Using aggregate data to estimate the standard error of a treatment–covariate interaction in an individual patient data meta‐analysis

Subgroup analyses are important to medical research because they shed light on the heterogeneity of treatment effectts. A treatment–covariate interaction in an individual patient data (IPD) meta‐analysis is the most reliable means to estimate how a subgroup factor modifies a treatment's effectiveness. However, owing to the challenges in collecting participant data, an approach based on aggregate data might be the only option. In these circumstances, it would be useful to assess the relative efficiency and power loss of a subgroup analysis without patient‐level data. We present methods that use aggregate data to estimate the standard error of an IPD meta‐analysis’ treatment–covariate interaction for regression models of a continuous or dichotomous patient outcome. Numerical studies indicate that the estimators have good accuracy. An application to a previously published meta‐regression illustrates the practical utility of the methodology.     

A framework for prospective,adaptive meta-analysis (FAME) of aggregate data from randomised trials

BackgroundThe vast majority of systematic reviews are planned retrospectively, once most eligible trials have completed and reported, and are based on aggregate data that can be extracted from publications. Prior knowledge of trial results can introduce bias into both review and meta-analysis methods, and the omission of unpublished data can lead to reporting biases. We present a collaborative framework for prospective, adaptive meta-analysis (FAME) of aggregate data to provide results that are less prone to bias. Also, with FAME, we monitor how evidence from trials is accumulating, to anticipate the earliest opportunity for a potentially definitive meta-analysis.MethodologyWe developed and piloted FAME alongside 4 systematic reviews in prostate cancer, which allowed us to refine the key principles. These are to: (1) start the systematic review process early, while trials are ongoing or yet to report; (2) liaise with trial investigators to develop a detailed picture of all eligible trials; (3) prospectively assess the earliest possible timing for reliable meta-analysis based on the accumulating aggregate data; (4) develop and register (or publish) the systematic review protocol before trials produce results and seek appropriate aggregate data; (5) interpret meta-analysis results taking account of both available and unavailable data; and (6) assess the value of updating the systematic review and meta-analysis. These principles are illustrated via a hypothetical review and their application to 3 published systematic reviews.ConclusionsFAME can reduce the potential for bias, and produce more timely, thorough and reliable systematic reviews of aggregate data.

Jayne Tierney and coauthors discuss FAME, an approach for adaptive meta-analysis of data from randomised trials.     

Obtaining data from randomised controlled trials: how much do we need for reliable and informative meta-analyses?

Many randomised controlled trials compare treatments that will produce only moderate differences in outcome, but these differences can be clinically important. However, they are difficult to assess reliably and require a large amount of randomised evidence. This can be achieved through large prospective randomised trials which will accrue future patients, the meta-analysis of results from randomised trials involving patients from the past, or--ideally--both. The techniques require that all possible biases are minimised, and in meta-analyses this can best be achieved by ensuring that all of the randomised evidence--both trials and participants in those trials--is included. The meta-analysis of individual patient data has been described as the gold standard for this approach. It will remove many of the problems associated with relying solely on published data and some of the problems arising from a reliance on aggregate data, and will also add to the analyses that can be performed. Such projects, however, require considerable time and effort.     

Propensity Score-Based Approaches to Confounding by Indication in Individual Patient Data Meta-Analysis: Non-Standardized Treatment for Multidrug Resistant Tuberculosis

Background

In the absence of randomized clinical trials, meta-analysis of individual patient data (IPD) from observational studies may provide the most accurate effect estimates for an intervention. However, confounding by indication remains an important concern that can be addressed by incorporating individual patient covariates in different ways. We compared different analytic approaches to account for confounding in IPD from patients treated for multi-drug resistant tuberculosis (MDR-TB).

Methods

Two antibiotic classes were evaluated, fluoroquinolones—considered the cornerstone of effective MDR-TB treatment—and macrolides, which are known to be safe, yet are ineffective in vitro. The primary outcome was treatment success against treatment failure, relapse or death. Effect estimates were obtained using multivariable and propensity-score based approaches.

