Meta-analysis of continuous outcomes combining individual patient data and aggregate data

Meta-analysis of individual patient data (IPD) is the gold-standard for synthesizing evidence across clinical studies. However, for some studies IPD may not be available and only aggregate data (AD), such as a treatment effect estimate and its standard error, may be obtained. In this situation, methods for combining IPD and AD are important to utilize all the available evidence. In this paper, we develop and assess a range of statistical methods for combining IPD and AD in meta-analysis of continuous outcomes from randomized controlled trials.The methods take either a one-step or a two-step approach. The latter is simple, with IPD reduced to AD so that standard AD meta-analysis techniques can be employed. The one-step approach is more complex but offers a flexible framework to include both patient-level and trial-level parameters. It uses a dummy variable to distinguish IPD trials from AD trials and to constrain which parameters the AD trials estimate. We show that this is important when assessing how patient-level covariates modify treatment effect, as aggregate-level relationships across trials are subject to ecological bias and confounding. We thus develop models to separate within-trial and across-trials treatment-covariate interactions; this ensures that only IPD trials estimate the former, whilst both IPD and AD trials estimate the latter in addition to the pooled treatment effect and any between-study heterogeneity. Extension to multiple correlated outcomes is also considered. Ten IPD trials in hypertension, with blood pressure the continuous outcome of interest, are used to assess the models and identify the benefits of utilizing AD alongside IPD.     

Individual participant data meta-analysis to examine interactions between treatment effect and participant-level covariates: Statistical recommendations for conduct and planning

Precision medicine research often searches for treatment-covariate interactions, which refers to when a treatment effect (eg, measured as a mean difference, odds ratio, hazard ratio) changes across values of a participant-level covariate (eg, age, gender, biomarker). Single trials do not usually have sufficient power to detect genuine treatment-covariate interactions, which motivate the sharing of individual participant data (IPD) from multiple trials for meta-analysis. Here, we provide statistical recommendations for conducting and planning an IPD meta-analysis of randomized trials to examine treatment-covariate interactions. For conduct, two-stage and one-stage statistical models are described, and we recommend: (i) interactions should be estimated directly, and not by calculating differences in meta-analysis results for subgroups; (ii) interaction estimates should be based solely on within-study information; (iii) continuous covariates and outcomes should be analyzed on their continuous scale; (iv) nonlinear relationships should be examined for continuous covariates, using a multivariate meta-analysis of the trend (eg, using restricted cubic spline functions); and (v) translation of interactions into clinical practice is nontrivial, requiring individualized treatment effect prediction. For planning, we describe first why the decision to initiate an IPD meta-analysis project should not be based on between-study heterogeneity in the overall treatment effect; and second, how to calculate the power of a potential IPD meta-analysis project in advance of IPD collection, conditional on characteristics (eg, number of participants, standard deviation of covariates) of the trials (potentially) promising their IPD. Real IPD meta-analysis projects are used for illustration throughout.     

A linearization approach for the model‐based analysis of combined aggregate and individual patient data

The application of model‐based meta‐analysis in drug development has gained prominence recently, particularly for characterizing dose‐response relationships and quantifying treatment effect sizes of competitor drugs. The models are typically nonlinear in nature and involve covariates to explain the heterogeneity in summary‐level literature (or aggregate data (AD)). Inferring individual patient‐level relationships from these nonlinear meta‐analysis models leads to aggregation bias. Individual patient‐level data (IPD) are indeed required to characterize patient‐level relationships but too often this information is limited. Since combined analyses of AD and IPD allow advantage of the information they share to be taken, the models developed for AD must be derived from IPD models; in the case of linear models, the solution is a closed form, while for nonlinear models, closed form solutions do not exist. Here, we propose a linearization method based on a second order Taylor series approximation for fitting models to AD alone or combined AD and IPD. The application of this method is illustrated by an analysis of a continuous landmark endpoint, i.e., change from baseline in HbA1c at week 12, from 18 clinical trials evaluating the effects of DPP‐4 inhibitors on hyperglycemia in diabetic patients. The performance of this method is demonstrated by a simulation study where the effects of varying the degree of nonlinearity and of heterogeneity in covariates (as assessed by the ratio of between‐trial to within‐trial variability) were studied. A dose‐response relationship using an Emax model with linear and nonlinear effects of covariates on the emax parameter was used to simulate data. The simulation results showed that when an IPD model is simply used for modeling AD, the bias in the emax parameter estimate increased noticeably with an increasing degree of nonlinearity in the model, with respect to covariates. When using an appropriately derived AD model, the linearization method adequately corrected for bias. It was also noted that the bias in the model parameter estimates decreased as the ratio of between‐trial to within‐trial variability in covariate distribution increased. Taken together, the proposed linearization approach allows addressing the issue of aggregation bias in the particular case of nonlinear models of aggregate data. Copyright © 2014 John Wiley & Sons, Ltd.     

