posted on 2019-04-17, 13:41authored byR Owen, NJ Cooper, T Quinn, A Sutton
Objectives
Network meta-analyses have extensively been used to compare the effectiveness of multiple interventions for healthcare policy and decision-making. Methods for evaluating the performance of multiple diagnostic tests are less established. In a decision-making context, we are often interested in comparing and ranking the performance of multiple diagnostic tests, at varying levels of test thresholds. The aim of this research was to develop a network meta-analysis framework for evaluating multiple diagnostic tests, at varying test thresholds in one simultaneous analysis.
Methods
Motivated by an example of cognitive impairment diagnosis following stroke, we synthesized data from 13 studies assessing the efficiency of two diagnostic tests: Mini-Mental State Examination (MMSE) and Montreal Cognitive Assessment (MoCA), at two test thresholds: MMSE <25/30 and <27/30, and MoCA <22/30 and <26/30. Using Markov Chain Monte Carlo (MCMC) methods, we fitted a bivariate network meta-analysis model, accounting for the correlations between multiple test accuracy measures from the same study, and incorporating constraints on increasing test thresholds assuming that higher test thresholds had an increased sensitivity but decreased specificity.
Results
We developed and successfully fitted a model comparing multiple tests/threshold combinations while imposing threshold constraints. Applying constraints on increasing test thresholds reduced the within-study variability and increased the precision in estimates of sensitivity and specificity. Using this model, we found that MoCA at threshold <26/30 appeared to have the best true positive rate (estimated sensitivity: 0.98; 95% credible interval (CrI): 0.94,0.99), whilst MMSE at threshold <25/30 appeared to have the best true negative rate (estimated specificity: 0.84, 95%CrI: 0.79,0.88).
Conclusions
In a health technology assessment setting, there is an increasing need to compare the efficiency of multiple diagnostics tests. The combined analysis of multiple tests at multiple thresholds allowed for more rigorous comparisons between competing diagnostics tests for decision-making.
Funding
The Complex Reviews Support Unit (CRSU) is funded by the National Institute for Health
Research (project number 14/178/29).
History
Citation
Value in Health, 2018, 21, pp. S10-S10 (1)
Author affiliation
/Organisation/COLLEGE OF LIFE SCIENCES/School of Medicine/Department of Health Sciences
Version
AM (Accepted Manuscript)
Published in
Value in Health
Publisher
Elsevier for International Society for Pharmacoeconomics and Outcomes Research
The file associated with this record is under embargo until 12 months after publication, in accordance with the publisher's self-archiving policy. The full text may be available through the publisher links provided above.