Journal of neural engineering最新文献

{"title":"Diffusion transformer-augmented fMRI functional connectivity for enhanced autism spectrum disorder diagnosis.","authors":"Haokai Zhao, Haowei Lou, Lina Yao, Yu Zhang","doi":"10.1088/1741-2552/adb07a","DOIUrl":"10.1088/1741-2552/adb07a","url":null,"abstract":"<p><p><i>Objective.</i>Functional magnetic resonance imaging (fMRI) is often modeled as networks of Regions of Interest and their functional connectivity to study brain functions and mental disorders. Limited fMRI data due to high acquisition costs hampers recognition model performance. We aim to address this issue using generative diffusion models for data augmentation.<i>Approach.</i>We propose Brain-Net-Diffusion, a transformer-based latent diffusion model to generate realistic functional connectivity for augmenting fMRI datasets and evaluate its impact on classification tasks.<i>Main results.</i>The Brain-Net-Diffusion effectively generates connectivity patterns resembling real data and significantly enhances classification performance. Augmentation using Brain-Net-Diffusion increased downstream autism spectrum disorder classification accuracy by 4.3% compared to no augmentation. It also outperformed other augmentation methods, with accuracy improvements ranging from 1.3% to 2.2%.<i>Significance.</i>Our approach demonstrates the effectiveness of diffusion models for fMRI data augmentation, providing a robust solution for overcoming data scarcity in functional connectivity analysis. To facilitate further research, we have made our code publicly available athttps://github.com/JoeZhao527/brain-net-diffusion.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143070454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ringing suppression design for pulse parameter controllable transcranial magnetic stimulation.","authors":"Ziqi Zhang, Hongfa Ding, Zhou He, Chengyue Zhao, Xiao Fang, Dandi Zhang, Yingzhe Liu","doi":"10.1088/1741-2552/adaef1","DOIUrl":"10.1088/1741-2552/adaef1","url":null,"abstract":"<p><p><i>Objective</i>. Pulse parameter controllable transcranial magnetic stimulation (cTMS) devices with fully-controlled semiconductor switches are increasingly being developed, but the primary waveform they generate is often accompanied by ringing, which is due to the resonance between the stimulation coil inductance and the snubber capacitors paired with the switches at the end of the pulse. This study provides a ringing suppression design method to effectively suppress it and reduce its impact on stimulation efficacy.<i>Approach</i>. A three-pronged design method is developed to suppress the ringing at its source. Firstly, laminated busbars are designed to connect main components, reducing parasitic inductance and thus decreasing the snubber energy requirement and the energy stored in the snubber capacitors, which is the main source of ringing energy. Secondly, the snubber circuit structure is improved by employing unidirectional snubber circuits to cut off the ringing loop. Lastly, a specially designed converter is used to transfer the energy stored in the snubber circuit, which to some extent represents the energy of the ringing, back to the cTMS storage capacitor.<i>Main</i><i>results</i>. The suppressed ringing duration has been significantly reduced from around 1000<i>μ</i>s to within 30<i>μ</i>s. The proposed method effectively suppresses ringing, making the realized waveform much closer to the ideal waveform, which minimizes the impact of ringing on the stimulation effect and reduces the uncontrollable deviation between the actual activated region and the ideal target activation region.<i>Significance</i>. The method can be easily transferred to other cTMS devices, enhancing the controllability of stimulation efficacy.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143054707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Few-shot transfer learning for individualized braking intent detection on neuromorphic hardware.","authors":"Nathan A Lutes, Venkata Sriram Siddhardh Nadendla, K Krishnamurthy","doi":"10.1088/1741-2552/adb079","DOIUrl":"10.1088/1741-2552/adb079","url":null,"abstract":"<p><p><i>Objective.</i>This work explores use of a few-shot transfer learning method to train and implement a convolutional spiking neural network (CSNN) on a BrainChip Akida AKD1000 neuromorphic system-on-chip for developing individual-level, instead of traditionally used group-level, models using electroencephalographic data. The efficacy of the method is studied on an advanced driver assist system related task of predicting braking intention.<i>Approach.