Time-dependent ROC analysis for censored biomarker data due to limit of detection

Yeonhee Kim, Lan Kong

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Receiver operating characteristic (ROC) curve is a well-established analysis method to evaluate biomarker’s discrimination accuracy for binary outcomes. When the endpoint of interest is time to event outcome such as time to cancer recurrence, a biomarker’s time-varying discriminatory performance is often assessed by time-dependent ROC analysis. In practice, biomarkers are often imprecisely measured due to the limitation of assay sensitivity. The values below the limit of detection are not detectable. Ignorance of such data characteristic may lead to inaccurate estimation of marker’s potential discriminatory power. The objective of this article is to extend time-dependent ROC method to censored biomarker data by using parameter estimates from the Cox regression model that accommodates censored biomarker measurements. In the simulation study, the proposed methods are shown to outperform the simple substitution method that has been conventionally adopted for handling censored data. Application data are also given to illustrate our methods.

Original languageEnglish (US)
Pages (from-to)612-621
Number of pages10
JournalJournal of Biopharmaceutical Statistics
Volume28
Issue number4
DOIs
StatePublished - Jul 4 2018

Fingerprint

Operating Characteristics
Biomarkers
ROC Curve
Limit of Detection
Receiver
Cox Regression Model
Characteristics Method
Binary Outcomes
Receiver Operating Characteristic Curve
Censored Data
Inaccurate
Proportional Hazards Models
Recurrence
Discrimination
Substitution
Time-varying
Cancer
Simulation Study
Evaluate
Estimate

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Pharmacology
  • Pharmacology (medical)

Cite this

@article{e181e099bb4a47beacf2f60ef765d3fb,
title = "Time-dependent ROC analysis for censored biomarker data due to limit of detection",
abstract = "Receiver operating characteristic (ROC) curve is a well-established analysis method to evaluate biomarker’s discrimination accuracy for binary outcomes. When the endpoint of interest is time to event outcome such as time to cancer recurrence, a biomarker’s time-varying discriminatory performance is often assessed by time-dependent ROC analysis. In practice, biomarkers are often imprecisely measured due to the limitation of assay sensitivity. The values below the limit of detection are not detectable. Ignorance of such data characteristic may lead to inaccurate estimation of marker’s potential discriminatory power. The objective of this article is to extend time-dependent ROC method to censored biomarker data by using parameter estimates from the Cox regression model that accommodates censored biomarker measurements. In the simulation study, the proposed methods are shown to outperform the simple substitution method that has been conventionally adopted for handling censored data. Application data are also given to illustrate our methods.",
author = "Yeonhee Kim and Lan Kong",
year = "2018",
month = "7",
day = "4",
doi = "10.1080/10543406.2017.1372768",
language = "English (US)",
volume = "28",
pages = "612--621",
journal = "Journal of Biopharmaceutical Statistics",
issn = "1054-3406",
publisher = "Taylor and Francis Ltd.",
number = "4",

}

Time-dependent ROC analysis for censored biomarker data due to limit of detection. / Kim, Yeonhee; Kong, Lan.

In: Journal of Biopharmaceutical Statistics, Vol. 28, No. 4, 04.07.2018, p. 612-621.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Time-dependent ROC analysis for censored biomarker data due to limit of detection

AU - Kim, Yeonhee

AU - Kong, Lan

PY - 2018/7/4

Y1 - 2018/7/4

N2 - Receiver operating characteristic (ROC) curve is a well-established analysis method to evaluate biomarker’s discrimination accuracy for binary outcomes. When the endpoint of interest is time to event outcome such as time to cancer recurrence, a biomarker’s time-varying discriminatory performance is often assessed by time-dependent ROC analysis. In practice, biomarkers are often imprecisely measured due to the limitation of assay sensitivity. The values below the limit of detection are not detectable. Ignorance of such data characteristic may lead to inaccurate estimation of marker’s potential discriminatory power. The objective of this article is to extend time-dependent ROC method to censored biomarker data by using parameter estimates from the Cox regression model that accommodates censored biomarker measurements. In the simulation study, the proposed methods are shown to outperform the simple substitution method that has been conventionally adopted for handling censored data. Application data are also given to illustrate our methods.

AB - Receiver operating characteristic (ROC) curve is a well-established analysis method to evaluate biomarker’s discrimination accuracy for binary outcomes. When the endpoint of interest is time to event outcome such as time to cancer recurrence, a biomarker’s time-varying discriminatory performance is often assessed by time-dependent ROC analysis. In practice, biomarkers are often imprecisely measured due to the limitation of assay sensitivity. The values below the limit of detection are not detectable. Ignorance of such data characteristic may lead to inaccurate estimation of marker’s potential discriminatory power. The objective of this article is to extend time-dependent ROC method to censored biomarker data by using parameter estimates from the Cox regression model that accommodates censored biomarker measurements. In the simulation study, the proposed methods are shown to outperform the simple substitution method that has been conventionally adopted for handling censored data. Application data are also given to illustrate our methods.

UR - http://www.scopus.com/inward/record.url?scp=85030570997&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030570997&partnerID=8YFLogxK

U2 - 10.1080/10543406.2017.1372768

DO - 10.1080/10543406.2017.1372768

M3 - Article

C2 - 28862526

AN - SCOPUS:85030570997

VL - 28

SP - 612

EP - 621

JO - Journal of Biopharmaceutical Statistics

JF - Journal of Biopharmaceutical Statistics

SN - 1054-3406

IS - 4

ER -