Estimation Techniques

MTC (Mixed Treatment Comparison)


1. Description

MTC (Mixed Treatment Comparison) is a meta-analytic method to synthesise different pieces of evidence into a coherent set of estimates (of treatment effects).[1][2][3] MTC generalises the concept of ITC by providing a method to synthesise both direct and indirect evidence. MTC serves two purposes: to strengthen the inference on relative treatment effects by including both direct and indirect evidence; and to facilitate simultaneous inference for all treatments.

2. Evaluation

2.1 Principle
  • MTC is based on probabilities and is a meta-analytic technique.
  • MTC offers increased transparency when the sources of evidence, bias, and uncertainties from the data are documented carefully.
  • MTC can handle and quantify statistical uncertainties on the estimates of benefits and risks.
  • There is no concept of incorporating value judgements in standard MTC literature, because it is not a specific method for benefit-risk analysis.
  • MTC relies on the assumption that the direct and indirect evidence to be combined are consistent. See Dias et al. (2010) on checking consistency in MTC.[4]

2.2 Features
  • MTC borrows the strengths from related trials in a network of direct and indirect evidence of benefits and risks of treatments, where there is a common comparator.
  • Multiple criteria of benefits and risks as well as multiple treatment options can also be taken into consideration and be estimated simultaneously in a single MTC model.
  • MTC are used in combination with other benefit-risk approaches to characterise the benefit-risk profile of treatments.
  • Sensitivity analyses can be performed on the various parameters in the model

2.3 Visualisation
  • A network diagram was suggested to visualise the structure of an MTC model.
  • Visual representations of the results are dependent on the actual metric use to quantify benefits and risks.

2.4 Assessability and accessibility
  • The parameters and results from MTC analyses can be understood fairly easily without technical knowledge of the method.
  • The variance modelling and comprehension in MTC requires greater level of statistical understanding.
  • The flexibility in the application of MTC means it may be suitable to most stakeholders.
  • MTC provides decision-makers with a general and flexible technique to assess benefits and risks to support decision making when used appropriately.

This method was tested in the Natalizumab and Rimonabant case studies.

3. References

[1] Lumley T. Network meta-analysis for indirect treatment comparisons. Stat Med 2002;21(16):2313-24.
[2] Lu G, Ades AE. Combination of direct and indirect evidence in mixed treatment comparisons. Stat Med 2004;23(20):3105-24.
[3] Nixon RM, Bansback N, Brennan A. Using mixed treatment comparisons and meta-regression to perform indirect comparisons to estimate the efficacy of biologic treatments in rheumatoid arthritis. Stat Med 2007;26(6):1237-54.
[4] Dias S, Welton NJ, Caldwell DM, Ades, AE. Checking consistency in mixed treatment comparison meta-analysis. Stat Med 2010; 29(7-8):932-944.