Search

BackgroundPostoperative Delirium (POD) is the most frequent neurocognitive complication after general anesthesia in older patients. The development of POD is associated with prolonged periods of burst suppression activity in the intraoperative electroencephalogram (EEG). The risk to present burst suppression activity depends not only on the age of the patient but is also more frequent during propofol anesthesia as compared to inhalative anesthesia. The aim of our study is to determine, if the risk to develop POD differs depending on the anesthetic agent given and if this correlates with a longer duration of intraoperative burst suppression.MethodsIn this secondary analysis of the SuDoCo trail [ISRCTN 36437985] 1277 patients, older than 60 years undergoing general anesthesia were included. We preprocessed and analyzed the raw EEG files from each patient and evaluated the intraoperative burst suppression duration. In a logistic regression analysis, we assessed the impact of burst suppression duration and anesthetic agent used for maintenance on the risk to develop POD.Results18.7% of patients developed POD. Burst suppression duration was prolonged in POD patients (POD 27.5 min ± 21.3 min vs. NoPOD 21.4 ± 16.2 min, p

ObjectiveIn older patients receiving general anesthesia, postoperative delirium (POD) is the most frequent form of cerebral dysfunction. Early identification of patients at higher risk to develop POD could provide the opportunity to adapt intraoperative and postoperative therapy. We, therefore, propose a machine learning approach to predict the risk of POD in elderly patients, using routine intraoperative electroencephalography (EEG) and clinical data that are readily available in the operating room.MethodsWe conducted a retrospective analysis of the data of a single-center study at the Charité-Universitätsmedizin Berlin, Department of Anesthesiology [ISRCTN 36437985], including 1,277 patients, older than 60 years with planned surgery and general anesthesia. To deal with the class imbalance, we used balanced ensemble methods, specifically Bagging and Random Forests and as a performance measure, the area under the ROC curve (AUC-ROC). We trained our models including basic clinical parameters and intraoperative EEG features in particular classical spectral and burst suppression signatures as well as multi-band covariance matrices, which were classified, taking advantage of the geometry of a Riemannian manifold. The models were validated with 10 repeats of a 10-fold cross-validation.ResultsIncluding EEG data in the classification resulted in a robust and reliable risk evaluation for POD. The clinical parameters alone achieved an AUC-ROC score of 0.75. Including EEG signatures improved the classification when the patients were grouped by anesthetic agents and evaluated separately for each group. The spectral features alone showed an AUC-ROC score of 0.66; the covariance features showed an AUC-ROC score of 0.68. The AUC-ROC scores of EEG features relative to patient data differed by anesthetic group. The best performance was reached, combining both the EEG features and the clinical parameters. Overall, the AUC-ROC score was 0.77, for patients receiving Propofol it was 0.78, for those receiving Sevoflurane it was 0.8 and for those receiving Desflurane 0.73. Applying the trained prediction model to an independent data set of a different clinical study confirmed these results for the combined classification, while the classifier on clinical parameters alone did not generalize.ConclusionA machine learning approach combining intraoperative frontal EEG signatures with clinical parameters could be an easily applicable tool to early identify patients at risk to develop POD.

Brain signal decoding promises significant advances in the development of clinical brain computer interfaces (BCI). In Parkinson’s disease (PD), first bidirectional BCI implants for adaptive deep brain stimulation (DBS) are now available. Brain signal decoding can extend the clinical utility of adaptive DBS but the impact of neural source, computational methods and PD pathophysiology on decoding performance are unknown. This represents an unmet need for the development of future neurotechnology. To address this, we developed an invasive brain-signal decoding approach based on intraoperative sensorimotor electrocorticography (ECoG) and subthalamic LFP to predict grip-force, a representative movement decoding application, in 11 PD patients undergoing DBS. We demonstrate that ECoG is superior to subthalamic LFP for accurate grip-force decoding. Gradient boosted decision trees (XGBOOST) outperformed other model architectures. ECoG based decoding performance negatively correlated with motor impairment, which could be attributed to subthalamic beta bursts in the motor preparation and movement period. This highlights the impact of PD pathophysiology on the neural capacity to encode movement vigor. Finally, we developed a connectomic analysis that could predict grip-force decoding performance of individual ECoG channels across patients by using their connectomic fingerprints. Our study provides a neurophysiological and computational framework for invasive brain signal decoding to aid the development of an individualized precision-medicine approach to intelligent adaptive DBS.

