1,720,995 research outputs found
Implementing physiologically-based approaches to improve Brain-Computer Interfaces usability in post-stroke motor rehabilitation
Full text linkStroke is one of the leading causes of long-term motor disability and, as such, directly impacts on daily living activities. Identifying new strategies to recover motor function is a central goal of clinical research. In the last years the approach to the post-stroke function restore has moved from the physical rehabilitation to the evidence-based neurological rehabilitation. Brain-Computer Interface (BCI) technology offers the possibility to detect, monitor and eventually modulate brain activity. The potential of guiding altered brain activity back to a physiological condition through BCI and the assumption that this recovery of brain activity leads to the restoration of behaviour is the key element for the use of BCI systems for therapeutic purposes. To bridge the gap between research-oriented methodology in BCI design and the usability of a system in the clinical realm requires efforts towards BCI signal processing procedures that would optimize the balance between system accuracy and usability. The thesis focused on this issue and aimed to propose new algorithms and signal processing procedures that, by combining physiological and engineering approaches, would provide the basis for designing more usable BCI systems to support post-stroke motor recovery. Results showed that introduce new physiologically-driven approaches to the pre-processing of BCI data, methods to support professional end-users in the BCI control parameter selection according to evidence-based rehabilitation principles and algorithms for the parameter adaptation in time make the BCI technology more affordable, more efficient, and more usable and, therefore, transferable to the clinical realm
Neurophysiological constraints of control parameters for a brain computer interface system to support post-stroke motor rehabilitation
Full text linkThe Promotɶr is an all-in-one Brain Computer Interface (BCI)-system developed at Fondazione Santa Lucia (Rome, Italy) to support hand motor imagery practice after stroke. In this paper we focus on the optimization of control parameters for the BCI training. We compared two procedures for the feature selection: in the first, features were selected by means of a manual procedure (requiring “skilled users”), in the second a semiautomatic method, developed by us combining physiological and machine learning approaches, guided the feature selection. EEG-based BCI data set collected from 13 stroke patients were analyzed to the aim. No differences were found between the two procedures (paired-samples t-test, p=0.13). Results suggest that the semiautomatic procedure could be applied to support the manual feature selection, allowing no-skilled users to approach BCI technology for motor rehabilitation of stroke patients
Spatial filters selection towards a rehabilitation BCI
Full text linkIntroducing BCI technology in supporting motor imagery (MI) training has revealed the rehabilitative potential of MI, contributing to significantly better motor functional outcomes in stroke patients. To provide the most accurate and personalized feedback during the treatment, several stages of the electroencephalographic signal processing have to be optimized, including spatial filtering. This study focuses on data-independent approaches to optimize spatial filtering step.
Specific aims were: i) assessment of spatial filters' performance in relation to the hand and foot scalp areas; ii) evaluation of simultaneous use of multiple spatial filters; iii) minimization of the number of electrodes needed for training.
Our findings indicate that different spatial filters showed different performance related to the scalp areas considered. The simultaneous use of EEG signals conditioned with different spatial filters could either improve classification performance or, at same level of performance could lead to a reduction of the number of electrodes needed for successive training, thus improving usability of BCIs in clinical rehabilitation context
The Promotoer: a successful story of translational research in BCI for motor rehabilitation
Full text linkSeveral groups have recently demonstrated in the context of randomized controlled trials (RCTs) how sensorimotor Brain-Computer Interface (BCI) systems can be beneficial for post-stroke motor recovery. Following a successful RCT, at Fondazione Santa Lucia (FSL) a further translational effort was made with the implementation of the Promotœr, an all in-one BCIsupported MI training station. Up to now, 25 patients underwent training with the Promotɶr during their admission for rehabilitation purposes (in add-on to standard therapy). Two illustrative cases are presented. Though currently limited to FSL, the Promotɶr represents a successful story of translational research in BCI for stroke rehabilitation. Results are promising both in terms of feasibility of a BCI training in the context of a real rehabilitation program and in terms of clinical and neurophysiological benefits observed in the patients
P300-based Brain-Computer Interface for communication in assistive technology centers: influence of users’ profile on BCI access
No full textObjective. Assistive technology (AT) refers to any product that enables people to live independently and with dignity and to participate in activities of daily life. A Brain-Computer Interface (BCI) is an AT that provides an alternative output, based on neurophysiological signals, to control an external device. The aim of the study is to screen patients accessing an AT-center to investigate their eligibility for BCI access and the factors influencing the BCI control.
Approach. Thirty-five users and 11 healthy controls were included in the study. Participants were required to operate a P300-speller BCI. We investigated differences in BCI performance metrics (online accuracy and Information Transfer Rate) between end-user and control groups and we evaluated the influence of clinical diagnosis, socio-demographic factors, level of dependence and disability of users, neuropsychological profile on BCI performance.
Main results. 7.1% of the users controlled the system with a mean accuracy of 93.6±8.0%, while 8 users had an online accuracy below 70%. We found that the neuropsychological profile significantly affected online accuracy and ITR.
