Cox's proportional hazards model with Lp penalty for biomarker identification and survival prediction

Zhenqiu Liu

doi:10.1109/ICMLA.2007.37

Cox's proportional hazards model with L_p penalty for biomarker identification and survival prediction

Zhenqiu Liu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

Advances in high throughput technology provide massive high dimensional data. It is very important and challenging to study the association of genes with various clinical outcomes. Due to large variability in time to certain clinical event among patients, studying possibly censored survival data can be more informative than classification. We proposed the Cox's proportional hazards model with L_p penalty method for simultaneous feature (gene) selection and survival prediction. L_p penalty shrinks coefficients and produces some coefficients that are exactly zero. It has been shown that L_p (p < 1) regularization performs better than L₁ in the regression and classification framework (Knight & Fu 2000, Liu et al. 2007). Experimental results with different data demonstrate that the proposed procedures can be used for identifying important genes (features) that are related to time to death due to cancer and for building parsimonious model for predicting the survival of future patients.

Original language	English (US)
Title of host publication	Proceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007
Pages	624-628
Number of pages	5
DOIs	https://doi.org/10.1109/ICMLA.2007.37
State	Published - 2007
Event	6th International Conference on Machine Learning and Applications, ICMLA 2007 - Cincinnati, OH, United States Duration: Dec 13 2007 → Dec 15 2007

Publication series

Name	Proceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007

Other

Other	6th International Conference on Machine Learning and Applications, ICMLA 2007
Country/Territory	United States
City	Cincinnati, OH
Period	12/13/07 → 12/15/07

All Science Journal Classification (ASJC) codes

Computer Science Applications
Human-Computer Interaction
Control and Systems Engineering

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ICMLA.2007.37

Cite this

Liu, Z. (2007). Cox's proportional hazards model with L_p penalty for biomarker identification and survival prediction. In Proceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007 (pp. 624-628). Article 4457299 (Proceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007). https://doi.org/10.1109/ICMLA.2007.37

@inproceedings{6c8836e025204791b33fe70b93b3b774,

title = "Cox's proportional hazards model with Lp penalty for biomarker identification and survival prediction",

abstract = "Advances in high throughput technology provide massive high dimensional data. It is very important and challenging to study the association of genes with various clinical outcomes. Due to large variability in time to certain clinical event among patients, studying possibly censored survival data can be more informative than classification. We proposed the Cox's proportional hazards model with Lp penalty method for simultaneous feature (gene) selection and survival prediction. Lp penalty shrinks coefficients and produces some coefficients that are exactly zero. It has been shown that Lp (p < 1) regularization performs better than L1 in the regression and classification framework (Knight & Fu 2000, Liu et al. 2007). Experimental results with different data demonstrate that the proposed procedures can be used for identifying important genes (features) that are related to time to death due to cancer and for building parsimonious model for predicting the survival of future patients.",

author = "Zhenqiu Liu",

year = "2007",

doi = "10.1109/ICMLA.2007.37",

language = "English (US)",

isbn = "0769530699",

series = "Proceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007",

pages = "624--628",

booktitle = "Proceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007",

note = "6th International Conference on Machine Learning and Applications, ICMLA 2007 ; Conference date: 13-12-2007 Through 15-12-2007",

}

Liu, Z 2007, Cox's proportional hazards model with L_p penalty for biomarker identification and survival prediction. in Proceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007., 4457299, Proceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007, pp. 624-628, 6th International Conference on Machine Learning and Applications, ICMLA 2007, Cincinnati, OH, United States, 12/13/07. https://doi.org/10.1109/ICMLA.2007.37

Cox's proportional hazards model with L_p penalty for biomarker identification and survival prediction. / Liu, Zhenqiu.
Proceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007. 2007. p. 624-628 4457299 (Proceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Cox's proportional hazards model with Lp penalty for biomarker identification and survival prediction

AU - Liu, Zhenqiu

PY - 2007

Y1 - 2007

N2 - Advances in high throughput technology provide massive high dimensional data. It is very important and challenging to study the association of genes with various clinical outcomes. Due to large variability in time to certain clinical event among patients, studying possibly censored survival data can be more informative than classification. We proposed the Cox's proportional hazards model with Lp penalty method for simultaneous feature (gene) selection and survival prediction. Lp penalty shrinks coefficients and produces some coefficients that are exactly zero. It has been shown that Lp (p < 1) regularization performs better than L1 in the regression and classification framework (Knight & Fu 2000, Liu et al. 2007). Experimental results with different data demonstrate that the proposed procedures can be used for identifying important genes (features) that are related to time to death due to cancer and for building parsimonious model for predicting the survival of future patients.

AB - Advances in high throughput technology provide massive high dimensional data. It is very important and challenging to study the association of genes with various clinical outcomes. Due to large variability in time to certain clinical event among patients, studying possibly censored survival data can be more informative than classification. We proposed the Cox's proportional hazards model with Lp penalty method for simultaneous feature (gene) selection and survival prediction. Lp penalty shrinks coefficients and produces some coefficients that are exactly zero. It has been shown that Lp (p < 1) regularization performs better than L1 in the regression and classification framework (Knight & Fu 2000, Liu et al. 2007). Experimental results with different data demonstrate that the proposed procedures can be used for identifying important genes (features) that are related to time to death due to cancer and for building parsimonious model for predicting the survival of future patients.

UR - http://www.scopus.com/inward/record.url?scp=47349083416&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47349083416&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2007.37

DO - 10.1109/ICMLA.2007.37

M3 - Conference contribution

AN - SCOPUS:47349083416

SN - 0769530699

SN - 9780769530697

T3 - Proceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007

SP - 624

EP - 628

BT - Proceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007

T2 - 6th International Conference on Machine Learning and Applications, ICMLA 2007

Y2 - 13 December 2007 through 15 December 2007

ER -