Abstract
Transcranial magnetic stimulation (TMS) has transformed non-invasive brain therapies but faces challenges due to variability in outcomes, likely stemming from inter-individual differences in brain function. This study aimed to address this challenge by integrating personalized functional networks (PFNs) derived from functional magnetic resonance imaging (fMRI) with a neural network-based decoder to optimize stimulation in real time during a working memory (WM) task. After identification of individualized stimulation targets, participants completed a TMS/fMRI session, performing a WM task while receiving rTMS at randomized frequencies. Decoder outputs and behavioral data during this session guided selection of optimal and suboptimal stimulation frequencies. Participants then underwent six stimulation sessions (three optimal, three suboptimal) in a randomized crossover design, performing WM and control tasks. The optimal stimulation improved WM performance by the final session, with no improvement observed in the control task. Additionally, the decoder output predicted behavioral performance on the WM task, both during the TMS/fMRI and neuromodulation sessions. These findings show that neural network-guided closed-loop neuromodulation can improve TMS effectiveness, marking a step forward in personalized brain stimulation.