AI-Driven Multimodal Brain-State Decoding for Personalized Closed-Loop TENS: A Comprehensive Review

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Chronic pain is a dynamic, brain-wide condition that eludes effective management by conventional, static treatment approaches. Transcutaneous Electrical Nerve Stimulation (TENS), traditionally perceived as a simple and generic modality, is on the verge of a significant transformation. Guided by advances in brain-state decoding and adaptive algorithms, TENS can evolve into a precision neuromodulation system tailored to individual needs. By integrating multimodal neuroimaging—including the spatial resolution of functional magnetic resonance imaging (fMRI), the temporal sensitivity of an Electroencephalogram (EEG), and the ecological validity of functional near-infrared spectroscopy (fNIRS)—with real-time machine learning, we envision a paradigm shift from fixed stimulation protocols to personalized, closed-loop modulation. This comprehensive review outlines a translational framework to reengineer TENS from an open-loop device into a responsive, intelligent therapeutic platform. We examine the underlying neurophysiological mechanisms, artificial intelligence (AI)-driven infrastructures, and ethical considerations essential for implementing this vision in clinical practice—not only for chronic pain management but also for broader neuroadaptive healthcare applications.
Funding Information
  • National Natural Science Foundation of China (62371300)

This publication has 64 references indexed in Scilit: