skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Modeling Alzheimer’s Disease Progression with Fused Laplacian Sparse Group Lasso

Abstract

Alzheimer’s disease (AD), the most common type of dementia, not only imposes a huge financial burden on the health care system, but also a psychological and emotional burden on patients and their families. There is furthermore an urgent need to infer trajectories of cognitive performance over time and identify biomarkers predictive of the progression. Here, we introduce the multi-task learning with fused Laplacian sparse group lasso model, which can identify biomarkers closely related to cognitive measures due to its sparsity-inducing property, and model the disease progression with a general weighted (undirected) dependency graphs among the tasks. An efficient alternative directions method of multipliers based optimization algorithm is derived to solve the proposed non-smooth objective formulation. The effectiveness of the presented model is demonstrated by its superior prediction performance over multiple state-of-the-art methods and accurate identification of compact sets of cognition-relevant imaging biomarkers that are consistent with prior medical studies.

Authors:
 [1];  [2];  [3];  [2];  [4]
  1. Northeastern Univ., Shenyang (China); Univ. of Minnesota, Minneapolis, MN (United States)
  2. Northeastern Univ., Shenyang (China)
  3. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
  4. Univ. of Minnesota, Minneapolis, MN (United States)
Publication Date:
Research Org.:
Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA); National Natural Science Foundation of China (NSF)
OSTI Identifier:
1557047
Report Number(s):
LLNL-JRNL-753218
Journal ID: ISSN 1556-4681; 939429
Grant/Contract Number:  
AC52-07NA27344
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
ACM Transactions on Knowledge Discovery from Data
Additional Journal Information:
Journal Volume: 12; Journal Issue: 6; Journal ID: ISSN 1556-4681
Publisher:
Association for Computing Machinery
Country of Publication:
United States
Language:
English
Subject:
59 BASIC BIOLOGICAL SCIENCES; 97 MATHEMATICS AND COMPUTING; Alzheimer’s Disease; Disease Progression; Multi-task Learning; Graph Laplacian; ADMM

Citation Formats

Liu, Xiaoli, Cao, Peng, Gonçalves, André R., Zhao, Dazhe, and Banerjee, Arindam. Modeling Alzheimer’s Disease Progression with Fused Laplacian Sparse Group Lasso. United States: N. p., 2018. Web. doi:10.1145/3230668.
Liu, Xiaoli, Cao, Peng, Gonçalves, André R., Zhao, Dazhe, & Banerjee, Arindam. Modeling Alzheimer’s Disease Progression with Fused Laplacian Sparse Group Lasso. United States. doi:10.1145/3230668.
Liu, Xiaoli, Cao, Peng, Gonçalves, André R., Zhao, Dazhe, and Banerjee, Arindam. Wed . "Modeling Alzheimer’s Disease Progression with Fused Laplacian Sparse Group Lasso". United States. doi:10.1145/3230668. https://www.osti.gov/servlets/purl/1557047.
@article{osti_1557047,
title = {Modeling Alzheimer’s Disease Progression with Fused Laplacian Sparse Group Lasso},
author = {Liu, Xiaoli and Cao, Peng and Gonçalves, André R. and Zhao, Dazhe and Banerjee, Arindam},
abstractNote = {Alzheimer’s disease (AD), the most common type of dementia, not only imposes a huge financial burden on the health care system, but also a psychological and emotional burden on patients and their families. There is furthermore an urgent need to infer trajectories of cognitive performance over time and identify biomarkers predictive of the progression. Here, we introduce the multi-task learning with fused Laplacian sparse group lasso model, which can identify biomarkers closely related to cognitive measures due to its sparsity-inducing property, and model the disease progression with a general weighted (undirected) dependency graphs among the tasks. An efficient alternative directions method of multipliers based optimization algorithm is derived to solve the proposed non-smooth objective formulation. The effectiveness of the presented model is demonstrated by its superior prediction performance over multiple state-of-the-art methods and accurate identification of compact sets of cognition-relevant imaging biomarkers that are consistent with prior medical studies.},
doi = {10.1145/3230668},
journal = {ACM Transactions on Knowledge Discovery from Data},
issn = {1556-4681},
number = 6,
volume = 12,
place = {United States},
year = {2018},
month = {10}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Save / Share:

Works referenced in this record:

3D Mapping of Mini-mental State Examination Performance in Clinical and Preclinical Alzheimer Disease
journal, January 2006


Convex multi-task feature learning
journal, January 2008

  • Argyriou, Andreas; Evgeniou, Theodoros; Pontil, Massimiliano
  • Machine Learning, Vol. 73, Issue 3
  • DOI: 10.1007/s10994-007-5040-8

Optimization with Sparsity-Inducing Penalties
journal, January 2011

  • Bach, Francis
  • Foundations and Trends® in Machine Learning, Vol. 4, Issue 1
  • DOI: 10.1561/2200000015

