Brain computer interfaces (BCI) for the rehabilitation of motor impairments exploit sensorimotor rhythms (SMR) in the electroencephalogram (EEG). However, the neurophysiological processes underpinning the SMR often vary over time and across subjects. Inherent intra-and inter-subject variability causes covariate shift in data distributions that impede the transferability of model parameters amongst sessions/subjects. Transfer learning includes machine learning-based methods to compensate for inter-subject and inter-session (intra-subject) variability manifested in EEG-derived feature distributions as a covariate shift for BCI. Besides transfer learning approaches, recent studies have explored psychological and neurophysiological predictors as well as inter-subject associativity assessment, which may augment transfer learning in EEG-based BCI. Here, we highlight the importance of measuring inter-session/subject performance predictors for generalized BCI frameworks for both normal and motor-impaired people, reducing the necessity for tedious and annoying calibration sessions and BCI training.
Brain computer interfaces (BCI) provide a direct communication link between the brain and a computer or other external devices. They offer an extended degree of freedom either by strengthening or by substituting human peripheral working capacity and have potential applications in various fields such as rehabilitation, affective computing, robotics, gaming, and neuroscience. Significant research efforts on a global scale have delivered common platforms for technology standardization and help tackle highly complex and non-linear brain dynamics and related feature extraction and classification challenges. Time-variant psycho-neurophysiological fluctuations and their impact on brain signals impose another challenge for BCI researchers to transform the technology from laboratory experiments to plug-and-play daily life. This review summarizes state-of-the-art progress in the BCI field over the last decades and highlights critical challenges.
Electroencephalography (EEG) captures electrophysiological signatures of cortical events from the scalp with high-dimensional electrode montages. Usually, excessive sources produce outliers and potentially affect the actual event related sources. Besides, EEG manifests inherent inter-subject variability of the brain dynamics, at the resting state and/or under the performance of task(s), caused probably due to the instantaneous fluctuation of psychophysiological states. A wavelet coherence (WC) analysis for optimally selecting associative inter-subject channels is proposed here and is being used to boost performances of motor imagery (MI)-based inter-subject brain computer interface (BCI). The underlying hypothesis is that optimally associative inter-subject channels can reduce the effects of outliers and, thus, eliminate dissimilar cortical patterns. The proposed approach has been tested on the dataset IVa from BCI competition III, including EEG data acquired from five healthy subjects who were given visual cues to perform 280 trials of MI for the right hand and right foot. Experimental results have shown increased classification accuracy (81.79%) using the WC-based selected 16 channels compared to the one (56.79%) achieved using all the available 118 channels. The associative channels lie mostly around the sensorimotor regions of the brain, reinforced by the previous literature, describing spatial brain dynamics during sensorimotor oscillations. Apparently, the proposed approach paves the way for optimised EEG channel selection that could boost further the efficiency and real-time performance of BCI systems.
We propose event-related cortical sources estimation from subject-independent electroencephalography (EEG) recordings for motor imagery brain computer interface (BCI). By using wavelet-based maximum entropy on the mean (wMEM), task-specific EEG channels are selected to predict right hand and right foot sensorimotor tasks, employing common spatial pattern (CSP) and regularized common spatial pattern (RCSP). EEG from five healthy individuals (Dataset IVa, BCI Competition III) were evaluated by a cross-subject paradigm. Prediction performance was evaluated via a two-layer feed-forward neural network, where the classifier was trained and tested by data from two subjects independently. On average, the overall mean prediction accuracies obtained using all 118 channels are (55.98±6.53) and (71.20±5.32) in cases of CSP and RCSP, respectively, which are slightly lower than the accuracies obtained using only the selected channels, i.e., (58.95±6.90) and (71.41±6.65), respectively. The highest mean prediction accuracy achieved for a specific subject pair by using selected EEG channels was on average (90.36±5.59) and outperformed that achieved by using all available channels (86.07 ± 10.71). Spatially projected cortical sources approximated using wMEM may be useful for capturing inter-subject associative sensorimotor brain dynamics and pave the way toward an enhanced subject-independent BCI.