Repeated-measures modeling improved comparison of diagnostic tests in meta-analysis of dependent studies

OBJECTIVE: Current methods for meta-analysis of diagnostic tests do not allow utilizing all the information from papers in which several tests have been studied on the same patient sample. We demonstrate how to combine several studies of diagnostic tests, where each study reports on more than one test and some tests (but not necessarily all of them) are shared with other papers selected for the meta-analysis. We adopt statistical methodology for repeated measurements for the purpose of meta-analysis of diagnostic tests. STUDY DESIGN AND SETTING: The method allows for missing values of some tests for some papers, takes into account different sample sizes of papers, adjusts for background and confounding factors including test-specific covariates and paper-specific covariates, and accounts for correlations of the repeated measurements within each paper. It does not need individual-level data, although it can be modified to use them, and uses the two-by-two table of test results vs. gold standard. RESULTS: The results are translated from diagnostic odds ratios (DOR) to more clinically useful measures such as predictive values, post-test probabilities, and likelihood ratios. Models to capture between-study variation are introduced. The fit and influence of specific studies on the regression can be evaluated. Furthermore, model-based tests for homogeneity of DORs across papers are presented. CONCLUSION: The use of this new method is illustrated using a recent meta-analysis of the D-dimer test for the diagnosis of deep venous thrombosis.     

A hierarchical regression approach to meta-analysis of diagnostic test accuracy evaluations

An important quality of meta-analytic models for research synthesis is their ability to account for both within- and between-study variability. Currently available meta-analytic approaches for studies of diagnostic test accuracy work primarily within a fixed-effects framework. In this paper we describe a hierarchical regression model for meta-analysis of studies reporting estimates of test sensitivity and specificity. The model allows more between- and within-study variability than fixed-effect approaches, by allowing both test stringency and test accuracy to vary across studies. It is also possible to examine the effects of study specific covariates. Estimates are computed using Markov Chain Monte Carlo simulation with publicly available software (BUGS). This estimation method allows flexibility in the choice of summary statistics. We demonstrate the advantages of this modelling approach using a recently published meta-analysis comparing three tests used to detect nodal metastasis of cervical cancer.     

Evidence synthesis combining individual patient data and aggregate data: a systematic review identified current practice and possible methods

OBJECTIVE: Meta-analysis of individual patient data (IPD) is the "gold-standard" for synthesizing evidence across several studies. Some studies, however, may only provide aggregate data (AD). In this situation researchers might need to combine IPD with AD to utilize all the evidence available. Here, we review applied IPD meta-analysis articles to assess if and how AD is combined with IPD in practice. STUDY DESIGN AND SETTING: A systematic review of articles identified from bibliographic databases and searches. RESULTS: We identified 33 applied IPD articles that combined IPD and AD and 166 that did not. For each article, we recorded the proportion of total studies providing IPD, and found that articles combining IPD and AD had, on average, IPD available in only 64% of studies (compared to 90% in articles not combining IPD and AD). Two different methods were used to combine IPD and AD, the two-stage method and analysis of partially reconstructed IPD, but a review of methodological articles identified two further methods, multilevel modeling and Bayesian hierarchical related regression. We summarize each method to aid practitioners. CONCLUSION: Combining IPD and AD is a relevant issue for evidence synthesis, and the further development and validation of suitable meta-analysis methods is needed.     

Exploring sources of heterogeneity in systematic reviews of diagnostic tests

It is indispensable for any meta-analysis that potential sources of heterogeneity are examined, before one considers pooling the results of primary studies into summary estimates with enhanced precision. In reviews of studies on the diagnostic accuracy of tests, variability beyond chance can be attributed to between-study differences in the selected cutpoint for positivity, in patient selection and clinical setting, in the type of test used, in the type of reference standard, or any combination of these factors. In addition, heterogeneity in study results can also be caused by flaws in study design. This paper critically examines some of the potential reasons for heterogeneity and the methods to explore them. Empirical support for the existence of different sources of variation is reviewed. Incorporation of sources of variability explicitly into systematic reviews on diagnostic accuracy is demonstrated with data from a recent review. Application of regression techniques in meta-analysis of diagnostic tests can provide relevant additional information. Results of such analyses will help understand problems with the transferability of diagnostic tests and to point out flaws in primary studies. As such, they can guide the design of future studies.     