Results

Fluoroquinolone antibiotics were used in 28 included studies, within which 6,612 patients received a fluoroquinolone and 723 patients did not. Macrolides were used in 15 included studies, within which 459 patients received this class of antibiotics and 3,670 did not. Both standard multivariable regression and propensity score-based methods resulted in similar effect estimates for early and late generation fluoroquinolones, while macrolide antibiotics use was associated with reduced treatment success.

Conclusions

In this individual patient data meta-analysis, standard multivariable and propensity-score based methods of adjusting for individual patient covariates for observational studies yielded produced similar effect estimates. Even when adjustment is made for potential confounding, interpretation of adjusted estimates must still consider the potential for residual bias.     

Evaluating the Quality of Evidence from a Network Meta-Analysis

Systematic reviews that collate data about the relative effects of multiple interventions via network meta-analysis are highly informative for decision-making purposes. A network meta-analysis provides two types of findings for a specific outcome: the relative treatment effect for all pairwise comparisons, and a ranking of the treatments. It is important to consider the confidence with which these two types of results can enable clinicians, policy makers and patients to make informed decisions. We propose an approach to determining confidence in the output of a network meta-analysis. Our proposed approach is based on methodology developed by the Grading of Recommendations Assessment, Development and Evaluation (GRADE) Working Group for pairwise meta-analyses. The suggested framework for evaluating a network meta-analysis acknowledges (i) the key role of indirect comparisons (ii) the contributions of each piece of direct evidence to the network meta-analysis estimates of effect size; (iii) the importance of the transitivity assumption to the validity of network meta-analysis; and (iv) the possibility of disagreement between direct evidence and indirect evidence. We apply our proposed strategy to a systematic review comparing topical antibiotics without steroids for chronically discharging ears with underlying eardrum perforations. The proposed framework can be used to determine confidence in the results from a network meta-analysis. Judgements about evidence from a network meta-analysis can be different from those made about evidence from pairwise meta-analyses.     

The Effect of Disease Modifying Therapies on Brain Atrophy in Patients with Relapsing-Remitting Multiple Sclerosis: A Systematic Review and Meta-Analysis

Background

The aim of the present meta-analysis was to evaluate the effect of disease-modifying drugs (DMD) on brain atrophy in patients with relapsing-remitting multiple sclerosis (RRMS) using available randomized-controlled trial (RCT) data.

Methods

We conducted a systematic review and meta-analysis according to PRISMA guidelines of all available RCTs of patients with RRMS that reported data on brain volume measurements during the study period.

Results

We identified 4 eligible studies, including a total of 1819 RRMS patients (71% women, mean age 36.5 years, mean baseline EDSS-score: 2.4). The mean percentage change in brain volume was found to be significantly lower in DMD versus placebo subgroup (standardized mean difference: -0.19; 95%CI: -0.27–-0.11; p<0.001). We detected no evidence of heterogeneity between estimates (I² = 30%, p = 0.19) nor publication bias in the Funnel plots. Sensitivity analyses stratifying studies according to brain atrophy neuroimaging protocol disclosed no evidence of heterogeneity (p = 0.16). In meta-regression analyses, the percentage change in brain volume was found to be inversely related with duration of observation period in both DMD (meta-regression slope = -0.03; 95% CI: -0.04–-0.02; p<0.001) and placebo subgroups (meta-regression slope = -0.05; 95% CI: -0.06–-0.04; p<0.001). However, the rate of percentage brain volume loss over time was greater in placebo than in DMD subgroup (p = 0.017, ANCOVA).

Conclusions

DMD appear to be effective in attenuating brain atrophy in comparison to placebo and their benefit in delaying the rate of brain volume loss increases linearly with longer treatment duration.     

