Blind testing based on ICA for quasi-brain-death EEG

Electroencephalography (EEG) signal analysis and EEG-based preliminary examination has been proposed in the clinical brain death determination. In our previous studies, with knowing the clinical diagnosis of the patient, the result that obtained by using independent component analysis (ICA) for quasi-brain-death EEG is the same with that from the standard clinical procedure. In this paper, we present a blind analysis process based on ICA in the condition of unknowing the clinical symptoms of patients. Significant feature differences between three cases indicate one patient being in coma and the another changing to quasi-brain-death. Being identical to further clinical diagnose, the result illustrates the effectiveness of our time-saving method and implies its value as a reference for brain death diagnosis in clinical practice.