Several of the neurological diseases that human beings can suffer result in severe disabilities. For instance, the ability of people affected by amyotrophic lateral sclerosis (ALS), muscular distrophy or spinal cord injuries to physically interact with the environment is usually reduced, and they may even lose it completely.
ALS patients suffer from a syndrome known as locked-in syndrome. In its classical modality, this syndrome is defined by the patient’s inability to make any movement but blinks and vertical eye displacements, despite being still conscious. This renders them completely dependent not only on their close family, but also on ventilatory machines to remain alive. If the disease draws on, the patient is bound to be unable to make even those residual movements, thus remaining completely isolated.
In some cases patients can use interaction systems as eyetrackers to communicate, but in extreme situations it is crucial to provide the patient with a non-muscular communication path. This is nowadays feasible thanks to an array of systems, which are grouped under the name of brain—computer interfaces (BCI). Their common feature is to process the brain’s electrical activity for extracting information that can be used to command an external device (e.g., a computer or a wheelchair).
Although there are infinite applications of such systems, the main one has been and still is aimed at the medical field, specifically assistive technology and neurorehabilitation, being particularly related to ALS.
Considering the painful situation of these patients and others that suffer from severe motor disabilities, the efforts of the scientific community were aimed from the very beginning at developing applications for BCI systems with two clear goals in mind: controlling a wheelchair and a virtual keyboard, in order to restore the patient’s ability to move and communicate, respectively. However, one of the long-standing obstacles that have prevented the daily use of such applications is their low reliability, mainly due to the great variability of patients, regarding not only their brain activity, but also their psychological features (personality, attentional resources, tolerance to frustration, etc.). This lack of a single user model implies that BCI systems have to be tailored to each particular patient, which, in turn, entails applying a user-centred design and evaluation protocol.
This project aims to perform research tasks that improve the usability of these systems applied to the control of a virtual keyboard and a BCI-robotic wheelchair.