Identifying Imaging Markers for Predicting Cognitive Assessments Using Wasserstein Distances Based Matrix Regression

Abstract

Alzheimer's disease (AD) is a severe type of neurodegeneration which worsens human memory, thinking and cognition along a temporal continuum. How to identify the informative phenotypic neuroimaging markers and accurately predict cognitive assessment are crucial for early detection and diagnosis Alzheimer's disease. Regression models are widely used to predict the relationship between imaging biomarkers and cognitive assessment, and identify discriminative neuroimaging markers. Most existing methods use different matrix norms as the similarity measures of the empirical loss or regularization to improve the prediction performance, but ignore the inherent geometry of the cognitive data. To tackle this issue, in this paper we propose a novel robust matrix regression model with imposing Wasserstein distances on both loss function and regularization. It successfully integrate Wasserstein distance into the regression model, which can excavate the latent geometry of cognitive data. We introduce an efficient algorithm to solve the proposed new model with convergence analysis. Empirical results on cognitive data of the ADNI cohort demonstrate the great effectiveness of the proposed method for clinical cognitive predication.

Self-regulation learning as active inference: dynamic causal modeling of an fMRI neurofeedback task

“…To ensure methodological rigor and prevent double-dipping, we employed the Wasserstein distance (WD) (Panaretos and Zemel, 2019 ) as a measure of learning in line with recent research (Yan et al, 2019 ). This distance metric allowed us to quantify the relationship between target area activity and cognitive performance by comparing the baseline run and the transfer run (Fede et al, 2020 ).…”

Cognitive biomarker prioritization in Alzheimer’s Disease using brain morphometric data

“…As a result, numerous data-driven machine learning models have been developed for early AD detection and AD-relevant biomarker identification including cognitive measures. These models are often designed to accomplish tasks such as classification (e.g., [21]), regression (e.g., [1,2,22]) or both (e.g., [23,24]), where imaging and other biomarker data are used to predict diagnostic, cognitive and/or other outcome(s) of interest. A drawback of these methods is that, although outcome-relevant biomarkers can be identified, they are identified at the population level and not specific to any individual subject.…”

Prioritization of Cognitive Assessments in Alzheimer's Disease via Learning to Rank using Brain Morphometric Data

“…The importance of big data to enhance AD biomarker study has been widely recognized [25], resulting in numerous data-driven machine learning models developed for early detection of AD and identification of relevant biomarkers including cognitive measures. These models are often designed to accomplish tasks such as classification (e.g., [24]), regression (e.g., [22,26,27]) or both (e.g., [4,23]), where imaging and other biomarker data are used to predict diagnostic, cognitive and/or other outcome(s) of interest. Although outcome-relevant biomarkers can be identified here, they are selected at the population level and not specific to any individual subject.…”