Abstract

Cardiovascular disease (CVD) is considered as the leading cause of morbidity and mortality in type 2 diabetes (T2D) patients. In 2008 the US FDA issued a Guidance to Industry statement, recognizing the conjoined nature of CVD and T2D and emphasizing the need to monitor cardiovascular risk during new diabetic drug trials. This led researchers to work towards identifying panels of markers that are able to distinguish subtypes of CVD in the context of T2D. Immunoassays are used to detect and quantify biomolecules in a solution. Mass spectrometric immunoassay analysis of various proteins in the blood serum of 212 subjects belonging to multiple disease groups resulted in the identification of 41 molecular species as potential biomarkers. In this paper, support vector machines are used to measure the effectiveness of using these species as a diagnosis tool. We suggest an any-vs-rest SVM multiclass classification method by dividing the problem into a series of binary SVM classification problems and using a MAP decision rule to predict the correct class. One-vs-rest and discriminant analysis approaches are also evaluated for comparison.

Original languageEnglish (US)
Title of host publicationProceedings - 10th International Conference on Machine Learning and Applications, ICMLA 2011
Pages338-341
Number of pages4
Volume2
DOIs
StatePublished - 2011
Event10th International Conference on Machine Learning and Applications, ICMLA 2011 - Honolulu, HI, United States
Duration: Dec 18 2011Dec 21 2011

Other

Other10th International Conference on Machine Learning and Applications, ICMLA 2011
CountryUnited States
CityHonolulu, HI
Period12/18/1112/21/11

Fingerprint

Biomarkers
Medical problems
Biomolecules
Discriminant analysis
Support vector machines
Blood
Proteins
Industry

ASJC Scopus subject areas

  • Computer Science Applications
  • Human-Computer Interaction

Cite this

Buddi, S., Taylor, T., Borges, C., & Nelson, R. (2011). SVM multi-classification of T2D/CVD patients using biomarker features. In Proceedings - 10th International Conference on Machine Learning and Applications, ICMLA 2011 (Vol. 2, pp. 338-341). [6147700] https://doi.org/10.1109/ICMLA.2011.182

SVM multi-classification of T2D/CVD patients using biomarker features. / Buddi, Sai; Taylor, Thomas; Borges, Chad; Nelson, Randall.

Proceedings - 10th International Conference on Machine Learning and Applications, ICMLA 2011. Vol. 2 2011. p. 338-341 6147700.

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

Buddi, S, Taylor, T, Borges, C & Nelson, R 2011, SVM multi-classification of T2D/CVD patients using biomarker features. in Proceedings - 10th International Conference on Machine Learning and Applications, ICMLA 2011. vol. 2, 6147700, pp. 338-341, 10th International Conference on Machine Learning and Applications, ICMLA 2011, Honolulu, HI, United States, 12/18/11. https://doi.org/10.1109/ICMLA.2011.182
Buddi S, Taylor T, Borges C, Nelson R. SVM multi-classification of T2D/CVD patients using biomarker features. In Proceedings - 10th International Conference on Machine Learning and Applications, ICMLA 2011. Vol. 2. 2011. p. 338-341. 6147700 https://doi.org/10.1109/ICMLA.2011.182
Buddi, Sai ; Taylor, Thomas ; Borges, Chad ; Nelson, Randall. / SVM multi-classification of T2D/CVD patients using biomarker features. Proceedings - 10th International Conference on Machine Learning and Applications, ICMLA 2011. Vol. 2 2011. pp. 338-341
@inproceedings{7bd3e63dbf7d4c3d813ccc2416e0a257,
title = "SVM multi-classification of T2D/CVD patients using biomarker features",
abstract = "Cardiovascular disease (CVD) is considered as the leading cause of morbidity and mortality in type 2 diabetes (T2D) patients. In 2008 the US FDA issued a Guidance to Industry statement, recognizing the conjoined nature of CVD and T2D and emphasizing the need to monitor cardiovascular risk during new diabetic drug trials. This led researchers to work towards identifying panels of markers that are able to distinguish subtypes of CVD in the context of T2D. Immunoassays are used to detect and quantify biomolecules in a solution. Mass spectrometric immunoassay analysis of various proteins in the blood serum of 212 subjects belonging to multiple disease groups resulted in the identification of 41 molecular species as potential biomarkers. In this paper, support vector machines are used to measure the effectiveness of using these species as a diagnosis tool. We suggest an any-vs-rest SVM multiclass classification method by dividing the problem into a series of binary SVM classification problems and using a MAP decision rule to predict the correct class. One-vs-rest and discriminant analysis approaches are also evaluated for comparison.",
author = "Sai Buddi and Thomas Taylor and Chad Borges and Randall Nelson",
year = "2011",
doi = "10.1109/ICMLA.2011.182",
language = "English (US)",
isbn = "9780769546070",
volume = "2",
pages = "338--341",
booktitle = "Proceedings - 10th International Conference on Machine Learning and Applications, ICMLA 2011",

}

TY - GEN

T1 - SVM multi-classification of T2D/CVD patients using biomarker features

AU - Buddi, Sai

AU - Taylor, Thomas

AU - Borges, Chad

AU - Nelson, Randall

PY - 2011

Y1 - 2011

N2 - Cardiovascular disease (CVD) is considered as the leading cause of morbidity and mortality in type 2 diabetes (T2D) patients. In 2008 the US FDA issued a Guidance to Industry statement, recognizing the conjoined nature of CVD and T2D and emphasizing the need to monitor cardiovascular risk during new diabetic drug trials. This led researchers to work towards identifying panels of markers that are able to distinguish subtypes of CVD in the context of T2D. Immunoassays are used to detect and quantify biomolecules in a solution. Mass spectrometric immunoassay analysis of various proteins in the blood serum of 212 subjects belonging to multiple disease groups resulted in the identification of 41 molecular species as potential biomarkers. In this paper, support vector machines are used to measure the effectiveness of using these species as a diagnosis tool. We suggest an any-vs-rest SVM multiclass classification method by dividing the problem into a series of binary SVM classification problems and using a MAP decision rule to predict the correct class. One-vs-rest and discriminant analysis approaches are also evaluated for comparison.

AB - Cardiovascular disease (CVD) is considered as the leading cause of morbidity and mortality in type 2 diabetes (T2D) patients. In 2008 the US FDA issued a Guidance to Industry statement, recognizing the conjoined nature of CVD and T2D and emphasizing the need to monitor cardiovascular risk during new diabetic drug trials. This led researchers to work towards identifying panels of markers that are able to distinguish subtypes of CVD in the context of T2D. Immunoassays are used to detect and quantify biomolecules in a solution. Mass spectrometric immunoassay analysis of various proteins in the blood serum of 212 subjects belonging to multiple disease groups resulted in the identification of 41 molecular species as potential biomarkers. In this paper, support vector machines are used to measure the effectiveness of using these species as a diagnosis tool. We suggest an any-vs-rest SVM multiclass classification method by dividing the problem into a series of binary SVM classification problems and using a MAP decision rule to predict the correct class. One-vs-rest and discriminant analysis approaches are also evaluated for comparison.

UR - http://www.scopus.com/inward/record.url?scp=84857846432&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84857846432&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2011.182

DO - 10.1109/ICMLA.2011.182

M3 - Conference contribution

AN - SCOPUS:84857846432

SN - 9780769546070

VL - 2

SP - 338

EP - 341

BT - Proceedings - 10th International Conference on Machine Learning and Applications, ICMLA 2011

ER -