Aggregate-data estimation of an individual patient data linear random effects meta-analysis with a patient covariate-treatment interaction term.
Ontology highlight
ABSTRACT:
SUBMITTER: Kovalchik SA
PROVIDER: S-EPMC3590924 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The aim of the study was to examine how well aggregate data meta-analyses (ADMAs) and individual patient data meta-analyses (IPDMAs) agree in their overall results and how frequently interactions are detected in IPDMAs and ADMAs.ADMA articles immediately published before the IPDMA and matching the research topic were identified. Agreement in the overall result was achieved if the estimate was in the same direction. The number of subgroup analyses, in particular that of significant interactions, was compared between the 2 types of meta-analyses.A total of 829 IPDMA articles were identified; 129 (15.6%) were found to have a matched ADMA article and 204 paired meta-analyses were identified. Agreement in the overall effect was observed in 187 (91.7%) of the 204 paired meta-analyses. Fifty-three (26.0%) ADMAs and 121 (59.3%) IPDMAs conducted subgroup analyses and presented 150 and 634 subgroup analyses, respectively. The IPDMAs conducted 7 times more subgroup analyses on interaction (544 in IPDMAs vs 68 in ADMAs) and identified 14 times more potential interactions (44 in IPDMAs vs 3 in ADMAs).ADMAs will almost always agree with their corresponding IPDMAs in the overall result if greater efforts are made to improve the methodology in conducting ADMAs. The IPDMA is required mostly if interactions are suspected.
| S-EPMC4998822 | biostudies-literature
Project description:BackgroundNetwork meta-analysis methods extend the standard pair-wise framework to allow simultaneous comparison of multiple interventions in a single statistical model. Despite published work on network meta-analysis mainly focussing on the synthesis of aggregate data, methods have been developed that allow the use of individual patient-level data specifically when outcomes are dichotomous or continuous. This paper focuses on the synthesis of individual patient-level and summary time to event data, motivated by a real data example looking at the effectiveness of high compression treatments on the healing of venous leg ulcers.MethodsThis paper introduces a novel network meta-analysis modelling approach that allows individual patient-level (time to event with censoring) and summary-level data (event count for a given follow-up time) to be synthesised jointly by assuming an underlying, common, distribution of time to healing. Alternative model assumptions were tested within the motivating example. Model fit and adequacy measures were used to compare and select models.ResultsDue to the availability of individual patient-level data in our example we were able to use a Weibull distribution to describe time to healing; otherwise, we would have been limited to specifying a uniparametric distribution. Absolute effectiveness estimates were more sensitive than relative effectiveness estimates to a range of alternative specifications for the model.ConclusionsThe synthesis of time to event data considering individual patient-level data provides modelling flexibility, and can be particularly important when absolute effectiveness estimates, and not just relative effect estimates, are of interest.
| S-EPMC4236567 | biostudies-literature
Project description:Network meta-analysis can synthesize evidence from studies comparing multiple treatments for the same disease. Sometimes the treatments of a network are complex interventions, comprising several independent components in different combinations. A component network meta-analysis (CNMA) can be used to analyze such data and can in principle disentangle the individual effect of each component. However, components may interact with each other, either synergistically or antagonistically. Deciding which interactions, if any, to include in a CNMA model may be difficult, especially for large networks with many components. In this article, we present two Bayesian CNMA models that can be used to identify prominent interactions between components. Our models utilize Bayesian variable selection methods, namely the stochastic search variable selection and the Bayesian LASSO, and can benefit from the inclusion of prior information about important interactions. Moreover, we extend these models to combine data from studies providing aggregate information and studies providing individual patient data (IPD). We illustrate our models in practice using three real datasets, from studies in panic disorder, depression, and multiple myeloma. Finally, we describe methods for developing web-applications that can utilize results from an IPD-CNMA, to allow for personalized estimates of relative treatment effects given a patient's characteristics.
| S-EPMC9314605 | biostudies-literature
Project description:Dealing with high dimensional markers, such as gene expression data obtained using microarray chip technology or genomics studies, is a key challenge because the numbers of features greatly exceeds the number of biological samples. After selecting biologically relevant genes, how to summarize the expression of selected genes and then further build predicted model is an important issue in medical applications. One intuitive method of addressing this challenge assigns different weights to different features, subsequently combining this information into a single score, named the compound covariate. Investigators commonly employ this score to assess whether an association exists between the compound covariate and clinical outcomes adjusted for baseline covariates. However, we found that some clinical papers concerned with such analysis report bias p-values based on flawed compound covariate in their training data set.We correct this flaw in the analysis and we also propose treating the compound score as a random covariate, to achieve more appropriate results and significantly improve study power for survival outcomes. With this proposed method, we thoroughly assess the performance of two commonly used estimated gene weights through simulation studies. When the sample size is 100, and censoring rates are 50%, 30%, and 10%, power is increased by 10.6%, 3.5%, and 0.4%, respectively, by treating the compound score as a random covariate rather than a fixed covariate. Finally, we assess our proposed method using two publicly available microarray data sets.In this article, we correct this flaw in the analysis and the propose method, treating the compound score as a random covariate, can achieve more appropriate results and improve study power for survival outcomes.
