TITLE:
Detection of Epilepsy Cases in Newborns
AUTHORS:
Gérard Behou N’Guessan, Kouassi Saha Bernard, Coulibaly Tiékoura, Diarra Bassira
KEYWORDS:
Neonatal Epilepsy, Electroencephalogram Signal, Supervised Classification, Random Forest, Extratrees, Gradient Boosting Tree
JOURNAL NAME:
Engineering,
Vol.15 No.2,
February
28,
2023
ABSTRACT: Epilepsy
is a very common worldwide neurological disorder that can affect a person’s
quality of life at any age. People with epilepsy typically have recurrent
seizures that can lead to injury or in some cases even death. Curing epilepsy
requires risky surgery. If not, the patient may be subjected to a long drug
treatment associated with lifestyle advice without guarantee of total recovery.
However, regardless of the type of treatment performed, late treatment
necessarily creates psychological instability in the patient. It is therefore
important to be able to diagnose the disease as early as possible if we desire
that the patient does not suffer from its consequences on their mental health.
That is why the study aims to propose a model for detecting epilepsy in order
to be able to identify it as early as possible, especially in newborns. The
objective of the article is to propose a model for detecting epilepsy using
data from electroencephalogram signals from 10 newborns. This model developed using
the extra trees classifier technique offers the possibility of predicting
epilepsy in infants with an accuracy of around 99.4%.