No abstract

Recent advances in neuroimaging technologies have provided insights into detecting residual consciousness and assessing cognitive abilities in patients with disorders of consciousness (DOC). Functional near-infrared spectroscopy (fNIRS) is non-invasive and portable and can be used for longitudinal bedside monitoring, making it uniquely suited for evaluating brain function in patients with DOC at appropriate spatiotemporal resolutions. In this pilot study, an active command-driven motor imagery (MI) paradigm based on fNIRS was used to detect residual consciousness in patients with prolonged DOC. A support vector machine (SVM) classifier was used to classify yes-or-no responses. The results showed that relatively reliable responses were detected from three out of five patients in a minimally consciousness state (MCS). One of the patients answered all the questions accurately when assessed according to this method. This study confirmed the feasibility of using portable fNIRS technology to detect residual cognitive ability in patients with prolonged DOC by active command-driven motor imagery. We hope to detect the exact level of consciousness in DOC patients who may have a higher level of consciousness.

Canonical correlation analysis (CCA) has been used for the steady-state visual evoked potential (SSVEP) based brain-computer interface (BCI) for a long time. However, the reference signal of CCA is relatively simple and lacks subject-specific information. Moreover, over-fitting may occur when a short time window (TW) length was used in CCA. In this article, an optimized L1-regularized multiway canonical correlation analysis (L1-MCCA) is combined with a support vector machine (SVM) to overcome the aforementioned shortcomings in CCA. The correlation coefficients obtained by L1-MCCA were transferred into a particle-swarm-optimization (PSO)-optimized support vector machine (SVM) classifier to improve the classification accuracy. The performance of the proposed method was evaluated and compared with the traditional CCA and power spectral density (PSD) methods. The results showed that the accuracy of the L1-MCCA-PSO-SVM was 96.36% and 98.18% respectively when the TW lengths were 2 s and 6 s. This accuracy is higher than that of the traditional CCA and PSD methods.