EEG-PRISM: Physiologically-Grounded Interpretability of Predictions by EEG Foundation Models
作者: Deeksha M Shama, Punnisa Amornsirikul, Archana Venkataraman
分类: cs.LG
发布日期: 2026-08-13
💡 一句话要点
提出EEG-PRISM以解决EEG基础模型可解释性不足问题
🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)
关键词: EEG分析 可解释人工智能 生物标志物 癫痫 自闭症 基础模型 线性变换 频率域
📋 核心要点
- 现有的EEG分析方法在可解释性方面存在不足,无法与临床直觉有效对接。
- EEG-PRISM通过线性变换和反向传播规则,将归因分数映射到生理相关的频率和源域。
- 实验结果表明,EEG-PRISM在频谱恢复和空间准确性方面表现优异,尤其在癫痫和自闭症的应用中取得了良好效果。
📝 摘要(中文)
本研究旨在解决当前EEG分析中基础模型的可解释性不足问题。现有的可解释人工智能技术在时间-通道输入空间提供归因分数,但与临床直觉不符。EEG-PRISM通过线性变换和反向传播规则,将时间-通道归因分数映射到频率域和源域,支持对瞬态事件的窗口级分析及临床相关生物标志物的群体级识别。实验结果显示,EEG-PRISM在模拟和真实数据中均表现出色,能够准确恢复频谱和空间信息,推动了可解释EEG基础模型的发展。
🔬 方法详解
问题定义:本研究旨在解决当前EEG基础模型的可解释性不足问题,现有方法在时间-通道输入空间提供的归因分数与临床直觉不符,限制了其应用。
核心思路:EEG-PRISM的核心思路是利用线性变换和反向传播规则,将时间-通道归因分数映射到频率域和源域,从而实现更符合生理学的解释。
技术框架:EEG-PRISM的整体架构包括两个主要模块:首先,通过可逆离散傅里叶变换(DFT)将归因分数映射到频率域;其次,利用近似可逆的EEG生成模型将其映射到源域。
关键创新:EEG-PRISM的最大创新在于其能够在不修改或重新训练基础模型的情况下,提供生理学基础的可解释性,这与现有方法的局限性形成鲜明对比。
关键设计:在设计上,EEG-PRISM采用了标准的反向传播规则,并结合线性变换,确保了映射过程的准确性和有效性。
🖼️ 关键图片
📊 实验亮点
在实验中,EEG-PRISM在模拟数据中实现了近乎完美的频谱恢复,空间准确率达到69.2%。在癫痫分析中,EEG-PRISM成功定位癫痫发作区域的准确率为50%。在自闭症研究中,能够将预测的生物标志物准确定位于额叶和颞叶区域,验证了其有效性。
🎯 应用场景
EEG-PRISM的研究成果在临床EEG分析中具有广泛的应用潜力,能够帮助医生更好地定位癫痫发作区域和识别自闭症相关的生物标志物。这种方法的引入将推动EEG基础模型在临床实践中的应用,提高对复杂神经活动的理解。
📄 摘要(原文)
Objective: Foundation models represent the next advancement in AI for EEG analysis; however current explainable AI techniques provide attribution scores in the time-channel input space, which is mismatched to clinical intuition about EEG. Thus, there is a critical need for a universal method that can extend the interpretability of any foundation model to alternative and physiologically relevant domains without modifying or retraining the underlying model. Methods: EEG-PRISM leverages linear transformations and established backpropagation rules to map time-channel attribution scores into alternative domains. We derive mappings to the frequency domain via an invertible DFT and to the source domain via an approximately invertible EEG generative model. We evaluate EEG-PRISM in simulated and real data, assessing recovery of ground-truth phenomena across domains with five foundation models and four AI explainers. Results: In simulation, EEG-PRISM achieves near-perfect spectral recovery and 69.2% spatial accuracy. In epilepsy, EEG-PRISM correctly determines that delta-theta activity is most salient and correctly localizes the seizure onset region with 50% accuracy. In autism, EEG-PRISM localizes the predictive delta-alpha biomarkers to frontal and temporal regions, consistent with prior work. Conclusion: EEG-PRISM is a theoretically-grounded post-hoc attribution method with accurate mapping into the spectral and spatial domains. It supports window-level analysis of transient events (e.g., seizures) and group-level identification of clinically relevant biomarkers (e.g., autism), thus advancing interpretable EEG foundation models. Significance: This work enables physiologically-grounded interpretation of EEG foundation models and supports clinically relevant insights such as event localization and biomarker identification.