Canonical Joint and Individual Variation Explained (CJIVE) provides a method for jointly analyzing multi-block datasets collected from the same individuals. We apply this method to measures of brain morhometry and cognition from a sample of older adults. We found latent patterns of joint variation across data types which were statistically associated with diagnoses of Alzheimer's Disease and mild cognitive impairment. We also found that the unique patterns of variation within each data type were not associated with diagnoses.
This abstract and the presentation materials are available to members only; a login is required.