Universidade Federal de Goiás, Brazil.
Universidade de São Paulo, Brazil.
Seizure. 2024 Nov;122:80-86. doi: 10.1016/j.seizure.2024.09.019. Epub 2024 Sep 25.
Interictal epileptiform discharges (IEDs) in electroencephalograms (EEGs) are an important biomarker for epilepsy. Currently, the gold standard for IED detection is the visual analysis performed by experts. However, this process is expert-biased, and time-consuming. Developing fast, accurate, and robust detection methods for IEDs based on EEG may facilitate epilepsy diagnosis. We aim to assess the performance of deep learning (DL) and classic machine learning (ML) algorithms in classifying EEG segments into IED and non-IED categories, as well as distinguishing whether the entire EEG contains IED or not.
We systematically searched PubMed, Embase, and Web of Science following PRISMA guidelines. We excluded studies that only performed the detection of IEDs instead of binary segment classification. Risk of Bias was evaluated with Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). Meta-analysis with the overall area under the Summary Receiver Operating Characteristic (SROC), sensitivity, and specificity as effect measures, was performed with R software.
A total of 23 studies, comprising 3,629 patients, were eligible for synthesis. Eighteen models performed discharge-level classification, and 6 whole-EEG classification. For the IED-level classification, 3 models were validated in an external dataset with more than 50 patients and achieved a sensitivity of 84.9 % (95 % CI: 82.3-87.2) and a specificity of 68.7 % (95 % CI: 7.9-98.2). Five studies reported model performance using both internal validation (cross-validation) and external datasets. The meta-analysis revealed higher performance for internal validation, with 90.4 % sensitivity and 99.6 % specificity, compared to external validation, which showed 78.1 % sensitivity and 80.1 % specificity.
Meta-analysis showed higher performance for models validated with resampling methods compared to those using external datasets. Only a minority of models use more robust validation techniques, which often leads to overfitting.
脑电图（EEG）中的发作间期癫痫样放电（IED）是癫痫的一个重要生物标志物。目前，IED 检测的金标准是专家进行的视觉分析。然而，这个过程受到专家的影响，并且很耗时。基于 EEG 开发快速、准确和强大的 IED 检测方法可能有助于癫痫诊断。我们旨在评估深度学习（DL）和经典机器学习（ML）算法在将 EEG 段分类为 IED 和非 IED 类别以及区分 EEG 是否包含 IED 方面的性能。
我们按照 PRISMA 指南系统地搜索了 PubMed、Embase 和 Web of Science。我们排除了仅进行 IED 检测而不进行二进制段分类的研究。使用 Quality Assessment of Diagnostic Accuracy Studies（QUADAS-2）评估偏倚风险。使用 R 软件进行汇总受试者工作特征（SROC）曲线下面积、敏感性和特异性作为效应测量的元分析。
共有 23 项研究，包括 3629 名患者，符合综合标准。18 个模型进行了放电级分类，6 个模型进行了整个 EEG 分类。对于 IED 级分类，有 3 个模型在包含 50 多名患者的外部数据集上进行了验证，其敏感性为 84.9%（95%CI：82.3-87.2），特异性为 68.7%（95%CI：7.9-98.2）。有 5 项研究报告了使用内部验证（交叉验证）和外部数据集的模型性能。荟萃分析显示，内部验证的性能更高，敏感性为 90.4%，特异性为 99.6%，而外部验证的敏感性为 78.1%，特异性为 80.1%。
荟萃分析显示，使用重采样方法验证的模型性能优于使用外部数据集的模型。只有少数模型使用更稳健的验证技术，这往往导致过拟合。
