A visual brain-computer interface as communication aid for patients with amyotrophic lateral sclerosis

Machine learning and brain-computer interface approaches in prognosis and individualized care strategies for individuals with amyotrophic lateral sclerosis: A systematic review

Amyotrophic lateral sclerosis (ALS) characterized by progressive degeneration of motor neurons is a debilitating disease, posing substantial challenges in both prognosis and daily life assistance. However, with the advancement of machine learning (ML) which is renowned for tackling many real-world settings, it can offer unprecedented opportunities in prognostic studies and facilitate individuals with ALS in motor-imagery tasks. ML models, such as random forests (RF), have emerged as the most common and effective algorithms for predicting disease progression and survival time in ALS. The findings revealed that RF models had an excellent predictive performance for ALS, with a testing R2 of 0.524 and minimal treatment effects of 0.0717 for patient survival time. Despite significant limitations in sample size, with a maximum of 18 participants, which may not adequately reflect the population diversity being studied, ML approaches have been effectively applied to ALS datasets, and numerous prognostic models have been tested using neuroimaging data, longitudinal datasets, and core clinical variables. In many literatures, the constraints of ML models are seldom explicitly enunciated. Therefore, the main objective of this research is to provide a review of the most significant studies on the usage of ML models for analyzing ALS. This review covers a variation of ML algorithms involved in applications in ALS prognosis besides, leveraging ML to improve the efficacy of brain-computer interfaces (BCIs) for ALS individuals in later stages with restricted voluntary muscular control. The key future advances in individualized care and ALS prognosis may include the advancement of more personalized care aids that enable real-time input and ongoing validation of ML in diverse healthcare contexts.

Evaluation of Different Visual Feedback Methods for Brain-Computer Interfaces (BCI) Based on Code-Modulated Visual Evoked Potentials (cVEP)

Brain-computer interfaces (BCIs) enable direct communication between the brain and external devices using electroencephalography (EEG) signals. BCIs based on code-modulated visual evoked potentials (cVEPs) are based on visual stimuli, thus appropriate visual feedback on the interface is crucial for an effective BCI system. Many previous studies have demonstrated that implementing visual feedback can improve information transfer rate (ITR) and reduce fatigue. This research compares a dynamic interface, where target boxes change their sizes based on detection certainty, with a threshold bar interface in a three-step cVEP speller. In this study, we found that both interfaces perform well, with slight variations in accuracy, ITR, and output characters per minute (OCM). Notably, some participants showed significant performance improvements with the dynamic interface and found it less distracting compared to the threshold bars. These results suggest that while average performance metrics are similar, the dynamic interface can provide significant benefits for certain users. This study underscores the potential for personalized interface choices to enhance BCI user experience and performance. By improving user friendliness, performance, and reducing distraction, dynamic visual feedback could optimize BCI technology for a broader range of users.

Multi-source domain adaptation based tempo-spatial convolution network for cross-subject EEG classification in RSVP task

Objective.Many subject-dependent methods were proposed for electroencephalogram (EEG) classification in rapid serial visual presentation (RSVP) task, which required a large amount of data from new subject and were time-consuming to calibrate system. Cross-subject classification can realize calibration reduction or zero calibration. However, cross-subject classification in RSVP task is still a challenge.Approach.This study proposed a multi-source domain adaptation based tempo-spatial convolution (MDA-TSC) network for cross-subject RSVP classification. The proposed network consisted of three modules. First, the common feature extraction with multi-scale tempo-spatial convolution was constructed to extract domain-invariant features across all subjects, which could improve generalization of the network. Second, the multi-branch domain-specific feature extraction and alignment was conducted to extract and align domain-specific feature distributions of source and target domains in pairs, which could consider feature distribution differences among source domains. Third, the domain-specific classifier was exploited to optimize the network through loss functions and obtain prediction for the target domain.Main results.The proposed network was evaluated on the benchmark RSVP dataset, and the cross-subject classification results showed that the proposed MDA-TSC network outperformed the reference methods. Moreover, the effectiveness of the MDA-TSC network was verified through both ablation studies and visualization.Significance.The proposed network could effectively improve cross-subject classification performance in RSVP task, and was helpful to reduce system calibration time.

Recent Progress in Wearable Brain-Computer Interface (BCI) Devices Based on Electroencephalogram (EEG) for Medical Applications: A Review

Importance: Brain-computer interface (BCI) decodes and converts brain signals into machine instructions to interoperate with the external world. However, limited by the implantation risks of invasive BCIs and the operational complexity of conventional noninvasive BCIs, applications of BCIs are mainly used in laboratory or clinical environments, which are not conducive to the daily use of BCI devices. With the increasing demand for intelligent medical care, the development of wearable BCI systems is necessary. Highlights: Based on the scalp-electroencephalogram (EEG), forehead-EEG, and ear-EEG, the state-of-the-art wearable BCI devices for disease management and patient assistance are reviewed. This paper focuses on the EEG acquisition equipment of the novel wearable BCI devices and summarizes the development direction of wearable EEG-based BCI devices. Conclusions: BCI devices play an essential role in the medical field. This review briefly summarizes novel wearable EEG-based BCIs applied in the medical field and the latest progress in related technologies, emphasizing its potential to help doctors, patients, and caregivers better understand and utilize BCI devices.

