Transformer-based long-term predictor of subthalamic beta activity in Parkinson’s disease

Abstract Deep brain stimulation (DBS) of the subthalamic nucleus (STN) is a mainstay treatment for patients with Parkinson’s disease (PD). The adaptive DBS approach (aDBS) modulates stimulation, based on the power in the beta range ([12–30] Hz) of STN local field potentials, aiming to follow the pat...

Full description

Saved in:
Bibliographic Details
Main Authors: Salvatore Falciglia, Laura Caffi, Claudio Baiata, Chiara Palmisano, Ioannis Ugo Isaias, Alberto Mazzoni
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:npj Parkinson's Disease
Online Access:https://doi.org/10.1038/s41531-025-01011-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849237574122471424
author Salvatore Falciglia
Laura Caffi
Claudio Baiata
Chiara Palmisano
Ioannis Ugo Isaias
Alberto Mazzoni
author_facet Salvatore Falciglia
Laura Caffi
Claudio Baiata
Chiara Palmisano
Ioannis Ugo Isaias
Alberto Mazzoni
author_sort Salvatore Falciglia
collection DOAJ
description Abstract Deep brain stimulation (DBS) of the subthalamic nucleus (STN) is a mainstay treatment for patients with Parkinson’s disease (PD). The adaptive DBS approach (aDBS) modulates stimulation, based on the power in the beta range ([12–30] Hz) of STN local field potentials, aiming to follow the patient’s clinical state. Control of aDBS relies on identifying the correct thresholds of pathological beta power. Currently, in-person reprogramming sessions, due to changes in beta power distribution over time, are needed to ensure clinical efficacy. Here we present LAURA, a Transformer-based framework predicting the nonlinear evolution of subthalamic beta power up to 6 days in advance, based on the analysis of chronic recordings. High prediction accuracy (>90%) was achieved in four PD patients with chronic DBS over months of recordings, independently of stimulation parameters. Our study paves the way for remote monitoring strategies and the implementation of new algorithms for personalized auto-tuning aDBS devices.
format Article
id doaj-art-e3b51aa99fbc40e6a6d833709127bfa1
institution Kabale University
issn 2373-8057
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series npj Parkinson's Disease
spelling doaj-art-e3b51aa99fbc40e6a6d833709127bfa12025-08-20T04:01:56ZengNature Portfolionpj Parkinson's Disease2373-80572025-07-0111111210.1038/s41531-025-01011-1Transformer-based long-term predictor of subthalamic beta activity in Parkinson’s diseaseSalvatore Falciglia0Laura Caffi1Claudio Baiata2Chiara Palmisano3Ioannis Ugo Isaias4Alberto Mazzoni5The BioRobotics Institute, Scuola Superiore Sant’AnnaThe BioRobotics Institute, Scuola Superiore Sant’Anna Pezzoli Foundation for Parkinson’s DiseaseUniversity Hospital Wuerzburg and Julius Maximilian, University of WuerzburgUniversity Hospital Wuerzburg and Julius Maximilian, University of WuerzburgThe BioRobotics Institute, Scuola Superiore Sant’AnnaAbstract Deep brain stimulation (DBS) of the subthalamic nucleus (STN) is a mainstay treatment for patients with Parkinson’s disease (PD). The adaptive DBS approach (aDBS) modulates stimulation, based on the power in the beta range ([12–30] Hz) of STN local field potentials, aiming to follow the patient’s clinical state. Control of aDBS relies on identifying the correct thresholds of pathological beta power. Currently, in-person reprogramming sessions, due to changes in beta power distribution over time, are needed to ensure clinical efficacy. Here we present LAURA, a Transformer-based framework predicting the nonlinear evolution of subthalamic beta power up to 6 days in advance, based on the analysis of chronic recordings. High prediction accuracy (>90%) was achieved in four PD patients with chronic DBS over months of recordings, independently of stimulation parameters. Our study paves the way for remote monitoring strategies and the implementation of new algorithms for personalized auto-tuning aDBS devices.https://doi.org/10.1038/s41531-025-01011-1
spellingShingle Salvatore Falciglia
Laura Caffi
Claudio Baiata
Chiara Palmisano
Ioannis Ugo Isaias
Alberto Mazzoni
Transformer-based long-term predictor of subthalamic beta activity in Parkinson’s disease
npj Parkinson's Disease
title Transformer-based long-term predictor of subthalamic beta activity in Parkinson’s disease
title_full Transformer-based long-term predictor of subthalamic beta activity in Parkinson’s disease
title_fullStr Transformer-based long-term predictor of subthalamic beta activity in Parkinson’s disease
title_full_unstemmed Transformer-based long-term predictor of subthalamic beta activity in Parkinson’s disease
title_short Transformer-based long-term predictor of subthalamic beta activity in Parkinson’s disease
title_sort transformer based long term predictor of subthalamic beta activity in parkinson s disease
url https://doi.org/10.1038/s41531-025-01011-1
work_keys_str_mv AT salvatorefalciglia transformerbasedlongtermpredictorofsubthalamicbetaactivityinparkinsonsdisease
AT lauracaffi transformerbasedlongtermpredictorofsubthalamicbetaactivityinparkinsonsdisease
AT claudiobaiata transformerbasedlongtermpredictorofsubthalamicbetaactivityinparkinsonsdisease
AT chiarapalmisano transformerbasedlongtermpredictorofsubthalamicbetaactivityinparkinsonsdisease
AT ioannisugoisaias transformerbasedlongtermpredictorofsubthalamicbetaactivityinparkinsonsdisease
AT albertomazzoni transformerbasedlongtermpredictorofsubthalamicbetaactivityinparkinsonsdisease