Mixed treatment comparisons using aggregate and individual participant level data

Mixed treatment comparisons (MTC) extend the traditional pair‐wise meta‐analytic framework to synthesize information on more than two interventions. Although most MTCs use aggregate data (AD), a proportion of the evidence base might be available at the individual level (IPD). We develop a series of novel Bayesian statistical MTC models to allow for the simultaneous synthesis of IPD and AD, potentially incorporating study and individual level covariates. The effectiveness of different interventions to increase the provision of functioning smoke alarms in households with children was used as a motivating dataset. This included 20 studies (11 AD and 9 IPD), including 11 500 participants. Incorporating the IPD into the network allowed the inclusion of information on subject level covariates, which produced markedly more accurate treatment–covariate interaction estimates than an analysis solely on the AD from all studies. Including evidence at the IPD level in the MTC is desirable when exploring participant level covariates; even when IPD is available only for a fraction of the studies. Such modelling may not only reduce inconsistencies within networks of trials but also assist the estimation of intervention subgroup effects to guide more individualised treatment decisions. Copyright © 2012 John Wiley & Sons, Ltd.     

One-stage individual participant data meta-analysis models for continuous and binary outcomes: Comparison of treatment coding options and estimation methods

A one-stage individual participant data (IPD) meta-analysis synthesizes IPD from multiple studies using a general or generalized linear mixed model. This produces summary results (eg, about treatment effect) in a single step, whilst accounting for clustering of participants within studies (via a stratified study intercept, or random study intercepts) and between-study heterogeneity (via random treatment effects). We use simulation to evaluate the performance of restricted maximum likelihood (REML) and maximum likelihood (ML) estimation of one-stage IPD meta-analysis models for synthesizing randomized trials with continuous or binary outcomes. Three key findings are identified. First, for ML or REML estimation of stratified intercept or random intercepts models, a t-distribution based approach generally improves coverage of confidence intervals for the summary treatment effect, compared with a z-based approach. Second, when using ML estimation of a one-stage model with a stratified intercept, the treatment variable should be coded using “study-specific centering” (ie, 1/0 minus the study-specific proportion of participants in the treatment group), as this reduces the bias in the between-study variance estimate (compared with 1/0 and other coding options). Third, REML estimation reduces downward bias in between-study variance estimates compared with ML estimation, and does not depend on the treatment variable coding; for binary outcomes, this requires REML estimation of the pseudo-likelihood, although this may not be stable in some situations (eg, when data are sparse). Two applied examples are used to illustrate the findings.     

Meta-analysis of continuous outcome data from individual patients

Meta-analyses using individual patient data are becoming increasingly common and have several advantages over meta-analyses of summary statistics. We explore the use of multilevel or hierarchical models for the meta-analysis of continuous individual patient outcome data from clinical trials. A general framework is developed which encompasses traditional meta-analysis, as well as meta-regression and the inclusion of patient-level covariates for investigation of heterogeneity. Unexplained variation in treatment differences between trials is considered as random. We focus on models with fixed trial effects, although an extension to a random effect for trial is described. The methods are illustrated on an example in Alzheimer's disease in a classical framework using SAS PROC MIXED and MLwiN, and in a Bayesian framework using BUGS. Relative merits of the three software packages for such meta-analyses are discussed, as are the assessment of model assumptions and extensions to incorporate more than two treatments.     