Insights on bias and information in group-level studies

Ecological and aggregate data studies are examples of group-level studies. Even though the link between the predictors and outcomes is not preserved in these studies, inference about individual-level exposure effects is often a goal. The disconnection between the level of inference and the level of analysis expands the array of potential biases that can invalidate the inference from group-level studies. While several sources of bias, specifically due to measurement error and confounding, may be more complex in group-level studies, two sources of bias, cross-level and model specification bias, are a direct consequence of the disconnection. With the goal of aligning inference from individual versus group-level studies, I discuss the interplay between exposure and study design. I specify the additional assumptions necessary for valid inference, specifically that the between- and within-group exposure effects are equal. Then cross-level inference is possible. However, all the information in the group-level analysis comes from between-group comparisons. Models where the group-level analysis provides even a small percentage of information about the within-group exposure effect are most susceptible to model specification bias. Model specification bias can be even more serious when the group-level model isn't derived from an individual-level model.     

Which polyunsaturated fatty acids are active in children with attention-deficit hyperactivity disorder receiving PUFA supplementation? A fatty acid validated meta-regression analysis of randomized controlled trials

Concerns about growth retardation and unknown effects on long-term brain development with stimulants have prompted interest in polyunsaturated fatty acid supplementation (PUFA) as an alternative treatment. However, randomized controlled trials (RCTs) and meta-analyses of PUFA supplementation in ADHD have shown marginal benefit, and uncertainty exists as to which, if any, PUFA might be effective in alleviating symptoms of ADHD. We conducted an updated meta-analysis of RCTs in ADHD together with multivariable meta-regression analyses using data on PUFA content obtained from independent fatty acid methyl ester analyses of each study PUFA regimen. The PubMed, Embase and PsycINFO databases were searched with no start date and up to 28th July 2013. Study inclusion criteria were: randomized design, placebo controlled, PUFA preparation as active intervention, reporting change scores on ADHD rating-scale measures. Rating-scale measures of inattention and hyperactive-impulsive symptoms were extracted, study authors were contacted to obtain missing data, studies not reporting negative findings had these data imputed, and study quality was assessed using the Jadad system plus other indicators. Random-effects models were used for pooled effects and for meta-regression analyses. Standardized mean differences (SMD) in inattention, hyperactive-impulsive and combined symptoms were assessed as rated by parents, teachers or all raters. The influence of study characteristics and PUFA regimen content was explored in multivariable meta-regression analyses. The overall pooled estimate from 18 studies showed that combined ADHD symptoms rated by all raters decreased with PUFA supplementation; SMD −0.192 (95% CI: −0.297, −0.086; P<0.001). However, when analyzed by rater, only parent-rated symptoms decreased significantly. Multivariable meta-regression showed that longer study duration, γ-linolenic acid (GLA), and the interaction between GLA and eicosapentaenoic acid (EPA) were associated with significant decreases in inattention; however, PUFA regimen content was unrelated to changes in hyperactive-impulsive symptoms. Certain fatty acids present in placebo preparations may potentially have been psychoactive. This meta-analysis provides modest evidence of PUFA effectiveness in ADHD, especially GLA and EPA for inattention symptoms; however, evidence of reporting bias, publication bias, variable methodological quality, and use of potentially psychoactive placebos limit the generalizability of these findings.     

