Individualized AI-driven Neuromodulation Selectively Enhances and Reorganizes Human Tongue Sensorimotor Networks.

AI-driven individualized fMRI neuromodulation (iNM) increased tongue sensorimotor control network occupancy from 82% to 97% while suppressing swallow-state interference by 83% in participants.

• Why it matters: Fixed neuromodulation targets can miss subject-specific tongue motor and sensory control network architecture, limiting precision for neurorehabilitation.
• What they did: They built a neurofunctional twin from each participant’s anatomy and function and used unsupervised machine learning with hidden Markov modeling to adaptively reinforce targeted TMSC activity and suppress competing states in real time.
• The result: iNM strengthened cortico-subcortical connectivity from 53% to 74% across motor, sensory, and attention networks and reorganized the inferior parietal lobule, with effects persisting into non-iNM blocks.

AI summary of the abstract · may contain errors · not medical advice · read the paper.