scholarly journals Simulation results on the performance of statistical methods in cumulative meta analysis

2021 ◽  
Author(s):  
Elena Kulinskaya ◽  
Eung Yaw Mah
Keyword(s):  
Meta Analysis ◽  
Temporal Trends ◽  
Two Stage ◽  
Type 1 Error ◽  
Effect Measure ◽  
Inverse Variance ◽  
Study Results ◽  
Heterogeneity Variance ◽  
Stage 1 ◽  
Weighted Estimation

Cumulative meta-analysis (CMA) is a process of updating the results of existing meta-analysis to incorporate new study results. This is a popular way to present time-varying evidence. We investigate the properties of CMA, suggest possible improvements and provide the first in-depth simulation study of the use of CMA and CUSUM methods for detection of temporal trends in random-effects meta-analysis. We use the standardized mean difference (SMD) as an effect measure of interest. For CMA, we compare the standard inverse-variance-weighted estimation of the overall effect using REML-estimated between-study variance $\tau^2$ with the sample-size-weighted estimation of the effect combined with Kulinskaya-Dollinger-Bjørkestøl (2011) (KDB) estimation of $\tau^2$. For all methods, we consider type 1 error under no shift and power under shift in the mean. To ameliorate the lack of power in CMA, we introduce the two-stage CMA, where the heterogeneity variance $\tau^2$ is estimated at stage 1 (first 5-10 studies), and the further CMA monitors a target value of effect, keeping the $\tau^2$ value fixed. We recommend the use of this two-stage CMA combined with cumulative testing for positive shift in $\tau^2$.

scholarly journals Exploring consequences of simulation design for apparent performance of methods of meta-analysis

2021 ◽  
pp. 096228022110130
Author(s):  
Elena Kulinskaya ◽  
David C. Hoaglin ◽  
Ilyas Bakbergenuly
Keyword(s):  
Odds Ratio ◽  
Meta Analysis ◽  
Data Generation ◽  
Sample Sizes ◽  
Simulation Design ◽  
Two Stage ◽  
Inverse Variance ◽  
Log Odds ◽  
Heterogeneity Variance ◽  
The Impact

Contemporary statistical publications rely on simulation to evaluate performance of new methods and compare them with established methods. In the context of random-effects meta-analysis of log-odds-ratios, we investigate how choices in generating data affect such conclusions. The choices we study include the overall log-odds-ratio, the distribution of probabilities in the control arm, and the distribution of study-level sample sizes. We retain the customary normal distribution of study-level effects. To examine the impact of the components of simulations, we assess the performance of the best available inverse–variance–weighted two-stage method, a two-stage method with constant sample-size-based weights, and two generalized linear mixed models. The results show no important differences between fixed and random sample sizes. In contrast, we found differences among data-generation models in estimation of heterogeneity variance and overall log-odds-ratio. This sensitivity to design poses challenges for use of simulation in choosing methods of meta-analysis.

scholarly journals Correction of Hyponatremia May Be a Treatment Stratification Biomarker: A Two-Stage Systematic Review and Meta-Analysis

2018 ◽  
Vol 7 (9) ◽  
pp. 262 ◽  
Author(s):  
Francisco Herrera-Gómez ◽  
Diana Monge-Donaire ◽  
Carlos Ochoa-Sangrador ◽  
Juan Bustamante-Munguira ◽  
Eric Alamartine ◽  
...  
Keyword(s):  
Systematic Review ◽  
Clinical Outcomes ◽  
Meta Analysis ◽  
Sodium Concentration ◽  
Evidence Base ◽  
The Body ◽  
Two Stage ◽  
Translational Pharmacology ◽  
New Treatment ◽  
Stage 1

Changes in serum sodium concentration ([Na+]serum) can permit evaluation of the treatment effect of vasopressin antagonists (vaptans) in patients with worsening heart failure (HF) or cirrhotic ascites; that is, they may act as a treatment stratification biomarker. A two-stage systematic review and meta-analysis were carried out and contextualized by experts in fluid resuscitation and translational pharmacology (registration ID in the International Prospective Register of Systematic Reviews (PROSPERO): CRD42017051440). Meta-analysis of aggregated dichotomous outcomes was performed. Pooled estimates for correction of hyponatremia (normalization or an increase in [Na+]serum of at least 3–5 mEq/L) under treatment with vaptans (Stage 1) and for clinical outcomes in both worsening HF (rehospitalization and/or death) and cirrhotic ascites (ascites worsening) when correction of hyponatremia is achieved (Stage 2) were calculated. The body of evidence was assessed. Correction of hyponatremia was achieved under vaptans (odds ratio (OR)/95% confidence interval (95% CI)/I2/number of studies (n): 7.48/4.95–11.30/58%/15). Clinical outcomes in both worsening HF and cirrhotic ascites improved when correction of hyponatremia was achieved (OR/95% CI/I2/n: 0.51/0.26–0.99/52%/3). Despite the appropriateness of the study design, however, there are too few trials to consider that correction of hyponatremia is a treatment stratification biomarker. Patients with worsening HF or with cirrhotic ascites needing treatment with vaptans, have better clinical outcomes when correction of hyponatremia is achieved. However, the evidence base needs to be enlarged to propose formally correction of hyponatremia as a new treatment stratification biomarker. Markers for use with drugs are needed to improve outcomes related to the use of medicines.

