Performance evaluation of brain state discrimination using near-infrared spectroscopy for brain-computer interface: an exploratory case study

Abstract

A new method of environmental control that does not depend on motor functions is eagerly awaited to support independent living for people with severe quadriplegia. In this study, we conducted an exploratory case study of brain state discrimination in a quadriplegic subject to develop a brain-computer interface controlled by a mental task execution. We measured near-infrared spectroscopy (NIRS) signals in a patient with a cervical spinal cord injury while performing mental tasks. A block design with a task and a rest separated by 30 seconds was used to measure brain function. The utilized mental tasks were mental arithmetic and Japanese word chains. Seventeen trials of the NIRS signal were acquired for each task, and 52 samples with 24-dimensional features per trial data were extracted. Random forest was used as the classifier, and the number of correct responses in the binary discrimination of the brain states were calculated by cross-validation. The exact binomial test was used for the statistical analysis, and a two-tailed test with a significance level of 5% was performed. The results showed that the number of correct responses was 15 out of 17 (p = 0.002) for the mental arithmetic task and 14 out of 17 (p = 0.013) for the Japanese word chains task, for an overall accuracy of 85%. These results indicate that this method can discriminate the brain state of a patient with quadriplegia from the NIRS signal. By applying these findings to a brain-computer interface, it will be possible to provide a new means of environmental control for individuals with quadriplegia.

Keywords

• brain-computer interface
• near-infrared spectroscopy
• machine learning
• mental task
• occupational therapy
• assistive technology
• spinal cord injury