PMID- 31561098
OWN - NLM
STAT- MEDLINE
DCOM- 20200928
LR  - 20200928
IS  - 1879-0534 (Electronic)
IS  - 0010-4825 (Linking)
VI  - 114
DP  - 2019 Nov
TI  - Nonconvulsive epileptic seizure monitoring with incremental learning.
PG  - 103434
LID - S0010-4825(19)30311-7 [pii]
LID - 10.1016/j.compbiomed.2019.103434 [doi]
AB  - Nonconvulsive epileptic seizures (NCSz) and nonconvulsive status epilepticus 
      (NCSE) are two neurological entities associated with increment in morbidity and 
      mortality in critically ill patients. In a previous work, we introduced a method 
      which accurately detected NCSz in EEG data (referred here as 'Batch method'). 
      However, this approach was less effective when the EEG features identified at the 
      beginning of the recording changed over time. Such pattern drift is an issue that 
      causes failures of automated seizure detection methods. This paper presents a 
      support vector machine (SVM)-based incremental learning method for NCSz detection 
      that for the first time addresses the seizure evolution in EEG records from 
      patients with epileptic disorders and from ICU having NCSz. To implement the 
      incremental learning SVM, three methodologies are tested. These approaches differ 
      in the way they reduce the set of potentially available support vectors that are 
      used to build the decision function of the classifier. To evaluate the 
      suitability of the three incremental learning approaches proposed here for NCSz 
      detection, first, a comparative study between the three methods is performed. 
      Secondly, the incremental learning approach with the best performance is compared 
      with the Batch method and three other batch methods from the literature. From 
      this comparison, the incremental learning method based on maximum relevance 
      minimum redundancy (MRMR_IL) obtained the best results. MRMR_IL method proved to 
      be an effective tool for NCSz detection in a real-time setting, achieving 
      sensitivity and accuracy values above 99%.
CI  - Copyright (c) 2019. Published by Elsevier Ltd.
FAU - Rodriguez Aldana, Yissel
AU  - Rodriguez Aldana Y
AD  - Universidad de Oriente, Center of Neuroscience and Signals and Image Processing. 
      Santiago de Cuba, Cuba; KU Leuven, Department of Electrical Engineering (ESAT), 
      Stadius Center for Dynamical Systems, Signal Processing and Data Analytics, 
      Leuven, Belgium. Electronic address: yaldana@uo.edu.cu.
FAU - Maranon Reyes, Enrique J
AU  - Maranon Reyes EJ
AD  - Universidad de Oriente, Center of Neuroscience and Signals and Image Processing. 
      Santiago de Cuba, Cuba.
FAU - Macias, Frank Sanabria
AU  - Macias FS
AD  - Escuela Politecnica Superior, Universidad de Alcala, Alcala de Henares, Spain.
FAU - Rodriguez, Valia Rodriguez
AU  - Rodriguez VR
AD  - Aston University, Birmingham, United Kingdom; Cuban Neuroscience Center, Havana, 
      Cuba; Clinical-Surgical Hospital "Hermanos Almeijeiras", Havana, Cuba.
FAU - Chacon, Lilia Morales
AU  - Chacon LM
AD  - International Center of Neurological Restoration, Havana, Cuba.
FAU - Van Huffel, Sabine
AU  - Van Huffel S
AD  - KU Leuven, Department of Electrical Engineering (ESAT), Stadius Center for 
      Dynamical Systems, Signal Processing and Data Analytics, Leuven, Belgium.
FAU - Hunyadi, Borbala
AU  - Hunyadi B
AD  - KU Leuven, Department of Electrical Engineering (ESAT), Stadius Center for 
      Dynamical Systems, Signal Processing and Data Analytics, Leuven, Belgium; 
      Department of Microelectronics, Delft University of Technology, Delft, 
      Netherlands.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20190906
PL  - United States
TA  - Comput Biol Med
JT  - Computers in biology and medicine
JID - 1250250
SB  - IM
MH  - Adolescent
MH  - Adult
MH  - Electroencephalography
MH  - Female
MH  - Humans
MH  - *Machine Learning
MH  - Male
MH  - Middle Aged
MH  - Seizures/*diagnosis
MH  - *Signal Processing, Computer-Assisted
MH  - Support Vector Machine
MH  - Young Adult
OTO - NOTNLM
OT  - Hilbert huang transform
OT  - Incremental learning
OT  - Multiway data analysis
OT  - Nonconvulsive epileptic seizures
EDAT- 2019/09/29 06:00
MHDA- 2020/09/29 06:00
CRDT- 2019/09/28 06:00
PHST- 2019/05/06 00:00 [received]
PHST- 2019/09/02 00:00 [revised]
PHST- 2019/09/03 00:00 [accepted]
PHST- 2019/09/29 06:00 [pubmed]
PHST- 2020/09/29 06:00 [medline]
PHST- 2019/09/28 06:00 [entrez]
AID - S0010-4825(19)30311-7 [pii]
AID - 10.1016/j.compbiomed.2019.103434 [doi]
PST - ppublish
SO  - Comput Biol Med. 2019 Nov;114:103434. doi: 10.1016/j.compbiomed.2019.103434. Epub 
      2019 Sep 6.