Significance. The percentage of users who had an accuracy considered as functional communication is an encouraging data in terms of BCI effectiveness. The results regarding accuracy and to the factors influencing (and not influencing) it, are a contribution to the process of introducing BCIs in the AT-centers, considering the BCI for communication as an additional input to provide multimodal access to AT
Automatic features selection in BCI-supported motor imagery practice for stroke rehabilitation
No full textBrain Computer Interfaces (BCIs) can support motor imagery practice during the neuromotor rehabilitation of post-stroke patients. The practical application of this approach in a clinical setting implies to simplify configuration procedures: the EEG activity to be employed in the BCI setting, and thus reinforced via the training, should be selected taking into account neurophysiological evidence and rehabilitation principles. In this study, we tested an automatic procedure to select the BCI control parameters (i.e. specific EEG signal’s characteristics) based on neurophysiological and rehabilitation principles. To this aim, we compared the classification’s performance of an algorithm for the automatic features selection (stepwise linear discriminant analysis) with a configuration procedures based on human choices. Preliminary results did not show significant differences of the proposed method with respect to the selection of features performed by highly skilled medical doctors and therapists
Corticomuscular and Intermuscular Coupling in Simple Hand Movements to Enable a Hybrid Brain-Computer Interface
Full text linkHybrid Brain-Computer Interfaces (BCIs) for upper limb rehabilitation after stroke should enable the reinforcement of "more normal" brain and muscular activity. Here, we propose the combination of corticomuscular coherence (CMC) and intermuscular coherence (IMC) as control features for a novel hybrid BCI for rehabilitation purposes. Multiple electroencephalographic (EEG) signals and surface electromyography (EMG) from 5 muscles per side were collected in 20 healthy participants performing finger extension (Ext) and grasping (Grasp) with both dominant and non-dominant hand. Grand average of CMC and IMC patterns showed a bilateral sensorimotor area as well as multiple muscles involvement. CMC and IMC values were used as features to classify each task versus rest and Ext versus Grasp. We demonstrated that a combination of CMC and IMC features allows for classification of both movements versus rest with better performance (Area Under the receiver operating characteristic Curve, AUC) for the Ext movement (0.97) with respect to Grasp (0.88). Classification of Ext versus Grasp also showed high performances (0.99). All in all, these preliminary findings indicate that the combination of CMC and IMC could provide for a comprehensive framework for simple hand movements to eventually be employed in a hybrid BCI system for post-stroke rehabilitation
GUIDER: a GUI for semiautomatic, physiologically driven EEG feature selection for a rehabilitation BCI
Full text linkGUIDER is a graphical user interface developed in MATLAB software environment to identify electroencephalography (EEG)-based brain computer interface (BCI) control features for a rehabilitation application (i.e. post-stroke motor imagery training). In this context, GUIDER aims to combine physiological and machine learning approaches. Indeed, GUIDER allows therapists to set parameters and constraints according to the rehabilitation principles (e.g. affected hemisphere, sensorimotor relevant frequencies) and foresees an automatic method to select the features among the defined subset. As a proof of concept, we compared offline performances between manual, just based on operator’s expertise and experience, and GUIDER semiautomatic features selection on BCI data collected from stroke patients during BCI-supported motor imagery training. Preliminary results suggest that this semiautomatic approach could be successfully applied to support the human selection reducing operator dependent variability in view of future multi-centric clinical trials
Brain and Muscle derived features to discriminate simple hand motor tasks for a rehabilitative BCI: comparative study on healthy and post-stroke individuals
No full textBrain-Computer Interfaces targeting post-stroke recovery of the upper limb employ mainly electroencephalography to decode movement-related brain activation. Recently hybrid systems including muscular activity were introduced. We compared the motor task discrimination abilities of three different features, namely event-related desynchronization/synchronization (ERD/ERS) and movement-related cortical potential (MRCP) as brain-derived features and cortico-muscular coherence (CMC) as a hybrid brain-muscle derived feature, elicited in 13 healthy subjects and 13 stroke patients during the execution/attempt of two simple hand motor tasks (finger extension and grasping) commonly employed in upper limb rehabilitation protocols.
Approach. We employed a three-way statistical design to investigate whether their ability to discriminate the two movements follows a specific temporal evolution along the movement execution and is eventually different among the three features and between the two groups. We also investigated the differences in performance at the single-subject level.
Main results. The ERD/ERS and the CMC-based classification showed similar temporal evolutions of the performance with a significant increase in accuracy during the execution phase while MRCP-based accuracy peaked at movement onset. Such temporal dynamics were similar but slower in stroke patients when the movements were attempted with the affected hand. Moreover, CMC outperformed the two brain features in healthy subjects and stroke patients when performing the task with their unaffected hand, whereas a higher variability across subjects was observed in patients performing the tasks with their affected hand. Interestingly, brain features performed better in this latter condition with respect to healthy subjects.
Significance. Our results provide hints to improve the design of Brain-Computer Interfaces for post-stroke rehabilitation, emphasizing the need for personalized approaches tailored to patients' characteristics and to the intended rehabilitative target
- …