基于meta分析的中国森林生态系统服务价值评估

meta分析作为价值转移方法中最有效的手段之一，已在生态系统服务价值评估中得到了较为广泛的应用。然而国内相关研究的meta回归模型大多依据传统的最小二乘法建立，忽略了原始数据的层次结构特征。通过收集关于中国森林生态系统服务已有实证研究的价值评估结果，建立meta分析数据库；通过面板数据回归方法构建meta回归模型，对模型的价值转移有效性进行评估；在构建的meta回归模型基础上，根据IPCC SRES中的四类情景——A1B、A2、B1、B2，计算中国森林生态系统2010-2100年的生态系统服务价值。研究结果表明：（1）相较基于普通最小二乘法和加权最小二乘法建立的回归模型，基于面板数据回归方法建立的模型平均转移误差最小（11.57%），模型有效性较高，因此为适合本研究的meta回归方法；对于不同价值观察值，转移误差存在较大差异，随着观察值的增大，模型预测值由高估逐渐转变为低估，转移误差趋向减小。（2）基于面板数据回归方法建立的meta回归模型能够有效揭示中国森林生态系统服务的价值转移规律，生态系统服务类型、植被区划、森林面积、森林丰度、人均GDP和铁路长度是中国森林生态系统服务价值的重要影响因素。（3）中国森林生态系统2010-2100年价值变化的情景分析表明，情景A1B和B1下森林面积和生态系统服务总价值持续增加，情景A2下森林面积和生态系统服务总价值持续下降，情景B2下森林面积和生态系统服务总价值先上升后下降；其中情景B1下中国森林生态系统服务总价值增长最大，至2100年达到41.58万亿元，情景B2下价值损失最为显著，至2100年降至22.97万亿元。     

Statistical issues in a metaregression analysis of randomized trials: impact on the dietary sodium intake and blood pressure relationship

In a meta-analysis of randomized trials of the effects of dietary sodium interventions on blood pressure, we found substantial heterogeneity among the studies. We were interested in evaluating whether measurement error, known to be a problem for dietary sodium measures, publication bias, or confounding factors could be responsible for the heterogeneity. A measurement error correction was developed that corrects both the slope and the intercept and takes into account the sample size of each study and the number of measurements taken on an individual. The measurement error correction had a minimal effect on the estimates, although it performed well in simulated data. A smoothed scatter plot was used to assess publication bias. Metaregressions provide a convenient way to jointly assess the effects of several factors, but care must be taken to fit an appropriate model.     

An alternative model for bivariate random-effects meta-analysis when the within-study correlations are unknown

Multivariate meta-analysis models can be used to synthesize multiple, correlated endpoints such as overall and disease-free survival. A hierarchical framework for multivariate random-effects meta-analysis includes both within-study and between-study correlation. The within-study correlations are assumed known, but they are usually unavailable, which limits the multivariate approach in practice. In this paper, we consider synthesis of 2 correlated endpoints and propose an alternative model for bivariate random-effects meta-analysis (BRMA). This model maintains the individual weighting of each study in the analysis but includes only one overall correlation parameter, rho, which removes the need to know the within-study correlations. Further, the only data needed to fit the model are those required for a separate univariate random-effects meta-analysis (URMA) of each endpoint, currently the common approach in practice. This makes the alternative model immediately applicable to a wide variety of evidence synthesis situations, including studies of prognosis and surrogate outcomes. We examine the performance of the alternative model through analytic assessment, a realistic simulation study, and application to data sets from the literature. Our results show that, unless rho is very close to 1 or -1, the alternative model produces appropriate pooled estimates with little bias that (i) are very similar to those from a fully hierarchical BRMA model where the within-study correlations are known and (ii) have better statistical properties than those from separate URMAs, especially given missing data. The alternative model is also less prone to estimation at parameter space boundaries than the fully hierarchical model and thus may be preferred even when the within-study correlations are known. It also suitably estimates a function of the pooled estimates and their correlation; however, it only provides an approximate indication of the between-study variation. The alternative model greatly facilitates the utilization of correlation in meta-analysis and should allow an increased application of BRMA in practice.     

Selective serotonin reuptake inhibitors,and serotonin and norepinephrine reuptake inhibitors for anxiety,obsessive-compulsive,and stress disorders: A 3-level network meta-analysis

