Please use this identifier to cite or link to this item:
Title: Deep learning for automated epileptiform discharge detection from scalp EEG: A systematic review.
Austin Authors: Nhu, Duong;Janmohamed, Mubeen;Antonic-Baker, Ana;Perucca, Piero ;O'Brien, Terence J;Gilligan, Amanda K ;Kwan, Patrick;Tan, Chang Wei;Kuhlmann, Levin
Affiliation: Neurology
Medicine (University of Melbourne)
Neurosciences Clinical Institute, Epworth Healthcare, Melbourne, Victoria, Australia
Department of Data Science and AI, Faculty of Information Technology, Monash University, Clayton, Victoria, Australia
Department of Neuroscience, Central Clinical School, Monash University, Melbourne, Victoria, Australia
Department of Neurology, Alfred Health, Melbourne, Victoria, Australia
Department of Neurology, The Royal Melbourne Hospital, Melbourne, Victoria, Australia
Issue Date: 2022 2022
Publication information: Journal of Neural Engineering 2022; 19(5)
Abstract: Automated interictal epileptiform discharge (IED) detection has been widely studied, with machine learning methods at the forefront in recent years. As computational resources become more accessible, researchers have applied deep learning (DL) to IED detection with promising results. This systematic review aims to provide an overview of the current DL approaches to automated IED detection from scalp electroencephalography (EEG) and establish recommendations for the clinical research community. We conduct a systematic review according to the PRISMA guidelines. We searched for studies published between 2012 and 2022 implementing DL for automating IED detection from scalp EEG in major medical and engineering databases. We highlight trends and formulate recommendations for the research community by analyzing various aspects: data properties, preprocessing methods, DL architectures, evaluation metrics and results, and reproducibility. The search yielded 66 studies, and 23 met our inclusion criteria. There were two main DL networks, convolutional neural networks in 14 studies and long short-term memory networks in three studies. A hybrid approach combining a hidden Markov model with an autoencoder was employed in one study. Graph convolutional network was seen in one study, which considered a montage as a graph. All DL models involved supervised learning. The median number of layers was 9 (IQR: 5-21). The median number of IEDs was 11 631 (IQR: 2663-16 402). Only six studies acquired data from multiple clinical centers. AUC was the most reported metric (median: 0.94; IQR: 0.94-0.96). The application of DL to IED detection is still limited and lacks standardization in data collection, multi-center testing, and reporting of clinically relevant metrics (i.e. F1, AUCPR, and false-positive/minute). However, the performance is promising, suggesting that DL might be a helpful approach. Further testing on multiple datasets from different clinical centers is required to confirm the generalizability of these methods.
DOI: 10.1088/1741-2552/ac9644
ORCID: 0000-0001-9021-9716
Journal: Journal of Neural Engineering
PubMed URL: 36174541
Type: Journal Article
Subjects: automation
deep learning
interictal epileptiform discharges
Appears in Collections:Journal articles

Show full item record

Page view(s)

checked on May 29, 2023

Google ScholarTM


Items in AHRO are protected by copyright, with all rights reserved, unless otherwise indicated.