Modeling disease progression via fused sparse group lasso

Jiayu Zhou, Jun Liu, Vaibhav A. Narayan, Jieping Ye

Research output: Chapter in Book/Report/Conference proceedingConference contribution

77 Citations (Scopus)

Abstract

Alzheimer's Disease (AD) is the most common neurodegenerative disorder associated with aging. Understanding how the disease progresses and identifying related pathological biomarkers for the progression is of primary importance in Alzheimer's disease research. In this paper, we develop novel multi-task learning techniques to predict the disease progression measured by cognitive scores and select biomarkers predictive of the progression. In multi-task learning, the prediction of cognitive scores at each time point is considered as a task, and multiple prediction tasks at different time points are performed simultaneously to capture the temporal smoothness of the prediction models across different time points. Specifically, we propose a novel convex fused sparse group Lasso (cFSGL) formulation that allows the simultaneous selection of a common set of biomarkers for multiple time points and specific sets of biomarkers for different time points using the sparse group Lasso penalty and in the meantime incorporates the temporal smoothness using the fused Lasso penalty. The proposed formulation is challenging to solve due to the use of several non-smooth penalties. We show that the proximal operator associated with the proposed formulation exhibits a certain decomposition property and can be computed efficiently; thus cFSGL can be solved efficiently using the accelerated gradient method. To further improve the model, we propose two non-convex formulations to reduce the shrinkage bias inherent in the convex formulation. We employ the difference of convex programming technique to solve the non-convex formulations. Our extensive experiments using data from the Alzheimer's Disease Neuroimaging Initiative demonstrate the effectiveness of the proposed progression models in comparison with existing methods for disease progression. We also perform longitudinal stability selection to identify and analyze the temporal patterns of biomarkers in disease progression.

Original languageEnglish (US)
Title of host publicationProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Pages1095-1103
Number of pages9
DOIs
StatePublished - 2012
Event18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2012 - Beijing, China
Duration: Aug 12 2012Aug 16 2012

Other

Other18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2012
CountryChina
CityBeijing
Period8/12/128/16/12

Fingerprint

Biomarkers
Neuroimaging
Gradient methods
Convex optimization
Aging of materials
Decomposition
Experiments

Keywords

  • alzheimer's disease
  • cognitive score
  • fused lasso
  • multi-task learning
  • regression
  • sparse group lasso

ASJC Scopus subject areas

  • Software
  • Information Systems

Cite this

Zhou, J., Liu, J., Narayan, V. A., & Ye, J. (2012). Modeling disease progression via fused sparse group lasso. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1095-1103) https://doi.org/10.1145/2339530.2339702

Modeling disease progression via fused sparse group lasso. / Zhou, Jiayu; Liu, Jun; Narayan, Vaibhav A.; Ye, Jieping.

Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2012. p. 1095-1103.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhou, J, Liu, J, Narayan, VA & Ye, J 2012, Modeling disease progression via fused sparse group lasso. in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. pp. 1095-1103, 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2012, Beijing, China, 8/12/12. https://doi.org/10.1145/2339530.2339702
Zhou J, Liu J, Narayan VA, Ye J. Modeling disease progression via fused sparse group lasso. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2012. p. 1095-1103 https://doi.org/10.1145/2339530.2339702
Zhou, Jiayu ; Liu, Jun ; Narayan, Vaibhav A. ; Ye, Jieping. / Modeling disease progression via fused sparse group lasso. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2012. pp. 1095-1103
@inproceedings{25814cfbcc5b41bc8cf5e2bf574bef52,
title = "Modeling disease progression via fused sparse group lasso",
abstract = "Alzheimer's Disease (AD) is the most common neurodegenerative disorder associated with aging. Understanding how the disease progresses and identifying related pathological biomarkers for the progression is of primary importance in Alzheimer's disease research. In this paper, we develop novel multi-task learning techniques to predict the disease progression measured by cognitive scores and select biomarkers predictive of the progression. In multi-task learning, the prediction of cognitive scores at each time point is considered as a task, and multiple prediction tasks at different time points are performed simultaneously to capture the temporal smoothness of the prediction models across different time points. Specifically, we propose a novel convex fused sparse group Lasso (cFSGL) formulation that allows the simultaneous selection of a common set of biomarkers for multiple time points and specific sets of biomarkers for different time points using the sparse group Lasso penalty and in the meantime incorporates the temporal smoothness using the fused Lasso penalty. The proposed formulation is challenging to solve due to the use of several non-smooth penalties. We show that the proximal operator associated with the proposed formulation exhibits a certain decomposition property and can be computed efficiently; thus cFSGL can be solved efficiently using the accelerated gradient method. To further improve the model, we propose two non-convex formulations to reduce the shrinkage bias inherent in the convex formulation. We employ the difference of convex programming technique to solve the non-convex formulations. Our extensive experiments using data from the Alzheimer's Disease Neuroimaging Initiative demonstrate the effectiveness of the proposed progression models in comparison with existing methods for disease progression. We also perform longitudinal stability selection to identify and analyze the temporal patterns of biomarkers in disease progression.",
keywords = "alzheimer's disease, cognitive score, fused lasso, multi-task learning, regression, sparse group lasso",
author = "Jiayu Zhou and Jun Liu and Narayan, {Vaibhav A.} and Jieping Ye",
year = "2012",
doi = "10.1145/2339530.2339702",
language = "English (US)",
isbn = "9781450314626",
pages = "1095--1103",
booktitle = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",