Changing and often class-dependent non-stationarities of signals are a big challenge in the transfer of common findings in cognitive workload estimation using Electroencephalography (EEG) from laboratory experiments to realistic scenarios or other experiments. Additionally, it often remains an open question whether actual cognitive workload reflected by brain signals was the main contribution to the estimation or discriminative and class-dependent muscle and eye activity, which can be secondary effects of changing workload levels. Within this study, we investigated a novel approach to spatial filtering based on beamforming adapted to changing settings. We compare it to no spatial filtering and Common Spatial Patterns (CSP). We used a realistic maneuvering task, as well as an auditory n-back secondary task on a tugboat simulator as two different conditions to induce workload changes on professional tugboat captains. Apart from the typical within condition classification, we investigated the ability of the different classification methods to transfer between the n-back condition and the maneuvering task. The results show a clear advantage of the proposed approach over the others in the challenging transfer setting. While no filtering leads to lowest within-condition normalized classification loss on average in two scenarios (22 and 10%), our approach using adaptive beamforming (30 and 18%) performs comparably to CSP (33 and 15%). Importantly, in the transfer from one to another setting, no filtering and CSP lead to performance around chance level (45 to 53%), while our approach in contrast is the only one capable of classifying in all other scenarios (34 and 35%) with a significant difference from chance level. The changing signal composition over the scenarios leads to a need to adapt the spatial filtering in order to be transferable. With our approach, the transfer is successful due to filtering being optimized for the extraction of neural components and additional investigation of their scalp patterns revealed mainly neural origin. Interesting findings are that rather the patterns slightly change between conditions. We conclude that the approaches with low normalized loss depend on eye and muscle activity which is successful for classification within conditions, but fail in the classifier transfer since eye and muscle contributions are highly condition-specific.

Brain-Computer Interfaces (BCIs) are inefficient for a non-negligible part of the population, estimated around 25%. To understand this phenomenon in Sensorimotor Rhythm (SMR) based BCIs, data from a large-scale screening study conducted on 80 novice participants with the Berlin BCI system and its standard machine-learning approach were investigated. Each participant performed one BCI session with resting state Encephalography, Motor Observation, Motor Execution and Motor Imagery recordings and 128 electrodes. A significant portion of the participants (40%) could not achieve BCI control (feedback performance > 70%). Based on the performance of the calibration and feedback runs, BCI users were stratified in three groups. Analyses directed to detect and elucidate the differences in the SMR activity of these groups were performed. Statistics on reactive frequencies, task prevalence and classification results are reported. Based on their SMR activity, also a systematic list of potential reasons leading to performance drops and thus hints for possible improvements of BCI experimental design are given. The categorization of BCI users has several advantages, allowing researchers 1) to select subjects for further analyses as well as for testing new BCI paradigms or algorithms, 2) to adopt a better subject-dependent training strategy and 3) easier comparisons between different studies.

Schizophrenia (SZ) and bipolar mood disorder (BMD) patients demonstrate some similar signs and symptoms; therefore, distinguishing those using qualitative criteria is not an easy task especially when these patients experience manic or hallucination phases. This study is aimed at classifying these patients by spatial analysis of their electroencephalogram (EEG) signals. In this way, 22-channels EEG signals were recorded from 52 patients (26 patients with SZ and 26 patients with BMD). No stimulus has been used during the signal recording in order to investigate whether background EEGs of these patients in the idle state contain discriminative information or not. The EEG signals of all channels were segmented into stationary intervals called “frame” and the covariance matrix of each frame is separately represented in manifold space. Exploiting Riemannian metrics in the manifold space, the classification of sample covariance matrices is carried out by a simple nearest neighbor classifier. To evaluate our method, leave one patient out cross validation approach has been used. The achieved results imply that the difference in the spatial information between the patients along with control subjects is meaningful. Nevertheless, to enhance the diagnosis rate, a new algorithm is introduced in the manifold space to select those frames which are less deviated around the mean as the most probable noise free frames. The classification accuracy is highly improved up to 98.95% compared to the conventional methods. The achieved result is promising and the computational complexity is also suitable for real time processing.