BackgroundAnxiety, obsessive-compulsive, and stress-related disorders frequently co-occur, and patients often present symptoms of several domains. Treatment involves the use of selective serotonin reuptake inhibitors (SSRIs) and serotonin and norepinephrine reuptake inhibitors (SNRIs), but data on comparative efficacy and acceptability are lacking. We aimed to compare the efficacy of SSRIs, SNRIs, and placebo in multiple symptom domains in patients with these diagnoses over the lifespan through a 3-level network meta-analysis.Methods and findingsWe searched for published and unpublished randomized controlled trials that aimed to assess the efficacy of SSRIs or SNRIs in participants (adults and children) with diagnosis of any anxiety, obsessive-compulsive, or stress-related disorder in MEDLINE, PsycINFO, Embase, and Cochrane Library from inception to 23 April 2015, with an update on 11 November 2020. We supplemented electronic database searches with manual searches for published and unpublished randomized controlled trials registered in publicly accessible clinical trial registries and pharmaceutical companies’ databases. No restriction was made regarding comorbidities with any other mental disorder, participants’ age and sex, blinding of participants and researchers, date of publication, or study language. The primary outcome was the aggregate measure of internalizing symptoms of these disorders. Secondary outcomes included specific symptom domains and treatment discontinuation rate. We estimated standardized mean differences (SMDs) with 3-level network meta-analysis with random slopes by study for medication and assessment instrument. Risk of bias appraisal was performed using the Cochrane Collaboration’s risk of bias tool. This study was registered in PROSPERO (CRD42017069090). We analyzed 469 outcome measures from 135 studies (n = 30,245). All medications were more effective than placebo for the aggregate measure of internalizing symptoms (SMD −0.56, 95% CI −0.62 to −0.51, p < 0.001), for all symptom domains, and in patients from all diagnostic categories. We also found significant results when restricting to the most used assessment instrument for each diagnosis; nevertheless, this restriction led to exclusion of 72.71% of outcome measures. Pairwise comparisons revealed only small differences between medications in efficacy and acceptability. Limitations include the moderate heterogeneity found in most outcomes and the moderate risk of bias identified in most of the trials.ConclusionsIn this study, we observed that all SSRIs and SNRIs were effective for multiple symptom domains, and in patients from all included diagnostic categories. We found minimal differences between medications concerning efficacy and acceptability. This three-level network meta-analysis contributes to an ongoing discussion about the true benefit of antidepressants with robust evidence, considering the significantly larger quantity of data and higher statistical power when compared to previous studies. The 3-level approach allowed us to properly assess the efficacy of these medications on internalizing psychopathology, avoiding potential biases related to the exclusion of information due to distinct assessment instruments, and to explore the multilevel structure of transdiagnostic efficacy.

In a meta-analysis of randomized trials, Natan Pereira Gosmann and colleagues study efficacy of SSRIs and SNRIs for symptoms of anxiety, obsessive-compulsive, and stress-related disorders.     

Epistasis Test in Meta-Analysis: A Multi-Parameter Markov Chain Monte Carlo Model for Consistency of Evidence

Conventional genome-wide association studies (GWAS) have been proven to be a successful strategy for identifying genetic variants associated with complex human traits. However, there is still a large heritability gap between GWAS and transitional family studies. The “missing heritability” has been suggested to be due to lack of studies focused on epistasis, also called gene–gene interactions, because individual trials have often had insufficient sample size. Meta-analysis is a common method for increasing statistical power. However, sufficient detailed information is difficult to obtain. A previous study employed a meta-regression-based method to detect epistasis, but it faced the challenge of inconsistent estimates. Here, we describe a Markov chain Monte Carlo-based method, called “Epistasis Test in Meta-Analysis” (ETMA), which uses genotype summary data to obtain consistent estimates of epistasis effects in meta-analysis. We defined a series of conditions to generate simulation data and tested the power and type I error rates in ETMA, individual data analysis and conventional meta-regression-based method. ETMA not only successfully facilitated consistency of evidence but also yielded acceptable type I error and higher power than conventional meta-regression. We applied ETMA to three real meta-analysis data sets. We found significant gene–gene interactions in the renin–angiotensin system and the polycyclic aromatic hydrocarbon metabolism pathway, with strong supporting evidence. In addition, glutathione S-transferase (GST) mu 1 and theta 1 were confirmed to exert independent effects on cancer. We concluded that the application of ETMA to real meta-analysis data was successful. Finally, we developed an R package, etma, for the detection of epistasis in meta-analysis [etma is available via the Comprehensive R Archive Network (CRAN) at https://cran.r-project.org/web/packages/etma/index.html].     

