A review of published analyses of case-cohort studies and recommendations for future reporting.

Stephen J Sharp,Simon G Thompson,Manon Poulaliou,Angela M Wood,Ian R White,Joel Joseph Gagnier

doi:10.1371/journal.pone.0101176

Abstract

The case-cohort study design combines the advantages of a cohort study with the efficiency of a nested case-control study. However, unlike more standard observational study designs, there are currently no guidelines for reporting results from case-cohort studies. Our aim was to review recent practice in reporting these studies, and develop recommendations for the future. By searching papers published in 24 major medical and epidemiological journals between January 2010 and March 2013 using PubMed, Scopus and Web of Knowledge, we identified 32 papers reporting case-cohort studies. The median subcohort sampling fraction was 4.1% (interquartile range 3.7% to 9.1%). The papers varied in their approaches to describing the numbers of individuals in the original cohort and the subcohort, presenting descriptive data, and in the level of detail provided about the statistical methods used, so it was not always possible to be sure that appropriate analyses had been conducted. Based on the findings of our review, we make recommendations about reporting of the study design, subcohort definition, numbers of participants, descriptive information and statistical methods, which could be used alongside existing STROBE guidelines for reporting observational studies.

Highlights

The case-cohort study design was originally proposed by Prentice [1]
The process of obtaining measurements on baseline samples from individuals in the random subcohort can be initiated at any time after the original cohort has been set up, whereas in a nested case-control study the cases need to be identified before the controls can be defined and the measurement process begin
Treating each EPIC centre or grouping of centres as a separate cohort, the 32 papers were based on 17 original cohorts

Summary

Introduction

The case-cohort study design was originally proposed by Prentice [1]. Nested within a larger cohort, the study comprises a random ‘‘subcohort’’ of individuals from the original cohort (sampled irrespective of disease status), together with all cases [Figure 1]. An advantage of a case-cohort study over a nested case-control study is that the same random subcohort can be used as the comparison group for studying different diseases, rather than identifying a new set of controls for each disease. The process of obtaining measurements on baseline samples from individuals in the random subcohort can be initiated at any time after the original cohort has been set up, whereas in a nested case-control study the cases need to be identified before the controls can be defined and the measurement process begin. Cox proportional hazards (PH) regression models need to be weighted, with cases outside the subcohort only included in the risk set at the time of their event [1]. Weighted Cox regression models can be fit using standard statistical software packages, including Stata [5] and R [6]

Objectives

Methods

Results

Conclusion