Classification of schizophrenia patients with combined analysis of SNP and fMRI data based on sparse representation

Dongdong Lin, Hongbao Cao, Yu Ping Wang, Vince Daniel Calhoun

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

Abstract

We designed a sparse representation clustering (SRC) model to select the significant single nucleotide polymorphisms (SNPs) and proposed a novel SRC with a sliding window model for functional magnetic resonance imaging (fMRI) voxels selection. Then we combined two types of data to classify schizophrenia patients from healthy controls by linear support vector machine (SVM) to achieve a better diagnosis of schizophrenia. The effectiveness of the selected variables (SNPs or voxels) was validated by the leave one out (LOO) cross-validation method. The experimental results show that our proposed SRC method can effectively select the most discriminative variables in both SNPs and fMRI data. In particular, the combination of complementary fMRI and SNP data can significantly improve the classification of schizophrenia patients, which provides new insights in the study of schizophrenia.

Original languageEnglish (US)
Title of host publicationProceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011
Pages394-397
Number of pages4
DOIs
StatePublished - 2011
Externally publishedYes
Event2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011 - Atlanta, GA, United States
Duration: Nov 12 2011Nov 15 2011

Other

Other2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011
CountryUnited States
CityAtlanta, GA
Period11/12/1111/15/11

Fingerprint

Nucleotides
Polymorphism
Single Nucleotide Polymorphism
Schizophrenia
Magnetic Resonance Imaging
Cluster Analysis
Support vector machines

Keywords

  • Combined analysis
  • Schizophrenia
  • Sparse Representation Clustering
  • Variables selection

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Cite this

Lin, D., Cao, H., Wang, Y. P., & Calhoun, V. D. (2011). Classification of schizophrenia patients with combined analysis of SNP and fMRI data based on sparse representation. In Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011 (pp. 394-397). [6120472] https://doi.org/10.1109/BIBM.2011.41

Classification of schizophrenia patients with combined analysis of SNP and fMRI data based on sparse representation. / Lin, Dongdong; Cao, Hongbao; Wang, Yu Ping; Calhoun, Vince Daniel.

Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011. 2011. p. 394-397 6120472.

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

Lin, D, Cao, H, Wang, YP & Calhoun, VD 2011, Classification of schizophrenia patients with combined analysis of SNP and fMRI data based on sparse representation. in Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011., 6120472, pp. 394-397, 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011, Atlanta, GA, United States, 11/12/11. https://doi.org/10.1109/BIBM.2011.41
Lin D, Cao H, Wang YP, Calhoun VD. Classification of schizophrenia patients with combined analysis of SNP and fMRI data based on sparse representation. In Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011. 2011. p. 394-397. 6120472 https://doi.org/10.1109/BIBM.2011.41
Lin, Dongdong ; Cao, Hongbao ; Wang, Yu Ping ; Calhoun, Vince Daniel. / Classification of schizophrenia patients with combined analysis of SNP and fMRI data based on sparse representation. Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011. 2011. pp. 394-397
@inproceedings{84f16273748742fab0cda7c7930c6602,
title = "Classification of schizophrenia patients with combined analysis of SNP and fMRI data based on sparse representation",
abstract = "We designed a sparse representation clustering (SRC) model to select the significant single nucleotide polymorphisms (SNPs) and proposed a novel SRC with a sliding window model for functional magnetic resonance imaging (fMRI) voxels selection. Then we combined two types of data to classify schizophrenia patients from healthy controls by linear support vector machine (SVM) to achieve a better diagnosis of schizophrenia. The effectiveness of the selected variables (SNPs or voxels) was validated by the leave one out (LOO) cross-validation method. The experimental results show that our proposed SRC method can effectively select the most discriminative variables in both SNPs and fMRI data. In particular, the combination of complementary fMRI and SNP data can significantly improve the classification of schizophrenia patients, which provides new insights in the study of schizophrenia.",
keywords = "Combined analysis, Schizophrenia, Sparse Representation Clustering, Variables selection",
author = "Dongdong Lin and Hongbao Cao and Wang, {Yu Ping} and Calhoun, {Vince Daniel}",
year = "2011",
doi = "10.1109/BIBM.2011.41",
language = "English (US)",
isbn = "9780769545745",
pages = "394--397",
booktitle = "Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011",

}

TY - GEN

T1 - Classification of schizophrenia patients with combined analysis of SNP and fMRI data based on sparse representation

AU - Lin, Dongdong

AU - Cao, Hongbao

AU - Wang, Yu Ping

AU - Calhoun, Vince Daniel

PY - 2011

Y1 - 2011

N2 - We designed a sparse representation clustering (SRC) model to select the significant single nucleotide polymorphisms (SNPs) and proposed a novel SRC with a sliding window model for functional magnetic resonance imaging (fMRI) voxels selection. Then we combined two types of data to classify schizophrenia patients from healthy controls by linear support vector machine (SVM) to achieve a better diagnosis of schizophrenia. The effectiveness of the selected variables (SNPs or voxels) was validated by the leave one out (LOO) cross-validation method. The experimental results show that our proposed SRC method can effectively select the most discriminative variables in both SNPs and fMRI data. In particular, the combination of complementary fMRI and SNP data can significantly improve the classification of schizophrenia patients, which provides new insights in the study of schizophrenia.

AB - We designed a sparse representation clustering (SRC) model to select the significant single nucleotide polymorphisms (SNPs) and proposed a novel SRC with a sliding window model for functional magnetic resonance imaging (fMRI) voxels selection. Then we combined two types of data to classify schizophrenia patients from healthy controls by linear support vector machine (SVM) to achieve a better diagnosis of schizophrenia. The effectiveness of the selected variables (SNPs or voxels) was validated by the leave one out (LOO) cross-validation method. The experimental results show that our proposed SRC method can effectively select the most discriminative variables in both SNPs and fMRI data. In particular, the combination of complementary fMRI and SNP data can significantly improve the classification of schizophrenia patients, which provides new insights in the study of schizophrenia.

KW - Combined analysis

KW - Schizophrenia

KW - Sparse Representation Clustering

KW - Variables selection

UR - http://www.scopus.com/inward/record.url?scp=84862935127&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862935127&partnerID=8YFLogxK

U2 - 10.1109/BIBM.2011.41

DO - 10.1109/BIBM.2011.41

M3 - Conference contribution

AN - SCOPUS:84862935127

SN - 9780769545745

SP - 394

EP - 397

BT - Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011

ER -