Learning from brain control: clinical application of brain–computer interfaces

A dataset of EEG and EOG from an auditory EOG-based communication system for patients in locked-in state

The dataset presented here contains recordings of electroencephalogram (EEG) and electrooculogram (EOG) from four advanced locked-in state (LIS) patients suffering from ALS (amyotrophic lateral sclerosis). These patients could no longer use commercial eye-trackers, but they could still move their eyes and used the remnant oculomotor activity to select letters to form words and sentences using a novel auditory communication system. Data were recorded from four patients during a variable range of visits (from 2 to 10), each visit comprised of 3.22 ± 1.21 days and consisted of 5.57 ± 2.61 sessions recorded per day. The patients performed a succession of different sessions, namely, Training, Feedback, Copy spelling, and Free spelling. The dataset provides an insight into the progression of ALS and presents a valuable opportunity to design and improve assistive and alternative communication technologies and brain-computer interfaces. It might also help redefine the course of progression in ALS, thereby improving clinical judgement and treatment.

EEG-Based Adaptive Driver-Vehicle Interface Using Variational Autoencoder and PI-TSVM

Event-related potential (ERP)-based driver-vehicle interfaces (DVIs) have been developed to provide a communication channel for people with disabilities to drive a vehicle. However, they require a tedious and time-consuming training procedure to build the decoding model, which can translate EEG signals into commands. In this paper, to address this problem, we propose an adaptive DVI by using a new semi-supervised algorithm. The decoding model of the proposed DVI is first built with a small labeled training set, and then gradually improved by updating the proposed semi-supervised decoding model with new collected unlabeled EEG signals. In our semi-supervised algorithm, independent component analysis (ICA) and Kalman smoother are first used to improve the signal-to-noise ratio (SNR). After that, variational autoencoder is applied to provide a robust feature representation of EEG signals. Finally, a prior information-based transductive support vector machine (PI-TSVM) classifier is developed to translate these features into commands. Experimental results show that the proposed DVI can significantly reduce the training effort. After a short updating, its performance can be close to that of the supervised DVI requiring a lengthy training procedure. This work is vital for advancing the application of these DVIs.

Brain-Computer Interface-Based Communication in the Completely Locked-In State

Despite partial success, communication has remained impossible for persons suffering from complete motor paralysis but intact cognitive and emotional processing, a state called complete locked-in state (CLIS). Based on a motor learning theoretical context and on the failure of neuroelectric brain–computer interface (BCI) communication attempts in CLIS, we here report BCI communication using functional near-infrared spectroscopy (fNIRS) and an implicit attentional processing procedure. Four patients suffering from advanced amyotrophic lateral sclerosis (ALS)—two of them in permanent CLIS and two entering the CLIS without reliable means of communication—learned to answer personal questions with known answers and open questions all requiring a “yes” or “no” thought using frontocentral oxygenation changes measured with fNIRS. Three patients completed more than 46 sessions spread over several weeks, and one patient (patient W) completed 20 sessions. Online fNIRS classification of personal questions with known answers and open questions using linear support vector machine (SVM) resulted in an above-chance-level correct response rate over 70%. Electroencephalographic oscillations and electrooculographic signals did not exceed the chance-level threshold for correct communication despite occasional differences between the physiological signals representing a “yes” or “no” response. However, electroencephalogram (EEG) changes in the theta-frequency band correlated with inferior communication performance, probably because of decreased vigilance and attention. If replicated with ALS patients in CLIS, these positive results could indicate the first step towards abolition of complete locked-in states, at least for ALS.

"Locked in" patients suffering from advanced amyotrophic lateral sclerosis, with no reliable means of communication, can learn to answer questions requiring a “yes” or “no” thought using frontocentral oxygenation changes measurable by functional near-infrared spectroscopy.

Despite scientific and technological advances, communication has remained impossible for persons suffering from complete motor paralysis but intact cognitive and emotional processing, a condition that is called completely locked-in state. Brain–computer interfaces based on neuroelectrical technology (like an electroencephalogram) have failed at providing patients in a completely locked-in state with means to communicate. Therefore, here we explored if a brain–computer interface based on functional near infrared spectroscopy (fNIRS)—which measures brain hemodynamic responses associated with neuronal activity—could overcome this barrier. Four patients suffering from advanced amyotrophic lateral sclerosis (ALS), two of them in permanent completely locked-in state and two entering the completely locked-in state without reliable means of communication, learned to answer personal questions with known answers and open questions requiring a “yes” or “no” by using frontocentral oxygenation changes measured with fNIRS. These results are, potentially, the first step towards abolition of completely locked-in states, at least for patients with ALS.

Brain-computer interfaces for communication and rehabilitation

Brain-computer interfaces (BCIs) use brain activity to control external devices, thereby enabling severely disabled patients to interact with the environment. A variety of invasive and noninvasive techniques for controlling BCIs have been explored, most notably EEG, and more recently, near-infrared spectroscopy. Assistive BCIs are designed to enable paralyzed patients to communicate or control external robotic devices, such as prosthetics; rehabilitative BCIs are designed to facilitate recovery of neural function. In this Review, we provide an overview of the development of BCIs and the current technology available before discussing experimental and clinical studies of BCIs. We first consider the use of BCIs for communication in patients who are paralyzed, particularly those with locked-in syndrome or complete locked-in syndrome as a result of amyotrophic lateral sclerosis. We then discuss the use of BCIs for motor rehabilitation after severe stroke and spinal cord injury. We also describe the possible neurophysiological and learning mechanisms that underlie the clinical efficacy of BCIs.

Brain-computer interfaces in the completely locked-in state and chronic stroke

Brain-computer interfaces (BCIs) use brain activity to control external devices, facilitating paralyzed patients to interact with the environment. In this chapter, we discuss the historical perspective of development of BCIs and the current advances of noninvasive BCIs for communication in patients with amyotrophic lateral sclerosis and for restoration of motor impairment after severe stroke. Distinct techniques have been explored to control a BCI in patient population especially electroencephalography (EEG) and more recently near-infrared spectroscopy (NIRS) because of their noninvasive nature and low cost. Previous studies demonstrated successful communication of patients with locked-in state (LIS) using EEG- and invasive electrocorticography-BCI and intracortical recordings when patients still showed residual eye control, but not with patients with complete LIS (ie, complete paralysis). Recently, a NIRS-BCI and classical conditioning procedure was introduced, allowing communication in patients in the complete locked-in state (CLIS). In severe chronic stroke without residual hand function first results indicate a possible superior motor rehabilitation to available treatment using BCI training. Here we present an overview of the available studies and recent results, which open new doors for communication, in the completely paralyzed and rehabilitation in severely affected stroke patients. We also reflect on and describe possible neuronal and learning mechanisms responsible for BCI control and perspective for future BMI research for communication in CLIS and stroke motor recovery.