Machine Learning for EEG-based biomarkers
Ever since I began to work on electrophysiology and cognitive research, it has been my foremost conviction that tools like machine learning and deep learning combined with EEG data would enable a new paradigm for biomarker discovery in psychiatry and neurology.
During my PhD, I worked on different deep learning architectures applied to EEG to diagnose Attention Deficit Hyperactivity Disorder (ADHD) patients from healthy controls and to predict which patients with REM Behavior Disorder (RBD) would eventually develop Parkinson’s disease up to 6 years before they develop any symptoms.
Please consider the related publications listed below or more details.
- Transcranial Direct Current Stimulation Modulates Dysexecutive Deficits and its Neurophysiological Signatures in Attention-Deficit Hyperactivity Disorder
- Transcranial Direct Current Stimulation to the Left Dorsolateral Prefrontal Cortex Improves Cognitive Control in Patients With Attention-Deficit/Hyperactivity Disorder: A Randomized Behavioral and Neurophysiological Study
- Deep Learning With EEG Spectrograms in Rapid Eye Movement Behavior Disorder
- The effects of transcranial direct current stimulation in chronic spinal cord injury: a quantitative EEG study
- EEG Recordings During Sham Control Transcranial Direct Current Stimulation Protocol