Abstract

Background: Brain MRI holds promise to gauge different aspects of Parkinson's disease (PD)-related pathological changes. Its analysis, however, is hindered by the high-dimensional nature of the data. New method: This study introduces folded concave penalized (FCP) sparse logistic regression to identify biomarkers for PD from a large number of potential factors. The proposed statistical procedures target the challenges of high-dimensionality with limited data samples acquired. The maximization problem associated with the sparse logistic regression model is solved by local linear approximation. The proposed procedures then are applied to the empirical analysis of multimodal MRI data. Results: From 45 features, the proposed approach identified 15 MRI markers and the UPSIT, which are known to be clinically relevant to PD. By combining the MRI and clinical markers, we can enhance substantially the specificity and sensitivity of the model, as indicated by the ROC curves. Comparison to existing methods: We compare the folded concave penalized learning scheme with both the Lasso penalized scheme and the principle component analysis-based feature selection (PCA) in the Parkinson's biomarker identification problem that takes into account both the clinical features and MRI markers. The folded concave penalty method demonstrates a substantially better clinical potential than both the Lasso and PCA in terms of specificity and sensitivity. Conclusions: For the first time, we applied the FCP learning method to MRI biomarker discovery in PD. The proposed approach successfully identified MRI markers that are clinically relevant. Combining these biomarkers with clinical features can substantially enhance performance.

Original languageEnglish (US)
Pages (from-to)1-6
Number of pages6
JournalJournal of Neuroscience Methods
Volume268
DOIs
StatePublished - Aug 1 2016

Fingerprint

Parkinson Disease
Learning
Biomarkers
Passive Cutaneous Anaphylaxis
Logistic Models
Sensitivity and Specificity
ROC Curve
Brain
alachlor

All Science Journal Classification (ASJC) codes

  • Neuroscience(all)

Cite this

@article{9e4db623e6194aeab92ac77248e2b146,
title = "Folded concave penalized learning in identifying multimodal MRI marker for Parkinson's disease",
abstract = "Background: Brain MRI holds promise to gauge different aspects of Parkinson's disease (PD)-related pathological changes. Its analysis, however, is hindered by the high-dimensional nature of the data. New method: This study introduces folded concave penalized (FCP) sparse logistic regression to identify biomarkers for PD from a large number of potential factors. The proposed statistical procedures target the challenges of high-dimensionality with limited data samples acquired. The maximization problem associated with the sparse logistic regression model is solved by local linear approximation. The proposed procedures then are applied to the empirical analysis of multimodal MRI data. Results: From 45 features, the proposed approach identified 15 MRI markers and the UPSIT, which are known to be clinically relevant to PD. By combining the MRI and clinical markers, we can enhance substantially the specificity and sensitivity of the model, as indicated by the ROC curves. Comparison to existing methods: We compare the folded concave penalized learning scheme with both the Lasso penalized scheme and the principle component analysis-based feature selection (PCA) in the Parkinson's biomarker identification problem that takes into account both the clinical features and MRI markers. The folded concave penalty method demonstrates a substantially better clinical potential than both the Lasso and PCA in terms of specificity and sensitivity. Conclusions: For the first time, we applied the FCP learning method to MRI biomarker discovery in PD. The proposed approach successfully identified MRI markers that are clinically relevant. Combining these biomarkers with clinical features can substantially enhance performance.",
author = "Hongcheng Liu and Guangwei Du and Lijun Zhang and Mechelle Lewis and Xue Wang and Tao Yao and Runze Li and Xuemei Huang",
year = "2016",
month = "8",
day = "1",
doi = "10.1016/j.jneumeth.2016.04.016",
language = "English (US)",
volume = "268",
pages = "1--6",
journal = "Journal of Neuroscience Methods",
issn = "0165-0270",
publisher = "Elsevier",

}

TY - JOUR

T1 - Folded concave penalized learning in identifying multimodal MRI marker for Parkinson's disease

AU - Liu, Hongcheng

AU - Du, Guangwei

AU - Zhang, Lijun

AU - Lewis, Mechelle

AU - Wang, Xue

AU - Yao, Tao

AU - Li, Runze

AU - Huang, Xuemei

PY - 2016/8/1

Y1 - 2016/8/1

N2 - Background: Brain MRI holds promise to gauge different aspects of Parkinson's disease (PD)-related pathological changes. Its analysis, however, is hindered by the high-dimensional nature of the data. New method: This study introduces folded concave penalized (FCP) sparse logistic regression to identify biomarkers for PD from a large number of potential factors. The proposed statistical procedures target the challenges of high-dimensionality with limited data samples acquired. The maximization problem associated with the sparse logistic regression model is solved by local linear approximation. The proposed procedures then are applied to the empirical analysis of multimodal MRI data. Results: From 45 features, the proposed approach identified 15 MRI markers and the UPSIT, which are known to be clinically relevant to PD. By combining the MRI and clinical markers, we can enhance substantially the specificity and sensitivity of the model, as indicated by the ROC curves. Comparison to existing methods: We compare the folded concave penalized learning scheme with both the Lasso penalized scheme and the principle component analysis-based feature selection (PCA) in the Parkinson's biomarker identification problem that takes into account both the clinical features and MRI markers. The folded concave penalty method demonstrates a substantially better clinical potential than both the Lasso and PCA in terms of specificity and sensitivity. Conclusions: For the first time, we applied the FCP learning method to MRI biomarker discovery in PD. The proposed approach successfully identified MRI markers that are clinically relevant. Combining these biomarkers with clinical features can substantially enhance performance.

AB - Background: Brain MRI holds promise to gauge different aspects of Parkinson's disease (PD)-related pathological changes. Its analysis, however, is hindered by the high-dimensional nature of the data. New method: This study introduces folded concave penalized (FCP) sparse logistic regression to identify biomarkers for PD from a large number of potential factors. The proposed statistical procedures target the challenges of high-dimensionality with limited data samples acquired. The maximization problem associated with the sparse logistic regression model is solved by local linear approximation. The proposed procedures then are applied to the empirical analysis of multimodal MRI data. Results: From 45 features, the proposed approach identified 15 MRI markers and the UPSIT, which are known to be clinically relevant to PD. By combining the MRI and clinical markers, we can enhance substantially the specificity and sensitivity of the model, as indicated by the ROC curves. Comparison to existing methods: We compare the folded concave penalized learning scheme with both the Lasso penalized scheme and the principle component analysis-based feature selection (PCA) in the Parkinson's biomarker identification problem that takes into account both the clinical features and MRI markers. The folded concave penalty method demonstrates a substantially better clinical potential than both the Lasso and PCA in terms of specificity and sensitivity. Conclusions: For the first time, we applied the FCP learning method to MRI biomarker discovery in PD. The proposed approach successfully identified MRI markers that are clinically relevant. Combining these biomarkers with clinical features can substantially enhance performance.

UR - http://www.scopus.com/inward/record.url?scp=84966431190&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84966431190&partnerID=8YFLogxK

U2 - 10.1016/j.jneumeth.2016.04.016

DO - 10.1016/j.jneumeth.2016.04.016

M3 - Article

C2 - 27102045

AN - SCOPUS:84966431190

VL - 268

SP - 1

EP - 6

JO - Journal of Neuroscience Methods

JF - Journal of Neuroscience Methods

SN - 0165-0270

ER -