Adjusting for verification bias in diagnostic accuracy measures when comparing multiple screening tests - an application to the IP1-PROSTAGRAM study

TY - JOUR

T1 - Adjusting for verification bias in diagnostic accuracy measures when comparing multiple screening tests - an application to the IP1-PROSTAGRAM study

AU - Day, Emily

AU - Eldred-Evans, David

AU - Prevost, A. Toby

AU - Ahmed, Hashim U.

AU - Fiorentino, Francesca

N1 - Funding Information: The IP1-PROSTAGRAM study was funded by grant 204998/Z/16/Z from the Wellcome Trust as well as a BMA Foundation for Medical Research grant, a Urology Foundation Research Scholarship, a Royal College of Surgeons of England Research Fellowship, and a grant from UK National Institute of Health Research Imperial Biomedical Research Centre. Funding Information: HU Ahmed reported receiving grants from Wellcome Trust, the BMA Foundation for Medical Research, and The Urology Foundation during the conduct of the study and grants and personal fees from Sophiris Biocorp, Sonacare Inc., and Boston Scientific (previously Galil and BTG) and grants from Trod Medical, Prostate Cancer UK charity, NIHR, MRC (UK), Cancer Research UK charity, and Imperial Health Charity outside the submitted work. D Eldred-Evans reported receiving grants from the BMA Foundation for Medical Research, The Urology Foundation, and the Royal College of Surgeons of England during the conduct of the study; grants from Imperial Health Charity outside the submitted work. Publisher Copyright: © 2022, The Author(s).

PY - 2022/3/18

Y1 - 2022/3/18

N2 - Novel screening tests used to detect a target condition are compared against either a reference standard or other existing screening methods. However, as it is not always possible to apply the reference standard on the whole population under study, verification bias is introduced. Statistical methods exist to adjust estimates to account for this bias. We extend common methods to adjust for verification bias when multiple tests are compared to a reference standard using data from a prospective double blind screening study for prostate cancer. Begg and Greenes method and multiple imputation are extended to include the results of multiple screening tests which determine condition verification status. These two methods are compared to the complete case analysis using the IP1-PROSTAGRAM study data. IP1-PROSTAGRAM used a paired-cohort double-blind design to evaluate the use of imaging as alternative tests to screen for prostate cancer, compared to a blood test called prostate specific antigen (PSA). Participants with positive imaging (index) and/or PSA (control) underwent a prostate biopsy (reference standard). When comparing complete case results to Begg and Greenes and methods of multiple imputation there is a statistically significant increase in the specificity estimates for all screening tests. Sensitivity estimates remained similar across the methods, with completely overlapping 95% confidence intervals. Negative predictive value (NPV) estimates were higher when adjusting for verification bias, compared to complete case analysis, even though the 95% confidence intervals overlap. Positive predictive value (PPV) estimates were similar across all methods. Statistical methods are required to adjust for verification bias in accuracy estimates of screening tests. Expanding Begg and Greenes method to include multiple screening tests can be computationally intensive, hence multiple imputation is recommended, especially as it can be modified for low prevalence of the target condition. [Abstract copyright: © 2022. The Author(s).]

AB - Novel screening tests used to detect a target condition are compared against either a reference standard or other existing screening methods. However, as it is not always possible to apply the reference standard on the whole population under study, verification bias is introduced. Statistical methods exist to adjust estimates to account for this bias. We extend common methods to adjust for verification bias when multiple tests are compared to a reference standard using data from a prospective double blind screening study for prostate cancer. Begg and Greenes method and multiple imputation are extended to include the results of multiple screening tests which determine condition verification status. These two methods are compared to the complete case analysis using the IP1-PROSTAGRAM study data. IP1-PROSTAGRAM used a paired-cohort double-blind design to evaluate the use of imaging as alternative tests to screen for prostate cancer, compared to a blood test called prostate specific antigen (PSA). Participants with positive imaging (index) and/or PSA (control) underwent a prostate biopsy (reference standard). When comparing complete case results to Begg and Greenes and methods of multiple imputation there is a statistically significant increase in the specificity estimates for all screening tests. Sensitivity estimates remained similar across the methods, with completely overlapping 95% confidence intervals. Negative predictive value (NPV) estimates were higher when adjusting for verification bias, compared to complete case analysis, even though the 95% confidence intervals overlap. Positive predictive value (PPV) estimates were similar across all methods. Statistical methods are required to adjust for verification bias in accuracy estimates of screening tests. Expanding Begg and Greenes method to include multiple screening tests can be computationally intensive, hence multiple imputation is recommended, especially as it can be modified for low prevalence of the target condition. [Abstract copyright: © 2022. The Author(s).]

KW - Begg and Greenes

KW - Multiple imputation

KW - Sensitivity

KW - Specificity

KW - Verification bias

UR - http://www.scopus.com/inward/record.url?scp=85126533205&partnerID=8YFLogxK

U2 - 10.1186/s12874-021-01481-w

DO - 10.1186/s12874-021-01481-w

M3 - Article

AN - SCOPUS:85126533205

SN - 1471-2288

VL - 22

JO - BMC Medical Research Methodology

JF - BMC Medical Research Methodology

IS - 1

M1 - 70

ER -