Cargando…

Improved detection of Parkinsonian resting tremor with feature engineering and Kalman filtering

OBJECTIVE: Accurate and reliable detection of tremor onset in Parkinson’s disease (PD) is critical to the success of adaptive deep brain stimulation (aDBS) therapy. Here, we investigated the potential use of feature engineering and machine learning methods for more accurate detection of rest tremor...

Descripción completa

Detalles Bibliográficos
Autores principales: Yao, Lin, Brown, Peter, Shoaran, Mahsa
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6927801/
https://www.ncbi.nlm.nih.gov/pubmed/31744673
http://dx.doi.org/10.1016/j.clinph.2019.09.021
_version_ 1783482355995901952
author Yao, Lin
Brown, Peter
Shoaran, Mahsa
author_facet Yao, Lin
Brown, Peter
Shoaran, Mahsa
author_sort Yao, Lin
collection PubMed
description OBJECTIVE: Accurate and reliable detection of tremor onset in Parkinson’s disease (PD) is critical to the success of adaptive deep brain stimulation (aDBS) therapy. Here, we investigated the potential use of feature engineering and machine learning methods for more accurate detection of rest tremor in PD. METHODS: We analyzed the local field potential (LFP) recordings from the subthalamic nucleus region in 12 patients with PD (16 recordings). To explore the optimal biomarkers and the best performing classifier, the performance of state-of-the-art machine learning (ML) algorithms and various features of the subthalamic LFPs were compared. We further used a Kalman filtering technique in feature domain to reduce the false positive rate. RESULTS: The Hjorth complexity showed a higher correlation with tremor, compared to other features in our study. In addition, by optimal selection of a maximum of five features with a sequential feature selection method and using the gradient boosted decision trees as the classifier, the system could achieve an average F1 score of up to 88.7% and a detection lead of 0.52 s. The use of Kalman filtering in feature space significantly improved the specificity by 17.0% (p = 0.002), thereby potentially reducing the unnecessary power dissipation of the conventional DBS system. CONCLUSION: The use of relevant features combined with Kalman filtering and machine learning improves the accuracy of tremor detection during rest. SIGNIFICANCE: The proposed method offers a potential solution for efficient on-demand stimulation for PD tremor.
format Online
Article
Text
id pubmed-6927801
institution National Center for Biotechnology Information
language English
publishDate 2019
record_format MEDLINE/PubMed
spelling pubmed-69278012020-01-01 Improved detection of Parkinsonian resting tremor with feature engineering and Kalman filtering Yao, Lin Brown, Peter Shoaran, Mahsa Clin Neurophysiol Article OBJECTIVE: Accurate and reliable detection of tremor onset in Parkinson’s disease (PD) is critical to the success of adaptive deep brain stimulation (aDBS) therapy. Here, we investigated the potential use of feature engineering and machine learning methods for more accurate detection of rest tremor in PD. METHODS: We analyzed the local field potential (LFP) recordings from the subthalamic nucleus region in 12 patients with PD (16 recordings). To explore the optimal biomarkers and the best performing classifier, the performance of state-of-the-art machine learning (ML) algorithms and various features of the subthalamic LFPs were compared. We further used a Kalman filtering technique in feature domain to reduce the false positive rate. RESULTS: The Hjorth complexity showed a higher correlation with tremor, compared to other features in our study. In addition, by optimal selection of a maximum of five features with a sequential feature selection method and using the gradient boosted decision trees as the classifier, the system could achieve an average F1 score of up to 88.7% and a detection lead of 0.52 s. The use of Kalman filtering in feature space significantly improved the specificity by 17.0% (p = 0.002), thereby potentially reducing the unnecessary power dissipation of the conventional DBS system. CONCLUSION: The use of relevant features combined with Kalman filtering and machine learning improves the accuracy of tremor detection during rest. SIGNIFICANCE: The proposed method offers a potential solution for efficient on-demand stimulation for PD tremor. 2019-11-05 2019-11-05 /pmc/articles/PMC6927801/ /pubmed/31744673 http://dx.doi.org/10.1016/j.clinph.2019.09.021 Text en http://creativecommons.org/licenses/by-nc-nd/4.0/ This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Article
Yao, Lin
Brown, Peter
Shoaran, Mahsa
Improved detection of Parkinsonian resting tremor with feature engineering and Kalman filtering
title Improved detection of Parkinsonian resting tremor with feature engineering and Kalman filtering
title_full Improved detection of Parkinsonian resting tremor with feature engineering and Kalman filtering
title_fullStr Improved detection of Parkinsonian resting tremor with feature engineering and Kalman filtering
title_full_unstemmed Improved detection of Parkinsonian resting tremor with feature engineering and Kalman filtering
title_short Improved detection of Parkinsonian resting tremor with feature engineering and Kalman filtering
title_sort improved detection of parkinsonian resting tremor with feature engineering and kalman filtering
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6927801/
https://www.ncbi.nlm.nih.gov/pubmed/31744673
http://dx.doi.org/10.1016/j.clinph.2019.09.021
work_keys_str_mv AT yaolin improveddetectionofparkinsonianrestingtremorwithfeatureengineeringandkalmanfiltering
AT brownpeter improveddetectionofparkinsonianrestingtremorwithfeatureengineeringandkalmanfiltering
AT shoaranmahsa improveddetectionofparkinsonianrestingtremorwithfeatureengineeringandkalmanfiltering