Journal of neural engineering最新文献

{"title":"Ultrasound pulse repetition frequency preferentially activates different neuron populations independent of cell type.","authors":"Jack Sherman, Emma Bortz, Erynne San Antonio, Hua-An Tseng, Laura Raiff, Xue Han","doi":"10.1088/1741-2552/ad731c","DOIUrl":"10.1088/1741-2552/ad731c","url":null,"abstract":"<p><p><i>Objective</i>. Transcranial ultrasound (US) stimulation serves as an external input to a neuron, and thus the evoked response relies on neurons' intrinsic properties. Neural activity is limited to a couple hundred hertz and often exhibits preference to input frequencies. Accordingly, US pulsed at specific physiologic pulse repetition frequencies (PRFs) may selectively engage neurons with the corresponding input frequency preference. However, most US parametric studies examine the effects of supraphysiologic PRFs. It remains unclear whether pulsing US at different physiologic PRFs could activate distinct neurons in the awake mammalian brain.<i>Approach</i>. We recorded cellular calcium responses of individual motor cortex neurons to US pulsed at PRFs of 10, 40, and 140 Hz in awake mice. We compared the evoked responses across these PRFs in the same neurons. To further understand the cell-type dependent effects, we categorized the recorded neurons as parvalbumin positive fast spiking interneurons or putative excitatory neurons and analyzed single-cell mechanosensitive channel expression in mice and humans using the Allen Brain Institute's RNA-sequencing databases.<i>Main results</i>. We discovered that many neurons were preferentially activated by only one PRF and different PRFs selectively engaged distinct neuronal populations. US-evoked cellular calcium responses exhibited the same characteristics as those naturally occurring during spiking, suggesting that US increases intrinsic neuronal activity. Furthermore, evoked responses were similar between fast-spiking inhibitory neurons and putative excitatory neurons. Thus, variation in individual neuron's cellular properties dominates US-evoked response heterogeneity, consistent with our observed cell-type independent expression patterns of mechanosensitive channels across individual neurons in mice and humans. Finally, US transiently increased network synchrony without producing prolonged over-synchronization that could be detrimental to neural circuit functions.<i>Significance</i>. These results highlight the feasibility of activating distinct neuronal subgroups by varying PRF and the potential to improve neuromodulation effects by combining physiologic PRFs.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142047665","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":"Characterizing upper limb motor dysfunction with temporal and spatial distribution of muscle synergy extracted from high-density surface electromyography.","authors":"Haoshi Zhang, Boxing Peng, Ziyin Chen, Yinghu Peng, Xiaomeng Zhou, Yanjuan Geng, Guanglin Li","doi":"10.1088/1741-2552/ad6fd5","DOIUrl":"10.1088/1741-2552/ad6fd5","url":null,"abstract":"<p><p><i>Objective.</i>To promote the development of objective and comprehensive motion function assessment for patients, based on high-density surface electromyography (HD-sEMG), this study investigates the temporal and spatial variations of neuromuscular activities related to upper limb motor dysfunction.<i>Approach.</i>Patients with unilateral upper limb motor dysfunction and healthy controls were enrolled in the study. HD-sEMG was collected from both arms while they were performing eight hand and wrist movements. Muscle synergies were extracted from the HD-sEMG. Symmetry of bilateral upper limb synergies and synergy differences between motions were proposed as spatial indicators to measure alterations in synergy spatial distribution. Additionally, as a temporal characteristic, the correlation of bilateral upper limb activation coefficient was proposed to describe the coordination control of the central nervous system. All temporal and spatial indicators were compared between patients and healthy subjects.<i>Main results.</i>The patients showed a significant decrease (<i>p</i>< 0.05) in the symmetry of bilateral upper limb synergy spatial distribution and correlation of bilateral upper limb activation coefficient. Patients with motor dysfunction also showed an increase in synergy similarity between motions, indicating altered spatial distribution of muscle synergies.<i>Significance.</i>These findings provide valuable insights into specific patterns associated with motor dysfunction, informing motor function assessment, and guiding targeted interventions and rehabilitation strategies for neurologically disordered patients.