Sequential change detection and monitoring of temporal trends in random-effects meta-analysis.
Ontology highlight
ABSTRACT:
SUBMITTER: Dogo SH
PROVIDER: S-EPMC5484389 | biostudies-literature | 2017 Jun
REPOSITORIES: biostudies-literature
Publications
Sequential change detection and monitoring of temporal trends in random-effects meta-analysis.
Dogo Samson Henry SH Clark Allan A Kulinskaya Elena E
Research synthesis methods 20161208 2
Temporal changes in magnitude of effect sizes reported in many areas of research are a threat to the credibility of the results and conclusions of meta-analysis. Numerous sequential methods for meta-analysis have been proposed to detect changes and monitor trends in effect sizes so that meta-analysis can be updated when necessary and interpreted based on the time it was conducted. The difficulties of sequential meta-analysis under the random-effects model are caused by dependencies in increments ...[more]
Similar Datasets
Project description:Meta-analysis is widely used to compare and combine the results of multiple independent studies. To account for between-study heterogeneity, investigators often employ random-effects models, under which the effect sizes of interest are assumed to follow a normal distribution. It is common to estimate the mean effect size by a weighted linear combination of study-specific estimators, with the weight for each study being inversely proportional to the sum of the variance of the effect-size estimator and the estimated variance component of the random-effects distribution. Because the estimator of the variance component involved in the weights is random and correlated with study-specific effect-size estimators, the commonly adopted asymptotic normal approximation to the meta-analysis estimator is grossly inaccurate unless the number of studies is large. When individual participant data are available, one can also estimate the mean effect size by maximizing the joint likelihood. We establish the asymptotic properties of the meta-analysis estimator and the joint maximum likelihood estimator when the number of studies is either fixed or increases at a slower rate than the study sizes and we discover a surprising result: the former estimator is always at least as efficient as the latter. We also develop a novel resampling technique that improves the accuracy of statistical inference. We demonstrate the benefits of the proposed inference procedures using simulated and empirical data.
| S-EPMC4681410 | biostudies-literature
Project description:One of the reasons for the popularity of meta-analysis is the notion that these analyses will possess more power to detect effects than individual studies. This is inevitably the case under a fixed-effect model. However, the inclusion of the between-study variance in the random-effects model, and the need to estimate this parameter, can have unfortunate implications for this power. We develop methods for assessing the power of random-effects meta-analyses, and the average power of the individual studies that contribute to meta-analyses, so that these powers can be compared. In addition to deriving new analytical results and methods, we apply our methods to 1991 meta-analyses taken from the Cochrane Database of Systematic Reviews to retrospectively calculate their powers. We find that, in practice, 5 or more studies are needed to reasonably consistently achieve powers from random-effects meta-analyses that are greater than the studies that contribute to them. Not only is statistical inference under the random-effects model challenging when there are very few studies but also less worthwhile in such cases. The assumption that meta-analysis will result in an increase in power is challenged by our findings.