Blood pressure-lowering treatment for the prevention of cardiovascular events in patients with atrial fibrillation: An individual participant data meta-analysis

BackgroundRandomised evidence on the efficacy of blood pressure (BP)-lowering treatment to reduce cardiovascular risk in patients with atrial fibrillation (AF) is limited. Therefore, this study aimed to compare the effects of BP-lowering drugs in patients with and without AF at baseline.Methods and findingsThe study was based on the resource provided by the Blood Pressure Lowering Treatment Trialists’ Collaboration (BPLTTC), in which individual participant data (IPD) were extracted from trials with over 1,000 patient-years of follow-up in each arm, and that had randomly assigned patients to different classes of BP-lowering drugs, BP-lowering drugs versus placebo, or more versus less intensive BP-lowering regimens. For this study, only trials that had collected information on AF status at baseline were included. The effects of BP-lowering treatment on a composite endpoint of major cardiovascular events (stroke, ischaemic heart disease or heart failure) according to AF status at baseline were estimated using fixed-effect one-stage IPD meta-analyses based on Cox proportional hazards models stratified by trial. Furthermore, to assess whether the associations between the intensity of BP reduction and cardiovascular outcomes are similar in those with and without AF at baseline, we used a meta-regression. From the full BPLTTC database, 28 trials (145,653 participants) were excluded because AF status at baseline was uncertain or unavailable. A total of 22 trials were included with 188,570 patients, of whom 13,266 (7%) had AF at baseline. Risk of bias assessment showed that 20 trials were at low risk of bias and 2 trials at moderate risk. Meta-regression showed that relative risk reductions were proportional to trial-level intensity of BP lowering in patients with and without AF at baseline. Over 4.5 years of median follow-up, a 5-mm Hg systolic BP (SBP) reduction lowered the risk of major cardiovascular events both in patients with AF (hazard ratio [HR] 0.91, 95% confidence interval [CI] 0.83 to 1.00) and in patients without AF at baseline (HR 0.91, 95% CI 0.88 to 0.93), with no difference between subgroups. There was no evidence for heterogeneity of treatment effects by baseline SBP or drug class in patients with AF at baseline. The findings of this study need to be interpreted in light of its potential limitations, such as the limited number of trials, limitation in ascertaining AF cases due to the nature of the arrhythmia and measuring BP in patients with AF.ConclusionsIn this meta-analysis, we found that BP-lowering treatment reduces the risk of major cardiovascular events similarly in individuals with and without AF. Pharmacological BP lowering for prevention of cardiovascular events should be recommended in patients with AF.

In an individual patient data meta-analysis, Ana-Catarina Pinho-Gomes and colleagues investigate prevention of cardiovascular events with blood pressure-lowering treatment in those with and without atrial fibrillation.     

An Assessment of the Methodological Quality of Published Network Meta-Analyses: A Systematic Review

ObjectiveTo assess the methodological quality of published network meta-analysis.DesignSystematic review.MethodsWe searched the medical literature for network meta-analyses of pharmaceuticals. We assessed general study characteristics, study transparency and reproducibility, methodological approach, and reporting of findings. We compared studies published in journals with lower impact factors with those published in journals with higher impact factors, studies published prior to January 1^st, 2013 with those published after that date, and studies supported financially by industry with those supported by non-profit institutions or that received no support.ResultsThe systematic literature search identified 854 citations. Three hundred and eighteen studies met our inclusion criteria. The number of network meta-analyses has grown rapidly, with 48% of studies published since January 2013. The majority of network meta-analyses were supported by a non-profit institution or received no support (68%). We found considerable inconsistencies among reviewed studies. Eighty percent reported search terms, 61% a network diagram, 65% sufficient data to replicate the analysis, and 90% the characteristics of included trials. Seventy percent performed a risk of bias assessment of included trials, 40% an assessment of model fit, and 56% a sensitivity analysis. Among studies with a closed loop, 69% examined the consistency of direct and indirect evidence. Sixty-four percent of studies presented the full matrix of head-to-head treatment comparisons. For Bayesian studies, 41% reported the probability that each treatment was best, 31% reported treatment ranking, and 16% included the model code or referenced publicly-available code. Network meta-analyses published in higher impact factors journals and those that did not receive industry support performed better across the assessment criteria. We found few differences between older and newer studies.ConclusionsThere is substantial variation in the network meta-analysis literature. Consensus among guidelines is needed improve the methodological quality, transparency, and consistency of study conduct and reporting.     