</i>Data are collected from participants operating an NVIDIA JetBot on a testbed simulating urban streets for three different scenarios. Participants receive a braking indicator in the form of: (1) an audio countdown in a nominal baseline, stress-free environment; (2) an audio countdown in an environment with added elements of physical fatigue and active cognitive distraction; (3) a visual cue given through stoplights in a stress-free environment. These datasets are then used to develop individual-level models from group-level models using a few-shot transfer learning method, which involves: (1) creating a group-level model by training a CNN on group-level data followed by quantization and recouping any performance loss using quantization-aware retraining; (2) converting the CNN to be compatible with Akida AKD1000 processor; and (3) training the final decision layer on individual-level data subsets to create individual-customized models using an online Akida edge-learning algorithm.<i>Main results.</i>Efficacy of the above methodology to develop individual-specific braking intention predictive models by rapidly adapting the group-level model in as few as three training epochs while achieving at least 90% accuracy, true positive rate and true negative rate is presented. Further, results show the energy-efficiency of the neuromorphic hardware through a power reduction of over 97% with only a 1.3 × increase in latency when using the Akida AKD1000 processor for network inference compared to an Intel Xeon central processing unit. Similar results were obtained in a subsequent ablation study using a subset of five out of 19 channels.<i>Significance.</i>Especially relevant to real-time applications, this work presents an energy-efficient, few-shot transfer learning method that is implemented on a neuromorphic processor capable of training a CSNN as new data becomes available, operating conditions change, or to customize group-level models to yield personalized models unique to each individual.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143070460","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Decoding speech intent from non-frontal cortical areas.","authors":"Prashanth Ravi Prakash, Tianhao Lei, Robert D Flint, Jason K Hsieh, Zachary Fitzgerald, Emily Mugler, Jessica Templer, Matthew A Goldrick, Matthew C Tate, Joshua Rosenow, Joshua Glaser, Marc W Slutzky","doi":"10.1088/1741-2552/adaa20","DOIUrl":"10.1088/1741-2552/adaa20","url":null,"abstract":"<p><p><i>Objective</i>. Brain machine interfaces (BMIs) that can restore speech have predominantly focused on decoding speech signals from the speech motor cortices. A few studies have shown some information outside the speech motor cortices, such as in parietal and temporal lobes, that also may be useful for BMIs. The ability to use information from outside the frontal lobe could be useful not only for people with locked-in syndrome, but also to people with frontal lobe damage, which can cause nonfluent aphasia or apraxia of speech. However, temporal and parietal lobes are predominantly involved in perceptive speech processing and comprehension. Therefore, to be able to use signals from these areas in a speech BMI, it is important to ascertain that they are related to production. Here, using intracranial recordings, we sought evidence for whether, when and where neural information related to speech intent could be found in the temporal and parietal cortices<i>Approach</i>. Using intracranial recordings, we examined neural activity across temporal and parietal cortices to identify signals associated with speech intent. We employed causal information to distinguish speech intent from resting states and other language-related processes, such as comprehension and working memory. Neural signals were analyzed for their spatial distribution and temporal dynamics to determine their relevance to speech production.<i>Main results</i>. Causal information enabled us to distinguish speech intent from resting state and other processes involved in language processing or working memory. Information related to speech intent was distributed widely across the temporal and parietal lobes, including superior temporal, medial temporal, angular, and supramarginal gyri.<i>Significance</i>. Loss of communication due to neurological diseases can be devastating. While speech BMIs have made strides in decoding speech from frontal lobe signals, our study reveals that the temporal and parietal cortices contain information about speech production intent that can be causally decoded prior to the onset of voice. This information is distributed across a large network. This information can be used to improve current speech BMIs and potentially expand the patient population for speech BMIs to include people with frontal lobe damage from stroke or traumatic brain injury.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11822885/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142985856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Safety of non-invasive brain stimulation in patients with implants: a computational risk assessment.","authors":"Fariba Karimi, Antonino M Cassarà, Myles Capstick, Niels Kuster, Esra Neufeld","doi":"10.1088/1741-2552/ad8efa","DOIUrl":"10.1088/1741-2552/ad8efa","url":null,"abstract":"<p><p><i>Objective.