}

TY - GEN

T1 - Modeling disease progression via fused sparse group lasso

AU - Zhou, Jiayu

AU - Liu, Jun

AU - Narayan, Vaibhav A.

AU - Ye, Jieping

PY - 2012

Y1 - 2012

N2 - Alzheimer's Disease (AD) is the most common neurodegenerative disorder associated with aging. Understanding how the disease progresses and identifying related pathological biomarkers for the progression is of primary importance in Alzheimer's disease research. In this paper, we develop novel multi-task learning techniques to predict the disease progression measured by cognitive scores and select biomarkers predictive of the progression. In multi-task learning, the prediction of cognitive scores at each time point is considered as a task, and multiple prediction tasks at different time points are performed simultaneously to capture the temporal smoothness of the prediction models across different time points. Specifically, we propose a novel convex fused sparse group Lasso (cFSGL) formulation that allows the simultaneous selection of a common set of biomarkers for multiple time points and specific sets of biomarkers for different time points using the sparse group Lasso penalty and in the meantime incorporates the temporal smoothness using the fused Lasso penalty. The proposed formulation is challenging to solve due to the use of several non-smooth penalties. We show that the proximal operator associated with the proposed formulation exhibits a certain decomposition property and can be computed efficiently; thus cFSGL can be solved efficiently using the accelerated gradient method. To further improve the model, we propose two non-convex formulations to reduce the shrinkage bias inherent in the convex formulation. We employ the difference of convex programming technique to solve the non-convex formulations. Our extensive experiments using data from the Alzheimer's Disease Neuroimaging Initiative demonstrate the effectiveness of the proposed progression models in comparison with existing methods for disease progression. We also perform longitudinal stability selection to identify and analyze the temporal patterns of biomarkers in disease progression.

AB - Alzheimer's Disease (AD) is the most common neurodegenerative disorder associated with aging. Understanding how the disease progresses and identifying related pathological biomarkers for the progression is of primary importance in Alzheimer's disease research. In this paper, we develop novel multi-task learning techniques to predict the disease progression measured by cognitive scores and select biomarkers predictive of the progression. In multi-task learning, the prediction of cognitive scores at each time point is considered as a task, and multiple prediction tasks at different time points are performed simultaneously to capture the temporal smoothness of the prediction models across different time points. Specifically, we propose a novel convex fused sparse group Lasso (cFSGL) formulation that allows the simultaneous selection of a common set of biomarkers for multiple time points and specific sets of biomarkers for different time points using the sparse group Lasso penalty and in the meantime incorporates the temporal smoothness using the fused Lasso penalty. The proposed formulation is challenging to solve due to the use of several non-smooth penalties. We show that the proximal operator associated with the proposed formulation exhibits a certain decomposition property and can be computed efficiently; thus cFSGL can be solved efficiently using the accelerated gradient method. To further improve the model, we propose two non-convex formulations to reduce the shrinkage bias inherent in the convex formulation. We employ the difference of convex programming technique to solve the non-convex formulations. Our extensive experiments using data from the Alzheimer's Disease Neuroimaging Initiative demonstrate the effectiveness of the proposed progression models in comparison with existing methods for disease progression. We also perform longitudinal stability selection to identify and analyze the temporal patterns of biomarkers in disease progression.

KW - alzheimer's disease

KW - cognitive score

KW - fused lasso

KW - multi-task learning

KW - regression

KW - sparse group lasso

UR - http://www.scopus.com/inward/record.url?scp=84866037290&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866037290&partnerID=8YFLogxK

U2 - 10.1145/2339530.2339702

DO - 10.1145/2339530.2339702

M3 - Conference contribution

SN - 9781450314626

SP - 1095

EP - 1103

BT - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

ER -