xEEGNet: towards explainable AI in EEG dementia classification.

IF 3.8
Andrea Zanola, Louis Fabrice Tshimanga, Federico Del Pup, Marco Baiesi, Manfredo Atzori
{"title":"xEEGNet: towards explainable AI in EEG dementia classification.","authors":"Andrea Zanola, Louis Fabrice Tshimanga, Federico Del Pup, Marco Baiesi, Manfredo Atzori","doi":"10.1088/1741-2552/adf6e6","DOIUrl":null,"url":null,"abstract":"<p><p><i>Objective.</i>This work presents xEEGNet, a novel, compact, and explainable neural network for electroencephalography (EEG) data analysis. It is fully interpretable and reduces overfitting through a major parameter reduction.<i>Approach.</i>As an applicative use case to develop our model, we focused on the classification of common dementia conditions, Alzheimer's and frontotemporal dementia, versus controls. xEEGNet, however, is broadly applicable to other neurological conditions involving spectral alterations. We used ShallowNet, a simple and popular model in the EEGNet family, as a starting point. Its structure was analyzed and gradually modified to move from a 'black box' model to a more transparent one, without compromising performance. The learned kernels and weights were analyzed from a clinical standpoint to assess their medical significance. Model variants, including ShallowNet and the final xEEGNet, were evaluated using a robust nested-leave-n-subjects out cross-validation for unbiased performance estimates. Variability across data splits was explained using the embedded EEG representations, grouped by class and set, with pairwise separability to quantify group distinction. Overfitting was measured through training-validation loss correlation and training speed.<i>Main results.</i>xEEGNet uses only 168 parameters, 200 times fewer than ShallowNet, yet retains interpretability, resists overfitting, achieves comparable median performance (-1.5%), and reduces performance variability across splits. This variability is explained by the embedded EEG representations: higher accuracy correlates with greater separation between test-set controls and Alzheimer's cases, without significant influence from the training data.<i>Significance.</i>The capability of xEEGNet to filter specific EEG bands, learns band specific topographies and use the right EEG spectral bands for disease classification demonstrates its interpretability. While big deep learning models are typically prioritized for performance, this study shows that smaller architectures like xEEGNet can be equally effective in pathology classification, using EEG data.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":3.8000,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of neural engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1088/1741-2552/adf6e6","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Objective.This work presents xEEGNet, a novel, compact, and explainable neural network for electroencephalography (EEG) data analysis. It is fully interpretable and reduces overfitting through a major parameter reduction.Approach.As an applicative use case to develop our model, we focused on the classification of common dementia conditions, Alzheimer's and frontotemporal dementia, versus controls. xEEGNet, however, is broadly applicable to other neurological conditions involving spectral alterations. We used ShallowNet, a simple and popular model in the EEGNet family, as a starting point. Its structure was analyzed and gradually modified to move from a 'black box' model to a more transparent one, without compromising performance. The learned kernels and weights were analyzed from a clinical standpoint to assess their medical significance. Model variants, including ShallowNet and the final xEEGNet, were evaluated using a robust nested-leave-n-subjects out cross-validation for unbiased performance estimates. Variability across data splits was explained using the embedded EEG representations, grouped by class and set, with pairwise separability to quantify group distinction. Overfitting was measured through training-validation loss correlation and training speed.Main results.xEEGNet uses only 168 parameters, 200 times fewer than ShallowNet, yet retains interpretability, resists overfitting, achieves comparable median performance (-1.5%), and reduces performance variability across splits. This variability is explained by the embedded EEG representations: higher accuracy correlates with greater separation between test-set controls and Alzheimer's cases, without significant influence from the training data.Significance.The capability of xEEGNet to filter specific EEG bands, learns band specific topographies and use the right EEG spectral bands for disease classification demonstrates its interpretability. While big deep learning models are typically prioritized for performance, this study shows that smaller architectures like xEEGNet can be equally effective in pathology classification, using EEG data.

面向脑电痴呆分类的可解释AI。
目的:本文介绍了一种新颖、紧凑、可解释的脑电图数据分析神经网络xEEGNet。它是完全可解释的,并通过减少主要参数来减少过拟合。方法:作为开发模型的应用用例,我们重点研究了常见痴呆疾病,阿尔茨海默氏症和额颞叶痴呆与对照组的分类。然而,xEEGNet广泛适用于涉及频谱改变的其他神经系统疾病。我们使用了EEGNet家族中一个简单而流行的模型ShallowNet作为起点。在不影响性能的前提下,对其结构进行分析并逐步修改,从“黑箱”模型转变为更透明的模型。从临床角度分析学习到的核函数和权值,以评估其医学意义。模型变体,包括ShallowNet和最终的xEEGNet,使用稳健的Nested-Leave-N Subjects Out交叉验证来评估无偏性能估计。使用嵌入的脑电图表示来解释数据分割之间的可变性,按类和集分组,具有两两可分性来量化组区分。通过训练-验证损失相关性和训练速度来衡量过拟合。主要结果:xEEGNet仅使用168个参数,比ShallowNet少200倍,但保留了可解释性,抵制过拟合,实现了可比较的中位数性能(-1.5%),并减少了拆分之间的性能可变性。这种可变性可以通过嵌入的脑电图表示来解释:更高的准确性与测试集控制和阿尔茨海默病病例之间的更大分离相关,而不受训练数据的显著影响。意义:xEEGNet能够过滤特定的EEG波段,学习特定波段的地形,并使用正确的EEG频谱波段进行疾病分类,这证明了它的可解释性。虽然大型深度学习模型通常优先考虑性能,但该研究表明,使用脑电图数据,像xEEGNet这样的小型架构在病理分类方面同样有效。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信