使用紧凑生物标志物和Kolmogorov-Arnold网络的可解释多模式框架改善了阿尔茨海默病的早期诊断
An interpretable multimodal framework using compact biomarkers and Kolmogorov-Arnold networks improves the early diagnosis of Alzheimer's disease.
摘要(中文译文)
阿尔茨海默病（AD）的早期诊断，尤其是对轻度认知障碍（MCI）阶段的准确识别，对于延缓疾病进展至关重要。尽管深度学习在AD诊断中已取得令人瞩目的性能，但现有的多模态模型往往以“黑箱”方式运行，缺乏临床实践所需的透明度，且未能显式建模影像特征与临床特征之间的深层交互。为解决这些局限，本研究提出了一种可解释的多模态框架，即紧凑生物标志物柯尔莫哥洛夫-阿诺德网络（CBKAN）。具体而言，我们引入了具有疾病特异性注意力的EHCTNet从3D MRI数据中提取特征，并创新性地约束编码器输出一组紧凑的生物标志物，而非传统的高维抽象向量，从而模拟临床医生的诊断逻辑（例如判断脑萎缩）。此外，采用混合特征Transformer将这些影像生物标志物与临床及遗传数据进行融合，显式捕捉跨模态的互补关系。最后，采用柯尔莫哥洛夫-阿诺德网络（KAN）作为分类器，有效建模AD进展的高度非线性特征。在ADNI数据集800名受试者上的实验表明，CBKAN在AD/MCI/CN分类任务中达到91.1%的准确率和0.910的F1分数，显著优于现有主流方法。统计分析验证了模型各组件的有效性。所提出的模型为早期阿尔茨海默病诊断提供了一个具有潜在可解释性和高性能的决策支持框架，但其跨队列泛化能力和真实世界临床实用性仍需在独立外部数据集中进一步验证。
Abstract
Early diagnosis of Alzheimer's disease (AD), especially accurate identification at the mild cognitive impairment (MCI) stage, is crucial for slowing disease progression. Although deep learning has achieved promising performance in AD diagnosis, existing multimodal models often operate as "black boxes," lacking the transparency required for clinical practice and failing to explicitly model deep interactions between imaging and clinical features. To address these limitations, this study proposes an interpretable multimodal framework, namely the Compact Biomarker Kolmogorov-Arnold Network (CBKAN). Specifically, we introduce EHCTNet with disease-specific attention to extract features from 3D MRI data, and innovatively constrain the encoder to output a set of compact biomarkers instead of traditional high-dimensional abstract vectors, mimicking the diagnostic logic of clinicians (e.g., judging brain atrophy). In addition, a hybrid feature Transformer is used to fuse these imaging biomarkers with clinical and genetic data, explicitly capturing complementary relationships across modalities. Finally, the Kolmogorov-Arnold Network (KAN) is adopted as the classifier to effectively model the highly nonlinear characteristics of AD progression. Experiments on 800 subjects from the ADNI dataset show that CBKAN achieves 91.1% accuracy and an F1-score of 0.910 in the AD/MCI/CN classification task, significantly outperforming existing mainstream methods. Statistical analyses validate the effectiveness of each component of the model. The proposed model provides a potentially interpretable and high-performing decision-support framework for early Alzheimer's disease diagnosis, although its cross-cohort generalizability and real-world clinical utility require further validation in independent external datasets.
如何引用
AMA
Daiqing Tan, LianYing Song, Yan Tang, Aiqing Han. An interpretable multimodal framework using compact biomarkers and Kolmogorov-Arnold networks improves the early diagnosis of Alzheimer's disease.. Scientific reports. 2026; doi:10.1038/s41598-026-59430-w.
APA
Daiqing Tan, LianYing Song, Yan Tang, Aiqing Han (2026). An interpretable multimodal framework using compact biomarkers and Kolmogorov-Arnold networks improves the early diagnosis of Alzheimer's disease.. Scientific reports. https://doi.org/10.1038/s41598-026-59430-w
GB/T 7714
Daiqing Tan, LianYing Song, Yan Tang, Aiqing Han. An interpretable multimodal framework using compact biomarkers and Kolmogorov-Arnold networks improves the early diagnosis of Alzheimer's disease.[J]. Scientific reports, 2026 doi:10.1038/s41598-026-59430-w.
在 PubMed增强版 阅读全文
翻译全文 · AI 文献问答 · PDF 原文下载 · 引用导出