Thumbnail Image
Item

Automatic analysis of EEGs using big data and hybrid deep learning architectures

Golmohammadi, M
; 
Harati Nejad Torbati, AH
; 
Lopez de Diego, S
; 
Obeid, I
; 
Picone, J
Citations
Altmetric:
Genre
Journal Article
Date
2019-02-01
Advisor
Committee member
Group
Department
Subject
electroencephalography
 EEG
 hidden markov models
 HMM
 deep learning
 stochastic denoising autoencoders
 SdA
 automatic detection
Permanent link to this record
http://hdl.handle.net/20.500.12613/4576
Collections
Faculty/Researcher Works
Show all metadata
Files
Thumbnail Image
Automatic Analysis of EEGs Using Big Data and Hybrid Deep Learning Architectures.pdf
Adobe PDF, 3.15 MB
Research Projects
Organizational Units
Journal Issue
DOI
10.3389/fnhum.2019.00076
Abstract
© 2019 Golmohammadi, Harati Nejad Torbati, Lopez de Diego, Obeid and Picone. Brain monitoring combined with automatic analysis of EEGs provides a clinical decision support tool that can reduce time to diagnosis and assist clinicians in real-time monitoring applications (e.g., neurological intensive care units). Clinicians have indicated that a sensitivity of 95% with specificity below 5% was the minimum requirement for clinical acceptance. In this study, a high-performance automated EEG analysis system based on principles of machine learning and big data is proposed. This hybrid architecture integrates hidden Markov models (HMMs) for sequential decoding of EEG events with deep learning-based post-processing that incorporates temporal and spatial context. These algorithms are trained and evaluated using the Temple University Hospital EEG, which is the largest publicly available corpus of clinical EEG recordings in the world. This system automatically processes EEG records and classifies three patterns of clinical interest in brain activity that might be useful in diagnosing brain disorders: (1) spike and/or sharp waves, (2) generalized periodic epileptiform discharges, (3) periodic lateralized epileptiform discharges. It also classifies three patterns used to model the background EEG activity: (1) eye movement, (2) artifacts, and (3) background. Our approach delivers a sensitivity above 90% while maintaining a specificity below 5%. We also demonstrate that this system delivers a low false alarm rate, which is critical for any spike detection application.
Description
Citation
Citation to related work
Frontiers Media SA
Has part
Frontiers in Human Neuroscience
ADA compliance
For Americans with Disabilities Act (ADA) accommodation, including help with reading this content, please contact scholarshare@temple.edu
Embedded videos