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.
J Neural Eng. 2022 Oct 19;19(5). doi: 10.1088/1741-2552/ac9644.
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.
自动发作间期癫痫样放电 (IED) 检测已得到广泛研究，近年来机器学习方法处于前沿。随着计算资源变得更容易获得，研究人员已经将深度学习 (DL) 应用于 IED 检测，并取得了有希望的结果。本系统评价旨在提供一个从头皮脑电图 (EEG) 自动检测 IED 的当前 DL 方法概述，并为临床研究界提出建议。我们按照 PRISMA 指南进行系统评价。我们在主要的医学和工程数据库中搜索了 2012 年至 2022 年期间发表的实施 DL 以从头皮 EEG 自动检测 IED 的研究。我们通过分析各个方面来突出趋势并为研究界提出建议：数据特性、预处理方法、DL 架构、评估指标和结果以及可重复性。搜索产生了 66 项研究，其中 23 项符合纳入标准。有两种主要的 DL 网络，14 项研究中使用卷积神经网络，3 项研究中使用长短期记忆网络。一项研究采用了一种将隐藏马尔可夫模型与自动编码器相结合的混合方法。一项研究中使用了图卷积网络，该研究将导联视为图。所有 DL 模型都涉及监督学习。中位数的层数为 9（IQR：5-21）。中位数的 IED 数为 11631（IQR：2663-16402）。只有 6 项研究从多个临床中心获取数据。AUC 是报告最多的指标（中位数：0.94；IQR：0.94-0.96）。DL 应用于 IED 检测的应用仍然有限，在数据收集、多中心测试和报告临床相关指标（即 F1、AUCPR 和假阳性/分钟）方面缺乏标准化。然而，性能很有前景，表明 DL 可能是一种有帮助的方法。需要在来自不同临床中心的多个数据集上进一步测试，以确认这些方法的泛化能力。