scholarly journals The statistical importance of a study for a network meta-analysis estimate

2020 ◽  
Author(s):  
Gerta Rücker ◽  
Adriani Nikolakopoulou ◽  
Theodoros Papakonstantinou ◽  
Georgia Salanti ◽  
Richard D. Riley ◽  
...  
Keyword(s):  
Meta Analysis ◽  
Indirect Evidence ◽  
Two Stage ◽  
Percentage Contribution ◽  
One Stage ◽  
Inverse Variance ◽  
The Given ◽  
Intuitive Interpretation ◽  
Hat Matrix ◽  
Natural Way

Abstract Background: In pairwise meta-analysis, the contribution of each study to the pooled estimate is given by its weight, which is based on the inverse variance of the estimate from that study. For network meta-analysis (NMA), the contribution of direct (and indirect) evidence is easily obtained from the diagonal elements of a hat matrix. It is, however, not fully clear how to generalize this to the percentage contribution of each study to a NMA estimate. Methods: We define the importance of each study for a NMA estimate by the reduction of the estimate's variance when adding the given study to the others. An equivalent interpretation is the relative loss in precision when the study is left out. Importances are values between 0 and 1. An importance of 1 means that the study is an essential link of the pathway in the network connecting one of the treatments with another. Results: Importances can be defined for two-stage and one-stage NMA. These numbers in general do not add to one and thus cannot be interpreted as `percentage contributions'. After briefly discussing other available approaches, we question whether it is possible to obtain unique percentage contributions for NMA. Conclusions: Importances generalize the concept of weights in pairwise meta-analysis in a natural way. Moreover, they are uniquely defined, easily calculated, and have an intuitive interpretation. We give some real examples for illustration.

scholarly journals The statistical importance of a study for a network meta-analysis estimate

2020 ◽  
Author(s):  
Gerta Rücker ◽  
Adriani Nikolakopoulou ◽  
Theodoros Papakonstantinou ◽  
Georgia Salanti ◽  
Richard D. Riley ◽  
...  
Keyword(s):  
Meta Analysis ◽  
Indirect Evidence ◽  
Two Stage ◽  
Percentage Contribution ◽  
One Stage ◽  
Inverse Variance ◽  
The Given ◽  
Intuitive Interpretation ◽  
Hat Matrix ◽  
Natural Way

Abstract Background In pairwise meta-analysis, the contribution of each study to the pooled estimate is given by its weight, which is based on the inverse variance of the estimate from that study. For network meta-analysis (NMA), the contribution of direct (and indirect) evidence is easily obtained from the diagonal elements of a hat matrix. It is, however, not fully clear how to generalize this to the percentage contribution of each study to a NMA estimate.MethodsWe define the importance of each study for a NMA estimate by the reduction of the estimate's variance when adding the given study to the others. An equivalent interpretation is the relative loss in precision when the study is left out. Importances are values between 0 and 1. An importance of 1 means that the study is an essential link of the pathway in the network connecting one of the treatments with another. ResultsImportances can be defined for two-stage and one-stage NMA. These numbers in general do not add to one and thus cannot be interpreted as `percentage contributions'. After briefly discussing other available approaches, we question whether it is possible to obtain unique percentage contributions for NMA. ConclusionsImportances generalize the concept of weights in pairwise meta-analysis in a natural way. Moreover, they are uniquely defined, easily calculated, and have an intuitive interpretation. We give some real examples for illustration.

scholarly journals An Individual Patient Data Meta-Analysis with Colombian Studies on the Effect of Dark Chocolate Consumption on Cardiovascular Risk Parameters

2020 ◽  
Vol 2020 ◽  
pp. 1-8
Author(s):  
Leidy Alvarez ◽  
Javier Contreras ◽  
Mónica Giraldo
Keyword(s):  
Body Mass Index ◽  
Clinical Trials ◽  
Lipid Profile ◽  
Body Mass ◽  
Meta Analysis ◽  
Abdominal Circumference ◽  
Two Stage ◽  
One Stage ◽  
Study Results ◽  
The One

