Enhanced network synchronization connectivity following transcranial direct current stimulation (tDCS) in bipolar depression: effects on EEG oscillations and deep learning-based predictors of clinical remission

Abstract

AbstractAimTo investigate oscillatory networks in bipolar depression, effects of a home-based tDCS treatment protocol, and potential predictors of clinical response.Methods20 participants (14 women) with bipolar disorder, mean age 50.75 ± 10.46 years, in a depressive episode of severe severity (mean Montgomery-Åsberg Rating Scale (MADRS) score 24.60 ± 2.87) received home-based transcranial direct current stimulation (tDCS) treatment for 6 weeks. Clinical remission defined as MADRS score < 10. Resting-state EEG data were acquired at baseline, prior to the start of treatment, and at the end of treatment, using a portable 4-channel EEG device (electrode positions: AF7, AF8, TP9, TP10). EEG band power was extracted for each electrode and phase locking value (PLV) was computed as a functional connectivity measure of phase synchronization. Deep learning was applied to pre-treatment PLV features to examine potential predictors of clinical remission.ResultsFollowing treatment, 11 participants (9 women) attained clinical remission. A significant positive correlation was observed with improvements in depressive symptoms and delta band PLV in frontal and temporoparietal regional channel pairs. An interaction effect in network synchronisation was observed in beta band PLV in temporoparietal regions, in which participants who attained clinical remission showed increased synchronisation following tDCS treatment, which was decreased in participants who did not achieve clinical remission. Main effects of clinical remission status were observed in several PLV bands: clinical remission following tDCS treatment was associated with increased PLV in frontal and temporal regions and in several frequency bands, including delta, theta, alpha and beta, as compared to participants who did not achieve clinical remission. The highest deep learning prediction accuracy 69.45% (sensitivity 71.68%, specificity 66.72%) was obtained from PLV features combined from theta, beta, and gamma bands.ConclusionstDCS treatment enhances network synchronisation, potentially increasing inhibitory control, which underscores improvement in depressive symptoms. Baseline EEG-based measures might aid predicting clinical response.