PMID- 33635785
OWN - NLM
STAT- MEDLINE
DCOM- 20211101
LR  - 20220928
IS  - 1558-2531 (Electronic)
IS  - 0018-9294 (Print)
IS  - 0018-9294 (Linking)
VI  - 68
IP  - 11
DP  - 2021 Nov
TI  - Evaluating Performance of EEG Data-Driven Machine Learning for Traumatic Brain 
      Injury Classification.
PG  - 3205-3216
LID - 10.1109/TBME.2021.3062502 [doi]
AB  - OBJECTIVES: Big data analytics can potentially benefit the assessment and 
      management of complex neurological conditions by extracting information that is 
      difficult to identify manually. In this study, we evaluated the performance of 
      commonly used supervised machine learning algorithms in the classification of 
      patients with traumatic brain injury (TBI) history from those with stroke history 
      and/or normal EEG. METHODS: Support vector machine (SVM) and K-nearest neighbors 
      (KNN) models were generated with a diverse feature set from Temple EEG Corpus for 
      both two-class classification of patients with TBI history from normal subjects 
      and three-class classification of TBI, stroke and normal subjects. RESULTS: For 
      two-class classification, an accuracy of 0.94 was achieved in 10-fold cross 
      validation (CV), and 0.76 in independent validation (IV). For three-class 
      classification, 0.85 and 0.71 accuracy were reached in CV and IV respectively. 
      Overall, linear discriminant analysis (LDA) feature selection and SVM models 
      consistently performed well in both CV and IV and for both two-class and 
      three-class classification. Compared to normal control, both TBI and stroke 
      patients showed an overall reduction in coherence and relative PSD in delta 
      frequency, and an increase in higher frequency (alpha, mu, beta and gamma) power. 
      But stroke patients showed a greater degree of change and had additional global 
      decrease in theta power. CONCLUSIONS: Our study suggests that EEG data-driven 
      machine learning can be a useful tool for TBI classification. SIGNIFICANCE: Our 
      study provides preliminary evidence that EEG ML algorithm can potentially provide 
      specificity to separate different neurological conditions.
FAU - Vivaldi, Nicolas
AU  - Vivaldi N
FAU - Caiola, Michael
AU  - Caiola M
FAU - Solarana, Krystyna
AU  - Solarana K
FAU - Ye, Meijun
AU  - Ye M
LA  - eng
GR  - FD999999/ImFDA/Intramural FDA HHS/United States
PT  - Journal Article
PT  - Research Support, U.S. Gov't, P.H.S.
DEP - 20211019
PL  - United States
TA  - IEEE Trans Biomed Eng
JT  - IEEE transactions on bio-medical engineering
JID - 0012737
SB  - IM
MH  - Algorithms
MH  - *Brain Injuries, Traumatic/diagnosis
MH  - Discriminant Analysis
MH  - Electroencephalography
MH  - Humans
MH  - *Machine Learning
MH  - Support Vector Machine
PMC - PMC9513823
MID - NIHMS1833746
EDAT- 2021/02/27 06:00
MHDA- 2021/11/03 06:00
PMCR- 2022/09/27
CRDT- 2021/02/26 17:08
PHST- 2021/02/27 06:00 [pubmed]
PHST- 2021/11/03 06:00 [medline]
PHST- 2021/02/26 17:08 [entrez]
PHST- 2022/09/27 00:00 [pmc-release]
AID - 10.1109/TBME.2021.3062502 [doi]
PST - ppublish
SO  - IEEE Trans Biomed Eng. 2021 Nov;68(11):3205-3216. doi: 10.1109/TBME.2021.3062502. 
      Epub 2021 Oct 19.