Objective: Decoding neurocognitive processes on a single-trial basis with Brain-Computer Interface (BCI) techniques can reveal the user's internal interpretation of the current situation. Such information can potentially be exploited to make devices and interfaces more user aware. In this line of research, we took a further step by studying neural correlates of different levels of cognitive processes and developing a method that allows to quantify how deeply presented information is processed in the brain.Methods/Approach: Seventeen participants took part in an EEG study in which we evaluated different levels of cognitive processing (no processing, shallow, and deep processing) within three distinct domains (memory, language, and visual imagination). Our investigations showed gradual differences in the amplitudes of event-related potentials (ERPs) and in the extend and duration of event-related desynchronization (ERD) which both correlate with task difficulty. We performed multi-modal classification to map the measured correlates of neurocognitive processing to the corresponding level of processing.Results: Successful classification of the neural components was achieved, which reflects the level of cognitive processing performed by the participants. The results show performances above chance level for each participant and a mean performance of 70–90% for all conditions and classification pairs.Significance: The successful estimation of the level of cognition on a single-trial basis supports the feasibility of user-state adaptation based on ongoing neural activity. There is a variety of potential use cases such as: a user-friendly adaptive design of an interface or the development of assistance systems in safety critical workplaces.

The combined effect of fundamental results about neurocognitive processes and advancements in decoding mental states from ongoing brain signals has brought forth a whole range of potential neurotechnological applications. In this article, we review our developments in this area and put them into perspective. These examples cover a wide range of maturity levels with respect to their applicability. While we assume we are still a long way away from integrating Brain-Computer Interface (BCI) technology in general interaction with computers, or from implementing neurotechnological measures in safety-critical workplaces, results have already now been obtained involving a BCI as research tool. In this article, we discuss the reasons why, in some of the prospective application domains, considerable effort is still required to make the systems ready to deal with the full complexity of the real world.

Brain-computer interfaces (BCIs) that are based on event-related potentials (ERPs) can estimate to which stimulus a user pays particular attention. In typical BCIs, the user silently counts the selected stimulus (which is repeatedly presented among other stimuli) in order to focus the attention. The stimulus of interest is then inferred from the electroencephalogram (EEG). Detecting attention allocation implicitly could be also beneficial for human-computer interaction (HCI), because it would allow software to adapt to the user's interest. However, a counting task would be inappropriate for the envisaged implicit application in HCI. Therefore, the question was addressed if the detectable neural activity is specific for silent counting, or if it can be evoked also by other tasks that direct the attention to certain stimuli.Thirteen people performed a silent counting, an arithmetic and a memory task. The tasks required the subjects to pay particular attention to target stimuli of a random color. The stimulus presentation was the same in all three tasks, which allowed a direct comparison of the experimental conditions.Classifiers that were trained to detect the targets in one task, according to patterns present in the EEG signal, could detect targets in all other tasks (irrespective of some task-related differences in the EEG).The neural activity detected by the classifiers is not strictly task specific but can be generalized over tasks and is presumably a result of the attention allocation or of the augmented workload. The results may hold promise for the transfer of classification algorithms from BCI research to implicit relevance detection in HCI.

In the last years Brain Computer Interface (BCI) technology has benefited from the development of sophisticated machine leaning methods that let the user operate the BCI after a few trials of calibration. One remarkable example is the recent development of co-adaptive techniques that proved to extend the use of BCIs also to people not able to achieve successful control with the standard BCI procedure. Especially for BCIs based on the modulation of the Sensorimotor Rhythm (SMR) these improvements are essential, since a not negligible percentage of users is unable to operate SMR-BCIs efficiently. In this study we evaluated for the first time a fully automatic co-adaptive BCI system on a large scale. A pool of 168 participants naive to BCIs operated the co-adaptive SMR-BCI in one single session. Different psychological interventions were performed prior the BCI session in order to investigate how motor coordination training and relaxation could influence BCI performance. A neurophysiological indicator based on the Power Spectral Density (PSD) was extracted by the recording of few minutes of resting state brain activity and tested as predictor of BCI performances. Results show that high accuracies in operating the BCI could be reached by the majority of the participants before the end of the session. BCI performances could be significantly predicted by the neurophysiological indicator, consolidating the validity of the model previously developed. Anyway, we still found about 22% of users with performance significantly lower than the threshold of efficient BCI control at the end of the session. Being the inter-subject variability still the major problem of BCI technology, we pointed out crucial issues for those who did not achieve sufficient control. Finally, we propose valid developments to move a step forward to the applicability of the promising co-adaptive methods.