A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
journal, January 2009

  • Beck, Amir; Teboulle, Marc
  • SIAM Journal on Imaging Sciences, Vol. 2, Issue 1
  • DOI: 10.1137/080716542

Functional connectivity of the fusiform gyrus during a face-matching task in subjects with mild cognitive impairment
journal, March 2006


Alzheimer's disease
journal, February 2009


Vision in Alzheimer's Disease
journal, June 1995


Parallel Multi-Block ADMM with o(1 / k) Convergence
journal, November 2016


Hippocampal and entorhinal atrophy in mild cognitive impairment: Prediction of Alzheimer disease
journal, March 2007


Predicting progression of Alzheimer's disease
journal, January 2010

  • Doody, Rachelle S.; Pavlik, Valory; Massman, Paul
  • Alzheimer's Research & Therapy, Vol. 2, Issue 1
  • DOI: 10.1186/alzrt25

The clinical use of structural MRI in Alzheimer disease
journal, February 2010

  • Frisoni, Giovanni B.; Fox, Nick C.; Jack, Clifford R.
  • Nature Reviews Neurology, Vol. 6, Issue 2
  • DOI: 10.1038/nrneurol.2009.215

Classification of CT brain images based on deep learning networks
journal, January 2017

  • Gao, Xiaohong W.; Hui, Rui; Tian, Zengmin
  • Computer Methods and Programs in Biomedicine, Vol. 138
  • DOI: 10.1016/j.cmpb.2016.10.007

Subregions of the inferior parietal lobule are affected in the progression to Alzheimer's disease
journal, August 2010


Empowering imaging biomarkers of Alzheimer's disease
journal, January 2015


Alternating Direction Method with Gaussian Back Substitution for Separable Convex Programming
journal, January 2012

  • He, Bingsheng; Tao, Min; Yuan, Xiaoming
  • SIAM Journal on Optimization, Vol. 22, Issue 2
  • DOI: 10.1137/110822347

Molecular drivers and cortical spread of lateral entorhinal cortex dysfunction in preclinical Alzheimer's disease
journal, December 2013

  • Khan, Usman A.; Liu, Li; Provenzano, Frank A.
  • Nature Neuroscience, Vol. 17, Issue 2
  • DOI: 10.1038/nn.3606

Locally linear embedding (LLE) for MRI based Alzheimer's disease classification
journal, December 2013


Laplacian matrices of graphs: a survey
journal, January 1994


Sparsity and smoothness via the fused lasso
journal, February 2005

  • Tibshirani, Robert; Saunders, Michael; Rosset, Saharon
  • Journal of the Royal Statistical Society: Series B (Statistical Methodology), Vol. 67, Issue 1
  • DOI: 10.1111/j.1467-9868.2005.00490.x

Test-retest reliable coefficients and 5-year change scores for the MMSE and 3MS
journal, June 2005


Entorhinal cortex pathology in Alzheimer's disease
journal, January 1991

  • van Hoesen, Gary W.; Hyman, Bradley T.; Damasio, Antonio R.
  • Hippocampus, Vol. 1, Issue 1
  • DOI: 10.1002/hipo.450010102

MRI and CSF biomarkers in normal, MCI, and AD subjects: Predicting future clinical change
journal, July 2009


A New Alternating Minimization Algorithm for Total Variation Image Reconstruction
journal, January 2008

  • Wang, Yilun; Yang, Junfeng; Yin, Wotao
  • SIAM Journal on Imaging Sciences, Vol. 1, Issue 3
  • DOI: 10.1137/080724265

The Alzheimer's Disease Neuroimaging Initiative: Progress report and future plans
journal, May 2010


Recent publications from the Alzheimer's Disease Neuroimaging Initiative: Reviewing progress toward improved AD clinical trials
journal, April 2017


Multi-modality sparse representation-based classification for Alzheimer's disease and mild cognitive impairment
journal, November 2015


Cortical surface biomarkers for predicting cognitive outcomes using group l2,1 norm
journal, January 2015


Alternating Direction Algorithms for $\ell_1$-Problems in Compressive Sensing
journal, January 2011

  • Yang, Junfeng; Zhang, Yin
  • SIAM Journal on Scientific Computing, Vol. 33, Issue 1
  • DOI: 10.1137/090777761

Sparse learning and stability selection for predicting MCI to AD conversion using baseline ADNI data
journal, June 2012


Efficient Methods for Overlapping Group Lasso
journal, September 2013

  • Lei Yuan,
  • IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 35, Issue 9
  • DOI: 10.1109/TPAMI.2013.17

Subspace Regularized Sparse Multitask Learning for Multiclass Neurodegenerative Disease Identification
journal, March 2016

  • Zhu, Xiaofeng; Suk, Heung-Il; Lee, Seong-Whan
  • IEEE Transactions on Biomedical Engineering, Vol. 63, Issue 3
  • DOI: 10.1109/TBME.2015.2466616