| S-EPMC5590730 | biostudies-literature
Project description:BackgroundMultiple clinical conditions are associated with cerebral hypoxia/ischaemia and thereby an increased risk of hypoxic-ischaemic brain injury. Cerebral near-infrared spectroscopy monitoring (NIRS) is a tool to monitor brain oxygenation and perfusion, and the clinical uptake of NIRS has expanded over recent years. Specifically, NIRS is used in the neonatal, paediatric, and adult perioperative and intensive care settings. However, the available literature suggests that clinical benefits and harms of cerebral NIRS monitoring are uncertain. As rates of clinically significant hypoxic-ischaemic brain injuries are typically low, it is difficult for randomised clinical trials to capture a sufficiently large number of events to evaluate the clinical effect of cerebral NIRS monitoring, when focusing on specific clinical settings. The aim of this systematic review will be to evaluate the benefits and harms of clinical care with access to cerebral NIRS monitoring versus clinical care without cerebral NIRS monitoring in children and adults across all clinical settings.MethodsWe will conduct a systematic review with meta-analysis and trial sequential analysis. We will only include randomised clinical trials. The primary outcomes are all-cause mortality, moderate or severe persistent cognitive or neurological deficit, and proportion of participants with one or more serious adverse events. We will search CENTRAL, EMBASE, MEDLINE, and the Science Citation Index Expanded from their inception and onwards. Two reviewers will independently screen all citations, full-text articles, and extract data. The risk of bias will be appraised using the Cochrane risk of bias tool version 2.0. If feasible, we will conduct both random-effects meta-analysis and fixed-effect meta-analysis of outcome data. Additional analysis will be conducted to explore the potential sources of heterogeneity (e.g. risk of bias, clinical setting).DiscussionAs we include trials across multiple clinical settings, there is an increased probability of reaching a sufficient information size. However, heterogeneity between the included trials may impair our ability to interpret results to specific clinical settings. In this situation, we may have to depend on subgroup analyses with inherent increased risks of type I and II errors.Systematic review registrationPROSPERO CRD42020202986 . This systematic review protocol has been submitted for registration in the International Prospective Register of Systematic Reviews (PROSPERO) (http://www.crd.york.ac.uk/prospero) on the 12th of October 2020 and published on the 12th of November 2020 (registration ID CRD42020202986 ).
| S-EPMC8052775 | biostudies-literature
Project description:In a random effects meta-analysis model, true treatment effects for each study are routinely assumed to follow a normal distribution. However, normality is a restrictive assumption and the misspecification of the random effects distribution may result in a misleading estimate of overall mean for the treatment effect, an inappropriate quantification of heterogeneity across studies and a wrongly symmetric prediction interval.We focus on problems caused by an inappropriate normality assumption of the random effects distribution, and propose a novel random effects meta-analysis model where a Box-Cox transformation is applied to the observed treatment effect estimates. The proposed model aims to normalise an overall distribution of observed treatment effect estimates, which is sum of the within-study sampling distributions and the random effects distribution. When sampling distributions are approximately normal, non-normality in the overall distribution will be mainly due to the random effects distribution, especially when the between-study variation is large relative to the within-study variation. The Box-Cox transformation addresses this flexibly according to the observed departure from normality. We use a Bayesian approach for estimating parameters in the proposed model, and suggest summarising the meta-analysis results by an overall median, an interquartile range and a prediction interval. The model can be applied for any kind of variables once the treatment effect estimate is defined from the variable.A simulation study suggested that when the overall distribution of treatment effect estimates are skewed, the overall mean and conventional I 2 from the normal random effects model could be inappropriate summaries, and the proposed model helped reduce this issue. We illustrated the proposed model using two examples, which revealed some important differences on summary results, heterogeneity measures and prediction intervals from the normal random effects model.The random effects meta-analysis with the Box-Cox transformation may be an important tool for examining robustness of traditional meta-analysis results against skewness on the observed treatment effect estimates. Further critical evaluation of the method is needed.
| S-EPMC5517826 | biostudies-other
Project description:Temporal communities are the result of a consistent partitioning of nodes across multiple snapshots of an evolving network, and they provide insights into how dense clusters in a network emerge, combine, split and decay over time. To reliably detect temporal communities we need to not only find a good community partition in a given snapshot but also ensure that it bears some similarity to the partition(s) found in the previous snapshot(s), a particularly difficult task given the extreme sensitivity of community structure yielded by current methods to changes in the network structure. Here, motivated by the inertia of inter-node relationships, we present a new measure of partition distance called estrangement, and show that constraining estrangement enables one to find meaningful temporal communities at various degrees of temporal smoothness in diverse real-world datasets. Estrangement confinement thus provides a principled approach to uncovering temporal communities in evolving networks.
