Pre-trained Transformer-models using chronic invasive electrophysiology for symptom decoding without patient-individual training
This enables generalized state estimation for closed-loop neuromodulation therapy in Parkinson's disease patients, representing a novel approach but with incremental improvements in method.
The paper tackled the problem of decoding Parkinson's disease symptoms from neural data without needing patient-specific training, achieving this by using a pre-trained transformer model on chronic invasive electrophysiology recordings with a 30-minute context window and an optimized loss function.
Neural decoding of pathological and physiological states can enable patient-individualized closed-loop neuromodulation therapy. Recent advances in pre-trained large-scale foundation models offer the potential for generalized state estimation without patient-individual training. Here we present a foundation model trained on chronic longitudinal deep brain stimulation recordings spanning over 24 days. Adhering to long time-scale symptom fluctuations, we highlight the extended context window of 30 minutes. We present an optimized pre-training loss function for neural electrophysiological data that corrects for the frequency bias of common masked auto-encoder loss functions due to the 1-over-f power law. We show in a downstream task the decoding of Parkinson's disease symptoms with leave-one-subject-out cross-validation without patient-individual training.