Research Article
Structural Brain Imaging Phenotypes of Mild Cognitive Impairment (MCI) and Alzheimer’s Disease (AD) Found by Hierarchical Clustering
Table 1
Methods and key findings of cited literature.
| Reference | MCI or AD | Method | Application |
| [5] | MCI | Multilayer clustering | Identification of rapid and slow decliners | [11] | AD | Visual rating scales | Recognizing AD subtypes | [12] | AD | Random forest pairwise similarity and hierarchical clustering | Varying rates of degeneration of AD subtypes | [7] | AD | -means clustering and support vector machines | Subtypes of AD atrophy | [18] | MCI and AD | Voxel-wise statistical analysis and regression models | Brain atrophy w.r.t age and APOE genotype | [14] | AD | Voxel-based morphometry, statistical analysis using ANOVA | Regional atrophy patterns and progression rates of AD subtypes | [16] | AD | Neurofibrillary tangle count using digital microscopy, statistical methods (ANOVA, -tests) | Subtypes of AD and distinct clinical characteristics | [17] | AD | Cortical, hippocampal volume measurements, statistical methods | Progression rates of AD subtypes | [21] | MCI and AD | Voxel-based morphometry | Atrophy pattern related to progression from MCI to AD | [19] | MCI and AD | Semisupervised machine learning and random forest classification | Predicting conversion from MCI to AD | [22] | AD | Voxel-based morphometry and regression analysis | Precuneus atrophy in early-onset Alzheimer’s disease |
|
|