Complexity of resting cortical activity predicts neurophysiological responses to theta-burst stimulation but fails to generalize: A rigorous machine-learning approach

Background: Substantial variability in individual responses to intermittent theta-burst stimulation (iTBS) limits its clinical efficacy, yet neurophysiological mechanisms underlying this variability remain unclear. While most machine-learning studies have focused on modeling behavioral or clinical effects of repetitive transcranial magnetic stimulation (rTMS), the few studies examining neurophysiological outcomes utilized limited feature sets in single-visit settings, which captured only inter-subject variability and most importantly lacked independent validation sets. Methods: To address these gaps, we employed supervised machine learning models that integrated baseline resting-state EEG (rsEEG) features and baseline transcranial magnetic stimulation (TMS)-evoked measures, including motor-evoked potentials (MEPs) and TMS-evoked potentials (TEPs), to predict neurophysiological responses to a single iTBS session applied over the primary motor cortex in two independent test-retest studies of healthy adults. We also employed statistical and reliability analysis to understand the statistical relationship between resting state EEG and responses to iTBS. Results: Internal cross-validation within the training cohort yielded promising binary classification performance (accuracy: 81%), identifying coarse-grained multiscale distribution entropy of rsEEG as the most robust predictor of local cortical excitability changes indexed by the 100–131ms window of TEPs. However, predictive performance markedly declined upon external validation (accuracy: 69%), reflecting unstable relationships between predictors and outcomes likely driven by substantial intra- and inter-individual variability of iTBS-induced changes in neurophysiological outcomes. Conclusions: These findings emphasize that while EEG complexity measures can capture baseline brain states relevant for neuromodulation to a certain degree, the inherent instability of single-session iTBS effects significantly constrains model generalizability and underscores the necessity of test-retest paradigm to avoid overly optimistic performance estimates. Future studies with multi-session and individualized stimulation protocols are urgently needed to better characterize neurophysiological mechanisms underlying rTMS effects and ultimately enhance its therapeutic potential. Author summary: Repetitive transcranial magnetic stimulation (rTMS) is a promising non-invasive neuromodulation technique approved by FDA to treat medication-resistant depression, obsessive-compulsive disorder and smoking addiction, with active research for potential treatment of anxiety, bipolar II disorder and improve post-stroke motor rehabilitation. It’s also used experimentally to modify brain excitability, neural plasticity and behavior. However, it currently suffers from low inter- and intra-individual reliability, with some individuals showing improvement from rTMS while others don’t. To better understand the underlying mechanism as well as potentially improve its clinical efficacy, we developed a machine learning model that can identify neurophysiological features that will distinguish people who demonstrates cortical target engagement to rTMS apart from those who don’t. In order to capture both inter- and intra-individual variability, our participants completed identical rTMS protocols twice, initial session for the first time and retest session for the second time. Our results suggested that the relationship between features and rTMS responses changed over time, limiting our model’s ability to generalize. We finally concluded that single session of rTMS isn’t effective and suggested that multiple sessions with personalized rTMS parameters are needed to show reliable neurophysiological effects.