用生理概念引导的多项式网络提升脑电图痴呆早期检测的准确与可解释性
Interpretable Concept-Guided Polynomial Tabular Kolmogorov-Arnold Network for EEG-Based Mild Cognitive Impairment Detection
- 将脑电信号按生理概念分组，通过二次多项式扩展捕捉特征间交互
- 在372人数据上达0.9038加权F1，比梯度提升高5.65个百分点
- 揭示了频谱密度、熵值等关键指标及跨概念交互的作用，适合临床研究者
早期且可扩展地检测轻度认知障碍（MCI）仍是未解决的临床难题。现有基于脑电图（EEG）的筛查方法受限于人工设计的特征流程，丢失神经生理结构；而深度学习模型则牺牲可解释性以换取性能。目前尚无工作在睡眠脑电图基础上统一构建生理结构化概念编码、跨概念交互建模与非线性表格式分类。本研究提出概念引导的多项式表格式柯尔莫戈罗夫-阿诺德网络（CPTabKAN），将异质脑电特征映射为生理相关的概念表示，通过二阶多项式变换暴露一阶与二阶交互，并采用傅里叶参数化的表格式柯尔莫戈罗夫-阿诺德网络分类器学习非线性决策边界。在‘骨质疏松骨折研究’队列（372名受试者，整夜多导睡眠图）上，使用1,379个特征分为十个生理动机概念组进行评估。10折交叉验证下，CPTabKAN-二阶达到0.9038的加权F1（标准差0.034），优于梯度提升5.65个百分点（t(9)=1.934，p=0.043，单侧配对检验），且在SMOTE平衡后仍具优势。消融分析证实各组件独立贡献。概念重要性分析显示，功率谱密度、多尺度熵和赫约特参数主导一阶权重，而涉及勒姆佩尔-齐夫-威尔奇复杂度、统计量、人口学信息和慢振荡的跨概念交互超过所有一阶得分。结果表明，结构化概念与交互感知的表格式学习能呈现生理上一致的推理过程，增强临床信任。
原文摘要 · Abstract (English)
Early and scalable detection of mild cognitive impairment (MCI) remains an unresolved clinical challenge. Existing EEG-based screening approaches are constrained by handcrafted feature pipelines that discard neurophysiologically meaningful domain structure and deep learning classifiers that sacrifice interpretability for performance. No existing work unifies physiologically organized concept encoders, cross-concept interaction modeling, and nonlinear tabular classification in a sleep EEG-based MCI detection framework. This study proposes Concept-guided Polynomial-transformed Tabular learning using Kolmogorov-Arnold Network (CPTabKAN), which maps heterogeneous EEG-derived features into domain-informed concept representations, expands them via degree-2 polynomial transformation to expose first- and second-order interactions, and applies a Fourier-parameterized TabKAN classifier to learn nonlinear decision boundaries. CPTabKAN was evaluated on the Study of Osteoporotic Fractures cohort (372 subjects, overnight polysomnography), using 1,379 features organized into ten physiologically motivated concept groups. Under 10-fold cross-validation, CPTabKAN-Second Order achieved a weighted F1-score of 0.9038 (SD 0.034), outperforming GradientBoosting by 5.65 percentage points (t(9)=1.934,p=0.043, one-sided paired test), with advantages persisting under SMOTE-based balancing. Ablation analysis confirmed independent contributions from each component. Concept importance analysis revealed that power spectral density, multi-scale entropy, and Hjorth parameters dominated first-order weights, while cross-concept interactions involving Lempel-Ziv-Welch complexity, statistics, demographics, and slow oscillations exceeded all first-order scores. These results demonstrate that concept-structured, interaction-aware tabular learning surfaces physiologically coherent reasoning, supporting clinical trust.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。