Dataset Information

Estimating treatment effects in observational studies with both prevalent and incident cohorts.

ABSTRACT: Registry databases are increasingly being used for comparative effectiveness research in cancer. Such databases reflect the real-world patient population and physician practice, and thus are natural sources for comparing multiple treatment scenarios and the associated long-term clinical outcomes. Registry databases usually include both incident and prevalent cohorts, which provide valuable complementary information for patients with more recent diagnoses in the incident cohort as well as patients with long-term follow-up data in the prevalent cohort. However, utilizing such data to derive valid inference poses two major challenges: the data from a prevalent cohort are not random samples of the target population, and there may be substantial differences in the baseline characteristics of patients between treatment arms, which influences the decisions about treatment selection in both cohorts. In this article, we extend propensity score methodology to observational studies that involve both prevalent and incident cohorts, and assess the effectiveness of radiation therapy in SEER-Medicare patients diagnosed with stage IV breast cancer. Specifically, we utilize the incident cohort to estimate the propensity for receiving radiation therapy, and then combine data from both the incident and prevalent cohorts to estimate the effect of radiation therapy by adjusting for the propensity scores in the model. We evaluate the proposed method with simulations. We demonstrate that the proposed propensity score method simultaneously removes sampling bias and selection bias under several assumptions.

SUBMITTER: Ning J

PROVIDER: S-EPMC5646711 | biostudies-literature | 2017 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Estimating treatment effects in observational studies with both prevalent and incident cohorts.

Ning Jing J Hong Chuan C Li Liang L Huang Xuelin X Shen Yu Y

The Canadian journal of statistics = Revue canadienne de statistique 20170413 2

Registry databases are increasingly being used for comparative effectiveness research in cancer. Such databases reflect the real-world patient population and physician practice, and thus are natural sources for comparing multiple treatment scenarios and the associated long-term clinical outcomes. Registry databases usually include both incident and prevalent cohorts, which provide valuable complementary information for patients with more recent diagnoses in the incident cohort as well as patient ...[more]

PMID: 29056817

Similar Datasets

Project description:Clinical studies aimed at identifying effective treatments to reduce the risk of disease or death often require long term follow-up of participants in order to observe a sufficient number of events to precisely estimate the treatment effect. In such studies, observing the outcome of interest during follow-up may be difficult and high rates of censoring may be observed which often leads to reduced power when applying straightforward statistical methods developed for time-to-event data. Alternative methods have been proposed to take advantage of auxiliary information that may potentially improve efficiency when estimating marginal survival and improve power when testing for a treatment effect. Recently, Parast et al. (J Am Stat Assoc 109(505):384-394, 2014) proposed a landmark estimation procedure for the estimation of survival and treatment effects in a randomized clinical trial setting and demonstrated that significant gains in efficiency and power could be obtained by incorporating intermediate event information as well as baseline covariates. However, the procedure requires the assumption that the potential outcomes for each individual under treatment and control are independent of treatment group assignment which is unlikely to hold in an observational study setting. In this paper we develop the landmark estimation procedure for use in an observational setting. In particular, we incorporate inverse probability of treatment weights (IPTW) in the landmark estimation procedure to account for selection bias on observed baseline (pretreatment) covariates. We demonstrate that consistent estimates of survival and treatment effects can be obtained by using IPTW and that there is improved efficiency by using auxiliary intermediate event and baseline information. We compare our proposed estimates to those obtained using the Kaplan-Meier estimator, the original landmark estimation procedure, and the IPTW Kaplan-Meier estimator. We illustrate our resulting reduction in bias and gains in efficiency through a simulation study and apply our procedure to an AIDS dataset to examine the effect of previous antiretroviral therapy on survival.

Project description:Background and objectivesKidney disease is associated with physiologic changes that may predispose to frailty. This study sought to investigate whether lower levels of kidney function were associated with prevalent or incident frailty in Cardiovascular Health Study (CHS) participants.Design, setting, participants, & measurementsCHS enrolled community-dwelling adults age ≥65 years between 1989-1990 and 1992-1993. To examine prevalent frailty, included were 4150 participants without stroke, Parkinson disease, prescribed medications for Alzheimer disease or depression, or severely impaired cognition. To examine incident frailty, included were a subset of 3459 participants without baseline frailty or development of exclusion criteria during follow-up. The primary predictor was estimated GFR (eGFR) calculated using serum cystatin C (eGFR(cys)). Secondary analyses examined eGFR using serum creatinine (eGFR(SCr)). Outcomes were prevalent frailty and incident frailty at 4 years of follow-up. Frailty was ascertained on the basis of weight loss, exhaustion, weakness, slowness, and low physical activity.ResultsThe mean age was 75 years and the median eGFR(cys) was 73 ml/min per 1.73 m(2). Among participants with an eGFR(cys) <45 ml/min per 1.73 m(2), 24% had prevalent frailty. In multivariable analysis and compared with eGFR(cys) ≥90 ml/min per 1.73 m(2), eGFR(cys) categories of 45-59 (odds ratio [OR], 1.80; 95% confidence interval [CI], 1.17 to 2.75) and 15-44 (OR, 2.87; 95% CI, 1.72 to 4.77) were associated with higher odds of frailty, whereas 60-75 (OR, 1.14; 95% CI, 0.76 to 1.70) was not. In multivariable analysis, eGFR(cys) categories of 60-75 (incidence rate ratio [IRR], 1.72; 95% CI, 1.07 to 2.75) and 15-44 (IRR, 2.28; 95% CI, 1.23 to 4.22) were associated with higher incidence of frailty whereas 45-59 (IRR, 1.53; 95% CI, 0.90 to 2.60) was not. Lower levels of eGFR(SCr) were not associated with higher risk of prevalent or incident frailty.ConclusionsIn community-dwelling elders, lower eGFR(cys) was associated with a higher risk of prevalent and incident frailty whereas lower eGFR(SCr) was not. These findings highlight the importance of considering non-GFR determinants of kidney function.

Dataset Information

Estimating treatment effects in observational studies with both prevalent and incident cohorts.

Publications

Estimating treatment effects in observational studies with both prevalent and incident cohorts.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets