Screening Based on the Risk of Cancer Calculation from Bayesian Hierarchical Changepoint and Mixture Models of Longitudinal Markers

Steven J. Skates, Donna P Ankerst, Ian J. Jacobs

Research output: Contribution to journalArticle

103 Citations (Scopus)

Abstract

The standard approach to early detection of disease with a quantitative marker is to set a population-based fixed reference level for making further individual screening or referral decisions. For many types of disease, including prostate and ovarian cancer, additional information is contained in the subject-specific temporal behavior of the marker, which exhibits a characteristic alteration early in the course of the disease. In this article we derive a Bayesian approach to screening based on calculation of the posterior probability of disease given longitudinal marker levels. The method is motivated by a randomized ovarian cancer screening trial in the United Kingdom comprising 22,000 women screened over 4 years with an additional 5 years of follow-up on average. Levels of the antigen CA125 were recorded annually in the screened arm. CA125 profiles of cases and controls from the U.K. trial are modeled using hierarchical changepoint and mixture models, posterior distributions are calculated using Markov chain Monte Carlo methods, and the model is used to calculate the Bayesian posterior risk of having ovarian cancer given a new subject's single or multiple longitudinal CA125 levels. A screening strategy based on the risk calculation is then evaluated using data from an independent screening trial of 5,550 women performed in Sweden. A longitudinal CA125 screening strategy based on calculation of the risk of ovarian cancer is proposed. Simulations of a prospective trial using a strategy based on the risk calculated from longitudinal CA125 values indicate potentially large increases in sensitivity for a given specificity compared to the standard approach based on a fixed CA125 reference level for all subjects.

Original languageEnglish (US)
Pages (from-to)429-439
Number of pages11
JournalJournal of the American Statistical Association
Volume96
Issue number454
StatePublished - Jun 2001
Externally publishedYes

Fingerprint

Change-point Model
Hierarchical Model
Mixture Model
Screening
Ovarian Cancer
Cancer
Prostate Cancer
Sweden
Markov Chain Monte Carlo Methods
Posterior Probability
Posterior distribution
Bayesian Approach
Specificity
Change point
Mixture model
Calculate
Strategy

Keywords

  • Longitudinal CA125
  • Markov chain Monte Carlo
  • Mixtures
  • Ovarian cancer
  • Screening

ASJC Scopus subject areas

  • Mathematics(all)
  • Statistics and Probability

Cite this

Screening Based on the Risk of Cancer Calculation from Bayesian Hierarchical Changepoint and Mixture Models of Longitudinal Markers. / Skates, Steven J.; Ankerst, Donna P; Jacobs, Ian J.

In: Journal of the American Statistical Association, Vol. 96, No. 454, 06.2001, p. 429-439.

Research output: Contribution to journalArticle

@article{803d419520e847c3bfce4a94e5ace667,
title = "Screening Based on the Risk of Cancer Calculation from Bayesian Hierarchical Changepoint and Mixture Models of Longitudinal Markers",
abstract = "The standard approach to early detection of disease with a quantitative marker is to set a population-based fixed reference level for making further individual screening or referral decisions. For many types of disease, including prostate and ovarian cancer, additional information is contained in the subject-specific temporal behavior of the marker, which exhibits a characteristic alteration early in the course of the disease. In this article we derive a Bayesian approach to screening based on calculation of the posterior probability of disease given longitudinal marker levels. The method is motivated by a randomized ovarian cancer screening trial in the United Kingdom comprising 22,000 women screened over 4 years with an additional 5 years of follow-up on average. Levels of the antigen CA125 were recorded annually in the screened arm. CA125 profiles of cases and controls from the U.K. trial are modeled using hierarchical changepoint and mixture models, posterior distributions are calculated using Markov chain Monte Carlo methods, and the model is used to calculate the Bayesian posterior risk of having ovarian cancer given a new subject's single or multiple longitudinal CA125 levels. A screening strategy based on the risk calculation is then evaluated using data from an independent screening trial of 5,550 women performed in Sweden. A longitudinal CA125 screening strategy based on calculation of the risk of ovarian cancer is proposed. Simulations of a prospective trial using a strategy based on the risk calculated from longitudinal CA125 values indicate potentially large increases in sensitivity for a given specificity compared to the standard approach based on a fixed CA125 reference level for all subjects.",
keywords = "Longitudinal CA125, Markov chain Monte Carlo, Mixtures, Ovarian cancer, Screening",
author = "Skates, {Steven J.} and Ankerst, {Donna P} and Jacobs, {Ian J.}",
year = "2001",
month = "6",
language = "English (US)",
volume = "96",
pages = "429--439",
journal = "Journal of the American Statistical Association",
issn = "0162-1459",
publisher = "Taylor and Francis Ltd.",
number = "454",

