Literature DB >> 33357224

Categorisation of EEG suppression using enhanced feature extraction for SUDEP risk assessment.

Juan C Mier1,2, Yejin Kim3, Xiaoqian Jiang3, Guo-Qiang Zhang3,4, Samden Lhatoo4.   

Abstract

BACKGROUND: Sudden Unexpected Death in Epilepsy (SUDEP) has increased in awareness considerably over the last two decades and is acknowledged as a serious problem in epilepsy. However, the scientific community remains unclear on the reason or possible bio markers that can discern potentially fatal seizures from other non-fatal seizures. The duration of postictal generalized EEG suppression (PGES) is a promising candidate to aid in identifying SUDEP risk. The length of time a patient experiences PGES after a seizure may be used to infer the risk a patient may have of SUDEP later in life. However, the problem becomes identifying the duration, or marking the end, of PGES (Tomson et al. in Lancet Neurol 7(11):1021-1031, 2008; Nashef in Epilepsia 38:6-8, 1997).
METHODS: This work addresses the problem of marking the end to PGES in EEG data, extracted from patients during a clinically supervised seizure. This work proposes a sensitivity analysis on EEG window size/delay, feature extraction and classifiers along with associated hyperparameters. The resulting sensitivity analysis includes the Gradient Boosted Decision Trees and Random Forest classifiers trained on 10 extracted features rooted in fundamental EEG behavior using an EEG specific feature extraction process (pyEEG) and 5 different window sizes or delays (Bao et al. in Comput Intell Neurosci 2011:1687-5265, 2011).
RESULTS: The machine learning architecture described above scored a maximum AUC score of 76.02% with the Random Forest classifier trained on all extracted features. The highest performing features included SVD Entropy, Petrosan Fractal Dimension and Power Spectral Intensity.
CONCLUSION: The methods described are effective in automatically marking the end to PGES. Future work should include integration of these methods into the clinical setting and using the results to be able to predict a patient's SUDEP risk.

Entities:  

Keywords:  EEG; Epilepsy; Feature engineering; Machine learning; SUDS

Year:  2020        PMID: 33357224      PMCID: PMC7758934          DOI: 10.1186/s12911-020-01309-5

Source DB:  PubMed          Journal:  BMC Med Inform Decis Mak        ISSN: 1472-6947            Impact factor:   2.796


  7 in total

1.  Extracting multisource brain activity from a single electromagnetic channel.

Authors:  Christopher J James; David Lowe
Journal:  Artif Intell Med       Date:  2003-05       Impact factor: 5.326

2.  [Spectral entropy: a new method for anesthetic adequacy.].

Authors:  Rogean Rodrigues Nunes; Murilo Pereira de Almeida; James Wallace Sleigh
Journal:  Rev Bras Anestesiol       Date:  2004-06       Impact factor: 0.964

Review 3.  Sudden unexpected death in epilepsy: current knowledge and future directions.

Authors:  Torbjörn Tomson; Lina Nashef; Philippe Ryvlin
Journal:  Lancet Neurol       Date:  2008-09-19       Impact factor: 44.182

4.  EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces.

Authors:  Vernon J Lawhern; Amelia J Solon; Nicholas R Waytowich; Stephen M Gordon; Chou P Hung; Brent J Lance
Journal:  J Neural Eng       Date:  2018-06-22       Impact factor: 5.379

5.  Seizure lateralization in scalp EEG using Hjorth parameters.

Authors:  T Cecchin; R Ranta; L Koessler; O Caspary; H Vespignani; L Maillard
Journal:  Clin Neurophysiol       Date:  2009-12-11       Impact factor: 3.708

6.  Sudden unexpected death in epilepsy: terminology and definitions.

Authors:  L Nashef
Journal:  Epilepsia       Date:  1997-11       Impact factor: 5.864

7.  PyEEG: an open source Python module for EEG/MEG feature extraction.

Authors:  Forrest Sheng Bao; Xin Liu; Christina Zhang
Journal:  Comput Intell Neurosci       Date:  2011-03-29
  7 in total
  1 in total

1.  Interictal EEG and ECG for SUDEP Risk Assessment: A Retrospective Multicenter Cohort Study.

Authors:  Zhe Sage Chen; Aaron Hsieh; Guanghao Sun; Gregory K Bergey; Samuel F Berkovic; Piero Perucca; Wendyl D'Souza; Christopher J Elder; Pue Farooque; Emily L Johnson; Sarah Barnard; Russell Nightscales; Patrick Kwan; Brian Moseley; Terence J O'Brien; Shobi Sivathamboo; Juliana Laze; Daniel Friedman; Orrin Devinsky
Journal:  Front Neurol       Date:  2022-03-18       Impact factor: 4.086

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.