Automatic Detection of Epileptiform Discharges in the EEG

TL;DR

This paper presents an automatic multi-stage algorithm using wavelet analysis, mimetic analysis, and fuzzy logic to detect epileptiform discharges in EEG data, aiming to assist neurologists in diagnosing epilepsy more efficiently.

Contribution

It introduces a novel multi-stage detection system combining wavelet, mimetic analysis, and fuzzy logic for EEG epileptiform discharge detection.

Findings

Sensitivity and specificity above 80% and 70%

Effective detection in long-term ambulatory EEGs

Assists neurologists in epilepsy diagnosis

Abstract

The diagnosis of epilepsy generally includes a visual inspection of EEG recorded data by the Neurologist, with the purpose of checking the occurrence of transient waveforms called interictal epileptiform discharges. These waveforms have short duration (less than 100 ms), so the inspection process is usually time-consuming, particularly for ambulatory long term EEG records. Therefore, an automatic detection system of epileptiform discharges can be a valuable tool for a Neurology service. The proposed approach is the development of a multi stage detection algorithm, which processes the complete EEG signals and applies decision criteria to selected waveforms. It employs EEG analysis techniques such as Wavelet Transform and Mimetic Analysis, complemented with a classification based on Fuzzy Logic. In order to evaluate the algorithm's performance, data were collected from several epileptic patients, with epileptiform activity marked by a Neurologist. The average values obtained for both Sensitivity and Specificity were respectively higher than 80 and 70 percent.