}

TY - JOUR

T1 - Screening Based on the Risk of Cancer Calculation from Bayesian Hierarchical Changepoint and Mixture Models of Longitudinal Markers

AU - Skates, Steven J.

AU - Ankerst, Donna P

AU - Jacobs, Ian J.

PY - 2001/6

Y1 - 2001/6

N2 - The standard approach to early detection of disease with a quantitative marker is to set a population-based fixed reference level for making further individual screening or referral decisions. For many types of disease, including prostate and ovarian cancer, additional information is contained in the subject-specific temporal behavior of the marker, which exhibits a characteristic alteration early in the course of the disease. In this article we derive a Bayesian approach to screening based on calculation of the posterior probability of disease given longitudinal marker levels. The method is motivated by a randomized ovarian cancer screening trial in the United Kingdom comprising 22,000 women screened over 4 years with an additional 5 years of follow-up on average. Levels of the antigen CA125 were recorded annually in the screened arm. CA125 profiles of cases and controls from the U.K. trial are modeled using hierarchical changepoint and mixture models, posterior distributions are calculated using Markov chain Monte Carlo methods, and the model is used to calculate the Bayesian posterior risk of having ovarian cancer given a new subject's single or multiple longitudinal CA125 levels. A screening strategy based on the risk calculation is then evaluated using data from an independent screening trial of 5,550 women performed in Sweden. A longitudinal CA125 screening strategy based on calculation of the risk of ovarian cancer is proposed. Simulations of a prospective trial using a strategy based on the risk calculated from longitudinal CA125 values indicate potentially large increases in sensitivity for a given specificity compared to the standard approach based on a fixed CA125 reference level for all subjects.

AB - The standard approach to early detection of disease with a quantitative marker is to set a population-based fixed reference level for making further individual screening or referral decisions. For many types of disease, including prostate and ovarian cancer, additional information is contained in the subject-specific temporal behavior of the marker, which exhibits a characteristic alteration early in the course of the disease. In this article we derive a Bayesian approach to screening based on calculation of the posterior probability of disease given longitudinal marker levels. The method is motivated by a randomized ovarian cancer screening trial in the United Kingdom comprising 22,000 women screened over 4 years with an additional 5 years of follow-up on average. Levels of the antigen CA125 were recorded annually in the screened arm. CA125 profiles of cases and controls from the U.K. trial are modeled using hierarchical changepoint and mixture models, posterior distributions are calculated using Markov chain Monte Carlo methods, and the model is used to calculate the Bayesian posterior risk of having ovarian cancer given a new subject's single or multiple longitudinal CA125 levels. A screening strategy based on the risk calculation is then evaluated using data from an independent screening trial of 5,550 women performed in Sweden. A longitudinal CA125 screening strategy based on calculation of the risk of ovarian cancer is proposed. Simulations of a prospective trial using a strategy based on the risk calculated from longitudinal CA125 values indicate potentially large increases in sensitivity for a given specificity compared to the standard approach based on a fixed CA125 reference level for all subjects.

KW - Longitudinal CA125

KW - Markov chain Monte Carlo

KW - Mixtures

KW - Ovarian cancer

KW - Screening

UR - http://www.scopus.com/inward/record.url?scp=1542678929&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1542678929&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:1542678929

VL - 96

SP - 429

EP - 439

JO - Journal of the American Statistical Association

JF - Journal of the American Statistical Association

SN - 0162-1459

IS - 454

ER -