Assessing Evidence Inconsistency in Mixed Treatment Comparisons

By Guobing Lu, A. Ades. 2006

752 citations recorded by the source corpus.

Randomized comparisons among several treatments give rise to an incomplete-blocks structure known as mixed treatment comparisons (MTCs). To analyze such data structures, it is crucial to assess whether the disparate evidence sources provide consistent information about the treatment contrasts. In this article we propose a general method for assessing evidence inconsistency in the framework of Bayesian hierarchical models. We begin with the distinction between basic parameters, which have prior distributions, and functional parameters, which are defined in terms of basic parameters. Based on a graphical analysis of MTC structures, evidence inconsistency is defined as a relation between a functional parameter and at least two basic parameters, supported by at least three evidence sources. The inconsistency degrees of freedom (ICDF) is the number of such inconsistencies. We represent evidence consistency as a set of linear relations between effect parameters on the log odds ratio scale, then relax these relations to allow for inconsistency by adding to the model random inconsistency factors (ICFs). The number of ICFs is determined by the ICDF. The overall consistency between evidence sources can be assessed by comparing models with and without ICFs, whereas their posterior distribution reflects the extent of inconsistency in particular evidence cycles. The methods are elucidated using two published datasets, implemented with standard Markov chain Monte Carlo software.

Subfields: Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/436b4edebabeb8816a5610b41c39f7b4dcd20e17

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

Citations in the corpus

Conducting indirect-treatment-comparison and network-meta-analysis studies: report of the ISPOR Task Force on Indirect Treatment Comparisons Good Research Practices: part 2. (2011, background): “13] Lu G, Ades AE.”
GetReal in network meta‐analysis: a review of the methodology (2016, background): “Their difference measures inconsistency and is usually termed inconsistency factor (Lu and Ades, 2006): bwABC ¼ bμDirBC bμ IndBC , with variance var bwABCð Þ ¼ var bμ IndBC þ var bμDirBC .”
Network Meta-analysis (2015, methodology): “I demonstrate the network package using the smoking data (Lu and Ades 2006), starting with the data in wide format, with study and trt as identiﬁers, d containing the number of events, and n containing the total number.”
CINeMA: An approach for assessing confidence in the results of a network meta-analysis (2020, background): “Incoherence is the statistical manifestation of intransitivity; if transitivity holds, the direct and indirect evidence should be in agreement and coherent [50,51].”
Automated generation of node‐splitting models for assessment of inconsistency in network meta‐analysis (2015, methodology): “This problem was pointed out earlier for loop inconsistency models (Lu and Ades, 2006).”
Network Meta-Analysis Using R: A Review of Currently Available Automated Packages (2014, background): “Methods have been proposed to account for inconsistency if suspected [14].”
A graphical tool for locating inconsistency in network meta-analyses (2013, methodology): “Since the start and end point for different alternative network paths are the same, inconsistency can only be detected in such network loops [8,9].”
Is network meta-analysis as valid as standard pairwise meta-analysis? It all depends on the distribution of effect modifiers (2013, methodology): “However, when indirect evidence can wash out trial-specific biases that are sometimes not identifiable in a head-to-head meta-analysis, indirect estimates obtained with a network meta-analysis might be preferable [19,20].”
Network meta-analysis: application and practice using R software (2019, methodology): “The loop inconsistency is based on Lu & Ades [6], and the design inconsistency was approached through meta-regression analysis of the difference between study designs.”
Automating network meta‐analysis (2012, methodology): “In the Bayesian framework, an MTC is implemented as a BHM and estimated using MCMC simulation (Lu and Ades, 2006; Salanti et al ., 2008).”
Conceptual and Technical Challenges in Network Meta-analysis (2013, background): “Consistency in a network meta-analysis can be evaluated statistically by comparing the direct and indirect summary effects in specific loops (8, 18) or across a network by fitting models that allow and do not allow for inconsistency (4, 23, 24).”
Conducting quantitative synthesis when comparing medical interventions: AHRQ and the Effective Health Care Program. (2011, methodology): “MTM models provide the ability to check and quantify consistency or coherence of evidence for complex networks [12,13,22,23].”
Evaluating the Quality of Evidence from a Network Meta-Analysis (2014, background): “An alternative to a test is to estimate a global inconsistency parameter, such as the variance of the differences between direct and indirect evidence as described by Lu and Ades [28].”