Analyzing Hierarchical Multi-View MRI Data With StaPLR: An Application to Alzheimer's Disease Classification

Frontiers in Neuroscience, vol. 16, pp. 830630

Abstract

Multi-view data refers to a setting where features are divided into feature sets, for example because they correspond to different sources. Stacked penalized logistic regression (StaPLR) is a recently introduced method that can be used for classification and automatically selecting the views that are most important for prediction. We introduce an extension of this method to a setting where the data has a hierarchical multi-view structure. We also introduce a new view importance measure for StaPLR, which allows us to compare the importance of views at any level of the hierarchy. We apply our extended StaPLR algorithm to Alzheimer's disease classification where different MRI measures have been calculated from three scan types: structural MRI, diffusion-weighted MRI, and resting-state fMRI. StaPLR can identify which scan types and which derived MRI measures are most important for classification, and it outperforms elastic net regression in classification performance.

Authors 7

1. Wouter van Loon corresponding Aachen Department of Methodology and Statistics

   Leiden University

   Affiliation as printed

   Department of Methodology and Statistics, Leiden University, Leiden, Netherlands

2. Frank de Vos Aachen Department of Methodology and Statistics Department of Radiology, Leiden University Medical Center Leiden Institute for Brain and Cognition

   Leiden University · Leiden University Medical Center

   Affiliation as printed

   Department of Methodology and Statistics, Leiden University, Leiden, Netherlands

   Department of Radiology, Leiden University Medical Center, Leiden, Netherlands

   Leiden Institute for Brain and Cognition, Leiden, Netherlands

3. Marjolein Fokkema Aachen Department of Methodology and Statistics

   Leiden University

   Affiliation as printed

   Department of Methodology and Statistics, Leiden University, Leiden, Netherlands

4. Botond Szabó

   Bocconi University

   Affiliation as printed

   Bocconi Institute for Data Science and Analytics, Bocconi University, Milan, Italy

   Department of Decision Sciences, Bocconi University, Milan, Italy

5. Marisa Koini

   Medical University of Graz

   Affiliation as printed

   Division of Neurogeriatrics, Department of Neurology, Medical University of Graz, Graz, Austria

6. Reinhold Ernst Schmidt

   Medical University of Graz

   Affiliation as printed

   Division of Neurogeriatrics, Department of Neurology, Medical University of Graz, Graz, Austria

7. Mark de Rooij Aachen Department of Methodology and Statistics Leiden Institute for Brain and Cognition

   Leiden University

   Affiliation as printed

   Department of Methodology and Statistics, Leiden University, Leiden, Netherlands

   Leiden Institute for Brain and Cognition, Leiden, Netherlands