PMID- 31744673
OWN - NLM
STAT- MEDLINE
DCOM- 20200706
LR  - 20231112
IS  - 1872-8952 (Electronic)
IS  - 1388-2457 (Print)
IS  - 1388-2457 (Linking)
VI  - 131
IP  - 1
DP  - 2020 Jan
TI  - Improved detection of Parkinsonian resting tremor with feature engineering and 
      Kalman filtering.
PG  - 274-284
LID - S1388-2457(19)31253-2 [pii]
LID - 10.1016/j.clinph.2019.09.021 [doi]
AB  - 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.
CI  - Copyright (c) 2019 International Federation of Clinical Neurophysiology. Published 
      by Elsevier B.V. All rights reserved.
FAU - Yao, Lin
AU  - Yao L
AD  - ECE Department, Cornell University, Ithaca, NY, USA. Electronic address: 
      ly329@cornell.edu.
FAU - Brown, Peter
AU  - Brown P
AD  - Medical Research Council Brain Network Dynamics Unit, University of Oxford, 
      Oxford, UK; Nuffield Department of Clinical Neurosciences, John Radcliffe 
      Hospital, University of Oxford, Oxford, UK.
FAU - Shoaran, Mahsa
AU  - Shoaran M
AD  - ECE Department, Cornell University, Ithaca, NY, USA.
LA  - eng
GR  - MC_UU_00003/2/MRC_/Medical Research Council/United Kingdom
GR  - MC_UU_12024/1/MRC_/Medical Research Council/United Kingdom
PT  - Comparative Study
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20191105
PL  - Netherlands
TA  - Clin Neurophysiol
JT  - Clinical neurophysiology : official journal of the International Federation of 
      Clinical Neurophysiology
JID - 100883319
SB  - IM
CIN - Clin Neurophysiol. 2020 Jan;131(1):241-242. PMID: 31806418
MH  - Aged
MH  - *Algorithms
MH  - Analysis of Variance
MH  - Deep Brain Stimulation/*methods
MH  - Female
MH  - Humans
MH  - *Machine Learning
MH  - Male
MH  - Middle Aged
MH  - Parkinson Disease/*complications
MH  - Reaction Time
MH  - Rest
MH  - Subthalamic Nucleus
MH  - Tremor/*diagnostic imaging/etiology/*therapy
MH  - Wavelet Analysis
PMC - PMC6927801
MID - EMS85265
OTO - NOTNLM
OT  - Adaptive deep-brain stimulation
OT  - Kalman filtering
OT  - Local field potential (LFP)
OT  - Machine learning (ML)
OT  - Parkinson's disease (PD)
OT  - Tremor detection
COIS- Declaration of Competing Interest None.
EDAT- 2019/11/21 06:00
MHDA- 2020/07/07 06:00
PMCR- 2020/01/01
CRDT- 2019/11/21 06:00
PHST- 2019/05/14 00:00 [received]
PHST- 2019/07/25 00:00 [revised]
PHST- 2019/09/10 00:00 [accepted]
PHST- 2019/11/21 06:00 [pubmed]
PHST- 2020/07/07 06:00 [medline]
PHST- 2019/11/21 06:00 [entrez]
PHST- 2020/01/01 00:00 [pmc-release]
AID - S1388-2457(19)31253-2 [pii]
AID - 10.1016/j.clinph.2019.09.021 [doi]
PST - ppublish
SO  - Clin Neurophysiol. 2020 Jan;131(1):274-284. doi: 10.1016/j.clinph.2019.09.021. 
      Epub 2019 Nov 5.