Meta-analysis Of Test Accuracy Studies Research Articles

On estimating a constrained bivariate random effects model for meta-analysis of test accuracy studies.

Tailored meta-analysis uses setting-specific knowledge for the test positive rate and disease prevalence to constrain the possible values for a test's sensitivity and specificity. The constrained region is used to select those studies relevant to the setting for meta-analysis using an unconstrained bivariate random effects model (BRM). However, sometimes there may be no studies to aggregate, or the summary estimate may lie outside the plausible or “applicable” region. Potentially these shortcomings may be overcome by incorporating the constraints in the BRM to produce a constrained model. Using a penalised likelihood approach we developed an optimisation algorithm based on co-ordinate ascent and Newton-Raphson iteration to fit a constrained bivariate random effects model (CBRM) for meta-analysis. Using numerical examples based on simulation studies and real datasets we compared its performance with the BRM in terms of bias, mean squared error and coverage probability. We also determined the ‘closeness’ of the estimates to their true values using the Euclidian and Mahalanobis distances. The CBRM produced estimates which in the majority of cases had lower absolute mean bias and greater coverage probability than the BRM. The estimated sensitivities and specificity for the CBRM were, in general, closer to the true values than the BRM. For the two real datasets, the CBRM produced estimates which were in the applicable region in contrast to the BRM. When combining setting-specific data with test accuracy meta-analysis, a constrained model is more likely to yield a plausible estimate for the sensitivity and specificity in the practice setting than an unconstrained model.

Cost-effectiveness of testing for latent tuberculosis infection in people with HIV.

The aim of this study was to estimate the cost-effectiveness of screening strategies for predicting LTBI that progresses to active tuberculosis (TB) in people with HIV. We developed a decision-analytical model that constituted a decision tree covering diagnosis of LTBI and a Markov model covering progression to active TB. The model represents the lifetime experience following testing for LTBI, and discounting costs, and benefits at 3.5% per annum in line with UK standards. We undertook probabilistic and one-way sensitivity analyses. UK National Health Service and Personal Social Service perspective in a primary care setting. Hypothetical cohort of adults recently diagnosed with HIV. Interferon-gamma release assays and tuberculin skin test. Cost per quality-adjusted life year (QALY). All strategies except T-SPOT.TB were cost-effective at identifying LTBI, with the QFT-GIT-negative followed by TST5mm strategy being the most costly and effective. Results indicated that there was little preference between strategies at a willingness-to-pay threshold of £20 000. At thresholds above £40 000 per QALY, there was a clear preference for the QFT-GIT-negative followed by TST5mm, with a probability of 0.41 of being cost-effective. Results showed that specificity for QFT-GIT and TST5mm were the main drivers of the economic model. Screening for LTBI has important public health and clinical benefits. Most of the strategies are cost-effective. These results should be interpreted with caution because of the paucity of studies included in the meta-analysis of test accuracy studies. Additional high-quality primary studies are needed to have a definitive answer about, which strategy is the most effective.

A pseudo-likelihood approach for multivariate meta-analysis of test accuracy studies with multiple thresholds.

Multivariate meta-analysis of test accuracy studies when tests are evaluated in terms of sensitivity and specificity at more than one threshold represents an effective way to synthesize results by fully exploiting the data, if compared to univariate meta-analyses performed at each threshold independently. The approximation of logit transformations of sensitivities and specificities at different thresholds through a normal multivariate random-effects model is a recent proposal that straightforwardly extends the bivariate models well recommended for the one threshold case. However, drawbacks of the approach, such as poor estimation of the within-study correlations between sensitivities and between specificities, and severe computational issues can make it unappealing. We propose an alternative method for inference on common diagnostic measures using a pseudo-likelihood constructed under a working independence assumption between sensitivities and between specificities at different thresholds in the same study. The method does not require within-study correlations, overcomes the convergence issues and can be effortlessly implemented. Simulation studies highlight a satisfactory performance of the method, remarkably improving the results from the multivariate normal counterpart under different scenarios. The pseudo-likelihood approach is illustrated in the evaluation of a test used for diagnosis of preeclampsia as a cause of maternal and perinatal morbidity and mortality.

The accuracy of haemoglobin A1c as a screening and diagnostic test for gestational diabetes: a systematic review and meta-analysis of test accuracy studies.

