Extension of a Cox proportional hazards cure model when cure information is partially known

Yu Wu, Yong Lin, Shou En Lu, Chin-Shang Li, Weichung Joe Shih

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

When there is evidence of long-term survivors, cure models are often used to model the survival curve. A cure model is a mixture model consisting of a cured fraction and an uncured fraction. Traditional cure models assume that the cured or uncured status in the censored set cannot be distinguished. But in many practices, some diagnostic procedures may provide partial information about the cured or uncured status relative to certain sensitivity and specificity. The traditional cure model does not take advantage of this additional information. Motivated by a clinical study on bone injury in pediatric patients, we propose a novel extension of a traditional Cox proportional hazards (PH) cure model that incorporates the additional information about the cured status. This extension can be applied when the latency part of the cure model is modeled by the Cox PH model. Extensive simulations demonstrated that the proposed extension provides more efficient and less biased estimations, and the higher efficiency and smaller bias is associated with higher sensitivity and specificity of diagnostic procedures. When the proposed extended Cox PH cure model was applied to the motivating example, there was a substantial improvement in the estimation.

Original languageEnglish (US)
Pages (from-to)540-554
Number of pages15
JournalBiostatistics
Volume15
Issue number3
DOIs
StatePublished - 2014

Fingerprint

Cure Model
Hazard Models
Proportional Hazards
Proportional Hazards Models
Sensitivity and Specificity
Survivors
Specificity
Diagnostics
Pediatrics
Bone and Bones
Biased Estimation
Survival
Wounds and Injuries
Cox Proportional Hazards Model
Partial Information
Cox proportional hazards model
Mixture Model
Bone
High Efficiency
Latency

Keywords

  • Cure model
  • Expectation-maximization (EM) algorithm
  • Proportional hazards
  • Relative efficiency
  • Sensitivity and specificity

ASJC Scopus subject areas

  • Medicine(all)
  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Extension of a Cox proportional hazards cure model when cure information is partially known. / Wu, Yu; Lin, Yong; Lu, Shou En; Li, Chin-Shang; Shih, Weichung Joe.

In: Biostatistics, Vol. 15, No. 3, 2014, p. 540-554.

Research output: Contribution to journalArticle

Wu, Yu ; Lin, Yong ; Lu, Shou En ; Li, Chin-Shang ; Shih, Weichung Joe. / Extension of a Cox proportional hazards cure model when cure information is partially known. In: Biostatistics. 2014 ; Vol. 15, No. 3. pp. 540-554.
@article{9a44d1212bd242a784877be7e5a667d9,
title = "Extension of a Cox proportional hazards cure model when cure information is partially known",
abstract = "When there is evidence of long-term survivors, cure models are often used to model the survival curve. A cure model is a mixture model consisting of a cured fraction and an uncured fraction. Traditional cure models assume that the cured or uncured status in the censored set cannot be distinguished. But in many practices, some diagnostic procedures may provide partial information about the cured or uncured status relative to certain sensitivity and specificity. The traditional cure model does not take advantage of this additional information. Motivated by a clinical study on bone injury in pediatric patients, we propose a novel extension of a traditional Cox proportional hazards (PH) cure model that incorporates the additional information about the cured status. This extension can be applied when the latency part of the cure model is modeled by the Cox PH model. Extensive simulations demonstrated that the proposed extension provides more efficient and less biased estimations, and the higher efficiency and smaller bias is associated with higher sensitivity and specificity of diagnostic procedures. When the proposed extended Cox PH cure model was applied to the motivating example, there was a substantial improvement in the estimation.",
keywords = "Cure model, Expectation-maximization (EM) algorithm, Proportional hazards, Relative efficiency, Sensitivity and specificity",
author = "Yu Wu and Yong Lin and Lu, {Shou En} and Chin-Shang Li and Shih, {Weichung Joe}",
year = "2014",
doi = "10.1093/biostatistics/kxu002",
language = "English (US)",
volume = "15",
pages = "540--554",
journal = "Biostatistics",
issn = "1465-4644",
publisher = "Oxford University Press",
number = "3",

}

TY - JOUR

T1 - Extension of a Cox proportional hazards cure model when cure information is partially known

AU - Wu, Yu

AU - Lin, Yong

AU - Lu, Shou En

AU - Li, Chin-Shang

AU - Shih, Weichung Joe

PY - 2014

Y1 - 2014

N2 - When there is evidence of long-term survivors, cure models are often used to model the survival curve. A cure model is a mixture model consisting of a cured fraction and an uncured fraction. Traditional cure models assume that the cured or uncured status in the censored set cannot be distinguished. But in many practices, some diagnostic procedures may provide partial information about the cured or uncured status relative to certain sensitivity and specificity. The traditional cure model does not take advantage of this additional information. Motivated by a clinical study on bone injury in pediatric patients, we propose a novel extension of a traditional Cox proportional hazards (PH) cure model that incorporates the additional information about the cured status. This extension can be applied when the latency part of the cure model is modeled by the Cox PH model. Extensive simulations demonstrated that the proposed extension provides more efficient and less biased estimations, and the higher efficiency and smaller bias is associated with higher sensitivity and specificity of diagnostic procedures. When the proposed extended Cox PH cure model was applied to the motivating example, there was a substantial improvement in the estimation.

AB - When there is evidence of long-term survivors, cure models are often used to model the survival curve. A cure model is a mixture model consisting of a cured fraction and an uncured fraction. Traditional cure models assume that the cured or uncured status in the censored set cannot be distinguished. But in many practices, some diagnostic procedures may provide partial information about the cured or uncured status relative to certain sensitivity and specificity. The traditional cure model does not take advantage of this additional information. Motivated by a clinical study on bone injury in pediatric patients, we propose a novel extension of a traditional Cox proportional hazards (PH) cure model that incorporates the additional information about the cured status. This extension can be applied when the latency part of the cure model is modeled by the Cox PH model. Extensive simulations demonstrated that the proposed extension provides more efficient and less biased estimations, and the higher efficiency and smaller bias is associated with higher sensitivity and specificity of diagnostic procedures. When the proposed extended Cox PH cure model was applied to the motivating example, there was a substantial improvement in the estimation.

KW - Cure model

KW - Expectation-maximization (EM) algorithm

KW - Proportional hazards

KW - Relative efficiency

KW - Sensitivity and specificity

UR - http://www.scopus.com/inward/record.url?scp=84902651142&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902651142&partnerID=8YFLogxK

U2 - 10.1093/biostatistics/kxu002

DO - 10.1093/biostatistics/kxu002

M3 - Article

C2 - 24511081

AN - SCOPUS:84902651142

VL - 15

SP - 540

EP - 554

JO - Biostatistics

JF - Biostatistics

SN - 1465-4644

IS - 3

ER -