| S-EPMC3494021 | biostudies-literature
Project description:Recently, multivariate random-effects meta-analysis models have received a great deal of attention, despite its greater complexity compared to univariate meta-analyses. One of its advantages is its ability to account for the within-study and between-study correlations. However, the standard inference procedures, such as the maximum likelihood or maximum restricted likelihood inference, require the within-study correlations, which are usually unavailable. In addition, the standard inference procedures suffer from the problem of singular estimated covariance matrix. In this paper, we propose a pseudolikelihood method to overcome the aforementioned problems. The pseudolikelihood method does not require within-study correlations and is not prone to singular covariance matrix problem. In addition, it can properly estimate the covariance between pooled estimates for different outcomes, which enables valid inference on functions of pooled estimates, and can be applied to meta-analysis where some studies have outcomes missing completely at random. Simulation studies show that the pseudolikelihood method provides unbiased estimates for functions of pooled estimates, well-estimated standard errors, and confidence intervals with good coverage probability. Furthermore, the pseudolikelihood method is found to maintain high relative efficiency compared to that of the standard inferences with known within-study correlations. We illustrate the proposed method through three meta-analyses for comparison of prostate cancer treatment, for the association between paraoxonase 1 activities and coronary heart disease, and for the association between homocysteine level and coronary heart disease.
| S-EPMC4305202 | biostudies-literature
Project description:BackgroundRNA sequencing (RNA-Seq) allows an unbiased survey of the entire transcriptome in a high-throughput manner. A major application of RNA-Seq is to detect differential isoform expression across experimental conditions, which is of great biological interest due to its direct relevance to protein function and disease pathogenesis. Detection of differential isoform expression is challenging because of uncertainty in isoform expression estimation owing to ambiguous reads and variability in precision of the estimates across samples. It is desirable to have a method that can account for these issues and is flexible enough to allow adjustment for covariates.ResultsIn this paper, we present MetaDiff, a random-effects meta-regression model that naturally fits for the above purposes. Through extensive simulations and analysis of an RNA-Seq dataset on human heart failure, we show that the random-effects meta-regression approach is computationally fast, reliable, and can improve the power of differential expression analysis while controlling for false positives due to the effect of covariates or confounding variables. In contrast, several existing methods either fail to control false discovery rate or have reduced power in the presence of covariates or confounding variables. The source code, compiled JAR package and documentation of MetaDiff are freely available at https://github.com/jiach/MetaDiff.ConclusionOur results indicate that random-effects meta-regression offers a flexible framework for differential expression analysis of isoforms, particularly when gene expression is influenced by other variables.
| S-EPMC4489045 | biostudies-literature
Project description:BackgroundReported declines in sperm counts remain controversial today and recent trends are unknown. A definitive meta-analysis is critical given the predictive value of sperm count for fertility, morbidity and mortality.Objective and rationaleTo provide a systematic review and meta-regression analysis of recent trends in sperm counts as measured by sperm concentration (SC) and total sperm count (TSC), and their modification by fertility and geographic group.Search methodsPubMed/MEDLINE and EMBASE were searched for English language studies of human SC published in 1981-2013. Following a predefined protocol 7518 abstracts were screened and 2510 full articles reporting primary data on SC were reviewed. A total of 244 estimates of SC and TSC from 185 studies of 42 935 men who provided semen samples in 1973-2011 were extracted for meta-regression analysis, as well as information on years of sample collection and covariates [fertility group ('Unselected by fertility' versus 'Fertile'), geographic group ('Western', including North America, Europe Australia and New Zealand versus 'Other', including South America, Asia and Africa), age, ejaculation abstinence time, semen collection method, method of measuring SC and semen volume, exclusion criteria and indicators of completeness of covariate data]. The slopes of SC and TSC were estimated as functions of sample collection year using both simple linear regression and weighted meta-regression models and the latter were adjusted for pre-determined