</i>Non-invasive brain stimulation (NIBS) methodologies, such as transcranial electric stimulation (tES) are increasingly employed for therapeutic, diagnostic, or research purposes. The concurrent presence of active/passive implants can pose safety risks, affect the NIBS delivery, or generate confounding signals. A systematic investigation is required to understand the interaction mechanisms, quantify exposure, assess risks, and establish guidance for NIBS applications.<i>Approach.</i>We used measurements, simplified generic, and detailed anatomical modeling to: (i) systematically analyze exposure conditions with passive and active implants, considering local field enhancement, exposure dosimetry, tissue heating and neuromodulation, capacitive lead current injection, low-impedance pathways between electrode contacts, and insulation damage; (ii) identify risk metrics and efficient prediction strategies; (iii) quantify these metrics in relevant exposure cases and (iv) identify worst case conditions. Various aspects including implant design, positioning, scar tissue formation, anisotropy, and frequency were investigated.<i>Main results.</i>At typical tES frequencies, local enhancement of dosimetric exposure quantities can reach up to one order of magnitude for deep brain stimulation (DBS) and stereoelectroencephalography implants (more for elongated passive implants), potentially resulting in unwanted neuromodulation that can confound results but is still 2-3 orders of magnitude lower than active DBS. Under worst-case conditions, capacitive current injection in the active implants' lead can produce local exposures of similar magnitude as the passive field enhancement, while capacitive pathways between contacts are negligible. Above 10 kHz, applied current magnitudes increase, necessitating consideration of tissue heating. Furthermore, capacitive effects become more prominent, leading to current injection that can reach DBS-like levels. Adverse effects from abandoned/damaged leads in direct electrode vicinity cannot be excluded.<i>Significance.</i>Safety related concerns of tES application in the presence of implants are systematically identified and explored, resulting in specific and quantitative guidance and establishing basis for safety standards. Furthermore, several methods for reducing risks are suggested while acknowledging the limitations (see section4.5).</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142584010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"User-wise perturbations for user identity protection in EEG-based BCIs.","authors":"Xiaoqing Chen, Siyang Li, Yunlu Tu, Ziwei Wang, Dongrui Wu","doi":"10.1088/1741-2552/ad88a5","DOIUrl":"10.1088/1741-2552/ad88a5","url":null,"abstract":"<p><p><i>Objective</i>. An electroencephalogram (EEG)-based brain-computer interface (BCI) is a direct communication pathway between the human brain and a computer. Most research so far studied more accurate BCIs, but much less attention has been paid to the ethics of BCIs. Aside from task-specific information, EEG signals also contain rich private information, e.g. user identity, emotion, disorders, etc which should be protected.<i>Approach</i>. We show for the first time that adding user-wise perturbations can make identity information in EEG unlearnable. We propose four types of user-wise privacy-preserving perturbations, i.e. random noise, synthetic noise, error minimization noise, and error maximization noise. After adding the proposed perturbations to EEG training data, the user identity information in the data becomes unlearnable, while the BCI task information remains unaffected.<i>Main results</i>. Experiments on six EEG datasets using three neural network classifiers and various traditional machine learning models demonstrated the robustness and practicability of the proposed perturbations.<i>Significance</i>. Our research shows the feasibility of hiding user identity information in EEG data without impacting the primary BCI task information.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142484381","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Temporal properties of transcutaneous direct current motor conduction block.","authors":"David B Green, Shane A Bender, Gustaf M Van Acker Iii, Hannah E Hill, Kevin L Kilgore, Niloy Bhadra, Tina L Vrabec","doi":"10.1088/1741-2552/adb07b","DOIUrl":"10.1088/1741-2552/adb07b","url":null,"abstract":"<p><p><i>Objective</i>. Direct current (DC) electrical block of peripheral nerve conduction shows promise for clinical applications to treat spasticity, pain, and cardiac arrhythmias. Most previous work has used invasive nerve cuffs. Here we investigate the potential of non-invasive transcutaneous DC motor block (tDCB).