Globally suicidal behavior is the third most common cause of death among patients with major depressive disorder (MDD). This study presents multi-lag tone-entropy (T-E) analysis of heart rate variability (HRV) as a screening tool for identifying MDD patients with suicidal ideation. Sixty-one ECG recordings (10 min) were acquired and analyzed from control subjects (29 CONT), 16 MDD subjects with (MDDSI+) and 16 without suicidal ideation (MDDSI-). After ECG preprocessing, tone and entropy values were calculated for multiple lags (m: 1-10). The MDDSI+ group was found to have a higher mean tone value compared to that of the MDDSI- group for lags 1-8, whereas the mean entropy value was lower in MDDSI+ than that in CONT group at all lags (1-10). Leave-one-out cross-validation tests, using a classification and regression tree (CART), obtained 94.83 % accuracy in predicting MDDSI+ subjects by using a combination of tone and entropy values at all lags and including demographic factors (age, BMI and waist circumference) compared to results with time and frequency domain HRV analysis. The results of this pilot study demonstrate the usefulness of multi-lag T-E analysis in identifying MDD patients with suicidal ideation and highlight the change in autonomic nervous system modulation of the heart rate associated with depression and suicidal ideation.
Physiological and psychological underpinnings of suicidal behavior remain ill-defined and lessen timely diagnostic identification of this subgroup of patients. Arterial stiffness is associated with autonomic dysregulation and may be linked to major depressive disorder (MDD). The aim of this study was to investigate the association between arterial stiffness by photo-plethysmogram (PPG) in MDD with and without suicidal ideation (SI) by applying multiscale tone entropy (T-E) variability analysis. Sixty-one 10-min PPG recordings were analyzed from 29 control, 16 MDD patients with (MDDSI+) and 16 patients without SI (MDDSI−). MDD was based on a psychiatric evaluation and the Mini-International Neuropsychiatric Interview (MINI). Severity of depression was assessed using the Hamilton Depression Rating Scale (HAM-D). PPG features included peak (systole), trough (diastole), pulse wave amplitude (PWA), pulse transit time (PTT) and pulse wave velocity (PWV). Tone (Diastole) at all lags and Tone (PWA) at lags 8, 9, and 10 were found to be significantly different between the MDDSI+ and MDDSI− group. However, Tone (PWA) at all lags and Tone (PTT) at scales 3–10 were also significantly different between the MDDSI+ and CONT group. In contrast, Entropy (Systole), Entropy (Diastole) and Tone (Diastole) were significantly different between MDDSI− and CONT groups. The suicidal score was also positively correlated (r = 0.39 ~ 0.47; p < 0.05) with systolic and diastolic entropy values at lags 2–10. Multivariate logistic regression analysis and leave-one-out cross-validation were performed to study the effectiveness of multi-lag T–E features in predicting SI risk. The accuracy of predicting SI was 93.33% in classifying MDDSI+ and MDDSI− with diastolic T-E and lag between 2 and 10. After including anthropometric variables (Age, body mass index, and Waist Circumference), that accuracy increased to 96.67% for MDDSI+/− classification. Our findings suggest that tone-entropy based PPG variability can be used as an additional accurate diagnostic tool for patients with depression to identify SI.
Major Depressive Disorder (MDD) is a serious mental disorder that if untreated not only affects physical health but also has a high risk of suicide. While the neurophysiological phenomena that contribute to the formation of Suicidal Ideation (SI) are still ill-defined, clear links between MDD and cardiovascular disease have been reported. The aim of this study is to extract suitable features from arterial pulse signals with a view to predicting SI within MDD and control groups. Sixteen unmedicated MDD patients with a history of SI (MDDSI+), sixteen without SI (MDDSI-) and twenty-nine healthy subjects (CONT) were recruited at a psychiatric clinic in the UAE. Depression severity and SI were assessed using the Hamilton Depression Rating Scale and Beck Depression Inventory. Pulse Wave Amplitude (PWA) was calculated as the difference between the peak (Systole) and the valley (Diastole) of the arterial pulse within each cardiac cycle. Then, 2D Tone-Entropy (TE) features were extracted from the Systole, Diastole and PWA time series. The TE features extracted from Diastole were the best markers for predicting MDDSI+. The overall classification accuracies of Classification and Regression Tree (CART) model by using TE features of Systole, Diastole and PWA were 88.52%, 90.2% and 88.52% respectively. When all TE features were combined, accuracy increased up to 93.44% in identifying MDDSI+/MDDSI-/Control groups.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.