Classification of responders versus non-responders to tDCS by analyzing voltage between anode and cathode during treatment session

Abstract

Transcranial direct current stimulation (tDCS) has been shown to be beneficial as a potential treatment of several disorders such as depression, addiction and chronic pain. Despite promising results reported in research, there is variability in responsiveness to tDCS among subjects. However, the source of this variability is still unknown. Creating a mechanism of determining non-responders (vs. responders) is a crucial step in order to either understand the physiology behind tDCS or increase the effectiveness of treatment. This work proposes a versatile method to predict whether a subject responds to tDCS by analyzing the voltage measured between anode and cathode during a tDCS session. Two groups of subjects are determined as responders and non-responders by assessing the effect of tDCS on their motor potential evoked by transcranial magnetic stimulation (TMS). Voltage measurements are modeled by a double Debye model and two relaxation times are extracted for each measurement. A quadratic classifier is trained to recognize responders and nonresponders based on these relaxation times. Our classification results show that there is a significant correlation between relaxation times extracted from voltage and responsiveness to tDCS determined through motor evoked potentials. These results suggest that the relative speed of polarization processes occurring in electrodes and tissue may be associated the amount of current delivered to the brain.