PMID- 30619025
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20201001
IS  - 1664-2295 (Print)
IS  - 1664-2295 (Electronic)
IS  - 1664-2295 (Linking)
VI  - 9
DP  - 2018
TI  - Multimodal Data and Machine Learning for Detecting Specific Biomarkers in 
      Pediatric Epilepsy Patients With Generalized Tonic-Clonic Seizures.
PG  - 1038
LID - 10.3389/fneur.2018.01038 [doi]
LID - 1038
AB  - Previous neuroimaging studies of epilepsy with generalized tonic-clonic seizures 
      (GTCS) focus mainly on adults. However, the neural mechanisms that underline this 
      type of epilepsy remain unclear, especially for children. The aim of the present 
      study was to detect the effect of epilepsy on brains of children with GTCS and to 
      investigate whether the changes in the brain can be used to discriminate between 
      epileptic children and healthy children at the level of the individual. To 
      achieve this purpose, we measured gray matter (GM) volume and fractional 
      amplitude of low-frequency fluctuation (fALFF) differences on multimodel magnetic 
      resonance imaging in 14 children with GTCS and 30 age- and gender-matched healthy 
      controls. The patients showed GM volume reduction and a fALFF increase in the 
      thalamus, hippocampus, temporal and other deep nuclei. A significant decrease of 
      fALFF was mainly found in the default mode network (DMN). In addition, epileptic 
      duration was significantly negatively related to the GM volumes and significantly 
      positively related to the fALFF value of right thalamus. A support vector machine 
      (SVM) applied to the GM volume of the right thalamus correctly identified 
      epileptic children with a statistically significant accuracy of 74.42% (P < 
      0.002). A SVM applied to the fALFF of the right thalamus correctly identified 
      epileptic children with a statistically significant accuracy of 83.72% (P < 
      0.002). The consistent neuroimaging results indicated that the right thalamus 
      plays an important role in reflecting the chronic damaging effect of GTCS 
      epilepsy in children. The length of time of a child's epileptic history was 
      correlated with greater GM volume reduction and a fALFF increase in the right 
      thalamus. GM volumes and fALFF values in the right thalamus can identify children 
      with GTCS from the healthy controls with high accuracy and at an individual 
      subject level. These results are likely to be valuable in explaining the clinical 
      problems and understanding the brain abnormalities underlying this disorder.
FAU - Wang, Jianping
AU  - Wang J
AD  - The Second Affiliated Hospital of Guangzhou Medical University, Guangzhou, China.
FAU - Li, Yongxin
AU  - Li Y
AD  - Guangdong Provincial Key Laboratory of Medical Biomechanics, School of Basic 
      Medical Sciences, Southern Medical University, Guangzhou, China.
FAU - Wang, Ya
AU  - Wang Y
AD  - Guangdong Provincial Key Laboratory of Medical Biomechanics, School of Basic 
      Medical Sciences, Southern Medical University, Guangzhou, China.
FAU - Huang, Wenhua
AU  - Huang W
AD  - Guangdong Provincial Key Laboratory of Medical Biomechanics, School of Basic 
      Medical Sciences, Southern Medical University, Guangzhou, China.
LA  - eng
PT  - Journal Article
DEP - 20181210
PL  - Switzerland
TA  - Front Neurol
JT  - Frontiers in neurology
JID - 101546899
PMC - PMC6297879
OTO - NOTNLM
OT  - epilepsy children
OT  - fractional ALFF
OT  - generalized tonic-clonic seizures
OT  - gray matter volume
OT  - resting-state fMRI
OT  - support vector machine
OT  - voxel-based morphometry
EDAT- 2019/01/09 06:00
MHDA- 2019/01/09 06:01
PMCR- 2018/12/10
CRDT- 2019/01/09 06:00
PHST- 2018/09/07 00:00 [received]
PHST- 2018/11/19 00:00 [accepted]
PHST- 2019/01/09 06:00 [entrez]
PHST- 2019/01/09 06:00 [pubmed]
PHST- 2019/01/09 06:01 [medline]
PHST- 2018/12/10 00:00 [pmc-release]
AID - 10.3389/fneur.2018.01038 [doi]
PST - epublish
SO  - Front Neurol. 2018 Dec 10;9:1038. doi: 10.3389/fneur.2018.01038. eCollection 
      2018.