Prediction of Clinical Response of Transcranial Magnetic Stimulation Treatment for Major Depressive Disorder Using Hyperdimensional Computing

Cognitive control dysregulation is nearly universal across disorders, including major depressive disorder (MDD). Achieving comparable response rates to medication, the transcranial magnetic stimulation (TMS) mechanism and its effect on cognitive control have not been well understood yet. This paper investigates the predictive capability of the clinical response to TMS treatment using 34 cognitive variables measured from TMS treatment of 22 MDD subjects over an eight-week period. We employ a novel brain-inspired computing paradigm, hyperdimensional computing (HDC), to classify the effectiveness of TMS using leave-one-subject-out cross-validation (LOSOCV). Four performance metrics—accuracy, sensitivity, specificity and AUC—are used, with AUC being the primary metric. Experimental results reveal that: i). Although SVM outperforms HDC in terms of accuracy, HDC achieves an AUC of 0.82, surpassing SVM by 0.07. ii). The optimal performance for both classifiers is obtained with feature selection using SelectKBest. iii) Among the top features selected by SelectKBest for the two classifiers, ws_MedRT (median rate for the Websurf task) shows a more distinguishable distribution between clinical responses (“1”) and no clinical responses (“0”). In conclusion, these results highlight the potential of HDC for predicting clinical responses to TMS and underscore the importance of feature selection in improving classification performance.

I. Introduction

Patients who suffer from major depressive disorder (MDD) experience persistent sadness and loss of interest, which severely influences the quality of their daily life. Transcranial magnetic stimulation (TMS), a noninvasive form of brain stimulation can interfere with cognitive control and has been used to treat MDD over the past decade with some success [1], [2], [3], [4], [5]. However, TMS treatment poses several challenges, including high costs, the inconvenience of daily visits over a month, slow effects that require repetitive sessions, and variable clinical responses. In large naturalistic samples, 40-70% of TMS patients do not respond [1], [4] and remission rates to TMS range between 30% and 35% [5], [6]. Although TMS treatment can yield a comparable response rate to medication for MDD [5], the underlying mechanism and its effect on cognition are not well understood. Identifying biomarkers that can predict clinical responses to TMS could bridge this gap in understanding, leading to more efficient and personalized TMS treatments.