Analyzing hierarchical multi-view MRI data with StaPLR: An application to Alzheimer's disease classification

TL;DR

This paper extends the StaPLR method to hierarchical multi-view data, enabling better feature selection and interpretability in complex MRI datasets for Alzheimer's disease classification, and demonstrates improved performance over elastic net regression.

Contribution

The paper introduces a hierarchical extension of StaPLR and a new view importance measure, enhancing multi-view data analysis and interpretability in medical imaging.

Findings

StaPLR outperforms elastic net in classification accuracy.

The method identifies key MRI scan types and measures for Alzheimer's.

Hierarchical view importance measure improves interpretability.

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.