One of the major concerns of recent studies is the correct discrimination between vegetative and minimally conscious state as the distinction between these two conditions has major implications for subsequent patient rehabilitation. In particular, it would be advantageous to establish communication with these patients. This work describes a procedure using EEG to detect brain responses to imagery instruction in patients with disorders of consciousness. Five healthy subjects and five patients with different disorders of consciousness took part in the study. A support vector machine classifier applied to EEG data was used to distinguish two mental tasks (Imagery Trial) and to detect answers to simple yes or no questions (pre-Communication Trial). The proposed procedure uses feature selection based on a nested-leave-one-out algorithm to reduce the number of electrodes required. We obtained a mean classification accuracy of 82.0% (SD 5.1%) for healthy subjects and 84.6% (SD 9.1%) for patients in the Imagery Trial, and a mean classification accuracy of 80.7% (SD 11.5%) for healthy subjects and 91.7% (SD 7.4%) for patients in the pre-Communication Trial. The subset of electrodes selected was subject and session dependent.

This study evaluated the possibility to classify two mental states corresponding to two imagery tasks, using non-event-related EEG techniques, and to use them for communication purposes. Firstly, the authors outlined a general, automated procedure to identify the BE (Best Electrodes) sites in terms of statistical significance of the PSD features in the two tasks. They paid particular attention to issues related to discrimination between and communication with patients affected by different levels of consciousness disorders. This preliminary study involved just five healthy subjects and five patients and hence did not aim to define a standard protocol for clinical assessment. The proposed automated procedure provided good classification accuracy for the two investigated imagery tasks, while identifying suitable and clearly defined sites for EEG spectral parameters classification. These promising results suggest further studies and investigations, namely: 1) increasing the number of patients who are vegetative or minimally conscious; 2) developing an online procedure to establish communication with the patients.

The EEG data were collected using our Neurowave System.