Detection of Hypoglycemia using ear-EEG

Hypoglycemia refers to a condition in which the blood glucose level is below physiological normal level. It has previously been demonstrated that hypoglycemia results in characteristic changes in the EEG signals recorded from electrodes on the scalp. Scalp EEG is not suitable for continuous measurements, due to its obtrusive nature and limited capabilities for monitoring in real-life environments. The aim of this study was to assess the feasibility of detecting hypoglycemia episodes using EEG signals recorded with dry-contact in-ear electrodes, which have the potential for long-term EEG monitoring in real-life situations and provide similar information to that recorded with scalp EEG. Data from 5 diabetic patients was used for this study. Six ear-EEG channels recorded from the right ear, and channels C3, Pz, T7, and T8 were used for the analysis and classification procedures. A Support Vector Machine was used to detect the hypoglycemic episodes, using the RMS of the θ, α, β, and γ frequency bands as features. The results showed that there were no statistical differences between the sensitivity and specificity of the scalp-scalp and ear-scalp EEG channels.