Cox model with interval-censored covariate in cohort studies

Soohyun Ahn, Johan Lim, Myunghee Cho Paik, Ralph L Sacco, Mitchell S. Elkind

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In cohort studies the outcome is often time to a particular event, and subjects are followed at regular intervals. Periodic visits may also monitor a secondary irreversible event influencing the event of primary interest, and a significant proportion of subjects develop the secondary event over the period of follow-up. The status of the secondary event serves as a time-varying covariate, but is recorded only at the times of the scheduled visits, generating incomplete time-varying covariates. While information on a typical time-varying covariate is missing for entire follow-up period except the visiting times, the status of the secondary event are unavailable only between visits where the status has changed, thus interval-censored. One may view interval-censored covariate of the secondary event status as missing time-varying covariates, yet missingness is partial since partial information is provided throughout the follow-up period. Current practice of using the latest observed status produces biased estimators, and the existing missing covariate techniques cannot accommodate the special feature of missingness due to interval censoring. To handle interval-censored covariates in the Cox proportional hazards model, we propose an available-data estimator, a doubly robust-type estimator as well as the maximum likelihood estimator via EM algorithm and present their asymptotic properties. We also present practical approaches that are valid. We demonstrate the proposed methods using our motivating example from the Northern Manhattan Study.

Original languageEnglish (US)
JournalBiometrical Journal
DOIs
StateAccepted/In press - Jan 1 2018

Fingerprint

Cohort Study
Cox Model
Covariates
Time-varying Covariates
Interval
Missing Covariates
Estimator
Interval Censoring
Cox Proportional Hazards Model
Partial Information
EM Algorithm
Cohort study
Cox model
Maximum Likelihood Estimator
Asymptotic Properties
Biased
Monitor
Proportion
Entire
Valid

Keywords

  • Cohort study
  • Cox model
  • Interval-censored covariates
  • Missing time-varying covariate

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Cox model with interval-censored covariate in cohort studies. / Ahn, Soohyun; Lim, Johan; Paik, Myunghee Cho; Sacco, Ralph L; Elkind, Mitchell S.

In: Biometrical Journal, 01.01.2018.

Research output: Contribution to journalArticle

Ahn, Soohyun ; Lim, Johan ; Paik, Myunghee Cho ; Sacco, Ralph L ; Elkind, Mitchell S. / Cox model with interval-censored covariate in cohort studies. In: Biometrical Journal. 2018.
@article{31f14c4b2322410aadaac476057386fa,
title = "Cox model with interval-censored covariate in cohort studies",
abstract = "In cohort studies the outcome is often time to a particular event, and subjects are followed at regular intervals. Periodic visits may also monitor a secondary irreversible event influencing the event of primary interest, and a significant proportion of subjects develop the secondary event over the period of follow-up. The status of the secondary event serves as a time-varying covariate, but is recorded only at the times of the scheduled visits, generating incomplete time-varying covariates. While information on a typical time-varying covariate is missing for entire follow-up period except the visiting times, the status of the secondary event are unavailable only between visits where the status has changed, thus interval-censored. One may view interval-censored covariate of the secondary event status as missing time-varying covariates, yet missingness is partial since partial information is provided throughout the follow-up period. Current practice of using the latest observed status produces biased estimators, and the existing missing covariate techniques cannot accommodate the special feature of missingness due to interval censoring. To handle interval-censored covariates in the Cox proportional hazards model, we propose an available-data estimator, a doubly robust-type estimator as well as the maximum likelihood estimator via EM algorithm and present their asymptotic properties. We also present practical approaches that are valid. We demonstrate the proposed methods using our motivating example from the Northern Manhattan Study.",
keywords = "Cohort study, Cox model, Interval-censored covariates, Missing time-varying covariate",
author = "Soohyun Ahn and Johan Lim and Paik, {Myunghee Cho} and Sacco, {Ralph L} and Elkind, {Mitchell S.}",
year = "2018",
month = "1",
day = "1",
doi = "10.1002/bimj.201700090",
language = "English (US)",
journal = "Biometrical Journal",
issn = "0323-3847",
publisher = "Wiley-VCH Verlag",

}

TY - JOUR

T1 - Cox model with interval-censored covariate in cohort studies

AU - Ahn, Soohyun

AU - Lim, Johan

AU - Paik, Myunghee Cho

AU - Sacco, Ralph L

AU - Elkind, Mitchell S.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In cohort studies the outcome is often time to a particular event, and subjects are followed at regular intervals. Periodic visits may also monitor a secondary irreversible event influencing the event of primary interest, and a significant proportion of subjects develop the secondary event over the period of follow-up. The status of the secondary event serves as a time-varying covariate, but is recorded only at the times of the scheduled visits, generating incomplete time-varying covariates. While information on a typical time-varying covariate is missing for entire follow-up period except the visiting times, the status of the secondary event are unavailable only between visits where the status has changed, thus interval-censored. One may view interval-censored covariate of the secondary event status as missing time-varying covariates, yet missingness is partial since partial information is provided throughout the follow-up period. Current practice of using the latest observed status produces biased estimators, and the existing missing covariate techniques cannot accommodate the special feature of missingness due to interval censoring. To handle interval-censored covariates in the Cox proportional hazards model, we propose an available-data estimator, a doubly robust-type estimator as well as the maximum likelihood estimator via EM algorithm and present their asymptotic properties. We also present practical approaches that are valid. We demonstrate the proposed methods using our motivating example from the Northern Manhattan Study.

AB - In cohort studies the outcome is often time to a particular event, and subjects are followed at regular intervals. Periodic visits may also monitor a secondary irreversible event influencing the event of primary interest, and a significant proportion of subjects develop the secondary event over the period of follow-up. The status of the secondary event serves as a time-varying covariate, but is recorded only at the times of the scheduled visits, generating incomplete time-varying covariates. While information on a typical time-varying covariate is missing for entire follow-up period except the visiting times, the status of the secondary event are unavailable only between visits where the status has changed, thus interval-censored. One may view interval-censored covariate of the secondary event status as missing time-varying covariates, yet missingness is partial since partial information is provided throughout the follow-up period. Current practice of using the latest observed status produces biased estimators, and the existing missing covariate techniques cannot accommodate the special feature of missingness due to interval censoring. To handle interval-censored covariates in the Cox proportional hazards model, we propose an available-data estimator, a doubly robust-type estimator as well as the maximum likelihood estimator via EM algorithm and present their asymptotic properties. We also present practical approaches that are valid. We demonstrate the proposed methods using our motivating example from the Northern Manhattan Study.

KW - Cohort study

KW - Cox model

KW - Interval-censored covariates

KW - Missing time-varying covariate

UR - http://www.scopus.com/inward/record.url?scp=85047472586&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047472586&partnerID=8YFLogxK

U2 - 10.1002/bimj.201700090

DO - 10.1002/bimj.201700090

M3 - Article

JO - Biometrical Journal

JF - Biometrical Journal

SN - 0323-3847

ER -