BRAIN-COMPUTER INTERFACE COMMUNICATION FOR A LOCKED IN CHILD WITH EPILEPTIC ENCEPHALOPATHY E. Zewdie 1,2,3 , Z. Jadavji 1,2,3 , D. Kaketsis 1 , A. Kirton 1,2,3 1 Calgary Pediatric Stroke Program, University of Calgary, AB, Canada 2 Hotchkiss Brain Institute, University of Calgary, Calgary AB, Canada 3 Alberta Children’s Hospital Research Institute, University of Calgary, Calgary, AB, Canada E-mail: ephrem.zewdie@ahs.ca ABSTRACT: There are many technologies being developed to assist individuals with severe disability. Devices based on human machine interface have been used to restore or replace lost movement and communication. Unfortunately, these technologies have not yet been extensively explored in children with severe disability. This paper describes a case study of a 16 year old patient in a locked-in state with virtually no communication. She is unable to move her body and is non-verbal. BCI potential was assessed using the mindBEAGLE system which utilizes auditory and vibro-tactile modalities to evoke a response. Long-term monitoring on clinical EEG characterized the neurophysiology of the patient including nearly continuous generalized discharges. The best classification accuracy for auditory and vibrotactile BCI was 40%. Higher accuracy (54%) was achieved using the motor imagery modality. Clinical neurophysiology measures can inform or to some extend predict the success of BCI performance of different modalities contributing to the user-centered design in BCI development. INTRODUCTION Being able to communicate is an essential right and need of every human being. Imagine being aware of your environment, seeing, hearing and feeling everything around you, but being unable to move or speak to express yourself. Such Lock-in Syndrome (LIS) describes patients who are conscious and aware but severely paralyzed with complete immobility and loss of verbal communication. It can be caused by acute injuries (e.g., brainstem stroke, which is the most frequent cause of LIS) to chronic causes (e.g., amyotrophic lateral sclerosis; ALS)[1] that render the motor system non-functional[2]. LIS can be divided into incomplete (some voluntary movement in addition to eye movement), classic (preserved vertical eye movement and blinking) or complete (no voluntary movement). LIS involves loss of all voluntary muscle control other than sometimes restricted lateral or vertical eye movements. As a result, most communication attempts utilize eye movement [3] for communication control. For example, eye-gaze computers can be controlled by the user’s eye movement and be interpreted by a second person given the user has good control of eye movements. This kind of communication requires the help of a second person who needs to be willing and capable of following time- consuming procedures. Brain computer interface (BCI) systems based on sensorimotor rhythms and evoked potentials have been developed and used to provide such quadriplegic patients with potential options for communication and control independent of any movement input[4]. BCIs have been used by LIS patients to communicate[5,6] and even used to navigate a computer[7]. BCIs are also used to control devices that have permitted patients with spinal cord injury to regain movement[8] and control a wheelchair[9]. Virtually all of this progress has occurred in adults. EEG based BCI can use different modalities to evoke a response, such as event-related potentials (ERP). The most common ones are visual, auditory and vibro- tactile. Investigation of different modalities of BCI in a single LIS patient found that the vibro-tactile modality was more effective for communication than visual and auditory modalities[10]. Similarly, Guger et al. [11] reported that 2/3 LIS patients reached a classification of 100% using vibro-tactile modality. Such non-invasive BCI systems typically rely on EEG. However, some patients with acquired brain injuries and other conditions that may benefit from BCI may also have abnormal EEG. Epileptic encephalopathies may include frequent pathological generalized discharges that are not seizures but may impair cognition and awareness[12]. It is unknown if available EEG-based BI paradigms can still work in the presence of such overlying EEG patterns. The aim of this paper is to report a case study of exploring different BCI modalities and associated event related potentials (ERP) and event-related desynchronization(ERD) used to establish communication in a child with LIS and epileptic Proceedings of the 8th Graz Brain-Computer Interface Conference 2019 DOI: 10.3217/978-3-85125-682-6-27