1. A movement and tremor identification algorithm for evaluations during deep brain stimulation
- Author
-
Bourgeois, Frédéric, Pambakian, Nicola, Coste, Jérôme, de Lange, Ijsbrand, Lemaire, Jean-Jacques, Schkommodau, Erik, Hemm, Simone, University of Applied Sciences and Arts Northwestern Switzerland (FHNW), STIL B.V., Institut Pascal (IP), Centre National de la Recherche Scientifique (CNRS)-Université Clermont Auvergne (UCA)-Institut national polytechnique Clermont Auvergne (INP Clermont Auvergne), Université Clermont Auvergne (UCA)-Université Clermont Auvergne (UCA), The research was funded by the Eurostars programme (E! 113627)., Austrian, German and Swiss Societies for Biomedical Engineering, Daniel Baumgarten, and Coste, Jérôme
- Subjects
digital biomarkers ,Deep Brain Stimulation ,[SDV.NEU.NB]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Neurobiology ,[SDV.NEU.NB] Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Neurobiology ,Tremor estimation ,Weightedfrequency Fourier Linear combiner ,[INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM] ,[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing ,Microelectrode Recording ,[INFO.INFO-BI] Computer Science [cs]/Bioinformatics [q-bio.QM] ,[SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing - Abstract
Ethical approval: The research related to human use complies with all the relevant national regulations, institutional policies and was performed in accordance with the tenets of the Helsinki Declaration and has been approved by the authors’ institutional review board or equivalent committee.; International audience; Deep brain stimulation is widely used to alleviate symptoms of movement disorders. During intraoperative stimulation the influence of active or passive movements on the neuronal activity is often evaluated but the evaluation remains mostly subjective. The objective of this paper is to investigate the potential of a previously developed Weightedfrequency Fourier Linear combiner and Kalman filter-based algorithm to identify tremor types and to isolate the tremorous part. The method is applied to ten intraoperatively acquired accelerometer recordings from eight patients from which 186 phases were manually annotated into: rest, postural and kinetic phase without tremor, and rest, postural and kinetic phase with tremor. The overall accuracy for tremorous phases only is 89.1% and 76.3% when also non-tremorous phases are considered. Two main misclassification cases are identified and further discussed. The results demonstrate the potential of the developed algorithm for the use as an online tremorous movement classifier based on the acquired digital biomarkers.
- Published
- 2022