Search

Brain-Computer Interfaces (BCIs) transfer human brain activities into computer commands and enable a communication channel without requiring movement. Among other BCI approaches, steady-state visual evoked potential (SSVEP)-based BCIs have the potential to become accurate, assistive technologies for persons with severe disabilities. Those systems require customization of different kinds of parameters (e.g., stimulation frequencies). Calibration usually requires selecting predefined parameters by experienced/trained personnel, though in real-life scenarios an interface allowing people with no experience in programming to set up the BCI would be desirable. Another occurring problem regarding BCI performance is BCI illiteracy (also called BCI deficiency). Many articles reported that BCI control could not be achieved by a non-negligible number of users. In order to bypass those problems we developed a SSVEP-BCI wizard, a system that automatically determines user-dependent key-parameters to customize SSVEP-based BCI systems. This wizard was tested and evaluated with 61 healthy subjects. All subjects were asked to spell the phrase "RHINE WAAL UNIVERSITY" with a spelling application after key parameters were determined by the wizard. Results show that all subjects were able to control the spelling application. A mean (SD) accuracy of 97.14 (3.73)% was reached (all subjects reached an accuracy above 85% and 25 subjects even reached 100% accuracy). [ABSTRACT FROM AUTHOR]

Visual ERP (P300) based brain-computer interfaces (BCIs) allow for fast and reliable spelling and are intended as a muscle-independent communication channel for people with severe paralysis. However, they require the presentation of visual stimuli in the field of view of the user. A head-mounted display could allow convenient presentation of visual stimuli in situations, where mounting a conventional monitor might be difficult or not feasible (e.g., at a patient’s bedside). To explore if similar accuracies can be achieved with a virtual reality (VR) headset compared to a conventional flat screen monitor, we conducted an experiment with 18 healthy participants. We also evaluated it with a person in the locked-in state (LIS) to verify that usage of the headset is possible for a severely paralyzed person. Healthy participants performed online spelling with three different display methods. In one condition a 5 × 5 letter matrix was presented on a conventional 22 inch TFT monitor. Two configurations of the VR headset were tested. In the first (glasses A), the same 5×5 matrix filled the field of view of the user. In the second (glasses B), single letters of the matrix filled the field of view of the user. The participant in the LIS tested the VR headset on three different occasions (glasses A condition only). For healthy participants, average online spelling accuracies were 94% (15.5 bits/min) using three flash sequences for spelling with the monitor and glasses A and 96% (16.2 bits/min) with glasses B. In one session, the participant in the LIS reached an online spelling accuracy of 100% (10 bits/min) using the glasses A condition. We also demonstrated that spelling with one flash sequence is possible with the VR headset for healthy users (mean: 32.1 bits/min, maximum reached by one user: 71.89 bits/min at 100% accuracy). We conclude that the VR headset allows for rapid P300 BCI communication in healthy users and may be a suitable display option for severely paralyzed persons. [ABSTRACT FROM AUTHOR]

The aim of the study was to investigate conditioned electroencephalography (EEG) responses to factually correct and incorrect statements in order to enable binary communication by means of a brain-computer interface (BCI). In two experiments with healthy participants true and false statements (serving as conditioned stimuli, CSs) were paired with two different tones which served as unconditioned stimuli (USs). The features of the USs were varied and tested for their effectiveness to elicit differentiable conditioned reactions (CRs). After acquisition of the CRs, these CRs to true and false statements were classified offline using a radial basis function kernel support vector machine. A mean single-trial classification accuracy of 50.5% was achieved for differentiating conditioned "yes" versus "no" thinking and mean accuracies of 65.4% for classification of "yes" and 68.8% for "no" thinking (both relative to baseline) were found using the best US. Analysis of the area under the curve of the conditioned EEG responses revealed significant differences between conditioned "yes" and "no" answers. Even though improvements are necessary, these first results indicate that the semantic conditioning paradigm could be a useful basis for further research regarding BCI communication in patients in the complete locked-in state. [ABSTRACT FROM AUTHOR]

Cross-individual pain assessment models based on electroencephalography (EEG) allow pain assessment in individuals who cannot report pain (e.g., unresponsive patients). The main obstacle to the generalisation of pain assessment models is the individual variation of brain responses to pain. Hence, we took the individual variation into account in cross-individual model development. We developed two convolutional neural networks (CNN) sharing an encoder architecture. One CNN predicts pain, while the other predicts the identity of an individual. We performed a leave-one-out (LOO) test with the exclusion of each subject and applied evidence accumulation to it for validating the pain prediction model's performance, where the binary classifier involves the states of pain (Hot) and resting state (Eyes-open). The mean accuracy produced by the LOO tests was 57.81% (max: 73.33%), and the mean accuracy of evidence accumulation achieved 69.75% (max: 100.00%). The individual recognition model achieved an accuracy of 99.63%. Nevertheless, when we acquired the most similar subject to a novel subject using the individual recognition model, where the most similar subject was used to train a subject-wise pain prediction model. The accuracy of predicting the pain-related conditions of the novel subject by the subject-wise model was only 53.73% (max: 79.50%). Therefore, the approach to utilising the features related to individual variation extracted by the CNN model needs more investigation for improving cross-individual pain assessment.Clinical relevance- This model can be applied to assess pain from EEG signals at the bedside with future improvement, which can help caretakers of unresponsive patients.

