Applied Sciences, Journal Year: 2024, Volume and Issue: 14(16), P. 7398 - 7398

Published: Aug. 22, 2024

About 70 million people globally have been diagnosed with epilepsy. Electroencephalogram (EEG) devices are the primary method for identifying and monitoring seizures. The use of EEG expands preclinical research involving long-term recording neuro-activities in rodent models epilepsy targeted towards efficient testing prospective antiseizure medications. Typically, trained epileptologists visually analyse recordings, which is time-consuming subject to expert variability. Automated epileptiform discharge detection using machine learning or deep methods an effective approach tackling these challenges. This systematic review examined summarised last 30 years on detecting methods. A comprehensive literature search was conducted two databases, PubMed Google Scholar. Following PRISMA protocol, 3021 retrieved articles were filtered 21 based inclusion exclusion criteria. An additional article obtained through reference list. Hence, 22 selected critical analysis this review. These revealed seizure type, features feature engineering, methods, training methodologies, evaluation metrics so far explored, deployed real-world validation. Although studies advanced field research, majority experimental. Further required fill identified gaps expedite epilepsy, ultimately leading translational research.

Language: Английский