Semiparametric accelerated failure time cure rate mixture models with competing risks

Sangbum Choi, Liang Zhu, Xuelin Huang

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Modern medical treatments have substantially improved survival rates for many chronic diseases and have generated considerable interest in developing cure fraction models for survival data with a non-ignorable cured proportion. Statistical analysis of such data may be further complicated by competing risks that involve multiple types of endpoints. Regression analysis of competing risks is typically undertaken via a proportional hazards model adapted on cause-specific hazard or subdistribution hazard. In this article, we propose an alternative approach that treats competing events as distinct outcomes in a mixture. We consider semiparametric accelerated failure time models for the cause-conditional survival function that are combined through a multinomial logistic model within the cure-mixture modeling framework. The cure-mixture approach to competing risks provides a means to determine the overall effect of a treatment and insights into how this treatment modifies the components of the mixture in the presence of a cure fraction. The regression and nonparametric parameters are estimated by a nonparametric kernel-based maximum likelihood estimation method. Variance estimation is achieved through resampling methods for the kernel-smoothed likelihood function. Simulation studies show that the procedures work well in practical settings. Application to a sarcoma study demonstrates the use of the proposed method for competing risk data with a cure fraction.

Original languageEnglish
Pages (from-to)48-59
Number of pages12
JournalStatistics in Medicine
Volume37
Issue number1
DOIs
Publication statusPublished - 2018 Jan 15

Fingerprint

Competing Risks
Failure Time
Mixture Model
Cause-specific Hazard
kernel
Likelihood Functions
Accelerated Failure Time Model
Multinomial Model
Mixture Modeling
Resampling Methods
Chronic Disease
Statistical Data Interpretation
Proportional Hazards Model
Variance Estimation
Survival Function
Logistic Model
Survival Data
Semiparametric Model
Likelihood Function
Proportional Hazards Models

Keywords

  • competing risks
  • cure fraction
  • kernel smoothing
  • mixture model
  • nonparametric likelihood
  • subdistribution

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability

Cite this

Semiparametric accelerated failure time cure rate mixture models with competing risks. / Choi, Sangbum; Zhu, Liang; Huang, Xuelin.

In: Statistics in Medicine, Vol. 37, No. 1, 15.01.2018, p. 48-59.

Research output: Contribution to journalArticle

@article{14805b760f614c24ab669d73f5d8e9a3,
title = "Semiparametric accelerated failure time cure rate mixture models with competing risks",
abstract = "Modern medical treatments have substantially improved survival rates for many chronic diseases and have generated considerable interest in developing cure fraction models for survival data with a non-ignorable cured proportion. Statistical analysis of such data may be further complicated by competing risks that involve multiple types of endpoints. Regression analysis of competing risks is typically undertaken via a proportional hazards model adapted on cause-specific hazard or subdistribution hazard. In this article, we propose an alternative approach that treats competing events as distinct outcomes in a mixture. We consider semiparametric accelerated failure time models for the cause-conditional survival function that are combined through a multinomial logistic model within the cure-mixture modeling framework. The cure-mixture approach to competing risks provides a means to determine the overall effect of a treatment and insights into how this treatment modifies the components of the mixture in the presence of a cure fraction. The regression and nonparametric parameters are estimated by a nonparametric kernel-based maximum likelihood estimation method. Variance estimation is achieved through resampling methods for the kernel-smoothed likelihood function. Simulation studies show that the procedures work well in practical settings. Application to a sarcoma study demonstrates the use of the proposed method for competing risk data with a cure fraction.",
keywords = "competing risks, cure fraction, kernel smoothing, mixture model, nonparametric likelihood, subdistribution",
author = "Sangbum Choi and Liang Zhu and Xuelin Huang",
year = "2018",
month = "1",
day = "15",
doi = "10.1002/sim.7508",
language = "English",
volume = "37",
pages = "48--59",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "1",

}

TY - JOUR

T1 - Semiparametric accelerated failure time cure rate mixture models with competing risks

AU - Choi, Sangbum

AU - Zhu, Liang

AU - Huang, Xuelin

PY - 2018/1/15

Y1 - 2018/1/15

N2 - Modern medical treatments have substantially improved survival rates for many chronic diseases and have generated considerable interest in developing cure fraction models for survival data with a non-ignorable cured proportion. Statistical analysis of such data may be further complicated by competing risks that involve multiple types of endpoints. Regression analysis of competing risks is typically undertaken via a proportional hazards model adapted on cause-specific hazard or subdistribution hazard. In this article, we propose an alternative approach that treats competing events as distinct outcomes in a mixture. We consider semiparametric accelerated failure time models for the cause-conditional survival function that are combined through a multinomial logistic model within the cure-mixture modeling framework. The cure-mixture approach to competing risks provides a means to determine the overall effect of a treatment and insights into how this treatment modifies the components of the mixture in the presence of a cure fraction. The regression and nonparametric parameters are estimated by a nonparametric kernel-based maximum likelihood estimation method. Variance estimation is achieved through resampling methods for the kernel-smoothed likelihood function. Simulation studies show that the procedures work well in practical settings. Application to a sarcoma study demonstrates the use of the proposed method for competing risk data with a cure fraction.

AB - Modern medical treatments have substantially improved survival rates for many chronic diseases and have generated considerable interest in developing cure fraction models for survival data with a non-ignorable cured proportion. Statistical analysis of such data may be further complicated by competing risks that involve multiple types of endpoints. Regression analysis of competing risks is typically undertaken via a proportional hazards model adapted on cause-specific hazard or subdistribution hazard. In this article, we propose an alternative approach that treats competing events as distinct outcomes in a mixture. We consider semiparametric accelerated failure time models for the cause-conditional survival function that are combined through a multinomial logistic model within the cure-mixture modeling framework. The cure-mixture approach to competing risks provides a means to determine the overall effect of a treatment and insights into how this treatment modifies the components of the mixture in the presence of a cure fraction. The regression and nonparametric parameters are estimated by a nonparametric kernel-based maximum likelihood estimation method. Variance estimation is achieved through resampling methods for the kernel-smoothed likelihood function. Simulation studies show that the procedures work well in practical settings. Application to a sarcoma study demonstrates the use of the proposed method for competing risk data with a cure fraction.

KW - competing risks

KW - cure fraction

KW - kernel smoothing

KW - mixture model

KW - nonparametric likelihood

KW - subdistribution

UR - http://www.scopus.com/inward/record.url?scp=85037672067&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85037672067&partnerID=8YFLogxK

U2 - 10.1002/sim.7508

DO - 10.1002/sim.7508

M3 - Article

C2 - 28983935

AN - SCOPUS:85037672067

VL - 37

SP - 48

EP - 59

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 1

ER -