Non-invasive EEG-based BCI spellers from the beginning to today: a mini-review

The defeat of the central motor neuron leads to the motor disorders. Patients lose the ability to control voluntary muscles, for example, of the upper limbs, which introduces a fundamental dissonance in the possibility of daily use of a computer or smartphone. As a result, the patients lose the ability to communicate with other people. The article presents the most popular paradigms used in the brain-computer-interface speller system and designed for typing by people with severe forms of the movement disorders. Brain-computer interfaces (BCIs) have emerged as a promising technology for individuals with communication impairments. BCI-spellers are systems that enable users to spell words by selecting letters on a computer screen using their brain activity. There are three main types of BCI-spellers: P300, motor imagery (MI), and steady-state visual evoked potential (SSVEP). However, each type has its own limitations, which has led to the development of hybrid BCI-spellers that combine the strengths of multiple types. Hybrid BCI-spellers can improve accuracy and reduce the training period required for users to become proficient. Overall, hybrid BCI-spellers have the potential to improve communication for individuals with impairments by combining the strengths of multiple types of BCI-spellers. In conclusion, BCI-spellers are a promising technology for individuals with communication impairments. P300, MI, and SSVEP are the three main types of BCI-spellers, each with their own advantages and limitations. Further research is needed to improve the accuracy and usability of BCI-spellers and to explore their potential applications in other areas such as gaming and virtual reality.

Combining brain-computer interfaces and multiplayer video games: an application based on c-VEPs

Introduction and objective

Video games are crucial to the entertainment industry, nonetheless they can be challenging to access for those with severe motor disabilities. Brain-computer interfaces (BCI) systems have the potential to help these individuals by allowing them to control video games using their brain signals. Furthermore, multiplayer BCI-based video games may provide valuable insights into how competitiveness or motivation affects the control of these interfaces. Despite the recent advancement in the development of code-modulated visual evoked potentials (c-VEPs) as control signals for high-performance BCIs, to the best of our knowledge, no studies have been conducted to develop a BCI-driven video game utilizing c-VEPs. However, c-VEPs could enhance user experience as an alternative method. Thus, the main goal of this work was to design, develop, and evaluate a version of the well-known 'Connect 4' video game using a c-VEP-based BCI, allowing 2 users to compete by aligning 4 same-colored coins vertically, horizontally or diagonally.

Methods

The proposed application consists of a multiplayer video game controlled by a real-time BCI system processing 2 electroencephalograms (EEGs) sequentially. To detect user intention, columns in which the coin can be placed was encoded with shifted versions of a pseudorandom binary code, following a traditional circular shifting c-VEP paradigm. To analyze the usability of our application, the experimental protocol comprised an evaluation session by 22 healthy users. Firstly, each user had to perform individual tasks. Afterward, users were matched and the application was used in competitive mode. This was done to assess the accuracy and speed of selection. On the other hand, qualitative data on satisfaction and usability were collected through questionnaires.

Results

The average accuracy achieved was 93.74% ± 1.71%, using 5.25 seconds per selection. The questionnaires showed that users felt a minimal workload. Likewise, high satisfaction values were obtained, highlighting that the application was intuitive and responds quickly and smoothly.

Conclusions

This c-VEP based multiplayer video game has reached suitable performance on 22 users, supported by high motivation and minimal workload. Consequently, compared to other versions of "Connect 4" that utilized different control signals, this version has exhibited superior performance.

Blink-To-Live eye-based communication system for users with speech impairments

Eye-based communication languages such as Blink-To-Speak play a key role in expressing the needs and emotions of patients with motor neuron disorders. Most invented eye-based tracking systems are complex and not affordable in low-income countries. Blink-To-Live is an eye-tracking system based on a modified Blink-To-Speak language and computer vision for patients with speech impairments. A mobile phone camera tracks the patient's eyes by sending real-time video frames to computer vision modules for facial landmarks detection, eye identification and tracking. There are four defined key alphabets in the Blink-To-Live eye-based communication language: Left, Right, Up, and Blink. These eye gestures encode more than 60 daily life commands expressed by a sequence of three eye movement states. Once the eye gestures encoded sentences are generated, the translation module will display the phrases in the patient's native speech on the phone screen, and the synthesized voice can be heard. A prototype of the Blink-To-Live system is evaluated using normal cases with different demographic characteristics. Unlike the other sensor-based eye-tracking systems, Blink-To-Live is simple, flexible, and cost-efficient, with no dependency on specific software or hardware requirements. The software and its source are available from the GitHub repository ( https://github.com/ZW01f/Blink-To-Live ).