Imputation of systematically missing predictors in an individual participant data meta‐analysis: a generalized approach using MICE

Individual participant data meta‐analyses (IPD‐MA) are increasingly used for developing and validating multivariable (diagnostic or prognostic) risk prediction models. Unfortunately, some predictors or even outcomes may not have been measured in each study and are thus systematically missing in some individual studies of the IPD‐MA. As a consequence, it is no longer possible to evaluate between‐study heterogeneity and to estimate study‐specific predictor effects, or to include all individual studies, which severely hampers the development and validation of prediction models. Here, we describe a novel approach for imputing systematically missing data and adopt a generalized linear mixed model to allow for between‐study heterogeneity. This approach can be viewed as an extension of Resche‐Rigon's method (Stat Med 2013), relaxing their assumptions regarding variance components and allowing imputation of linear and nonlinear predictors. We illustrate our approach using a case study with IPD‐MA of 13 studies to develop and validate a diagnostic prediction model for the presence of deep venous thrombosis. We compare the results after applying four methods for dealing with systematically missing predictors in one or more individual studies: complete case analysis where studies with systematically missing predictors are removed, traditional multiple imputation ignoring heterogeneity across studies, stratified multiple imputation accounting for heterogeneity in predictor prevalence, and multilevel multiple imputation (MLMI) fully accounting for between‐study heterogeneity. We conclude that MLMI may substantially improve the estimation of between‐study heterogeneity parameters and allow for imputation of systematically missing predictors in IPD‐MA aimed at the development and validation of prediction models. Copyright © 2015 John Wiley & Sons, Ltd.     

A systematic review and meta-analysis of the diagnostic accuracy of rapid immunochromatographic assays for the detection of dengue virus IgM antibodies during acute infection

A meta-analysis of rapid (相似文献   

Investigating heterogeneity in an individual patient data meta-analysis of time to event outcomes

Differences across studies in terms of design features and methodology, clinical procedures, and patient characteristics, are factors that can contribute to variability in the treatment effect between studies in a meta-analysis (statistical heterogeneity). Regression modelling can be used to examine relationships between treatment effect and covariates with the aim of explaining the variability in terms of clinical, methodological, or other factors. Such an investigation can be undertaken using aggregate data or individual patient data. An aggregate data approach can be problematic as sufficient data are rarely available and translating aggregate effects to individual patients can often be misleading. An individual patient data approach, although usually more resource demanding, allows a more thorough investigation of potential sources of heterogeneity and enables a fuller analysis of time to event outcomes in meta-analysis. Hierarchical Cox regression models are used to identify and explore the evidence for heterogeneity in meta-analysis and examine the relationship between covariates and censored failure time data in this context. Alternative formulations of the model are possible and illustrated using individual patient data from a meta-analysis of five randomized controlled trials which compare two drugs for the treatment of epilepsy. The models are further applied to simulated data examples in which the degree of heterogeneity and magnitude of treatment effect are varied. The behaviour of each model in each situation is explored and compared.     

Coronary heart disease in primary care: accuracy of medical history and physical findings in patients with chest pain - a study protocol for a systematic review with individual patient data

ABSTRACT: BACKGROUND: Chest pain is a common complaint in primary care, with coronary heart disease (CHD) being the most concerning of many potential causes. Systematic reviews on the sensitivity and specificity of symptoms and signs summarize the evidence about which of them are most useful in making a diagnosis. Previous meta-analyses are dominated by studies of patients referred to specialists. Moreover, as the analysis is typically based on study-level data, the statistical analyses in these reviews are limited while meta-analyses based on individual patient data can provide additional information. Our patient-level meta-analysis has three unique aims. First, we strive to determine the diagnostic accuracy of symptoms and signs for myocardial ischemia in primary care. Second, we investigate associations between study- or patient-level characteristics and measures of diagnostic accuracy. Third, we aim to validate existing clinical prediction rules for diagnosing myocardial ischemia in primary care. This article describes the methods of our study and six prospective studies of primary care patients with chest pain. Later articles will describe the main results. METHODS: We will conduct a systematic review and IPD meta-analysis of studies evaluating the diagnostic accuracy of symptoms and signs for diagnosing coronary heart disease in primary care. We will perform bivariate analyses to determine the sensitivity, specificity and likelihood ratios of individual symptoms and signs and multivariate analyses to explore the diagnostic value of an optimal combination of all symptoms and signs based on all data of all studies. We will validate existing clinical prediction rules from each of the included studies by calculating measures of diagnostic accuracy separately by study. DISCUSSION: Our study will face several methodological challenges. First, the number of studies will be limited. Second, the investigators of original studies defined some outcomes and predictors differently. Third, the studies did not collect the same standard clinical data set. Fourth, missing data, varying from partly missing to fully missing, will have to be dealt with. Despite these limitations, we aim to summarize the available evidence regarding the diagnostic accuracy of symptoms and signs for diagnosing CHD in patients presenting with chest pain in primary care. Review registration Centre for Reviews and Dissemination (University of York): CRD42011001170.     