<i>Approach</i>. In anesthetized rats, force output from the tibialis and peroneus muscles was measured in response to stimulation proximally on the sciatic nerve. DC blocking waveforms were delivered via a surface electrode placed distally on the skin over the common peroneal nerve. The efficacy of the block was observed as the reduction/abolition of muscle force. Experiments using this model were performed with two different electrode types. A range of DC amplitudes and durations were used to elucidate the temporal properties of block.<i>Main results</i>. Higher levels of DC resulted in a larger block percentage. The amount of time needed to induce block depended on the level of DC, with smaller amplitudes resulting in longer induction times. When block was applied for a longer period of time (120s), the block was sustained following DC delivery. This 'recovery period' was longer for higher amplitudes of block. In addition to the block thresholds and temporal effects, two additional evaluations were made: In some animals the efficacy of tDCB to block tetanic muscle contractions was successfully verified. Finally, the effect of tDCB on the stability of nerve conduction was verified using a second distal electrode for comparison.<i>Significance</i>. In this study, tDCB has been shown to reversibly block action potentials in peripheral motor nerves. A subthreshold amplitude applied for a longer duration could produce complete or partial block following a brief induction time. Also, a higher amplitude was associated with a longer recovery time. These temporal properties are important considerations for potential clinical applications.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143070469","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Characterization of motor nerve stimulation using sinusoidal low frequency alternating currents and cuff electrodes.","authors":"A Alhawwash, M R Horn, N Lazorchak, K Yoshida","doi":"10.1088/1741-2552/adafdc","DOIUrl":"10.1088/1741-2552/adafdc","url":null,"abstract":"<p><p><i>Objective:</i>Direct electrical neurostimulation using continuous sinusoidal low frequency alternating currents (LFAC) is an emerging modality for neuromodulation. As opposed to the traditional rectangular pulse stimulation, there is limited background on the characteristics of peripheral nerves responses to sinusoidal LFAC stimulation; especially within the low frequency range (<50 Hz). In this study, we demonstrate LFAC activation as a means to activate motor nerves by direct bipolar nerve stimulation via cuff electrodes, and characterize the factors of activation. We study and quantify the effects of sinusoidal frequency and electrode geometry on the motor nerve activation threshold<i>in-vivo</i>and in computational models,<i>in-silico</i>.<i>Approach:</i>Acute<i>in-vivo</i>experiments (<i>N</i>= 34) were conducted on isoflurane-anaesthetized rats. A pure tone continuous sinusoidal current was applied to the rat sciatic nerve in bipolar configurations via bipolar or tripolar nerve cuff electrodes (different contact separations). LFAC activation thresholds were quantified by measuring the electromyogram (EMG) response of the triceps surae muscles and the induced twitch force to LFAC stimulation at six frequencies (1, 2, 3, 4, 8, and 20 Hz). Computationally, we utilized a volume conductor model of a bipolar cuff electrode around a single rat-size fascicle and projected the potentials to the McIntyre-Richardson-Grill models of myelinated motor nerve fibers. We compared the<i>in-silico</i>responses of a range of fiber diameters (5.7 to 16<i>µ</i>m) to LFAC stimulation and their activation thresholds to the<i>in-vivo</i>findings.<i>Main results</i>: Sinusoidal LFAC stimulation elicited motor nerve activity<i>in-vivo</i>and<i>in-silico</i>, with a remarkable convergence of the<i>in-silico</i>predictions to the<i>in-vivo</i>observations. The EMG activity showed that muscle responses to LFAC stimulation were phase-locked to the sinusoidal cycle but exhibited two distinct activation modes. These modes were classified as burst and unitary, indicating the presence of two distinct patterns of muscle activation during LFAC stimulation. The LFAC motor activation threshold was significantly dependent on frequency and influenced by the contact separation of the cuff electrode, with a greater extent of reduction at a higher frequency or wider separation. Moreover, the order of fiber recruitment was suggested to be normal-physiological (small-to-large caliber) given the nature of the induced EMG activity and<i>in-silico</i>predictions.<i>Significance</i>: These findings provide significant insights into the nature of sinusoidal LFAC stimulation, at the explored range of frequency, and the expected mammalian peripheral motor nerve responses to LFAC. The characteristics of sinusoidal LFAC stimulation would facilitate selectivity approaches in a broader range of therapeutic and rehabilitative neuromodulation applications.