Brain-machine interface-based training for improving upper extremity function after stroke: A meta-analysis of randomized controlled trials

Background

Upper extremity dysfunction after stroke is an urgent clinical problem that greatly affects patients' daily life and reduces their quality of life. As an emerging rehabilitation method, brain-machine interface (BMI)-based training can extract brain signals and provide feedback to form a closed-loop rehabilitation, which is currently being studied for functional restoration after stroke. However, there is no reliable medical evidence to support the effect of BMI-based training on upper extremity function after stroke. This review aimed to evaluate the efficacy and safety of BMI-based training for improving upper extremity function after stroke, as well as potential differences in efficacy of different external devices.

Methods

English-language literature published before April 1, 2022, was searched in five electronic databases using search terms including “brain-computer/machine interface”, “stroke” and “upper extremity.” The identified articles were screened, data were extracted, and the methodological quality of the included trials was assessed. Meta-analysis was performed using RevMan 5.4.1 software. The GRADE method was used to assess the quality of the evidence.

Results

A total of 17 studies with 410 post-stroke patients were included. Meta-analysis showed that BMI-based training significantly improved upper extremity motor function [standardized mean difference (SMD) = 0.62; 95% confidence interval (CI) (0.34, 0.90); I² = 38%; p < 0.0001; n = 385; random-effects model; moderate-quality evidence]. Subgroup meta-analysis indicated that BMI-based training significantly improves upper extremity motor function in both chronic [SMD = 0.68; 95% CI (0.32, 1.03), I² = 46%; p = 0.0002, random-effects model] and subacute [SMD = 1.11; 95%CI (0.22, 1.99); I² = 76%; p = 0.01; random-effects model] stroke patients compared with control interventions, and using functional electrical stimulation (FES) [SMD = 1.11; 95% CI (0.67, 1.54); I² = 11%; p < 0.00001; random-effects model]or visual feedback [SMD = 0.66; 95% CI (0.2, 1.12); I² = 4%; p = 0.005; random-effects model;] as the feedback devices in BMI training was more effective than using robot. In addition, BMI-based training was more effective in improving patients' activities of daily living (ADL) than control interventions [SMD = 1.12; 95% CI (0.65, 1.60); I² = 0%; p < 0.00001; n = 80; random-effects model]. There was no statistical difference in the dropout rate and adverse effects between the BMI-based training group and the control group.

Conclusion

BMI-based training improved upper limb motor function and ADL in post-stroke patients. BMI combined with FES or visual feedback may be a better combination for functional recovery than robot. BMI-based trainings are well-tolerated and associated with mild adverse effects.

Imaginary Finger Movements Decoding Using Empirical Mode Decomposition and a Stacked BiLSTM Architecture

Motor Imagery Electroencephalogram (MI-EEG) signals are widely used in Brain-Computer Interfaces (BCI). MI-EEG signals of large limbs movements have been explored in recent researches because they deliver relevant classification rates for BCI systems. However, smaller and noisy signals corresponding to hand-finger imagined movements are less frequently used because they are difficult to classify. This study proposes a method for decoding finger imagined movements of the right hand. For this purpose, MI-EEG signals from C3, Cz, P3, and Pz sensors were carefully selected to be processed in the proposed framework. Therefore, a method based on Empirical Mode Decomposition (EMD) is used to tackle the problem of noisy signals. At the same time, the sequence classification is performed by a stacked Bidirectional Long Short-Term Memory (BiLSTM) network. The proposed method was evaluated using k-fold cross-validation on a public dataset, obtaining an accuracy of 82.26%.

Brain-computer interfaces based on code-modulated visual evoked potentials (c-VEP): a literature review

Objective.Code-modulated visual evoked potentials (c-VEP) have been consolidated in recent years as robust control signals capable of providing non-invasive brain-computer interfaces (BCIs) for reliable, high-speed communication. Their usefulness for communication and control purposes has been reflected in an exponential increase of related articles in the last decade. The aim of this review is to provide a comprehensive overview of the literature to gain understanding of the existing research on c-VEP-based BCIs, since its inception (1984) until today (2021), as well as to identify promising future research lines.Approach.The literature review was conducted according to the Preferred Reporting Items for Systematic reviews and Meta-Analysis guidelines. After assessing the eligibility of journal manuscripts, conferences, book chapters and non-indexed documents, a total of 70 studies were included. A comprehensive analysis of the main characteristics and design choices of c-VEP-based BCIs was discussed, including stimulation paradigms, signal processing, modeling responses, applications, etc.Main results.The literature review showed that state-of-the-art c-VEP-based BCIs are able to provide an accurate control of the system with a large number of commands, high selection speeds and even without calibration. In general, a lack of validation in real setups was observed, especially regarding the validation with disabled populations. Future work should be focused toward developing self-paced c-VEP-based portable BCIs applied in real-world environments that could exploit the unique benefits of c-VEP paradigms. Some aspects such as asynchrony, unsupervised training, or code optimization still require further research and development.Significance.Despite the growing popularity of c-VEP-based BCIs, to the best of our knowledge, this is the first literature review on the topic. In addition to providing a joint discussion of the advances in the field, some future lines of research are suggested to contribute to the development of reliable plug-and-play c-VEP-based BCIs.