Gestational diabetes mellitus (GDM) is associated with adverse pregnancy complications. Accurate screening and diagnosis of gestational diabetes are critical to treatment, and in a pandemic scenario like coronavirus disease 2019 needing a simple test that minimises prolonged hospital stay. We undertook a meta-analysis on the screening and diagnostic accuracy of the haemoglobin A1c (HbA1c) test in women with and without risk factors for gestational diabetes. Unlike the oral glucose tolerance test, the HbA1c test is simple, quick and more acceptable. There is a growing body of evidence on the accuracy of HbA1c as a screening and diagnostic test for GDM. We searched Medline, Embase and Cochrane Library and selected relevant studies. Accuracy data for different thresholds within the final 23 included studies (16 921 women) were pooled using a multiple thresholds model. Summary accuracy indices were estimated by selecting an optimal threshold that optimises either sensitivity or specificity according to different scenarios. HbA1c is more useful as a specific test at a cut-off of 5.7% (39 mmol/mol) with a false positive rate of 10%, but should be supplemented by a more sensitive test to detect women with GDM.

Maximum likelihood estimation based on Newton-Raphson iteration for the bivariate random effects model in test accuracy meta-analysis.

A bivariate generalised linear mixed model is often used for meta-analysis of test accuracy studies. The model is complex and requires five parameters to be estimated. As there is no closed form for the likelihood function for the model, maximum likelihood estimates for the parameters have to be obtained numerically. Although generic functions have emerged which may estimate the parameters in these models, they remain opaque to many. From first principles we demonstrate how the maximum likelihood estimates for the parameters may be obtained using two methods based on Newton–Raphson iteration. The first uses the profile likelihood and the second uses the Observed Fisher Information. As convergence may depend on the proximity of the initial estimates to the global maximum, each algorithm includes a method for obtaining robust initial estimates. A simulation study was used to evaluate the algorithms and compare their performance with the generic generalised linear mixed model function glmer from the lme4 package in R before applying them to two meta-analyses from the literature. In general, the two algorithms had higher convergence rates and coverage probabilities than glmer. Based on its performance characteristics the method of profiling is recommended for fitting the bivariate generalised linear mixed model for meta-analysis.

A double SIMEX approach for bivariate random-effects meta-analysis of diagnostic accuracy studies

BackgroundBivariate random-effects models represent a widely accepted and recommended approach for meta-analysis of test accuracy studies. Standard likelihood methods routinely used for inference are prone to several drawbacks. Small sample size can give rise to unreliable inferential conclusions and convergence issues make the approach unappealing. This paper suggests a different methodology to address such difficulties.MethodsA SIMEX methodology is proposed. The method is a simulation-based technique originally developed as a correction strategy within the measurement error literature. It suits the meta-analysis framework as the diagnostic accuracy measures provided by each study are prone to measurement error. SIMEX can be straightforwardly adapted to cover different measurement error structures and to deal with covariates. The effortless implementation with standard software is an interesting feature of the method.ResultsExtensive simulation studies highlight the improvement provided by SIMEX over likelihood approach in terms of empirical coverage probabilities of confidence intervals under different scenarios, independently of the sample size and the values of the correlation between sensitivity and specificity. A remarkable amelioration is obtained in case of deviations from the normality assumption for the random-effects distribution. From a computational point of view, the application of SIMEX is shown to be neither involved nor subject to the convergence issues affecting likelihood-based alternatives. Application of the method to a diagnostic review of the performance of transesophageal echocardiography for assessing ascending aorta atherosclerosis enables overcoming limitations of the likelihood procedure.ConclusionsThe SIMEX methodology represents an interesting alternative to likelihood-based procedures for inference in meta-analysis of diagnostic accuracy studies. The approach can provide more accurate inferential conclusions, while avoiding convergence failure and numerical instabilities. The application of the method in the R programming language is possible through the code which is made available and illustrated using the real data example.

Performance of methods for meta-analysis of diagnostic test accuracy with few studies or sparse data.

