Defining and ranking effects of individual agents based on survival times of cancer patients treated with combination chemotherapies

Peter F. Thall, Diane D. Liu, Su G. Berrak, Johannes E. Wolff

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

An important problem in oncology is comparing chemotherapy (chemo) agents in terms of their effects on survival or progression-free survival time. When the goal is to evaluate individual agents, a difficulty commonly encountered with observational data is that many patients receive a chemo combination including two or more agents. Because agents given in combination may interact, quantifying the contribution of each individual agent to the combination's overall effect is problematic. Still, if on average combinations including a particular agent confer longer survival, then that agent may be considered superior to agents whose combinations confer shorter survival. Motivated by this idea, we propose a definition of individual agent effects based on observational survival data from patients treated with many different chemo combinations. We define an individual agent effect as the average of the effects of the chemo combinations that include the agent. Similarly, we define the effect of each pair of agents as the average of the effects of the combinations including the pair. Under a Bayesian regression model for survival time in which the chemo combination effects follow a hierarchical structure, these definitions are used as a basis for estimating the posterior effects and ranks of the individual agents, and of all pairs of agents. The methods are illustrated by a data set arising from 224 pediatric brain tumor patients treated with over 27 different chemo combinations involving seven chemo agents.

Original languageEnglish (US)
Pages (from-to)1777-1794
Number of pages18
JournalStatistics in Medicine
Volume30
Issue number15
DOIs
StatePublished - Jul 10 2011
Externally publishedYes

Fingerprint

Survival Time
Chemotherapy
Combination Drug Therapy
Cancer
Ranking
Survival
Neoplasms
Drug Therapy
Brain Neoplasms
Disease-Free Survival
Pediatrics
Brain Tumor
Oncology
Survival Data
Bayesian Model
Hierarchical Structure
Progression

Keywords

  • Bayesian analysis
  • Brain tumors
  • Hierarchical model
  • Ranking
  • Survival analysis

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability

Cite this

Defining and ranking effects of individual agents based on survival times of cancer patients treated with combination chemotherapies. / Thall, Peter F.; Liu, Diane D.; Berrak, Su G.; Wolff, Johannes E.

In: Statistics in Medicine, Vol. 30, No. 15, 10.07.2011, p. 1777-1794.

Research output: Contribution to journalArticle

Thall, Peter F. ; Liu, Diane D. ; Berrak, Su G. ; Wolff, Johannes E. / Defining and ranking effects of individual agents based on survival times of cancer patients treated with combination chemotherapies. In: Statistics in Medicine. 2011 ; Vol. 30, No. 15. pp. 1777-1794.
@article{70080ab44823428a9631ecdab434b393,
title = "Defining and ranking effects of individual agents based on survival times of cancer patients treated with combination chemotherapies",
abstract = "An important problem in oncology is comparing chemotherapy (chemo) agents in terms of their effects on survival or progression-free survival time. When the goal is to evaluate individual agents, a difficulty commonly encountered with observational data is that many patients receive a chemo combination including two or more agents. Because agents given in combination may interact, quantifying the contribution of each individual agent to the combination's overall effect is problematic. Still, if on average combinations including a particular agent confer longer survival, then that agent may be considered superior to agents whose combinations confer shorter survival. Motivated by this idea, we propose a definition of individual agent effects based on observational survival data from patients treated with many different chemo combinations. We define an individual agent effect as the average of the effects of the chemo combinations that include the agent. Similarly, we define the effect of each pair of agents as the average of the effects of the combinations including the pair. Under a Bayesian regression model for survival time in which the chemo combination effects follow a hierarchical structure, these definitions are used as a basis for estimating the posterior effects and ranks of the individual agents, and of all pairs of agents. The methods are illustrated by a data set arising from 224 pediatric brain tumor patients treated with over 27 different chemo combinations involving seven chemo agents.",
keywords = "Bayesian analysis, Brain tumors, Hierarchical model, Ranking, Survival analysis",
author = "Thall, {Peter F.} and Liu, {Diane D.} and Berrak, {Su G.} and Wolff, {Johannes E.}",
year = "2011",
month = "7",
day = "10",
doi = "10.1002/sim.4249",
language = "English (US)",
volume = "30",
pages = "1777--1794",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "15",

}

TY - JOUR

T1 - Defining and ranking effects of individual agents based on survival times of cancer patients treated with combination chemotherapies

AU - Thall, Peter F.

AU - Liu, Diane D.

AU - Berrak, Su G.

AU - Wolff, Johannes E.

PY - 2011/7/10

Y1 - 2011/7/10

N2 - An important problem in oncology is comparing chemotherapy (chemo) agents in terms of their effects on survival or progression-free survival time. When the goal is to evaluate individual agents, a difficulty commonly encountered with observational data is that many patients receive a chemo combination including two or more agents. Because agents given in combination may interact, quantifying the contribution of each individual agent to the combination's overall effect is problematic. Still, if on average combinations including a particular agent confer longer survival, then that agent may be considered superior to agents whose combinations confer shorter survival. Motivated by this idea, we propose a definition of individual agent effects based on observational survival data from patients treated with many different chemo combinations. We define an individual agent effect as the average of the effects of the chemo combinations that include the agent. Similarly, we define the effect of each pair of agents as the average of the effects of the combinations including the pair. Under a Bayesian regression model for survival time in which the chemo combination effects follow a hierarchical structure, these definitions are used as a basis for estimating the posterior effects and ranks of the individual agents, and of all pairs of agents. The methods are illustrated by a data set arising from 224 pediatric brain tumor patients treated with over 27 different chemo combinations involving seven chemo agents.

AB - An important problem in oncology is comparing chemotherapy (chemo) agents in terms of their effects on survival or progression-free survival time. When the goal is to evaluate individual agents, a difficulty commonly encountered with observational data is that many patients receive a chemo combination including two or more agents. Because agents given in combination may interact, quantifying the contribution of each individual agent to the combination's overall effect is problematic. Still, if on average combinations including a particular agent confer longer survival, then that agent may be considered superior to agents whose combinations confer shorter survival. Motivated by this idea, we propose a definition of individual agent effects based on observational survival data from patients treated with many different chemo combinations. We define an individual agent effect as the average of the effects of the chemo combinations that include the agent. Similarly, we define the effect of each pair of agents as the average of the effects of the combinations including the pair. Under a Bayesian regression model for survival time in which the chemo combination effects follow a hierarchical structure, these definitions are used as a basis for estimating the posterior effects and ranks of the individual agents, and of all pairs of agents. The methods are illustrated by a data set arising from 224 pediatric brain tumor patients treated with over 27 different chemo combinations involving seven chemo agents.

KW - Bayesian analysis

KW - Brain tumors

KW - Hierarchical model

KW - Ranking

KW - Survival analysis

UR - http://www.scopus.com/inward/record.url?scp=79958769040&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79958769040&partnerID=8YFLogxK

U2 - 10.1002/sim.4249

DO - 10.1002/sim.4249

M3 - Article

C2 - 21590700

AN - SCOPUS:79958769040

VL - 30

SP - 1777

EP - 1794

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 15

ER -