{"ID":2882953,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.10160","arxiv_id":"2508.10160","title":"Pre-trained Transformer-models using chronic invasive electrophysiology for symptom decoding without patient-individual training","abstract":"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.","short_abstract":"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 traine...","url_abs":"https://arxiv.org/abs/2508.10160","url_pdf":"https://arxiv.org/pdf/2508.10160v1","authors":"[\"Timon Merk\",\"Saeed Salehi\",\"Richard M. Koehler\",\"Qiming Cui\",\"Maria Olaru\",\"Amelia Hahn\",\"Nicole R. Provenza\",\"Simon Little\",\"Reza Abbasi-Asl\",\"Phil A. Starr\",\"Wolf-Julian Neumann\"]","published":"2025-08-13T19:49:46Z","proceeding":"cs.HC","tasks":"[\"cs.HC\",\"cs.LG\"]","methods":"[\"Transformer\"]","has_code":false}