Page 19 - brain-eBook

Team Project Name classifying blood oxygen activity features in brain

Digital Therapeutic Approaches to Brain tissues.
Neuromodulation for Anxiety Disorders Key Words
Research Project Digital Therapeutic, Transcranial Stimulation,
Functional Near-Infrared Spectroscopy, Neural
The team developed a near-infrared Feedback, Anxiety
spectroscopy(fNIRS) instrument for real-time
monitoring of anxiety-related brain activity, Global Cooperation
exploring the application of AI biomarkers in the
diagnosis and assessment of the progression of The team is developing a near-infrared
anxiety disorders. They integrated a high-definition spectroscopy instrument for real-time monitoring
transcranial electrical stimulation(HD-tES) of brain activity in anxiety disorders. We are
treatment system, along with a digital cognitive exploring the application of AI-based biomarkers
therapy system using fNIRS as neural feedback, in the diagnosis and assessment of the course of
to meet the unmet needs in clinical cognitive and the disease. The team is also integrating a high-
motor rehabilitation training. precision focal transcranial electrical stimulation
therapy system, as well as a digital behavioral
In previous studies with healthy subjects, the team cognitive therapy system using fNIRS as
found that simultaneous neural stimulation of both neurofeedback, to meet the unmet needs in clinical
hemispheres significantly enhanced oxygenation cognitive and motor rehabilitation training.
capacity during exercise training. The effects not
only showed a significant improvement during the We are looking forward to international
intervention but also persisted for some time after collaboration in executing clinical research projects
completion. In stroke patients undergoing upper to expand digital medical methods in the fields of
limb rehabilitation training intervention, the results neural regulation and neurofeedback.
indicated significant improvements in various Project Web Page
functional indicators compared to the control group.
Furthermore, the team discovered that subjects,
when exposed to different emotional stimuli,
achieved an overall classification accuracy of
95.7% through machine learning algorithms

18 19