Comparison of Single and Multitask Learning for Predicting Cognitive Decline Based on MRI Data

Vandad Imani,Jussi Tohka,Mithilesh Prakash,Marzieh Zare

doi:10.1109/access.2021.3127276

Abstract

The Alzheimer’s Disease Assessment Scale-Cognitive subscale (ADAS-Cog) is a neuropsychological tool that has been designed to assess the severity of cognitive symptoms of dementia. Personalized prediction of the changes in ADAS-Cog scores could help in timing therapeutic interventions in dementia and at-risk populations. In the present work, we compared single and multitask learning approaches to predict the changes in ADAS-Cog scores based on T1-weighted anatomical magnetic resonance imaging (MRI). In contrast to most machine learning-based prediction methods ADAS-Cog changes, we stratified the subjects based on their baseline diagnoses and evaluated the prediction performances in each group. Our experiments indicated a positive relationship between the predicted and observed ADAS-Cog score changes in each diagnostic group, suggesting that T1-weighted MRI has a predictive value for evaluating cognitive decline in the entire AD continuum. We further studied whether correction of the differences in the magnetic field strength of MRI would improve the ADAS-Cog score prediction. The partial least square-based domain adaptation slightly improved the prediction performance, but the improvement was marginal. In summary, this study demonstrated that ADAS-Cog change could be, to some extent, predicted based on anatomical MRI. Based on this study, the recommended method for learning the predictive models is a single-task regularized linear regression due to its simplicity and good performance. It appears important to combine the training data across all subject groups for the most effective predictive models.

Highlights

Alzheimer’s Disease (AD) is a chronic neurodegenerative disorder that occurs mainly among the elderly, and 152 million people are expected to suffer from AD in 2050 [1]
To correct for differences in features caused by imaging at two magnetic field strengths (MFS) in ADNI1 and ADNI2, we studied three different techniques: 1) partial least squares (PLS)-based domain adaptation introduced in [34], 2) ComBat harmonization originating from genetics [35], which has become widely used in brain imaging [42], [54], and 3) multi-task learning
These scatter plots imply that the ∆ ADAS-Cog scores with very high values for all time-points were the hardest to predict since the number of individuals with observed ADAS-Cog score change over 20 was small (e.g.., The number of Mild cognitive impairment (MCI) subjects at 12, 24, and 36 months were 2, 8, and 19, respectively)

Summary

Introduction

Alzheimer’s Disease (AD) is a chronic neurodegenerative disorder that occurs mainly among the elderly, and 152 million people are expected to suffer from AD in 2050 [1]. Pathophysiological changes of AD begin many years prior to clinical manifestations of disease and the spectrum of AD spans from clinically asymptomatic to severely impaired [2]. There is an appreciation that AD should be viewed with discrete and defined clinical stages but as a multifaceted process moving along a continuum. Mild cognitive impairment (MCI) is an important concept along this continuum, representing a transitional stage between healthy elderly and AD [3]. 10% to 20% of MCI patients tend to progress to AD annually, whereas others will continue with cognitive decline or even revert to normal control (NC) [4].

Objectives

Methods

Results

Discussion

Conclusion