Quantifying indirect evidence in network meta-analysis

Area of Science:

• Biostatistics
• Evidence Synthesis
• Comparative Effectiveness Research

Background:

• Network meta-analysis (NMA) synthesizes evidence from multiple studies comparing various treatments.
• Assessing the consistency between direct and indirect evidence is crucial for reliable NMA results.
• Inconsistencies can arise from differing evidence sources, potentially biasing treatment effect estimates.

Purpose of the Study:

• To develop an efficient method for quantifying indirect evidence in NMA.
• To introduce a testing procedure for evaluating the consistency of direct and indirect evidence.
• To assess the contribution of direct and indirect evidence to overall treatment effect estimates.

Main Methods:

• Developed an efficient method to quantify indirect evidence.
• Employed Lindsay's composite likelihood method for inconsistency testing.
• Utilized the developed method to assess consistency and contribution rates of evidence.

Main Results:

• The proposed method quantifies indirect evidence and tests for inconsistencies effectively.
• The estimator provides complete information regarding indirect evidence.
• The method allows for sensitivity analyses to evaluate the impact of inconsistent contrasts on overall results.

Conclusions:

• The developed methods enhance the reliability of comparative treatment effect estimates in NMA.
• These tools aid in identifying and managing potential biases arising from inconsistent evidence.
• The approach is validated through simulation studies and applied to antidepressant NMA.