Institute of Medical Informatics, Medical Faculty, RWTH Aachen University, Aachen, Germany.
Institute of Medical Informatics, University of Münster, Münster, Germany.
Stud Health Technol Inform. 2022 Aug 17;296:33-40. doi: 10.3233/SHTI220801.
Recent advances in machine learning show great potential for automatic detection of abnormalities in electroencephalography (EEG). While simple and interpretable models combined with expert-comprehensible input features offer full control of the decision making process, these methods commonly lag behind complex deep learning and feature extraction methods in terms of performance. Here we study a feasibility of a bridging solution, where deep learning is combined with interpretable input and an algorithm computing the importance of particular EEG features in the decision process. We built a convolutional neural network with multi-channel EEG frequency bands as input and investigated four different methods for feature importance attribution: Layer-wise Relevance Propagation (LRP), DeepLIFT, Integrated Gradients (IG) and Guided GradCAM. Our analysis showed consistency between the first three methods, and deviating attributions of the fourth method, suggesting the importance of using a package of methods together to ensure the robustness of medical interpretation.
机器学习的最新进展显示出在脑电图 (EEG) 中自动检测异常的巨大潜力。虽然简单且可解释的模型结合专家可理解的输入特征可以完全控制决策过程，但这些方法在性能方面通常落后于复杂的深度学习和特征提取方法。在这里，我们研究了一种桥接解决方案的可行性，即将深度学习与可解释的输入以及一种计算决策过程中特定 EEG 特征重要性的算法相结合。我们构建了一个具有多通道 EEG 频带作为输入的卷积神经网络，并研究了四种不同的特征重要性归因方法：层间相关性传播 (LRP)、DeepLIFT、集成梯度 (IG) 和引导梯度 Cam (Guided GradCAM)。我们的分析表明，前三种方法之间具有一致性，而第四种方法的归因存在差异，这表明使用一整套方法来确保医学解释的稳健性非常重要。