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143070446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Using transient, effector-specific neural responses to gate decoding for brain-computer interfaces.","authors":"Brian M Dekleva, Jennifer L Collinger","doi":"10.1088/1741-2552/adaa1f","DOIUrl":"10.1088/1741-2552/adaa1f","url":null,"abstract":"<p><p><i>Objective.</i>Real-world implementation of brain-computer interfaces (BCIs) for continuous control of devices should ideally rely on fully asynchronous decoding approaches. That is, the decoding algorithm should continuously update its output by estimating the user's intended actions from real-time neural activity, without the need for any temporal alignment to an external cue. This kind of open-ended temporal flexibility is necessary to achieve naturalistic and intuitive control. However, the relation between cortical activity and behavior is not stationary: neural responses that appear related to a certain aspect of behavior (e.g. grasp force) in one context will exhibit a relationship to something else in another context (e.g. reach speed). This presents a challenge for generalizable decoding, since the applicability of a decoder for a given parameter changes over time.<i>Approach.</i>We developed a method to simplify the problem of continuous decoding that uses transient, end effector-specific neural responses to identify periods of relevant effector engagement. Specifically, we use transient responses in the population response observed at the onset and offset of all hand-related actions to signal the applicability of hand-related feature decoders (e.g. digit movement or force). By using this transient-based gating approach, specific feature decoding models can be simpler (owing to local linearities) and are less sensitive to interference from cross-effector interference such as combined reaching and grasping actions.<i>Main results.</i>The transient-based decoding approach enabled high-quality online decoding of grasp force and individual finger control in multiple behavioral paradigms. The benefits of the gated approach are most evident in tasks that require both hand and arm control, for which standard continuous decoding approaches exhibit high output variability.<i>Significance.</i>The approach proposed here addresses the challenge of decoder generalization across contexts. By limiting decoding to identified periods of effector engagement, this approach can support reliable BCI control in real-world applications.Clinical Trial ID: NCT01894802.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142985866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Personalized<i>µ</i>-transcranial alternating current stimulation improves online brain-computer interface control.","authors":"Deland H Liu, Satyam Kumar, Hussein Alawieh, Frigyes Samuel Racz, José Del R Millán","doi":"10.1088/1741-2552/ada980","DOIUrl":"10.1088/1741-2552/ada980","url":null,"abstract":"<p><p><i>Objective.</i>A motor imagery (MI)-based brain-computer interface (BCI) enables users to engage with external environments by capturing and decoding electroencephalography (EEG) signals associated with the imagined movement of specific limbs. Despite significant advancements in BCI technologies over the past 40 years, a notable challenge remains: many users lack BCI proficiency, unable to produce sufficiently distinct and reliable MI brain patterns, hence leading to low classification rates in their BCIs. The objective of this study is to enhance the online performance of MI-BCIs in a personalized, biomarker-driven approach using transcranial alternating current stimulation (tACS).<i>Approach.</i>Previous studies have identified that the peak power spectral density value in sensorimotor idling rhythms is a neural correlate of participants' upper limb MI-BCI performances. In this active-controlled, single-blind study, we applied 20 min of tACS at the participant-specific, peak<i>µ</i>frequency in resting-state sensorimotor rhythms (SMRs), with the goal of enhancing resting-state<i>µ</i>SMRs.<i>Main results.</i>After tACS, we observed significant improvements in event-related desynchronizations (ERDs) of<i>µ</i>SMRs, and in the performance of an online MI-BCI that decodes left versus right hand commands in healthy participants (<i>N</i>= 10)-but not in an active control-stimulation control group (<i>N</i>= 10). Lastly, we showed a significant correlation between the resting-state<i>µ</i>SMRs and<i>µ</i>ERD, offering a mechanistic interpretation behind the observed changes in online BCI performances.<i>Significance.</i>Our research lays the groundwork for future non-invasive interventions designed to enhance BCI performances, thereby improving the independence and interactions of individuals who rely on these systems.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143018962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}