AI 中文总结
本研究提出 tPoE-EIB 方法，通过选择 EEG 的时间与通道证据构建受信息率限制的融合机制，在保持平衡准确率的同时提升了诊断的可审计性，适用于多种 EEG 诊断场景。
AI 中文摘要
预训练的脑电图（EEG）主干网络可提升迁移性能，但下游诊断头仍难以审计：预测由无限制的隐藏状态生成，而解释通常在决策后才产生。我们提出 tPoE-EIB，一种在仅使用证据进行预测的约束下适配 EEG 主干网络的证据信息瓶颈头。tPoE-EIB 选择时间和通道证据，将选定的摘要映射到共享潜在变量上的高斯专家，并通过 tempered 专家乘积后验对其进行融合。分类器仅观测该潜在变量，因此决策路径明确且受期望后验 KL 限制。这提供了带有信息率惩罚的可处理监督目标，而闭式形式的 tempered 后验缓解了相关证据轴融合时的过度自信问题。我们在六种诊断场景下，于预训练的 EEG 基础模型主干网络上评估 tPoE-EIB：事件类型分类、异常检测、癫痫发作检测、认知衰退分期、抑郁筛查及脑血管疾病分类。评估涵盖公共基准与内部临床队列、二分类筛查与细粒度分期、稀疏与密集导联配置。tPoE-EIB 保持了具有竞争力的平衡准确率，且在选择忠实性审计（包括插入-删除测试和门因果测试）上优于代表性的事后解释方法。其结构化后验还支持整合忠实性审计，包括专家丢弃、后验依赖及专家分歧测试。总体而言，这些结果表明，仅使用证据、受信息率限制的融合是在冻结的 EEG 基础模型之上实现可审计诊断的可行途径。
英文摘要
Pretrained EEG backbones improve transfer performance, but downstream diagnosis heads remain hard to audit: predictions are made from unrestricted hidden states, whereas explanations are usually produced only after the decision. We introduce tPoE-EIB, an evidence-information bottleneck head for adapting EEG backbones under an evidence-only prediction constraint. tPoE-EIB selects temporal and channel evidence, maps the selected summaries to Gaussian experts over a shared latent variable, and fuses them with a tempered product-of-experts posterior. The classifier observes only this latent, so the decision path is explicit and rate-limited by the expected posterior KL. This gives a tractable supervised objective with an information-rate penalty, while the closed-form tempered posterior mitigates overconfident fusion from correlated evidence axes. We evaluate tPoE-EIB on pretrained EEG foundation-model backbones across six diagnosis settings: event-type classification, abnormality detection, seizure detection, cognitive-decline staging, depression screening, and cerebrovascular-disease classification. The evaluation spans public benchmarks and in-house clinical cohorts, binary screening and fine-grained staging, and sparse and dense montages. tPoE-EIB preserves competitive balanced accuracy and improves over representative post-hoc explanations on selection-faithfulness audits, including insertion-deletion and gate-causality tests. Its structured posterior further enables integration-faithfulness audits, including expert-drop, posterior-reliance, and expert-disagreement tests. Overall, these results suggest that evidence-only, rate-limited fusion is a practical route to auditable diagnosis on top of frozen EEG foundation backbones.