covariates and modification by fertility and geographic group. Assumptions were examined using multiple sensitivity analyses and nonlinear models.OutcomesSC declined significantly between 1973 and 2011 (slope in unadjusted simple regression models -0.70 million/ml/year; 95% CI: -0.72 to -0.69; P < 0.001; slope in adjusted meta-regression models = -0.64; -1.06 to -0.22; P = 0.003). The slopes in the meta-regression model were modified by fertility (P for interaction = 0.064) and geographic group (P for interaction = 0.027). There was a significant decline in SC between 1973 and 2011 among Unselected Western (-1.38; -2.02 to -0.74; P < 0.001) and among Fertile Western (-0.68; -1.31 to -0.05; P = 0.033), while no significant trends were seen among Unselected Other and Fertile Other. Among Unselected Western studies, the mean SC declined, on average, 1.4% per year with an overall decline of 52.4% between 1973 and 2011. Trends for TSC and SC were similar, with a steep decline among Unselected Western (-5.33 million/year, -7.56 to -3.11; P < 0.001), corresponding to an average decline in mean TSC of 1.6% per year and overall decline of 59.3%. Results changed minimally in multiple sensitivity analyses, and there was no statistical support for the use of a nonlinear model. In a model restricted to data post-1995, the slope both for SC and TSC among Unselected Western was similar to that for the entire period (-2.06 million/ml, -3.38 to -0.74; P = 0.004 and -8.12 million, -13.73 to -2.51, P = 0.006, respectively).Wider implicationsThis comprehensive meta-regression analysis reports a significant decline in sperm counts (as measured by SC and TSC) between 1973 and 2011, driven by a 50-60% decline among men unselected by fertility from North America, Europe, Australia and New Zealand. Because of the significant public health implications of these results, research on the causes of this continuing decline is urgently needed.
| S-EPMC6455044 | biostudies-literature
Project description:The pooled estimate of the average effect is of primary interest when fitting the random-effects model for meta-analysis. However estimates of study specific effects, for example those displayed on forest plots, are also often of interest. In this tutorial, we present the case, with the accompanying statistical theory, for estimating the study specific true effects using so called 'empirical Bayes estimates' or 'Best Unbiased Linear Predictions' under the random-effects model. These estimates can be accompanied by prediction intervals that indicate a plausible range of study specific true effects. We coalesce and elucidate the available literature and illustrate the methodology using two published meta-analyses as examples. We also perform a simulation study that reveals that coverage probability of study specific prediction intervals are substantially too low if the between-study variance is small but not negligible. Researchers need to be aware of this defect when interpreting prediction intervals. We also show how empirical Bayes estimates, accompanied with study specific prediction intervals, can embellish forest plots. We hope that this tutorial will serve to provide a clear theoretical underpinning for this methodology and encourage its widespread adoption.
| S-EPMC8361666 | biostudies-literature
Project description:BackgroundBivariate random effects meta-analysis of diagnostic tests is becoming a well established approach when studies present one two-by-two table or one pair of sensitivity and specificity. When studies present multiple thresholds for test positivity, usually meta-analysts reduce the data to a two-by-two table or take one threshold value at a time and apply the well developed meta-analytic approaches. However, this approach does not fully exploit the data.MethodsIn this paper we generalize the bivariate random effects approach to the situation where test results are presented with k thresholds for test positivity, resulting in a 2 by (k+1) table per study. The model can be fitted with standard likelihood procedures in statistical packages such as SAS (Proc NLMIXED). We follow a multivariate random effects approach; i.e., we assume that each study estimates a study specific ROC curve that can be viewed as randomly sampled from the population of all ROC curves of such studies. In contrast to the bivariate case, where nothing can be said about the shape of study specific ROC curves without additional untestable assumptions, the multivariate model can be used to describe study specific ROC curves. The models are easily extended with study level covariates.ResultsThe method is illustrated using published meta-analysis data. The SAS NLMIXED syntax is given in the appendix.ConclusionWe conclude that the multivariate random effects meta-analysis approach is an appropriate and convenient framework to meta-analyse studies with multiple threshold without losing any information by dichotomizing the test results.
| S-EPMC2787531 | biostudies-literature