Predicting response to repetitive transcranial magnetic stimulation in patients with chronic insomnia disorder using...

Predicting responsvienss to repetitive transcranial magnetic stimulation (rTMS) can facilitate personalized treatments with improved efficacy; however, predictive features related to this response are still lacking. We explored whether resting-state electroencephalography (rsEEG) functional connectivity measured at baseline or during treatment could predict the response to 10-day rTMS targeted to the right dorsolateral prefrontal cortex (DLPFC) in 36 patients with chronic insomnia disorder (CID). Pre- and post-treatment rsEEG scans and the Pittsburgh Sleep Quality Index (PSQI) were evaluated, with an additional rsEEG scan conducted after four rTMS sessions. Machine-learning approaches were employed to assess the ability of each connectivity measure to distinguish between responders (PSQI improvement > 25%) and non-responders (PSQI improvement ≤ 25%). Furthermore, we analyzed the connectivity trends of the two subgroups throughout the treatment. Our results revealed that the machine learning model based on baseline theta connectivity achieved the highest accuracy (AUC = 0.843) in predicting treatment response. Decreased baseline connectivity at the stimulated site was associated with higher responsiveness to TMS, emphasizing the significance of functional connectivity characteristics in rTMS treatment. These findings enhance the clinical application of EEG functional connectivity markers in predicting treatment outcomes.