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141989846","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 working-memory load during<i>n</i>-back task performance from high channel fNIRS data.","authors":"Christian Kothe, Grant Hanada, Sean Mullen, Tim Mullen","doi":"10.1088/1741-2552/ad731b","DOIUrl":"10.1088/1741-2552/ad731b","url":null,"abstract":"<p><p><i>Objective.</i>Functional near-infrared spectroscopy (fNIRS) can measure neural activity through blood oxygenation changes in the brain in a wearable form factor, enabling unique applications for research in and outside the lab and in practical occupational settings. fNIRS has proven capable of measuring cognitive states such as mental workload, often using machine learning (ML) based brain-computer interfaces (BCIs). To date, this research has largely relied on probes with channel counts from under ten to several hundred, although recently a new class of wearable NIRS devices featuring thousands of channels has emerged. This poses unique challenges for ML classification, as fNIRS is typically limited by few training trials which results in severely under-determined estimation problems. So far, it is not well understood how such high-resolution data is best leveraged in practical BCIs and whether state-of-the-art or better performance can be achieved.<i>Approach.</i>To address these questions, we propose an ML strategy to classify working-memory load that relies on spatio-temporal regularization and transfer learning from other subjects in a combination that, to our knowledge, has not been used in previous fNIRS BCIs. The approach can be interpreted as an end-to-end generalized linear model and allows for a high degree of interpretability using channel-level or cortical imaging approaches.<i>Main results.</i>We show that using the proposed methodology, it is possible to achieve state-of-the-art decoding performance with high-resolution fNIRS data. We also replicated several state-of-the-art approaches on our dataset of 43 participants wearing a 3198 dual-channel NIRS device while performing the<i>n</i>-Back task and show that these existing methodologies struggle in the high-channel regime and are largely outperformed by the proposed pipeline.<i>Significance.</i>Our approach helps establish high-channel NIRS devices as a viable platform for state-of-the-art BCI and opens new applications using this class of headset while also enabling high-resolution model imaging and interpretation.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142047660","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":"Distraction impact of concurrent conversation on event-related potential based brain-computer interfaces.","authors":"Minju Kim, Sung-Phil Kim","doi":"10.1088/1741-2552/ad731e","DOIUrl":"10.1088/1741-2552/ad731e","url":null,"abstract":"<p><p><i>Objective.</i>This study investigates the impact of conversation on the performance of visual event-related potential (ERP)-based brain-computer interfaces (BCIs), considering distractions in real life environment. The research aims to understand how cognitive distractions from speaking and listening activities affect ERP-BCI performance.<i>Approach.</i>The experiment employs a dual-task paradigm where participants control a smart light using visual ERP-BCIs while simultaneously conducting speaking or listening tasks.<i>Main results.</i>The findings reveal that speaking notably degrades BCI accuracy and the amplitude of ERP components, while increases the latency variability of ERP components and occipital alpha power. In contrast, listening and simple syllable repetition tasks have a lesser impact on these variables. The results suggest that speaking activity significantly distracts visual attentional processes critical for BCI operation<i>Significance</i>. This study highlights the need to take distractions by daily conversation into account of the design and implementation of ERP-BCIs.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142047662","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":"Cryogel microcarriers loaded with glial cell line-derived neurotrophic factor enhance the engraftment of primary dopaminergic neurons in a rat model of Parkinson's disease.","authors":"Kaushik Narasimhan, Abrar Hakami, Giulia Comini, Tommy Patton, Ben Newland, Eilis Dowd","doi":"10.1088/1741-2552/ad7761","DOIUrl":"https://doi.org/10.1088/1741-2552/ad7761","url":null,"abstract":"<p><strong>Objective: </strong>Cryogel microcarriers made of poly(ethylene glycol) diacrylate and 3-sulfopropyl acrylate have the potential to act as delivery vehicles for long term retention of neurotrophic-factors in the brain. In addition, they can potentially enhance stem cell-derived dopaminergic cell replacement strategies for Parkinson's disease, by addressing the limitations of variable survival and poor differentiation of the transplanted precursors due to neurotrophic deprivation post transplantation in the brain. In this context, to develop a proof-of-concept, the aim of this-study was to determine the efficacy of GDNF-loaded cryogel microcarriers by assessing their impact on the survival of, and reinnervation by, primary dopaminergic grafts after intra-striatal delivery in Parkinsonian rat brains.