Bayesian meta-analysis models for microarray data: a comparative study

Background

With the growing abundance of microarray data, statistical methods are increasingly needed to integrate results across studies. Two common approaches for meta-analysis of microarrays include either combining gene expression measures across studies or combining summaries such as p-values, probabilities or ranks. Here, we compare two Bayesian meta-analysis models that are analogous to these methods.

Results

Two Bayesian meta-analysis models for microarray data have recently been introduced. The first model combines standardized gene expression measures across studies into an overall mean, accounting for inter-study variability, while the second combines probabilities of differential expression without combining expression values. Both models produce the gene-specific posterior probability of differential expression, which is the basis for inference. Since the standardized expression integration model includes inter-study variability, it may improve accuracy of results versus the probability integration model. However, due to the small number of studies typical in microarray meta-analyses, the variability between studies is challenging to estimate. The probability integration model eliminates the need to model variability between studies, and thus its implementation is more straightforward. We found in simulations of two and five studies that combining probabilities outperformed combining standardized gene expression measures for three comparison values: the percent of true discovered genes in meta-analysis versus individual studies; the percent of true genes omitted in meta-analysis versus separate studies, and the number of true discovered genes for fixed levels of Bayesian false discovery. We identified similar results when pooling two independent studies of Bacillus subtilis. We assumed that each study was produced from the same microarray platform with only two conditions: a treatment and control, and that the data sets were pre-scaled.

Conclusion

The Bayesian meta-analysis model that combines probabilities across studies does not aggregate gene expression measures, thus an inter-study variability parameter is not included in the model. This results in a simpler modeling approach than aggregating expression measures, which accounts for variability across studies. The probability integration model identified more true discovered genes and fewer true omitted genes than combining expression measures, for our data sets.     

Cumulative meta-analysis: a new tool for detection of temporal trends and publication bias in ecology

Temporal changes in the magnitude of research findings have recently been recognized as a general phenomenon in ecology, and have been attributed to the delayed publication of non-significant results and disconfirming evidence. Here we introduce a method of cumulative meta-analysis which allows detection of both temporal trends and publication bias in the ecological literature. To illustrate the application of the method, we used two datasets from recently conducted meta-analyses of studies testing two plant defence theories. Our results revealed three phases in the evolution of the treatment effects. Early studies strongly supported the hypothesis tested, but the magnitude of the effect decreased considerably in later studies. In the latest studies, a trend towards an increase in effect size was observed. In one of the datasets, a cumulative meta-analysis revealed publication bias against studies reporting disconfirming evidence; such studies were published in journals with a lower impact factor compared to studies with results supporting the hypothesis tested. Correlation analysis revealed neither temporal trends nor evidence of publication bias in the datasets analysed. We thus suggest that cumulative meta-analysis should be used as a visual aid to detect temporal trends and publication bias in research findings in ecology in addition to the correlative approach.     

Routine antenatal anti-D prophylaxis in women who are Rh(D) negative: meta-analyses adjusted for differences in study design and quality

Background

To estimate the effectiveness of routine antenatal anti-D prophylaxis for preventing sensitisation in pregnant Rhesus negative women, and to explore whether this depends on the treatment regimen adopted.

