# Fused Group Lasso Regularized Multi-Task Feature Learning and Its Application to the Cognitive Performance Prediction of Alzheimer’s Disease

@article{Liu2018FusedGL,
title={Fused Group Lasso Regularized Multi-Task Feature Learning and Its Application to the Cognitive Performance Prediction of Alzheimer’s Disease},
author={Xiaoli Liu and Peng Cao and Jianzhong Wang and Jun Kong and Dazhe Zhao},
journal={Neuroinformatics},
year={2018},
volume={17},
pages={271-294}
}
Alzheimer’s disease (AD) is characterized by gradual neurodegeneration and loss of brain function, especially for memory during early stages. Regression analysis has been widely applied to AD research to relate clinical and biomarker data such as predicting cognitive outcomes from MRI measures. Recently, multi-task based feature learning (MTFL) methods with sparsity-inducing ℓ2,1$\ell _{2,1}$-norm have been widely studied to select a discriminative feature subset from MRI features by…
9 Citations
Feature Selection and Combination of Information in the Functional Brain Connectome for Discrimination of Mild Cognitive Impairment and Analyses of Altered Brain Patterns
The findings demonstrate that optimal feature selection and combination of all connectome features can achieve good performance in discriminating NCs from MCI subjects and contribute to the early clinical diagnosis of AD.
Effective and Accurate Diagnosis of Subjective Cognitive Decline Based on Functional Connection and Graph Theory View
The comparison results of topological attributes suggested that the brain network integration function was weakened and network segregation function was enhanced in SCD patients and offered potential neuroimaging biomarkers for diagnosis of early-stage AD.
Machine learning-based estimation of cognitive performance using regional brain MRI markers: the Northern Manhattan Study
Structural brain MRI markers may be more useful for etiological than predictive modeling and elastic net models with only MRI markers performed significantly better than random MRI markers and yielded regions-of-interest consistent with previous literature and others not previously explored.
Neuroimaging-based Individualized Prediction of Cognition and Behavior for Mental Disorders and Health: Methods and Promises
• Medicine, Psychology
Biological Psychiatry
• 2020
An overview of recent studies that utilize machine learning approaches to identify neuroimaging predictors over the past decade is provided and connectome-based predictive modeling, which has grown in popularity in recent years is highlighted.
Supervised Multidimensional Scaling and its Application in MRI-Based Individual Age Predictions
• Computer Science, Medicine
Neuroinformatics
• 2020
When applied to features extracted from resting state fMRI data for individual age predictions,SMDS was observed to outperform classic DR techniques, including principal component analysis, locally linear embedding and multidimensional scaling (MDS).
Neuroimaging-based Individualized Prediction of Cognition and Behavior for Mental Disorders and Health: Methods and Promises
• Biology, Psychology
• 2020
An overview of recent studies that utilize machine learning approaches to identify neuroimaging predictors over the past decade is provided and connectome-based predictive modeling (CPM) is highlighted, which has grown in popularity in recent years.
Curcumin Neuroendocrine In Mitochondria Alzheimer’s Disease Predicting By Artificial Immune System
Alzheimer's affliction (AD) is a degenerative character illness that affects people and is acknowledged to be the most, for the most part, saw the reason behind dementia, regardless, dementia can in
Regularized Latent Class Analysis for Polytomous Item Responses: An Application to SPM-LS Data
• A. Robitzsch
• Medicine, Mathematics
Journal of Intelligence
• 2020
The last series of Raven’s standard progressive matrices (SPM-LS) test was studied with respect to its psychometric properties in a series of recent papers, and an alternative estimation approach based on fused regularization for RLCMs is proposed.

## References

SHOWING 1-10 OF 65 REFERENCES
Group Guided Sparse Group Lasso Multi-task Learning for Cognitive Performance Prediction of Alzheimer's Disease
• Computer Science
BI
• 2017
A novel Group guided Sparse group lasso (GSGL) regularized multi-task learning approach, to effectively incorporate both the relatedness among multiple cognitive score prediction tasks and useful inherent group structure in features within the MRI features.
Modeling Alzheimer's disease cognitive scores using multi-task sparse group lasso
• Computer Science, Medicine
Comput. Medical Imaging Graph.
• 2018
A multi-task sparse group lasso (MT-SGL) framework, which estimates sparse features coupled across tasks, and can work with loss functions associated with any Generalized Linear Models, is presented.
Sparse Multi-kernel Based Multi-task Learning for Joint Prediction of Clinical Scores and Biomarker Identification in Alzheimer's Disease
• Computer Science
MICCAI
• 2017
This work proposes a multi-kernel based multi-task learning with a mixed sparsity-inducing norm to better capture the complex relationship between the cognitive scores and the neuroimaging measures.
Sparse multi-task regression and feature selection to identify brain imaging predictors for memory performance
• Hua Wang, +4 authors Li Shen
• Computer Science, Medicine
2011 International Conference on Computer Vision
• 2011
A novel Sparse Multi-tAsk Regression and feaTure selection (SMART) method is proposed to jointly analyze all the imaging and clinical data under a single regression framework and with shared underlying sparse representations to enable sparsity as well as facilitate multi-task learning.
Sparse Bayesian multi-task learning for predicting cognitive outcomes from neuroimaging measures in Alzheimer's disease
• Jing Wan, +7 authors Li Shen
• Computer Science
2012 IEEE Conference on Computer Vision and Pattern Recognition
• 2012
An efficient sparse Bayesian multi-task learning algorithm is proposed, which adaptively learns and exploits the dependence among multiple scores derived from a single cognitive test to achieve improved prediction performance in AD.
Network-Guided Sparse Learning for Predicting Cognitive Outcomes from MRI Measures
A new sparse learning method is presented by introducing a novel network term to more flexibly model the relationship among imaging markers and improved prediction performance over several state-of-the-art competing methods and accurate identification of cognition-relevant imaging markers that are biologically meaningful.
High-Order Multi-Task Feature Learning to Identify Longitudinal Phenotypic Markers for Alzheimer's Disease Progression Prediction
A novel high-order multi-task learning model is proposed that explores the temporal correlations existing in imaging and cognitive data by structured sparsity-inducing norms and enables the selection of a small number of imaging measures while maintaining high prediction accuracy.
Cortical surface biomarkers for predicting cognitive outcomes using group l 2,1 norm
A new sparse multitask learning model called Group-Sparse Multi-task Regression and Feature Selection (G-SMuRFS) is proposed and demonstrates its effectiveness by examining the predictive power of detailed cortical thickness measures toward 3 types of cognitive scores in a large cohort.
Identifying the Neuroanatomical Basis of Cognitive Impairment in Alzheimer's Disease by Correlation- and Nonlinearity-Aware Sparse Bayesian Learning
• Jing Wan, +4 authors Li Shen
• Computer Science, Medicine
IEEE Transactions on Medical Imaging
• 2014
A sparse multivariate regression model for this task is built and an empirical sparse Bayesian learning algorithm is proposed, which models the response as a nonlinear function of the predictors by extending the predictor matrix with block structures.
Multi-modal multi-task learning for joint prediction of multiple regression and classification variables in Alzheimer's disease
• Psychology, Computer Science
NeuroImage
• 2012
This paper proposes a general methodology, namely multi-modal multi-task (M3T) learning, to jointly predict multiple variables from multi- modal data, which can achieve better performance on both regression and classification tasks than the conventional learning methods.