We provide a proof of concept for an EEG-based reconstruction of a visual image which is on a user's mind. Our approach is based on the Rapid Serial Visual Presentation (RSVP) of polygon primitives and Brain-Computer Interface (BCI) technology. In an experimental setup, subjects were presented bursts of polygons: some of them contributed to building a target image (because they matched the shape and/or color of the target) while some of them did not. The presentation of the contributing polygons triggered attention-related EEG patterns. These Event Related Potentials (ERPs) could be determined using BCI classification and could be matched to the stimuli that elicited them. These stimuli (i.e. the ERP-correlated polygons) were accumulated in the display until a satisfactory reconstruction of the target image was reached. As more polygons were accumulated, finer visual details were attained resulting in more challenging classification tasks. In our experiments, we observe an average classification accuracy of around 75%. An in-depth investigation suggests that many of the misclassifications were not misinterpretations of the BCI concerning the users' intent, but rather caused by ambiguous polygons that could contribute to reconstruct several different images. When we put our BCI-image reconstruction in perspective with other RSVP BCI paradigms, there is large room for improvement both in speed and accuracy. These results invite us to be optimistic. They open a plethora of possibilities to explore non-invasive BCIs for image reconstruction both in healthy and impaired subjects and, accordingly, suggest interesting recreational and clinical applications.

Note onsets in music are acoustic landmarks providing auditory cues that underlie the perception of more complex phenomena such as beat, rhythm, and meter. For naturalistic ongoing sounds a detailed view on the neural representation of onset structure is hard to obtain, since, typically, stimulus-related EEG signatures are derived by averaging a high number of identical stimulus presentations. Here, we propose a novel multivariate regression-based method extracting onset-related brain responses from the ongoing EEG. We analyse EEG recordings of nine subjects who passively listened to stimuli from various sound categories encompassing simple tone sequences, full-length romantic piano pieces and natural (non-music) soundscapes. The regression approach reduces the 61-channel EEG to one time course optimally reflecting note onsets. The neural signatures derived by this procedure indeed resemble canonical onset-related ERPs, such as the N1-P2 complex. This EEG projection was then utilized to determine the Cortico-Acoustic Correlation (CACor), a measure of synchronization between EEG signal and stimulus. We demonstrate that a significant CACor (i) can be detected in an individual listener's EEG of a single presentation of a full-length complex naturalistic music stimulus, and (ii) it co-varies with the stimuli's average magnitudes of sharpness, spectral centroid, and rhythmic complexity. In particular, the subset of stimuli eliciting a strong CACor also produces strongly coordinated tension ratings obtained from an independent listener group in a separate behavioral experiment. Thus musical features that lead to a marked physiological reflection of tone onsets also contribute to perceived tension in music.

For Brain-Computer Interface (BCI) systems that are designed for users with severe impairments of the oculomotor system, an appropriate mode of presenting stimuli to the user is crucial. To investigate whether multi-sensory integration can be exploited in the gaze-independent event-related potentials (ERP) speller and to enhance BCI performance, we designed a visual-auditory speller. We investigate the possibility to enhance stimulus presentation by combining visual and auditory stimuli within gaze-independent spellers. In this study with N = 15 healthy users, two different ways of combining the two sensory modalities are proposed: simultaneous redundant streams (Combined-Speller) and interleaved independent streams (Parallel-Speller). Unimodal stimuli were applied as control conditions. The workload, ERP components, classification accuracy and resulting spelling speed were analyzed for each condition. The Combined-speller showed a lower workload than uni-modal paradigms, without the sacrifice of spelling performance. Besides, shorter latencies, lower amplitudes, as well as a shift of the temporal and spatial distribution of discriminative information were observed for Combined-speller. These results are important and are inspirations for future studies to search the reason for these differences. For the more innovative and demanding Parallel-Speller, where the auditory and visual domains are independent from each other, a proof of concept was obtained: fifteen users could spell online with a mean accuracy of 87.7% (chance level

This paper introduces Pyff, the Pythonic Feedback Framework for feedbackapplications and stimulus presentation. Pyff provides a platform independentframework that allows users to develop and run neuroscientific experiments inthe programming language Python. Existing solutions have mostly beenimplemented in C++, which makes for a rather tedious programming task fornon-computer-scientists, or in Matlab, which is not well suited for moreadvanced visual or auditory applications. Pyff was designed to makeexperimental paradigms (i.e. feedback and stimulus applications) easilyprogrammable. It includes base classes for various types of common feedbacksand stimuli as well as useful libraries for external hardware such aseyetrackers. Pyff is also equipped with a steadily growing set of ready-to-usefeedbacks and stimuli. It can be used as a standalone application, for instanceproviding stimulus presentation in psychophysics experiments, or within aclosed loop such as in biofeedback or brain-computer interfacing experiments.Pyff communicates with other systems via a standardized communication protocoland is therefore suitable to be used with any system that may be adapted tosend its data in the specified format. Having such a general, open sourceframework will help foster a fruitful exchange of experimental paradigmsbetween research groups. In particular, it will decrease the need ofreprogramming standard paradigms, ease the reproducibility of publishedresults, and naturally entail some standardization of stimulus presentation.