| S-EPMC3524312 | biostudies-literature
Project description:Coefficient estimation in linear regression models with missing data is routinely done in the mean regression framework. However, the mean regression theory breaks down if the error variance is infinite. In addition, correct specification of the likelihood function for existing imputation approach is often challenging in practice, especially for skewed data. In this paper, we develop a novel composite quantile regression and a weighted quantile average estimation procedure for parameter estimation in linear regression models when some responses are missing at random. Instead of imputing the missing response by randomly drawing from its conditional distribution, we propose to impute both missing and observed responses by their estimated conditional quantiles given the observed data and to use the parametrically estimated propensity scores to weigh check functions that define a regression parameter. Both estimation procedures are resistant to heavy-tailed errors or outliers in the response and can achieve nice robustness and efficiency. Moreover, we propose adaptive penalization methods to simultaneously select significant variables and estimate unknown parameters. Asymptotic properties of the proposed estimators are carefully investigated. An efficient algorithm is developed for fast implementation of the proposed methodologies. We also discuss a model selection criterion, which is based on an IC Q -type statistic, to select the penalty parameters. The performance of the proposed methods is illustrated via simulated and real data sets.
| S-EPMC6070309 | biostudies-literature
Project description:BackgroundIn the last years more and more multi-omics data are becoming available, that is, data featuring measurements of several types of omics data for each patient. Using multi-omics data as covariate data in outcome prediction is both promising and challenging due to the complex structure of such data. Random forest is a prediction method known for its ability to render complex dependency patterns between the outcome and the covariates. Against this background we developed five candidate random forest variants tailored to multi-omics covariate data. These variants modify the split point selection of random forest to incorporate the block structure of multi-omics data and can be applied to any outcome type for which a random forest variant exists, such as categorical, continuous and survival outcomes. Using 20 publicly available multi-omics data sets with survival outcome we compared the prediction performances of the block forest variants with alternatives. We also considered the common special case of having clinical covariates and measurements of a single omics data type available.ResultsWe identify one variant termed "block forest" that outperformed all other approaches in the comparison study. In particular, it performed significantly better than standard random survival forest (adjusted p-value: 0.027). The two best performing variants have in common that the block choice is randomized in the split point selection procedure. In the case of having clinical covariates and a single omics data type available, the improvements of the variants over random survival forest were larger than in the case of the multi-omics data. The degrees of improvements over random survival forest varied strongly across data sets. Moreover, considering all clinical covariates mandatorily improved the performance. This result should however be interpreted with caution, because the level of predictive information contained in clinical covariates depends on the specific application.ConclusionsThe new prediction method block forest for multi-omics data can significantly improve the prediction performance of random forest and outperformed alternatives in the comparison. Block forest is particularly effective for the special case of using clinical covariates in combination with measurements of a single omics data type.
| S-EPMC6598279 | biostudies-literature
Project description:Meta-analyses of clinical trials typically focus on one outcome at a time. However, treatment decision-making depends on an overall assessment of outcomes balancing benefit in various domains and potential risks. This calls for meta-analysis methods for combined outcomes that encompass information from different domains. When individual patient data (IPD) are available from all studies, combined outcomes can be calculated for each individual and standard meta-analysis methods would apply. However, IPD are usually difficult to obtain. We propose a method to estimate the overall treatment effect for combined outcomes based on first reconstructing pseudo IPD from available summary statistics and then pooling estimates from multiple reconstructed datasets. We focus on combined outcomes constructed from two continuous original outcomes. The reconstruction step requires the specification of the joint distribution of these two original outcomes, including the correlation which is often unknown. For outcomes that are combined in a linear fashion, misspecifications of this correlation affect efficiency, but not consistency, of the resulting treatment effect estimator. For other combined outcomes, an accurate estimate of the correlation is necessary to ensure the consistency of treatment effect estimates. To this end, we propose several ways to estimate this correlation under different data availability scenarios. We evaluate the performance of the proposed methods through simulation studies and apply these to two examples: (a) a meta-analysis of dipeptidyl peptidase-4 inhibitors vs control on treating type 2 diabetes; and (b) a meta-analysis of positive airway pressure therapy vs control on lowering blood pressure among patients with obstructive sleep apnea.
| S-EPMC7680580 | biostudies-literature
Project description:Lack of data is an obvious limitation to what can be modelled. However, aggregate data in the form of means and possibly (co)variances, as well as previously published pharmacometric models, are often available. Being able to use all available data is desirable, and therefore this paper will outline several methods for using aggregate data as the basis of parameter estimation. The presented methods can be used for estimation of parameters from aggregate data, and as a computationally efficient alternative for the stochastic simulation and estimation procedure. They also allow for population PK/PD optimal design in the case when the data-generating model is different from the data-analytic model, a scenario for which no solutions have previously been available. Mathematical analysis and computational results confirm that the aggregate-data FO algorithm converges to the same estimates as the individual-data FO and yields near-identical standard errors when used in optimal design. The aggregate-data MC algorithm will asymptotically converge to the exactly correct parameter estimates if the data-generating model is the same as the data-analytic model. The performance of the aggregate-data methods were also compared to stochastic simulations and estimations (SSEs) when the data-generating model is different from the data-analytic model. The aggregate-data FO optimal design correctly predicted the sampling distributions of 200 models fitted to simulated datasets with the individual-data FO method.
