Anatomically mediated variability of hippocampal electric fields in temporal interference stimulation: A predictive...

Temporal interference stimulation (TIS) enables noninvasive targeting of deep brain regions. However, individual variability in the induced electric field (EF), particularly in terms of modulation depth (MD) and directional alignment, remains poorly understood.

We performed MRI-guided finite element modeling to simulate TIS-induced EF in the left hippocampus (LHippo), quantifying two metrics: MD and the angle between EF vectors and the hippocampal longitudinal axis. First, we evaluated these metrics across individuals stratified by age, sex, and cognitive status. To identify anatomical contributors to MD variability, we applied the least absolute shrinkage and selection operator (LASSO) regression for feature selection, followed by stepwise regression to construct a predictive model. We then conducted mediation analysis to determine whether the selected anatomical features accounted for the effects of age, sex, and cognitive status on MD.

MD varied significantly with age, sex, and cognitive status, whereas the directional angle remained relatively stable under the fixed electrode configuration. The final predictive model, incorporating eight anatomical features (e.g., skull thickness, CSF-to-head ratio), demonstrated strong generalizability in two independent validation cohorts. Mediation analysis confirmed that the model-predicted MD significantly mediated the effects of age, sex, and cognitive status.

These findings highlight the critical role of anatomical variability in shaping individual TIS outcomes and demonstrate that personalized MD could be efficiently estimated from clinically measurable features without subject-specific simulations. This anatomically informed framework supports scalable and interpretable strategies for precision-targeted brain stimulation.