&#xD;Approach: Rat embryonic day 14 ventral midbrain cells were transplanted into the 6-hydroxydopamine-lesioned striatum either alone, or with GDNF, or with unloaded cryogel microcarriers, or with GDNF-loaded cryogel microcarriers. Post-mortem, GDNF and tyrosine hydroxylase immunostaining were used to identify retention of the delivered GDNF within the implanted cryogel microcarriers, and to identify the transplanted dopaminergic neuronal cell bodies and fibres in the brains, respectively.&#xD;Main results: We found an intact presence of GDNF-stained cryogel microcarriers in graft sites, indicating their ability for long-term retention of the delivered GDNF up to 4 weeks in the brain. This resulted in an enhanced survival (1.9-fold) of, and striatal reinnervation (density & volume) by, the grafted dopaminergic neurons, in addition to an enhanced sprouting of fibres within graft sites.&#xD;Significance: This data provides an important proof-of-principle for the beneficial effects of neurotrophin-loaded cryogel microcarriers on engraftment of cells in the context of cell replacement therapy in Parkinson's disease. For clinical translation, further studies will be needed to assess the impact of cryogel microcarriers on the survival and differentiation of stem cell-derived dopaminergic precursors in Parkinsonian rat brains.&#xD.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142134931","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":"Binocularly incongruent, multifrequency-coded SSVEP in VR: feasibility and characteristics.","authors":"Liuyin Yang, Qiang Sun, Marc M Van Hulle","doi":"10.1088/1741-2552/ad775f","DOIUrl":"https://doi.org/10.1088/1741-2552/ad775f","url":null,"abstract":"<p><strong>Objective: </strong>Steady-state visual evoked potentials (SSVEPs) in response to flickering stimuli are popular in brain-computer interfacing (BCI) but their implementation in Virtual Reality (VR) offers new opportunities also for clinical applications. While traditional SSVEP target selection relies on single-frequency stimulation of both eyes simultaneously, further called congruent stimulation, recent studies attempted to improve the information transfer rate by using dual-frequency-coded SSVEP where each eye is presented with a stimulus flickering at a different frequency, further called incongruent stimulation. However, few studies have investigated incongruent multifrequency-coded SSVEP (MultiIncong-SSVEP).</p><p><strong>Approach: </strong>This paper reports on a systematical investigation of incongruent dual-, triple-, and quadruple-frequency-coded SSVEP for use in VR, several of which are entirely novel, and compares their performance with that of congruent dual-frequency-coded SSVEP.</p><p><strong>Main results: </strong>We were able to confirm the presence of a summation effect when comparing monocular- and binocular single-frequency congruent stimulation, and a suppression effect when comparing monocular- and binocular dual-frequency incongruent stimulation, as both tap into the binocular vision capabilities which, when hampered, could signal amblyopia.</p><p><strong>Significance: </strong>In sum, our findings not only evidence the potential of VR-based binocularly incongruent SSVEP but also underscore the importance of paradigm choice and decoder design to optimize system performance and user comfort.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142134930","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":"Utilizing diffusion tensor imaging as an image biomarker in exploring the therapeutic efficacy of forniceal deep brain stimulation in a mice model of Alzheimer's disease.","authors":"You-Yin Chen, Chih-Ju Chang, Yao-Wen Liang, Hsin-Yi Tseng, Ssu-Ju Li, Ching-Wen Chang, Yen-Ting Wu, Huai-Hsuan Shao, Po-Chun Chen, Ming-Liang Lai, Wen-Chun Deng, RuSiou Hsu, Yu-Chun Lo","doi":"10.1088/1741-2552/ad7322","DOIUrl":"https://doi.org/10.1088/1741-2552/ad7322","url":null,"abstract":"<p><p><i>Objective.