dataset for RSVP and P300 speller brain-computer interfaces[J]. SciData, 2022, 9(1): 388.

[14] CUI T, WANG P P, LIU S, et al. P300 amplitude and latency in autism spectrum disorder: A meta-analysis[J]. Eur Child Adolesc Psychiatry, 2017, 26(2): 177-190.

[15] PEKETI S, DHOK S B. Machine learning enabled P300 classifier for autism spectrum disorder using adaptive signal decomposition[J]. Brain Sci, 2023, 13(2): 315.

[16] ASH R T, NIX K C, NORCIA A M. Stability of steady-state visual evoked potential contrast response functions[J]. Psychophysiology, 2024, 61(1): e14412.

[17] TAKARAE Y, SABLICH S R, WHITE S P, et al. Neurophysiological hyperresponsivity to sensory input in autism spectrum disorders[J]. J Neurodev Disord, 2016, 8(1): 29.

[18] JEUNET C, LOTTE F, BATAIL J M, et al. Using recent BCI literature to deepen our understanding of clinical neurofeedback: A short review[J]. Neuroscience, 2018, 378: 225-233.

[19] NELSON S B, VALAKH V. Excitatory/Inhibitory balance and circuit homeostasis in Autism Spectrum Disorders[J]. Neuron, 2015, 87(4): 684-698.

[20] ELLINGFORD R A, PANASIUK M J, DE MERITENS E R, et al. Cell-type-specific synaptic imbalance and disrupted homeostatic plasticity in cortical circuits of ASD-associated Chd8 haploinsufficient mice[J]. Mol Psychiatr, 2021, 26(7): 3614-3624.

[21] ZHAO H, MAO X, ZHU C, et al. GABAergic system dysfunction in Autism Spectrum Disorders[J]. Front Cell Dev Biol, 2022, 9: 781327.

[22] 郭乃绮, 储莉婷, 姚宇凯, 等 . 基于虚拟现实技术的康复训练对学龄前期孤独症谱系障碍儿童的疗效研究[J]. 中国儿童保健杂志, 2025, 33(11): 1201-1206.

[23] HOURS C, RECASENS C, BALEYTE J M. ASD and ADHD comorbidity: What are we talking about?[J]. Front Psychiatry, 2022, 13(13): 837424.

[24] AMARAL C, MOUGA S, SIMÕES M, et al. A feasibility clinical trial to improve social attention in Autistic Spectrum Disorder (ASD) using a brain computer interface[J]. Front Neurosci-Switz, 2018, 12: 477.

[25] AMARAL C P, SIMÕES M A, MOUGA S, et al. A novel brain computer interface for classification of social joint attention in autism and comparison of 3 experimental setups: A feasibility study[J]. J Neurosci Meth, 2017, 290: 105-115.

[26] ALEXOPOULOU A, PERGANTIS P, KOUTSOJANNIS C, et al. Non-invasive BCI-VR applied protocols as intervention paradigms on school-aged subjects with ASD: A systematic review[J]. Sensors, 2025, 25(5): 1342.

[27] BERTACCHINI F, DEMARCO F, SCURO C, et al. A social robot connected with ChatGPT to improve cognitive functioning in ASD subjects[J]. Front Psychol, 2023, 14: 1232177.

[28] SUN C, MCEWAN A, BOULTON K A, et al. Artificial intelligence for tracking social behaviours and supporting an autism spectrum disorder diagnosis: Systematic review and meta-analysis[J]. eBioMedicine, 2025, 120: 105931.

[29] ZHANG T, ZHOU X, LI X, et al. Noninvasive brain-computer interfaces for children with neurodevelopmental disorders: Attention deficit hyperactivity disorder and autism spectrum disorder[J]. Displays, 2025, 86: 102886.

[30] WESTWOOD S J, AGGENSTEINER P M, KAISER A, et al. Neurofeedback for attention-deficit/hyperactivity disorder: A systematic review and meta-analysis[J]. JAMA psychiat, 2025, 82(2): 118-129.

[31] YANG D, SVOBODA A M, GEORGE T G, et al. Mapping neural correlates of biological motion perception in autistic children using high-density diffuse optical tomography[J]. Mol Autism, 2024, 15(1): 35.

[32] TAN J, ZHAN Y, TANG Y, et al. EEG decoding for effects of visual joint attention training on ASD patients with interpretable and lightweight convolutional neural network[J]. Cogn Neurodynamics, 2024, 18(3): 947-960.

[33] AKCAKAYA M, PETERS B, MOGHADAMFALAHI M, et al. Noninvasive brain-computer interfaces for augmentative and alternative communication[J]. IEEE Rev Biomed Eng, 2014, 7: 31-49.

基金资助

国家重点研发计划项目(2023YFC3605800)