Abstract
While the identification of biomarkers for Alzheimer’s disease (AD) is critical, emphasis must also be placed on defining the relationship between these and other indicators. To this end, we propose a network-based radial basis function-sparse partial least squares (RBF-sPLS) approach to analyze structural magnetic resonance imaging (sMRI) data of the brain. This intermediate phenotype for AD represents a more objective approach for exploring biomarkers in the blood and cerebrospinal fluid. The proposed method has two unique features for effective biomarker selection. The first is that applying RBF to sMRI data can reduce the dimensions without excluding information. The second is that the network analysis considers the relationship among the biomarkers, while applied to non-imaging data. As a result, the output can be interpreted as clusters of related biomarkers. In addition, it is possible to estimate the parameters between the sMRI data and biomarkers while simultaneously selecting the related brain regions and biomarkers. When applied to real data, this technique identified not only the hippocampus and traditional biomarkers, such as amyloid beta, as predictive of AD, but also numerous other regions and biomarkers.
Highlights
Alzheimer’s disease (AD) is the most common form of dementia and is a global problem, especially in developed countries, where the aging population is growing rapidly
From the components extracted by the sparse partial least squares (sPLS) procedure, we selected certain components to define brain regions and non-imaging biomarkers associated with the incidence of AD, using logistic regression models.We show that the proposed method is useful for achieving dimension reduction, based on typical real-life data
Scans at 1.5T were downloaded from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database for evaluation in March 2013; these consisted of 104 AD and 430 non-AD (NC + mild cognitive impairment (MCI)) scans
Summary
Alzheimer’s disease (AD) is the most common form of dementia and is a global problem, especially in developed countries, where the aging population is growing rapidly. A limitation of this voxel-wise neuroimaging system includes sample sizes that are generally small in comparison with the high dimensionality of the data, making it challenging to define correlations between the response (Y) and predictive (X) variables. Multivariate data sets, partial least squares (PLS), canonical correlation, reduced rank regression, and independent component analyses have been used to detect morphological abnormalities from sMRI data, in association with non-imaging markers. To analyze sMRI data as an intermediate phenotype and, in parallel, to explore non-imaging biomarkers from over 100 candidates, we have defined multivariate variables for both X and Y in a PLS regression model. We proposed the RBF-sPLS approach, which involves application of the radial basis function (RBF) method to 3D sMRI data as a pre-processing step for the sparse partial least squares (sPLS) approach for investigating the relationship between clinical characteristics and brain morphology. Wolz et al. have proposed the nonlinear dimension-reduction method for such studies, with a limited number of clinical characteristics
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
