Analysis of the Impact of the Presence of Physical Pain in fNIRS-based BCI Systems

An important application of brain computer interface devices (BCIs) is in assistive systems for patients with motor and communication disabilities. Due to their condition, these patients may experience pain. However, how the presence of pain influences the operation of such BCIs has not been fully investigated. This paper studies the impact of the presence of acute pain on the classification accuracy of a BCI, which employs functional near infrared spectroscopy (fNIRS) for brain signal acquisition. Cortical signals are obtained in the presence and absence of an external pain stimulus, while participants perform two mental arithmetic tasks. Convolutional neural network (CNN) is used to classify the tasks. It is observed that when the classifier is trained on pain-free data and tested on data obtained in the presence of pain, the classification accuracy significantly drops. Next, multi-label classification is performed to simultaneously identify the presence of pain and classify the tasks, further demonstrating that the distinction of tasks in the presence of pain is challenging. Finally, to mitigate the impact of pain, it is proposed to train the model collectively on data obtained in the presence and the absence of pain. It is observed that using this approach significantly improves the classification accuracy. Our results suggest that it is critical to include data obtained in the presence of pain in the training process of the classification models, when designing BCIs in assistive systems for patients.