What is it about?
When researchers combine survival rates from multiple studies in a meta-analysis, confidence intervals are needed to indicate how reliable each estimate is. However, many published studies report survival rates without providing confidence intervals. These studies are often excluded from meta-analyses, even though they contain useful information. Excluding them reduces the amount of available evidence and may lead to less reliable results. This study proposes a simple and practical method to estimate missing confidence intervals using basic information that is commonly reported, such as sample size, the number of patients at risk, and the survival rate itself. By imputing the missing confidence intervals, these studies can be included in the meta-analysis rather than discarded. Simulation studies and real-data examples show that this approach leads to more accurate and stable results than excluding studies without confidence intervals.
Featured Image
Photo by Campaign Creators on Unsplash
Why is it important?
Missing confidence intervals are a common problem in reports of survival rates, particularly in older studies and applied clinical research. When such studies are excluded from meta-analyses, important evidence may be lost, and conclusions may become less precise. This work is important because it offers a simple and transparent solution that allows more studies to be included without relying on complex statistical models. By making better use of existing data, the proposed method can improve the reliability of evidence synthesis and support more informed decision-making in medicine and public health.
Perspectives
In my own work on meta-analyses of survival outcomes, I frequently encountered studies that reported survival rates but did not provide confidence intervals. Excluding these studies always felt unsatisfactory, especially when the data were otherwise informative. This study was motivated by the need for a practical solution that researchers can easily apply in real-world evidence synthesis. We deliberately focused on simplicity and usability rather than methodological complexity. I hope this work helps researchers make fuller use of existing survival data and encourages clearer reporting of confidence intervals in future studies.
Kazushi Maruo
University of Tsukuba
Read the Original
This page is a summary of: Simple imputation method for meta-analysis of survival rates when precision information is missing, Research Synthesis Methods, September 2025, Cambridge University Press,
DOI: 10.1017/rsm.2025.10024.
You can read the full text:
Contributors
The following have contributed to this page