Methods

Ten studies identified in a previous systematic literature search were included. Potential sources of bias were systematically identified using bias checklists, and their impact and uncertainty were quantified using expert opinion. Study results were adjusted for biases and combined, first in a random-effects meta-analysis and then in a random-effects meta-regression analysis.

Results

In a conventional meta-analysis, the pooled odds ratio for sensitisation was estimated as 0.25 (95% CI 0.18, 0.36), comparing routine antenatal anti-D prophylaxis to control, with some heterogeneity (I ² = 19%). However, this naïve analysis ignores substantial differences in study quality and design. After adjusting for these, the pooled odds ratio for sensitisation was estimated as 0.31 (95% CI 0.17, 0.56), with no evidence of heterogeneity (I ² = 0%). A meta-regression analysis was performed, which used the data available from the ten anti-D prophylaxis studies to inform us about the relative effectiveness of three licensed treatments. This gave an 83% probability that a dose of 1250 IU at 28 and 34 weeks is most effective and a 76% probability that a single dose of 1500 IU at 28–30 weeks is least effective.

Conclusion

There is strong evidence for the effectiveness of routine antenatal anti-D prophylaxis for prevention of sensitisation, in support of the policy of offering routine prophylaxis to all non-sensitised pregnant Rhesus negative women. All three licensed dose regimens are expected to be effective.     

Meta-analysis of studies with missing data

Summary .  Consider a meta-analysis of studies with varying proportions of patient-level missing data, and assume that each primary study has made certain missing data adjustments so that the reported estimates of treatment effect size and variance are valid. These estimates of treatment effects can be combined across studies by standard meta-analytic methods, employing a random-effects model to account for heterogeneity across studies. However, we note that a meta-analysis based on the standard random-effects model will lead to biased estimates when the attrition rates of primary studies depend on the size of the underlying study-level treatment effect. Perhaps ignorable within each study, these types of missing data are in fact not ignorable in a meta-analysis. We propose three methods to correct the bias resulting from such missing data in a meta-analysis: reweighting the DerSimonian–Laird estimate by the completion rate; incorporating the completion rate into a Bayesian random-effects model; and inference based on a Bayesian shared-parameter model that includes the completion rate. We illustrate these methods through a meta-analysis of 16 published randomized trials that examined combined pharmacotherapy and psychological treatment for depression.     

Therapist-supported Internet-based cognitive behaviour therapy yields similar effects as face-to-face therapy for psychiatric and somatic disorders: an updated systematic review and meta-analysis

Providing therapist-guided cognitive behaviour therapy via the Internet (ICBT) has advantages, but a central research question is to what extent similar clinical effects can be obtained as with gold-standard face-to-face cognitive behaviour therapy (CBT). In a previous meta-analysis published in this journal, which was updated in 2018, we found evidence that the pooled effects for the two formats were equivalent in the treatment of psychiatric and somatic disorders, but the number of published randomized trials was relatively low (n=20). As this is a field that moves rapidly, the aim of the current study was to conduct an update of our systematic review and meta-analysis of the clinical effects of ICBT vs. face-to-face CBT for psychiatric and somatic disorders in adults. We searched the PubMed database for relevant studies published from 2016 to 2022. The main inclusion criteria were that studies had to compare ICBT to face-to-face CBT using a randomized controlled design and targeting adult populations. Quality assessment was made using the Cochrane risk of bias criteria (Version 1), and the main outcome estimate was the pooled standardized effect size (Hedges’ g) using a random effects model. We screened 5,601 records and included 11 new randomized trials, adding them to the 20 previously identified ones (total n=31). Sixteen different clinical conditions were targeted in the included studies. Half of the trials were in the fields of depression/depressive symptoms or some form of anxiety disorder. The pooled effect size across all disorders was g=0.02 (95% CI: –0.09 to 0.14) and the quality of the included studies was acceptable. This meta-analysis further supports the notion that therapist-supported ICBT yields similar effects as face-to-face CBT.