Hierarchical models such as the bivariate and hierarchical summary receiver operating characteristic (HSROC) models are recommended for meta-analysis of test accuracy studies. These models are challenging to fit when there are few studies and/or sparse data (for example zero cells in contingency tables due to studies reporting 100% sensitivity or specificity); the models may not converge, or give unreliable parameter estimates. Using simulation, we investigated the performance of seven hierarchical models incorporating increasing simplifications in scenarios designed to replicate realistic situations for meta-analysis of test accuracy studies. Performance of the models was assessed in terms of estimability (percentage of meta-analyses that successfully converged and percentage where the between study correlation was estimable), bias, mean square error and coverage of the 95% confidence intervals. Our results indicate that simpler hierarchical models are valid in situations with few studies or sparse data. For synthesis of sensitivity and specificity, univariate random effects logistic regression models are appropriate when a bivariate model cannot be fitted. Alternatively, an HSROC model that assumes a symmetric SROC curve (by excluding the shape parameter) can be used if the HSROC model is the chosen meta-analytic approach. In the absence of heterogeneity, fixed effect equivalent of the models can be applied.

Meta-analysis of test accuracy studies: an exploratory method for investigating the impact of missing thresholds.

BackgroundPrimary studies examining the accuracy of a continuous test evaluate its sensitivity and specificity at one or more thresholds. Meta-analysts then usually perform a separate meta-analysis for each threshold. However, the number of studies available for each threshold is often very different, as primary studies are inconsistent in the thresholds reported. Furthermore, of concern is selective reporting bias, because primary studies may be less likely to report a threshold when it gives low sensitivity and/or specificity estimates. This may lead to biased meta-analysis results. We developed an exploratory method to examine the potential impact of missing thresholds on conclusions from a test accuracy meta-analysis.MethodsOur method identifies studies that contain missing thresholds bounded between a pair of higher and lower thresholds for which results are available. The bounded missing threshold results (two-by-two tables) are then imputed, by assuming a linear relationship between threshold value and each of logit-sensitivity and logit-specificity. The imputed results are then added to the meta-analysis, to ascertain if original conclusions are robust. The method is evaluated through simulation, and application made to 13 studies evaluating protein:creatinine ratio (PCR) for detecting proteinuria in pregnancy with 23 different thresholds, ranging from one to seven per study.ResultsThe simulation shows the imputation method leads to meta-analysis estimates with smaller mean-square error. In the PCR application, it provides 50 additional results for meta-analysis and their inclusion produces lower test accuracy results than originally identified. For example, at a PCR threshold of 0.16, the summary specificity is 0.80 when using the original data, but 0.66 when also including the imputed data. At a PCR threshold of 0.25, the summary sensitivity is reduced from 0.95 to 0.85 when additionally including the imputed data.ConclusionsThe imputation method is a practical tool for researchers (often non-statisticians) to explore the potential impact of missing threshold results on their meta-analysis conclusions. Software is available to implement the method. In the PCR example, it revealed threshold results are vulnerable to the missing data, and so stimulates the need for advanced statistical models or, preferably, individual patient data from primary studies.Electronic supplementary materialThe online version of this article (doi:10.1186/2046-4053-4-12) contains supplementary material, which is available to authorized users.

Meta-Analysis of Test Accuracy Studies with Multiple and Missing Thresholds: A Multivariate-Normal Model

Background: When meta-analysing studies examining the diagnostic/predictive accuracy of classifications based on a continuous test, each study may provide results for one or more thresholds, which can vary across studies. Researchers typically meta-analyse each threshold independently. We consider a multivariate meta-analysis to synthesise results for all thresholds simultaneously and account for their correlation. Methods: We assume that the logit sensitivity and logit specificity estimates follow a multivariate-normal distribution within studies. We model the true logit sensitivity (logit specificity) as monotonically decreasing (increasing) functions of the continuous threshold. This produces a summary ROC curve, a summary estimate of sensitivity and specificity for each threshold, and reveals the heterogeneity in test accuracy across studies. Application is made to 13 studies of protein:creatinine ratio (PCR) for detecting significant proteinuria in pregnancy that each report up to nine thresholds, with 23 distinct thresholds across studies. Results: In the example there were large within-study and between-study correlations, which were accounted for by the method. A cubic relationship on the logit scale was a better fit for the summary ROC curve than a linear or quadratic one. Between-study heterogeneity was substantial. Based on the summary ROC curve, a PCR value of 0.30 to 0.35 corresponded to maximal pair of summary sensitivity and specificity. Limitations of the proposed model include the need to posit parametric functions for the relationship of sensitivity and specificity with the threshold, to ensure correct ordering of summary threshold results, and the multivariate-normal approximation to the within-study sampling distribution. Conclusion: The joint analysis of test performance data reported over multiple thresholds is feasible. The proposed approach handles different sets of available thresholds per study, and produces a summary ROC curve and summary results for each threshold to inform decision-making.