Synthesis Methods for Meta-Analysis: A Scoping Review

Meta-analysis is a statistical technique to combine and summarize prior quantitative studies to assess the impact of a specific subject or intervention. Synthesis analysis, which is derived from meta-analysis, extends meta-analysis by estimating the multivariable relationship between predictors and outcomes.

This study aims to conduct a comprehensive scoping review to identify and map the extent of available research on methodological and applied synthesis analysis across different statistical responses.

Eligible studies, such as peer-reviewed articles published in English between 2000 and 2025 that presented methodological innovations and applied examples relevant to a range of statistical outcomes, were included. Systematic searches were conducted in major databases, e.g., PubMed, Google Scholar, and Scopus. Studies lacking sufficient methodological detail or focusing primarily on non-statistical model analysis were excluded.

A total of 248 studies were identified. Among these, 10 studies met the inclusion criteria.

Synthesis analysis has advanced from simple univariable methods to advanced multivariable frameworks capable of handling incomplete, heterogeneous, and summary-only data. While these approaches improved estimation accuracy and enhanced clinical risk models, their application remains limited to mostly continuous and binary outcomes. A major gap is the absence of synthesis methods for time-to-event data, which is critical for survival analysis and clinical decision-making.

Synthesis analysis is a promising tool for integrating incomplete data, but current methods lack support for survival and complex outcomes. Future research should prioritize these extensions for broader clinical and public health impact.