Individual patient-versus literature-based meta-analysis of survival data: time to event and event rate at a particular time can make a difference, an example based on head and neck cancer

Abstract

The objective of this study is to compare the results of an individual patient-based and a literature-based meta-analysis in chemotherapy in head and neck cancer and to identify the sources of difference. For all head and neck cancer randomized controlled clinical trials comparing chemotherapy and loco-regional treatment with loco-regional treatment alone, both the literature data and the individual patient data are retrieved and meta-analyses performed and compared. Only survival data are used as outcome, although both time to death and mortality at specific time points are considered in different analyses. There are substantial differences between the individual patient-based and the literature-based meta-analyses. The most important reason for the differing results is that the individual patient-based meta-analysis is based on a time to event analysis, whereas the literature-based meta-analysis is based on mortality at a specific time point. Mortality can change substantially with follow-up time. The absolute survival differences in the case study, for instance, increase from 2.6% at 2 years to 5.6% at 5 years.