CaltechAUTHORS
  A Caltech Library Service

Towards Adaptive Deep Brain Stimulation in Parkinson's Disease: Lfp-Based Feature Analysis and Classification

Wang, Taige and Shoaran, Mahsa and Emami, Azita (2018) Towards Adaptive Deep Brain Stimulation in Parkinson's Disease: Lfp-Based Feature Analysis and Classification. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE , Piscataway, NJ, pp. 2536-2540. ISBN 978-1-5386-4658-8. http://resolver.caltech.edu/CaltechAUTHORS:20180920-111853534

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20180920-111853534

Abstract

Deep Brain Stimulation (DBS) is an established therapy for advanced Parkinson's disease (PD). Recent studies have applied the closed-loop control (adaptive DBS or aDBS) using feedback from local field potential (LFP) signals. However, current aDBS practices focus on simple feedback like beta band power and thresholding, without optimized control or classification algorithms. In this work, we study the capacity of several classifiers including automatic shrinkage linear discriminant analysis (LDA) to predict motor impairment. We use 20 features extracted from both monopolar and bipolar LFPs in 12 PD patients. In our best setting, we achieve a median accuracy of 70.2%, sensitivity of 81.2% and prediction lead time of 0.1 s across patients. By including relevant features other than beta power, a 13.6% improvement in accuracy is achieved. Moreover, the Hjorth parameters and high-frequency oscillation (HFO) features perform best according to the Analysis of Variance (ANOVA) p-value and classifier weights. These results suggest a great potential to improve current aDBS system for PD, by implementing a classifier with multiple features.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1109/ICASSP.2018.8462472DOIArticle
https://ieeexplore.ieee.org/document/8462472PublisherArticle
ORCID:
AuthorORCID
Emami, Azita0000-0003-2608-9691
Additional Information:© 2018 IEEE. We thank Prof. Peter Brown at the University of Oxford for providing us with LFP data and valuable comments, and Prof. Virginia de Sa at the University of California San Diego for insightful suggestions on classifiers and testing method. This project was supported by Heritage Medical Research Institute (HMRI) at Caltech.
Group:Heritage Medical Research Institute
Funders:
Funding AgencyGrant Number
Heritage Medical Research InstituteUNSPECIFIED
Subject Keywords:Parkinson’s disease, adaptive deep brain stimulation, classifier, labeling, motor impairment, Hjorth parameters
Record Number:CaltechAUTHORS:20180920-111853534
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20180920-111853534
Official Citation:T. Wang, M. Shoaran and A. Emami, "Towards Adaptive Deep Brain Stimulation in Parkinson'S Disease: Lfp-Based Feature Analysis and Classification," 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada, 2018, pp. 2536-2540. doi: 10.1109/ICASSP.2018.8462472
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:89786
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:20 Sep 2018 18:25
Last Modified:20 Sep 2018 18:25

Repository Staff Only: item control page