</i>With prolonged life expectancy, the incidence of memory deficits, especially in Alzheimer's disease (AD), has increased. Although multiple treatments have been evaluated, no promising treatment has been found to date. Deep brain stimulation (DBS) of the fornix area was explored as a possible treatment because the fornix is intimately connected to memory-related areas that are vulnerable in AD; however, a proper imaging biomarker for assessing the therapeutic efficiency of forniceal DBS in AD has not been established.<i>Approach.</i>This study assessed the efficacy and safety of DBS by estimating the optimal intersection volume between the volume of tissue activated and the fornix. Utilizing a gold-electroplating process, the microelectrode's surface area on the neural probe was increased, enhancing charge transfer performance within potential water window limits. Bilateral fornix implantation was conducted in triple-transgenic AD mice (3 × Tg-AD) and wild-type mice (strain: B6129SF1/J), with forniceal DBS administered exclusively to 3 × Tg-AD mice in the DBS-on group. Behavioral tasks, diffusion tensor imaging (DTI), and immunohistochemistry (IHC) were performed in all mice to assess the therapeutic efficacy of forniceal DBS.<i>Main results.</i>The results illustrated that memory deficits and increased anxiety-like behavior in 3 × Tg-AD mice were rescued by forniceal DBS. Furthermore, forniceal DBS positively altered DTI indices, such as increasing fractional anisotropy (FA) and decreasing mean diffusivity (MD), together with reducing microglial cell and astrocyte counts, suggesting a potential causal relationship between revised FA/MD and reduced cell counts in the anterior cingulate cortex, hippocampus, fornix, amygdala, and entorhinal cortex of 3 × Tg-AD mice following forniceal DBS.<i>Significance.</i>The efficacy of forniceal DBS in AD can be indicated by alterations in DTI-based biomarkers reflecting the decreased activation of glial cells, suggesting reduced neural inflammation as evidenced by improvements in memory and anxiety-like behavior.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142127767","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":"Motor imagery with cues in virtual reality, audio and screen.","authors":"Sonal Santosh Baberwal, Luz Alejandra Magre, K R Sanjaya D Gunawardhana, Michael Parkinson, Tomas Ward, Shirley Coyle","doi":"10.1088/1741-2552/ad775e","DOIUrl":"https://doi.org/10.1088/1741-2552/ad775e","url":null,"abstract":"<p><strong>Objective: </strong>Training plays a significant role in motor imagery (MI), particularly in applications such as Motor Imagery-based Brain-Computer Interface (MIBCI) systems and rehabilitation systems. Previous studies have investigated the intricate relationship between cues and MI signals. However, the medium of presentation still remains an emerging area to be explored, as possible factors to enhance Motor Imagery signals..&#xD;Approach: We hypothesise that the medium used for cue presentation can significantly influence both performance and training outcomes in MI tasks. To test this hypothesis, we designed and executed an experiment implementing no- feedback MI. Our investigation focused on three distinct cue presentation mediums -audio, screen, and virtual reality(VR) headsets-all of which have potential implications for BCI use in the Activities of Daily Lives.&#xD;Main Results: The results of our study uncovered notable variations in MI signals depending on the medium of cue presentation, where the analysis is based on 3 EEG channels. To substantiate our findings, we employed a comprehensive approach, utilizing various evaluation metrics including Event- Related Synchronisation(ERS)/Desynchronisation(ERD), Feature Extraction (using Recursive Feature Elimination (RFE)), Machine Learning methodologies (using Ensemble Learning), and participant Questionnaires. All the approaches signify that Motor Imagery signals are enhanced when presented in VR, followed by audio, and lastly screen. Applying a Machine Learning approach across all subjects, the mean cross-validation accuracy (Mean ± Std. Error) was 69.24 ± 3.12, 68.69 ± 3.3 and 66.1±2.59 when for the VR, audio-based, and screen-based instructions respectively.&#xD;Significance: This multi-faceted exploration provides evidence to inform MI- based BCI design and advocates the incorporation of different mediums into the design of MIBCI systems, experimental setups, and user studies. The influence of the medium used for cue presentation may be applied to develop more effective and inclusive MI applications in the realm of human-computer interaction and rehabilitation.