A Semiparametric Censoring Bias Model for Estimating the Cumulative Risk of a False-Positive Screening Test Under Dependent Censoring

Rebecca A. Hubbard, Diana L Miglioretti

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

False-positive test results are among the most common harms of screening tests and may lead to more invasive and expensive diagnostic testing procedures. Estimating the cumulative risk of a false-positive screening test result after repeat screening rounds is, therefore, important for evaluating potential screening regimens. Existing estimators of the cumulative false-positive risk are limited by strong assumptions about censoring mechanisms and parametric assumptions about variation in risk across screening rounds. To address these limitations, we propose a semiparametric censoring bias model for cumulative false-positive risk that allows for dependent censoring without specifying a fixed functional form for variation in risk across screening rounds. Simulation studies demonstrated that the censoring bias model performs similarly to existing models under independent censoring and can largely eliminate bias under dependent censoring. We used the existing and newly proposed models to estimate the cumulative false-positive risk and variation in risk as a function of baseline age and family history of breast cancer after 10 years of annual screening mammography using data from the Breast Cancer Surveillance Consortium. Ignoring potential dependent censoring in this context leads to underestimation of the cumulative risk of false-positive results. Models that provide accurate estimates under dependent censoring are critical for providing appropriate information for evaluating screening tests.

Original languageEnglish (US)
Pages (from-to)245-253
Number of pages9
JournalBiometrics
Volume69
Issue number1
DOIs
StatePublished - Mar 2013
Externally publishedYes

Fingerprint

cumulative risk
Dependent Censoring
Censoring
False Positive
Screening
screening
risk screening
breast neoplasms
Breast Cancer
Model
Breast Neoplasms
Mammography
testing
Estimate
Surveillance
Annual
Baseline
Diagnostics
Eliminate
monitoring

Keywords

  • Dependent censoring
  • False-positive
  • Mammography
  • Screening

ASJC Scopus subject areas

  • Applied Mathematics
  • Statistics and Probability
  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Immunology and Microbiology(all)
  • Medicine(all)

Cite this

A Semiparametric Censoring Bias Model for Estimating the Cumulative Risk of a False-Positive Screening Test Under Dependent Censoring. / Hubbard, Rebecca A.; Miglioretti, Diana L.

In: Biometrics, Vol. 69, No. 1, 03.2013, p. 245-253.

Research output: Contribution to journalArticle

@article{1e20d27e172d48cabedc6b520edef07f,
title = "A Semiparametric Censoring Bias Model for Estimating the Cumulative Risk of a False-Positive Screening Test Under Dependent Censoring",
abstract = "False-positive test results are among the most common harms of screening tests and may lead to more invasive and expensive diagnostic testing procedures. Estimating the cumulative risk of a false-positive screening test result after repeat screening rounds is, therefore, important for evaluating potential screening regimens. Existing estimators of the cumulative false-positive risk are limited by strong assumptions about censoring mechanisms and parametric assumptions about variation in risk across screening rounds. To address these limitations, we propose a semiparametric censoring bias model for cumulative false-positive risk that allows for dependent censoring without specifying a fixed functional form for variation in risk across screening rounds. Simulation studies demonstrated that the censoring bias model performs similarly to existing models under independent censoring and can largely eliminate bias under dependent censoring. We used the existing and newly proposed models to estimate the cumulative false-positive risk and variation in risk as a function of baseline age and family history of breast cancer after 10 years of annual screening mammography using data from the Breast Cancer Surveillance Consortium. Ignoring potential dependent censoring in this context leads to underestimation of the cumulative risk of false-positive results. Models that provide accurate estimates under dependent censoring are critical for providing appropriate information for evaluating screening tests.",
keywords = "Dependent censoring, False-positive, Mammography, Screening",
author = "Hubbard, {Rebecca A.} and Miglioretti, {Diana L}",
year = "2013",
month = "3",
doi = "10.1111/j.1541-0420.2012.01831.x",
language = "English (US)",
volume = "69",
pages = "245--253",
journal = "Biometrics",
issn = "0006-341X",
publisher = "Wiley-Blackwell",
number = "1",

}

TY - JOUR

T1 - A Semiparametric Censoring Bias Model for Estimating the Cumulative Risk of a False-Positive Screening Test Under Dependent Censoring

AU - Hubbard, Rebecca A.

AU - Miglioretti, Diana L

PY - 2013/3

Y1 - 2013/3

N2 - False-positive test results are among the most common harms of screening tests and may lead to more invasive and expensive diagnostic testing procedures. Estimating the cumulative risk of a false-positive screening test result after repeat screening rounds is, therefore, important for evaluating potential screening regimens. Existing estimators of the cumulative false-positive risk are limited by strong assumptions about censoring mechanisms and parametric assumptions about variation in risk across screening rounds. To address these limitations, we propose a semiparametric censoring bias model for cumulative false-positive risk that allows for dependent censoring without specifying a fixed functional form for variation in risk across screening rounds. Simulation studies demonstrated that the censoring bias model performs similarly to existing models under independent censoring and can largely eliminate bias under dependent censoring. We used the existing and newly proposed models to estimate the cumulative false-positive risk and variation in risk as a function of baseline age and family history of breast cancer after 10 years of annual screening mammography using data from the Breast Cancer Surveillance Consortium. Ignoring potential dependent censoring in this context leads to underestimation of the cumulative risk of false-positive results. Models that provide accurate estimates under dependent censoring are critical for providing appropriate information for evaluating screening tests.

AB - False-positive test results are among the most common harms of screening tests and may lead to more invasive and expensive diagnostic testing procedures. Estimating the cumulative risk of a false-positive screening test result after repeat screening rounds is, therefore, important for evaluating potential screening regimens. Existing estimators of the cumulative false-positive risk are limited by strong assumptions about censoring mechanisms and parametric assumptions about variation in risk across screening rounds. To address these limitations, we propose a semiparametric censoring bias model for cumulative false-positive risk that allows for dependent censoring without specifying a fixed functional form for variation in risk across screening rounds. Simulation studies demonstrated that the censoring bias model performs similarly to existing models under independent censoring and can largely eliminate bias under dependent censoring. We used the existing and newly proposed models to estimate the cumulative false-positive risk and variation in risk as a function of baseline age and family history of breast cancer after 10 years of annual screening mammography using data from the Breast Cancer Surveillance Consortium. Ignoring potential dependent censoring in this context leads to underestimation of the cumulative risk of false-positive results. Models that provide accurate estimates under dependent censoring are critical for providing appropriate information for evaluating screening tests.

KW - Dependent censoring

KW - False-positive

KW - Mammography

KW - Screening

UR - http://www.scopus.com/inward/record.url?scp=84875937252&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875937252&partnerID=8YFLogxK

U2 - 10.1111/j.1541-0420.2012.01831.x

DO - 10.1111/j.1541-0420.2012.01831.x

M3 - Article

C2 - 23383717

AN - SCOPUS:84875937252

VL - 69

SP - 245

EP - 253

JO - Biometrics

JF - Biometrics

SN - 0006-341X

IS - 1

ER -