The complexity of brain activity involved in the generation of the experience of pain makes it hard to identify neural markers able to predict pain states. The within and between subjects variability of pain hinders the predictive potential of machine learning models trained across participants. This challenge can be tackled by implementing deep learning classifiers based on convolutional neural networks (CNNs). We targeted phase-based connectivity in the alpha band recorded with electroencephalography (EEG) during resting states and sensory conditions (eyes open [O] and closed [C] as resting states, and warm [W] and hot [H] water as sensory conditions). Connectivity features were extracted and re-organized as square matrices, because CNNs are effective in detecting the patterns from 2D data. To assess the classifier performance we implemented two complementary approaches: we 1) trained and tested the classifier with data from all participants, and 2) using a leave-one-out approach, that is excluding one participant at a time during training while using their data as a test set. The accuracy of binary classification between pain condition (H) and eyes open resting state (O) was 94.16% with the first approach, and 61.01 % with the leave-one-out approach. Clinical relevance-Further validation of the CNN classifier may help caregivers track the rehabilitation of chronic pain patients and dynamically modify the therapy. Further refinement of the model may allow its application in critical care setting with unresponsive patients to identify pain-like states otherwise incommunicable to medical personnel.

The novel BackHome system offers individuals with disabilities a range of useful services available via brain-computer interfaces (BCIs), to help restore their independence. This is the time such technology is ready to be deployed in the real world, that is, at the target end users' home. This has been achieved by the development of practical electrodes, easy to use software, and delivering telemonitoring and home support capabilities which have been conceived, implemented, and tested within a user-centred design approach. The final BackHome system is the result of a 3-year long process involving extensive user engagement to maximize effectiveness, reliability, robustness, and ease of use of a home based BCI system. The system is comprised of ergonomic and hassle-free BCI equipment; one-click software services for Smart Home control, cognitive stimulation, and web browsing; and remote telemonitoring and home support tools to enable independent home use for nonexpert caregivers and users. BackHome aims to successfully bring BCIs to the home of people with limited mobility to restore their independence and ultimately improve their quality of life.

Electroencephalography (EEG) often fails to assess both the level (i.e., arousal) and the content (i.e., awareness) of pathologically altered consciousness in patients without motor responsiveness. This might be related to a decline of awareness, to episodes of low arousal and disturbed sleep patterns, and/or to distorting and attenuating effects of the skull and intermediate tissue on the recorded brain signals. Novel approaches are required to overcome these limitations. We introduced epidural electrocorticography (ECoG) for monitoring of cortical physiology in a late-stage amytrophic lateral sclerosis patient in completely locked-in state (CLIS). Despite long-term application for a period of six months, no implant-related complications occurred. Recordings from the left frontal cortex were sufficient to identify three arousal states. Spectral analysis of the intrinsic oscillatory activity enabled us to extract state-dependent dominant frequencies at <4, ~7 and ~20 Hz, representing sleep-like periods, and phases of low and elevated arousal, respectively. In the absence of other biomarkers, ECoG proved to be a reliable tool for monitoring circadian rhythmicity, i.e., avoiding interference with the patient when he was sleeping and exploiting time windows of responsiveness. Moreover, the effects of interventions addressing the patient's arousal, e.g., amantadine medication, could be evaluated objectively on the basis of physiological markers, even in the absence of behavioral parameters. Epidural ECoG constitutes a feasible trade-off between surgical risk and quality of recorded brain signals to gain information on the patient's present level of arousal. This approach enables us to optimize the timing of interactions and medical interventions, all of which should take place when the patient is in a phase of high arousal. Furthermore, avoiding low-responsiveness periods will facilitate measures to implement alternative communication pathways involving brain-computer interfaces (BCI).

Brain-computer interface (BCI) users can control very complex applications such as multimedia players or even web browsers. Therefore, different biosignal acquisition systems are available to noninvasively measure the electrical activity of the brain, the electroencephalogram (EEG). To make BCIs more practical, hardware and software are nowadays designed more user centered and user friendly. In this paper we evaluated one of the latest innovations in the area of BCI: A wireless EEG amplifier with dry electrode technology combined with a web browser which enables BCI users to use standard webmail. With this system ten volunteers performed a daily life task: Write, read and answer an email. Experimental results of this study demonstrate the power of the introduced BCI system.