Brain-Computer Interfacing (BCI) is a steadily growing area ofresearch. While initially BCI research was focused on applicationsfor paralyzed patients, increasingly more alternative applications inhealthy human subjects are proposed and investigated. In particular,monitoring of mental states and decoding of covert user states haveseen a strong rise of interest. Here, we present some examples ofsuch novel applications which provide evidence for the promisingpotential of BCI technology for non-medical uses. Furthermore, wediscuss distinct methodological improvements required to bringnon-medical applications of BCI technology to a diversity of laypersontarget groups, e.g., ease of use, minimal training, general usability,short control latencies.

Most P300-based brain-computer interface (BCI) approaches use the visual modality for stimulation. For use with patients suffering from amyotrophic lateral sclerosis (ALS) this might not be the preferable choice because of sight deterioration. Moreover, using a modality different from the visual one minimizes interference with possible visual feedback. Therefore, a multi-class BCI paradigm is proposed that uses spatially distributed, auditory cues. Ten healthy subjects participated in an offline oddball task with the spatial location of the stimuli being a discriminating cue. Experiments were done in free field, with an individual speaker for each location. Different inter-stimulus intervals of 1000 ms, 300 ms and 175 ms were tested. With averaging over multiple repetitions, selection scores went over 90% for most conditions, i.e., in over 90% of the trials the correct location was selected. One subject reached a 100% correct score. Corresponding information transfer rates were high, up to an average score of 17.39 bits/minute for the 175 ms condition (best subject 25.20 bits/minute). When presenting the stimuli through a single speaker, thus effectively canceling the spatial properties of the cue, selection scores went down below 70% for most subjects. We conclude that the proposed spatial auditory paradigm is successful for healthy subjects and shows promising results that may lead to a fast BCI that solely relies on the auditory sense.

Electroencephalogram (EEG) signals are highly subject-specific and vary considerably even between recording sessions of the same user within the same experimental paradigm. This challenges a stable operation of Brain-Computer Interface (BCI) systems. The classical approach is to train users by neurofeedback to produce fixed stereotypical patterns of brain activity. In the machine learning approach, a widely adapted method for dealing with those variances is to record a so called calibration measurement on the beginning of each session in order to optimize spatial filters and classifiers specifically for each subject and each day. This adaptation of the system to the individual brain signature of each user relieves from the need of extensive user training. In this paper we suggest a new method that overcomes the requirement of these time-consuming calibration recordings for long-term BCI users. The method takes advantage of knowledge collected in previous sessions: By a novel technique, prototypical spatial filters are determined which have better generalization properties compared to single-session filters. In particular, they can be used in follow-up sessions without the need to recalibrate the system. This way the calibration periods can be dramatically shortened or even completely omitted for these 'experienced' BCI users. The feasibility of our novel approach is demonstrated with a series of online BCI experiments. Although performed without any calibration measurement at all, no loss of classification performance was observed.

BACKGROUND: Brain computer interfaces (BCI) based on electro-encephalography (EEG) have been shown to detect mental states accurately and non-invasively, but the equipment required so far is cumbersome and the resulting signal is difficult to analyze. BCI requires accurate classification of small amplitude brain signal components in single trials from recordings which can be compromised by currents induced by muscle activity. METHODOLOGY/PRINCIPAL FINDINGS: A novel EEG cap based on dry electrodes was developed which does not need time-consuming gel application and uses far fewer electrodes than on a standard EEG cap set-up. After optimizing the placement of the 6 dry electrodes through off-line analysis of standard cap experiments, dry cap performance was tested in the context of a well established BCI cursor control paradigm in 5 healthy subjects using analysis methods which do not necessitate user training. The resulting information transfer rate was on average about 30% slower than the standard cap. The potential contribution of involuntary muscle activity artifact to the BCI control signal was found to be inconsequential, while the detected signal was consistent with brain activity originating near the motor cortex. CONCLUSIONS/SIGNIFICANCE: Our study shows that a surprisingly simple and convenient method of brain activity imaging is possible, and that simple and robust analysis techniques exist which discriminate among mental states in single trials. Within 15 minutes the dry BCI device is set-up, calibrated and ready to use. Peak performance matched reported EEG BCI state of the art in one subject. The results promise a practical non-invasive BCI solution for severely paralyzed patients, without the bottleneck of setup effort and limited recording duration that hampers current EEG recording technique. The presented recording method itself, BCI not considered, could significantly widen the use of EEG for emerging applications requiring long-term brain activity and mental state monitoring.