Bayesian meta-analysis and meta-regression for gene-disease associations and deviations from Hardy-Weinberg equilibrium

Violation of Hardy-Weinberg equilibrium (HWE) can raise doubts about the validity of the conclusions from genetic association studies. However, for most currently performed gene-disease association studies, the available tests have low power to detect deviations from HWE. We consider this issue from a meta-analysis perspective, and suggest an approach to estimate the deviation and investigate its relationship with the observed genetic effects. Different degrees of deviation from HWE have previously been proposed as a potential source of heterogeneity across studies. We present a hierarchical meta-regression model that can be applied to test this assumption, using the concept of the fixation coefficient. We re-analyse seven meta-analyses to illustrate these methods. The uncertainty in the genetic effect estimate tended to increase once the fixation coefficient was taken into account. Dependence of the genetic effect size on the deviation from HWE was found in one meta-analysis, while in the other six examples, deviations from HWE did not clearly explain between-study heterogeneity in the genetic effects. The proposed hierarchical models allow the synthesis of data across gene-disease association studies with appropriate consideration of HWE issues.     

Assessing the consistency assumption by exploring treatment by covariate interactions in mixed treatment comparison meta‐analysis: individual patient‐level covariates versus aggregate trial‐level covariates

Mixed treatment comparison (MTC) meta‐analysis allows several treatments to be compared in a single analysis while utilising direct and indirect evidence. Treatment by covariate interactions can be included in MTC models to explore how the covariate modifies the treatment effects. If interactions exist, the assumptions underlying MTCs may be invalidated. For conventional pair‐wise meta‐analysis, important benefits regarding the investigation of such interactions, gained from using individual patient data (IPD) rather than aggregate data (AD), have been described. We aim to compare IPD MTC models including patient‐level covariates with AD MTC models including study‐level covariates. IPD and AD random‐effects MTC models for dichotomous outcomes are specified. Three assumptions are made regarding the interactions (i.e. independent, exchangeable and common interactions). The models are applied to a dataset to compare four drugs for treating malaria (i.e. amodiaquine‐artesunate, dihydroartemisinin‐piperaquine (DHAPQ), artemether‐lumefantrine and chlorproguanil‐dapsone plus artesunate) using the outcome unadjusted treatment success at day 28. The treatment effects and regression coefficients for interactions from the IPD models were more precise than those from AD models. Using IPD, assuming independent or exchangeable interactions, the regression coefficient for chlorproguanil‐dapsone plus artesunate versus DHAPQ was statistically significant and assuming common interactions, the common coefficient was significant; whereas using AD, no coefficients were significant. Using IPD, DHAPQ was the best drug; whereas using AD, the best drug varied. Using AD models, there was no evidence that the consistency assumption was invalid; whereas, the assumption was questionable based on the IPD models. The AD analyses were misleading. Copyright © 2012 John Wiley & Sons, Ltd.     

Combining individual patient data and aggregate data in mixed treatment comparison meta‐analysis: Individual patient data may be beneficial if only for a subset of trials

Background Individual patient data (IPD) meta‐analysis is the gold standard. Aggregate data (AD) and IPD can be combined using conventional pairwise meta‐analysis when IPD cannot be obtained for all relevant studies. We extend the methodology to combine IPD and AD in a mixed treatment comparison (MTC) meta‐analysis. Methods The proposed random‐effects MTC models combine IPD and AD for a dichotomous outcome. We study the benefits of acquiring IPD for a subset of trials when assessing the underlying consistency assumption by including treatment‐by‐covariate interactions in the model. We describe three different model specifications that make increasingly stronger assumptions regarding the interactions. We illustrate the methodology through application to real data sets to compare drugs for treating malaria by using the outcome unadjusted treatment success at day 28. We compare results from AD alone, IPD alone and all data. Results When IPD contributed (i.e. either using IPD alone or combining IPD and AD), the chains converged, and we identified statistically significant regression coefficients for the interactions. Using IPD alone, we were able to compare only three of the six treatments of interest. When models were fitted to AD, the treatment effects and regression coefficients for the interactions were far more imprecise, and the chains did not converge. Conclusions The models combining IPD and AD encapsulated all available evidence. When exploring interactions, it can be beneficial to obtain IPD for a subset of trials and to combine IPD with additional AD. Copyright © 2012 John Wiley & Sons, Ltd.     

