An integrative pathway-based clinical-genomic model for cancer survival prediction

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

Prediction models that use gene expression levels are now being proposed for personalized treatment of cancer, but building accurate models that are easy to interpret remains a challenge. In this paper, we describe an integrative clinical-genomic approach that combines both genomic pathway and clinical information. First, we summarize information from genes in each pathway using Supervised Principal Components (SPCA) to obtain pathway-based genomic predictors. Next, we build a prediction model based on clinical variables and pathway-based genomic predictors using Random Survival Forests (RSF). Our rationale for this two-stage procedure is that the underlying disease process may be influenced by environmental exposure (measured by clinical variables) and perturbations in different pathways (measured by pathway-based genomic variables), as well as their interactions. Using two cancer microarray datasets, we show that the pathway-based clinical-genomic model outperforms gene-based clinical-genomic models, with improved prediction accuracy and interpretability.

Original languageEnglish
Pages (from-to)1313-1319
Number of pages7
JournalStatistics and Probability Letters
Volume80
Issue number17-18
DOIs
StatePublished - Sep 1 2010
Externally publishedYes

Fingerprint

Genomics
Pathway
Cancer
Prediction
Prediction Model
Predictors
Model
Gene
Two-stage Procedure
Interpretability
Principal Components
Microarray
Gene Expression
Model-based
Perturbation
Interaction

Keywords

  • Gene expression
  • Microarrays
  • Pathway analysis
  • Random survival forests
  • Survival prediction

ASJC Scopus subject areas

  • Statistics, Probability and Uncertainty
  • Statistics and Probability

Cite this

An integrative pathway-based clinical-genomic model for cancer survival prediction. / Chen, Xi; Wang, Lily; Ishwaran, Hemant.

In: Statistics and Probability Letters, Vol. 80, No. 17-18, 01.09.2010, p. 1313-1319.

Research output: Contribution to journalArticle

@article{868879651100457f9866479e62337421,
title = "An integrative pathway-based clinical-genomic model for cancer survival prediction",
abstract = "Prediction models that use gene expression levels are now being proposed for personalized treatment of cancer, but building accurate models that are easy to interpret remains a challenge. In this paper, we describe an integrative clinical-genomic approach that combines both genomic pathway and clinical information. First, we summarize information from genes in each pathway using Supervised Principal Components (SPCA) to obtain pathway-based genomic predictors. Next, we build a prediction model based on clinical variables and pathway-based genomic predictors using Random Survival Forests (RSF). Our rationale for this two-stage procedure is that the underlying disease process may be influenced by environmental exposure (measured by clinical variables) and perturbations in different pathways (measured by pathway-based genomic variables), as well as their interactions. Using two cancer microarray datasets, we show that the pathway-based clinical-genomic model outperforms gene-based clinical-genomic models, with improved prediction accuracy and interpretability.",
keywords = "Gene expression, Microarrays, Pathway analysis, Random survival forests, Survival prediction",
author = "Xi Chen and Lily Wang and Hemant Ishwaran",
year = "2010",
month = "9",
day = "1",
doi = "10.1016/j.spl.2010.04.011",
language = "English",
volume = "80",
pages = "1313--1319",
journal = "Statistics and Probability Letters",
issn = "0167-7152",
publisher = "Elsevier",
number = "17-18",

}

TY - JOUR

T1 - An integrative pathway-based clinical-genomic model for cancer survival prediction

AU - Chen, Xi

AU - Wang, Lily

AU - Ishwaran, Hemant

PY - 2010/9/1

Y1 - 2010/9/1

N2 - Prediction models that use gene expression levels are now being proposed for personalized treatment of cancer, but building accurate models that are easy to interpret remains a challenge. In this paper, we describe an integrative clinical-genomic approach that combines both genomic pathway and clinical information. First, we summarize information from genes in each pathway using Supervised Principal Components (SPCA) to obtain pathway-based genomic predictors. Next, we build a prediction model based on clinical variables and pathway-based genomic predictors using Random Survival Forests (RSF). Our rationale for this two-stage procedure is that the underlying disease process may be influenced by environmental exposure (measured by clinical variables) and perturbations in different pathways (measured by pathway-based genomic variables), as well as their interactions. Using two cancer microarray datasets, we show that the pathway-based clinical-genomic model outperforms gene-based clinical-genomic models, with improved prediction accuracy and interpretability.

AB - Prediction models that use gene expression levels are now being proposed for personalized treatment of cancer, but building accurate models that are easy to interpret remains a challenge. In this paper, we describe an integrative clinical-genomic approach that combines both genomic pathway and clinical information. First, we summarize information from genes in each pathway using Supervised Principal Components (SPCA) to obtain pathway-based genomic predictors. Next, we build a prediction model based on clinical variables and pathway-based genomic predictors using Random Survival Forests (RSF). Our rationale for this two-stage procedure is that the underlying disease process may be influenced by environmental exposure (measured by clinical variables) and perturbations in different pathways (measured by pathway-based genomic variables), as well as their interactions. Using two cancer microarray datasets, we show that the pathway-based clinical-genomic model outperforms gene-based clinical-genomic models, with improved prediction accuracy and interpretability.

KW - Gene expression

KW - Microarrays

KW - Pathway analysis

KW - Random survival forests

KW - Survival prediction

UR - http://www.scopus.com/inward/record.url?scp=77954541112&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77954541112&partnerID=8YFLogxK

U2 - 10.1016/j.spl.2010.04.011

DO - 10.1016/j.spl.2010.04.011

M3 - Article

AN - SCOPUS:77954541112

VL - 80

SP - 1313

EP - 1319

JO - Statistics and Probability Letters

JF - Statistics and Probability Letters

SN - 0167-7152

IS - 17-18

ER -