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142134933","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":"The effects of neuron morphology and spatial distribution on the selectivity of dorsal root ganglion stimulation.","authors":"Juhi Farooqui, Ameya C Nanivadekar, Marco Capogrosso, Scott F Lempka, Lee E Fisher","doi":"10.1088/1741-2552/ad7760","DOIUrl":"https://doi.org/10.1088/1741-2552/ad7760","url":null,"abstract":"<p><strong>Objective: </strong>&#xD;For prosthesis users, sensory feedback that appears to come from the missing limb can improve function, confidence, and phantom limb pain. Numerous pre-clinical studies have considered stimulation via penetrating microelectrodes at the dorsal root ganglion (DRG) as a potential approach for somatosensory neuroprostheses. However, to develop clinically translatable neuroprosthetic devices, a less invasive approach, such as stimulation via epineural macroelectrodes, would be preferable. This work explores the feasibility of using such electrodes to deliver focal sensory feedback by examining the mechanisms of selective activation in response to stimulation via epineural electrodes compared with penetrating electrodes.&#xD;Approach:&#xD;We developed computational models of the DRG, representing the biophysical properties of the DRG and surrounding tissue to evaluate neural responses to stimulation via penetrating microelectrodes and epineural macroelectrodes. To assess the role of properties such as neuron morphology and spatial arrangement we designed three models, including one that contained only axons (axon only), one with pseudounipolar neurons arranged randomly (random), and one with pseudounipolar neurons placed according to a realistic spatial distribution (realistic).&#xD;Main results:&#xD;Our models demonstrate that activation in response to stimulation via epineural electrodes in a realistic model is commonly initiated in the axon initial segment adjacent to the cell body, whereas penetrating electrodes commonly elicit responses in t-junctions and axons. Moreover, we see a wider dynamic range for epineural electrodes compared with penetrating electrodes. This difference appears to be driven by the spatial organization and neuron morphology of the realistic DRG.&#xD;Significance: We demonstrate that the anatomical features of the DRG make it a potentially effective target for epineural stimulation to deliver focal sensations from the limbs. Specifically, we show that epineural stimulation at the DRG can be highly selective thanks to the neuroanatomical arrangement of the DRG, making this a promising approach for future neuroprosthetic development.&#xD.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142134934","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":"Improving non-invasive trajectory decoding via neural correlates of continuous erroneous feedback processing.","authors":"Hannah Sophia Pulferer, Kyriaki Kostoglou, Gernot Müller-Putz","doi":"10.1088/1741-2552/ad7762","DOIUrl":"https://doi.org/10.1088/1741-2552/ad7762","url":null,"abstract":"<p><strong>Objective: </strong>Over the last decades, error-related potentials (ErrPs) have repeatedly proven especially useful as corrective mechanisms in invasive and non-invasive brain-computer interfaces (BCIs). However, research in this context exclusively investigated the distinction of discrete events into correct or erroneous to the present day. Due to this predominant formulation as a binary classification problem, classical ErrP-based BCIs fail to monitor tasks demanding quantitative information on error severity rather than mere qualitative decisions on error occurrence. As a result, fine-tuned and natural feedback control based on continuously perceived deviations from an intended target remains beyond the capabilities of previously used BCI setups.</p><p><strong>Approach: </strong>To address this issue for future BCI designs, we investigated the feasibility of regressing rather than classifying error-related activity non-invasively from the brain.</p><p><strong>Main results: </strong>Using pre-recorded data from ten able-bodied participants in three sessions each and a multi-output convolutional neural network, we demonstrated the above-chance regression of ongoing target-feedback discrepancies from brain signals in a pseudo-online fashion. In a second step, we used this inferred information about the target deviation to correct the initially displayed feedback accordingly, reporting significant improvements in correlations between corrected feedback and target trajectories across feedback conditions.</p><p><strong>Significance: </strong>Our results indicate that continuous information on target-feedback discrepancies can be successfully regressed from cortical activity, paving the way to increasingly naturalistic, fine-tuned correction mechanisms for future BCI applications.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142134932","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}