* Center for Advanced Technology and Education (CATE), Florida International University, 10555 W Flagler St., Miami, Florida 33174, USA.
† Wien Center for Alzheimer's Disease & Memory Disorders, Mount Sinai Medical Center Miami Beach, Florida 33140, USA.
Int J Neural Syst. 2018 Oct;28(8):1850017. doi: 10.1142/S012906571850017X. Epub 2018 Apr 12.
Over the past few years, several approaches have been proposed to assist in the early diagnosis of Alzheimer's disease (AD) and its prodromal stage of mild cognitive impairment (MCI). Using multimodal biomarkers for this high-dimensional classification problem, the widely used algorithms include Support Vector Machines (SVM), Sparse Representation-based classification (SRC), Deep Belief Networks (DBN) and Random Forest (RF). These widely used algorithms continue to yield unsatisfactory performance for delineating the MCI participants from the cognitively normal control (CN) group. A novel Gaussian discriminant analysis-based algorithm is thus introduced to achieve a more effective and accurate classification performance than the aforementioned state-of-the-art algorithms. This study makes use of magnetic resonance imaging (MRI) data uniquely as input to two separate high-dimensional decision spaces that reflect the structural measures of the two brain hemispheres. The data used include 190 CN, 305 MCI and 133 AD subjects as part of the AD Big Data DREAM Challenge #1. Using 80% data for a 10-fold cross-validation, the proposed algorithm achieved an average F1 score of 95.89% and an accuracy of 96.54% for discriminating AD from CN; and more importantly, an average F1 score of 92.08% and an accuracy of 90.26% for discriminating MCI from CN. Then, a true test was implemented on the remaining 20% held-out test data. For discriminating MCI from CN, an accuracy of 80.61%, a sensitivity of 81.97% and a specificity of 78.38% were obtained. These results show significant improvement over existing algorithms for discriminating the subtle differences between MCI participants and the CN group.
在过去的几年中，已经提出了几种方法来辅助阿尔茨海默病（AD）及其轻度认知障碍（MCI）前驱期的早期诊断。使用多模态生物标志物进行这种高维分类问题，广泛使用的算法包括支持向量机（SVM）、基于稀疏表示的分类（SRC）、深度置信网络（DBN）和随机森林（RF）。这些广泛使用的算法在将 MCI 参与者与认知正常对照组（CN）区分开来方面，性能仍然不尽如人意。因此，引入了一种新的基于高斯判别分析的算法，以实现比上述最先进算法更有效和准确的分类性能。本研究利用磁共振成像（MRI）数据作为输入，分别进入两个独立的高维决策空间，反映了两个大脑半球的结构测量。所使用的数据包括 190 名 CN、305 名 MCI 和 133 名 AD 作为 AD 大数据 DREAM 挑战赛 #1 的一部分。使用 80%的数据进行 10 折交叉验证，所提出的算法在区分 AD 与 CN 时的平均 F1 得分为 95.89%，准确率为 96.54%；更重要的是，在区分 MCI 与 CN 时，平均 F1 得分为 92.08%，准确率为 90.26%。然后，在剩余的 20%保留测试数据上进行了真实测试。在区分 MCI 与 CN 时，获得了 80.61%的准确率、81.97%的敏感性和 78.38%的特异性。这些结果表明，在区分 MCI 参与者和 CN 组之间的细微差异方面，与现有算法相比有显著改善。