Quantifying how diagnostic test accuracy depends on threshold in a meta-analysis

Tests for disease often produce a continuous measure, such as the concentration of some biomarker in a blood sample. In clinical practice, a threshold C is selected such that results, say, greater than C are declared positive and those less than C negative. Measures of test accuracy such as sensitivity and specificity depend crucially on C, and the optimal value of this threshold is usually a key question for clinical practice. Standard methods for meta-analysis of test accuracy (i) do not provide summary estimates of accuracy at each threshold, precluding selection of the optimal threshold, and furthermore, (ii) do not make use of all available data. We describe a multinomial meta-analysis model that can take any number of pairs of sensitivity and specificity from each study and explicitly quantifies how accuracy depends on C. Our model assumes that some prespecified or Box-Cox transformation of test results in the diseased and disease-free populations has a logistic distribution. The Box-Cox transformation parameter can be estimated from the data, allowing for a flexible range of underlying distributions. We parameterise in terms of the means and scale parameters of the two logistic distributions. In addition to credible intervals for the pooled sensitivity and specificity across all thresholds, we produce prediction intervals, allowing for between-study heterogeneity in all parameters. We demonstrate the model using two case study meta-analyses, examining the accuracy of tests for acute heart failure and preeclampsia. We show how the model can be extended to explore reasons for heterogeneity using study-level covariates.     

Patient-level compared with study-level meta-analyses demonstrate consistency of D-dimer as predictor of venous thromboembolic recurrences

ObjectiveWe compared the performance of aggregate data (AD)–based and individual patient data (IPD)–based meta-analyses to synthesize evidence on the ability of D-dimer to distinguish recurrence risk in patients with unprovoked venous thromboembolism (VTE) who stopped anticoagulation.Study Design and SettingWe compared the results of the published AD-based rate ratio of VTE recurrence for positive vs. negative D-dimer, estimated by a mixed-effect Poisson model, with those of the IPD-based hazard ratio obtained by a Cox regression stratified by trial. We performed three additional analyses to investigate the methodological reasons for differences between the two approaches, comparing the IPD Cox regression with AD generated from IPD Poisson regression (to control for differences in population on study), AD time-to-event meta-analysis, and AD generated from IPD meta-regression.ResultsPublished analyses agreed in direction and statistical significance when estimating the prognostic value of D-dimer even if IPD estimates suggested a stronger effect. The additional analyses suggested that differences in study populations might explain this slight difference. Poor reporting in published studies precluded a true comparison of AD- and IPD-based assessments of heterogeneity sources.ConclusionAD and IPD meta-analyses yielded similar estimates of D-dimer effect to distinguish risk for recurrent VTE. The IPD approach was justified by the need to investigate sources of heterogeneity.     

Empirical comparison of subgroup effects in conventional and individual patient data meta-analyses

OBJECTIVES: Individual patient data (IPD) meta-analyses have been proposed as a major improvement in meta-analytic methods to study subgroup effects. Subgroup effects of conventional and IPD meta-analyses using identical data have not been compared. Our objective is to compare such subgroup effects using the data of six trials (n = 1,643) on the effectiveness of antibiotics in children with acute otitis media (AOM). METHODS: Effects (relative risks, risk differences [RD], and their confidence intervals [CI]) of antibiotics in subgroups of children with AOM resulting from (i) conventional meta-analysis using summary statistics derived from published data (CMA), (ii) two-stage approach to IPD meta-analysis using summary statistics derived from IPD (IPDMA-2), and (iii) one-stage approach to IPD meta-analysis where IPD is pooled into a single data set (IPDMA-1) were compared. RESULTS: In the conventional meta-analysis, only two of the six studies were included, because only these reported on relevant subgroup effects. The conventional meta-analysis showed larger (age < 2 years) or smaller (age > or = 2 years) subgroup effects and wider CIs than both IPD meta-analyses (age < 2 years: RDCMA -21 percent, RDIPDMA-1 -16 percent, RDIPDMA-2 -15 percent; age > or =2 years: RDCMA -5 percent, RDIPDMA-1 -11 percent, RDIPDMA-2 -11 percent). The most important reason for these discrepant results is that the two studies included in the conventional meta-analysis reported outcomes that were different both from each other and from the IPD meta-analyses. CONCLUSIONS: This empirical example shows that conventional meta-analyses do not allow proper subgroup analyses, whereas IPD meta-analyses produce more accurate subgroup effects. We also found no differences between the one- and two-stage meta-analytic approaches.