Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, 44106, USA.
Sci Rep. 2017 Aug 15;7(1):8137. doi: 10.1038/s41598-017-03925-0.
The introduction of mild cognitive impairment (MCI) as a diagnostic category adds to the challenges of diagnosing Alzheimer's Disease (AD). No single marker has been proven to accurately categorize patients into their respective diagnostic groups. Thus, previous studies have attempted to develop fused predictors of AD and MCI. These studies have two main limitations. Most do not simultaneously consider all diagnostic categories and provide suboptimal fused representations using the same set of modalities for prediction of all classes. In this work, we present a combined framework, cascaded multiview canonical correlation (CaMCCo), for fusion and cascaded classification that incorporates all diagnostic categories and optimizes classification by selectively combining a subset of modalities at each level of the cascade. CaMCCo is evaluated on a data cohort comprising 149 patients for whom neurophysiological, neuroimaging, proteomic and genomic data were available. Results suggest that fusion of select modalities for each classification task outperforms (mean AUC = 0.92) fusion of all modalities (mean AUC = 0.54) and individual modalities (mean AUC = 0.90, 0.53, 0.71, 0.73, 0.62, 0.68). In addition, CaMCCo outperforms all other multi-class classification methods for MCI prediction (PPV: 0.80 vs. 0.67, 0.63).
轻度认知障碍 (MCI) 的引入增加了阿尔茨海默病 (AD) 诊断的挑战。没有单一的标志物被证明能够准确地将患者分类到各自的诊断组中。因此，以前的研究试图开发 AD 和 MCI 的融合预测因子。这些研究有两个主要的局限性。大多数研究没有同时考虑所有诊断类别，并且使用相同的模态集来预测所有类别，从而提供了次优的融合表示。在这项工作中，我们提出了一个组合框架，级联多视图正则相关 (CaMCCo)，用于融合和级联分类，该框架包含所有诊断类别，并通过在级联的每个级别选择性地组合模态的子集来优化分类。CaMCCo 在一个包含 149 名患者的数据队列上进行了评估，这些患者可获得神经生理学、神经影像学、蛋白质组学和基因组学数据。结果表明，针对每个分类任务选择融合的模态比融合所有模态 (平均 AUC=0.54) 和单个模态 (平均 AUC=0.90、0.53、0.71、0.73、0.62、0.68) 的效果更好。此外，CaMCCo 在 MCI 预测方面优于所有其他多类分类方法 (PPV: 0.80 与 0.67、0.63)。