| S-EPMC8405508 | biostudies-literature
Project description:BackgroundTestosterone is the standard treatment for male hypogonadism, but there is uncertainty about its cardiovascular safety due to inconsistent findings. We aimed to provide the most extensive individual participant dataset (IPD) of testosterone trials available, to analyse subtypes of all cardiovascular events observed during treatment, and to investigate the effect of incorporating data from trials that did not provide IPD.MethodsWe did a systematic review and meta-analysis of randomised controlled trials including IPD. We searched MEDLINE, MEDLINE In-Process & Other Non-Indexed Citations, MEDLINE Epub Ahead of Print, Embase, Science Citation Index, the Cochrane Controlled Trials Register, Cochrane Database of Systematic Reviews, and Database of Abstracts of Review of Effects for literature from 1992 onwards (date of search, Aug 27, 2018). The following inclusion criteria were applied: (1) men aged 18 years and older with a screening testosterone concentration of 12 nmol/L (350 ng/dL) or less; (2) the intervention of interest was treatment with any testosterone formulation, dose frequency, and route of administration, for a minimum duration of 3 months; (3) a comparator of placebo treatment; and (4) studies assessing the pre-specified primary or secondary outcomes of interest. Details of study design, interventions, participants, and outcome measures were extracted from published articles and anonymised IPD was requested from investigators of all identified trials. Primary outcomes were mortality, cardiovascular, and cerebrovascular events at any time during follow-up. The risk of bias was assessed using the Cochrane Risk of Bias tool. We did a one-stage meta-analysis using IPD, and a two-stage meta-analysis integrating IPD with data from studies not providing IPD. The study is registered with PROSPERO, CRD42018111005.Findings9871 citations were identified through database searches and after exclusion of duplicates and of irrelevant citations, 225 study reports were retrieved for full-text screening. 116 studies were subsequently excluded for not meeting the inclusion criteria in terms of study design and characteristics of intervention, and 35 primary studies (5601 participants, mean age 65 years, [SD 11]) reported in 109 peer-reviewed publications were deemed suitable for inclusion. Of these, 17 studies (49%) provided IPD (3431 participants, mean duration 9·5 months) from nine different countries while 18 did not provide IPD data. Risk of bias was judged to be low in most IPD studies (71%). Fewer deaths occurred with testosterone treatment (six [0·4%] of 1621) than placebo (12 [0·8%] of 1537) without significant differences between groups (odds ratio [OR] 0·46 [95% CI 0·17-1·24]; p=0·13). Cardiovascular risk was similar during testosterone treatment (120 [7·5%] of 1601 events) and placebo treatment (110 [7·2%] of 1519 events; OR 1·07 [95% CI 0·81-1·42]; p=0·62). Frequently occurring cardiovascular events included arrhythmia (52 of 166 vs 47 of 176), coronary heart disease (33 of 166 vs 33 of 176), heart failure (22 of 166 vs 28 of 176), and myocardial infarction (10 of 166 vs 16 of 176). Overall, patient age (interaction 0·97 [99% CI 0·92-1·03]; p=0·17), baseline testosterone (interaction 0·97 [0·82-1·15]; p=0·69), smoking status (interaction 1·68 [0·41-6·88]; p=0.35), or diabetes status (interaction 2·08 [0·89-4·82; p=0·025) were not associated with cardiovascular risk.InterpretationWe found no evidence that testosterone increased short-term to medium-term cardiovascular risks in men with hypogonadism, but there is a paucity of data evaluating its long-term safety. Long-term data are needed to fully evaluate the safety of testosterone.FundingNational Institute for Health Research Health Technology Assessment Programme.
| S-EPMC9184259 | biostudies-literature
Project description:Under covariate adaptive randomization, the covariate is tied to both randomization and analysis. Misclassification of such covariate will impact the intended treatment assignment; further, it is unclear what the appropriate analysis strategy should be. We explore the impact of such misclassification on the trial's statistical operating characteristics. Simulation scenarios were created based on the misclassification rate and the covariate effect on the outcome. Models including unadjusted, adjusted for the misclassified, or adjusted for the corrected covariate were compared using logistic regression for a binary outcome and Poisson regression for a count outcome. For the binary outcome using logistic regression, type I error can be maintained in the adjusted model, but the test is conservative using an unadjusted model. Power decreased with both increasing covariate effect on the outcome as well as the misclassification rate. Treatment effect estimates were biased towards the null for both the misclassified and unadjusted models. For the count outcome using a Poisson model, covariate misclassification led to inflated type I error probabilities and reduced power in the misclassified and the unadjusted model. The impact of covariate misclassification under covariate-adaptive randomization differs depending on the underlying distribution of the outcome.
| S-EPMC5476516 | biostudies-literature