Background. It is postulated that cocoa solids possess cardioprotective capacity by various mechanisms. In the different cocoa studies evaluating cardiovascular disease, there are no conclusive data on the role it plays in controlling the lipid profile and anthropometric variables, perhaps because the concentration of cocoa, the geographical origin of the population, and the different concentrations supplied lead to a high heterogeneity of results. This study aims to estimate the effect of consuming cocoa-rich chocolate compared to placebo on the lipid profile and anthropometric variables based on data from three clinical trials conducted in Colombia. Methods. Meta-analysis of individual data from three randomized clinical trials conducted in Colombia. The entire population of the primary studies was included, which was reassigned into intervention groups if they consumed 50 grams of 70% concentrated cocoa or placebo, which was considered to be cocoa-free or with a concentration less than 50 grams. The variables at the beginning of the study were analyzed with medians, interquartile ranges, means, and deviations according to whether they met the normality assumption. Multiple imputations were used to manage missing data and were analyzed using the two approaches proposed for this type of study, that of one and two stages. In the two-stage approach, the data were weighted on a conventional Forrest plot, while in the one-stage approach, linear regressions with mixed models were applied. This study is governed by the regulations described in the 2013 Declaration of Helsinki and by article 11 of Resolution 8430 of 1993, which classifies it as a risk-free study. Results. A total of 275 participants were included, who consumed cocoa or placebo for 81 days on average; 52.7% were female and few smoked at the time of the intervention (31/275). Physical activity performed in number of hours per week was comparable between the intervention groups. When evaluating total cholesterol, low-density cholesterol (LDL), high-density cholesterol (HDL), triglycerides, abdominal circumference, and final body mass index with both the one-stage and two-stage approaches, there were no significant differences between the two groups. Conclusions. According to the results obtained in the meta-analysis, the consumption of cocoa in the Colombian population does not seem to significantly modify variables such as lipid profile, abdominal circumference, and body mass index. This conclusion according to the quality of the evidence has a weak recommendation and a low-to-moderate certainty. However, the analysis through the two proposed approaches yielded similar results.

Impulsivity and Aggression: A Meta-analysis Using the UPPS Model of Impulsivity

2019 ◽  
Author(s):  
Konrad Bresin
Keyword(s):  
Structural Equation Modeling ◽  
Sensation Seeking ◽  
Structural Equation ◽  
Meta Analysis ◽  
The Other ◽  
Equation Modeling ◽  
Negative Urgency ◽  
Two Stage ◽  
Trait Impulsivity

Trait impulsivity has long been proposed to play a role in aggression, but the results across studies have been mixed. One possible explanation for the mixed results is that impulsivity is a multifaceted construct and some, but not all, facets are related to aggression. The goal of the current meta-analysis was to determine the relation between the different facets of impulsivity (i.e., negative urgency, positive urgency, lack of premeditation, lack of perseverance, and sensation seeking) and aggression. The results from 93 papers with 105 unique samples (N = 36, 215) showed significant and small-to-medium correlations between each facet of impulsivity and aggression across several different forms of aggression, with more impulsivity being associated with more aggression. Moreover, negative urgency (r = .24, 95% [.18, .29]), positive urgency (r = .34, 95% [.19, .44]), and lack of premeditation (r = .23, 95% [.20, .26]) had significantly stronger associations with aggression than the other scales (rs < .18). Two-stage meta-analytic structural equation modeling showed that these effects were not due to overlap among facets of impulsivity. These results help advance the field of aggression research by clarifying the role of impulsivity and may be of interest to researchers and practitioners in several disciplines.

ctDNA as a prognostic factor in operable colon cancer patients: a systematic review and meta-analysis

2020 ◽  
Author(s):  
Emre Yekedüz ◽  
Elif Berna Köksoy ◽  
Hakan Akbulut ◽  
Yüksel Ürün ◽  
Güngör Utkan
Keyword(s):  
Colon Cancer ◽  
Prognostic Factor ◽  
Cancer Patients ◽  
Meta Analysis ◽  
Circulating Tumor Dna ◽  
Random Effects Model ◽  
Inverse Variance ◽  
Increased Risk ◽  
Significant Step ◽  
Tumor Dna

Aim: Using circulating tumor DNA (ctDNA) instead of historical clinicopathological factors to select patients for adjuvant chemotherapy (ACT) may reduce inappropriate therapy. Material & methods: MEDLINE was searched on March 31, 2020. Studies, including data related to the prognostic value of ctDNA in the colon cancer patients after surgery and after ACT, were included. The generic inverse-variance method with a random-effects model was used for meta-analysis. Results: Four studies were included for this meta-analysis. ctDNA-positive colon cancer patients after surgery and ACT had a significantly increased risk of recurrence compared with ctDNA-negative patients. Conclusions: ctDNA is an independent prognostic factor, and this meta-analysis is a significant step for using ctDNA instead of historical prognostic factors in the adjuvant setting.

Genome-Wide Association Studies Identify Two Novel Loci Conferring Susceptibility to Diabetic Retinopathy in Japanese Patients with Type 2 Diabetes

2021 ◽  
Author(s):  
Minako Imamura ◽  
Atsushi Takahashi ◽  
Masatoshi Matsunami ◽  
Momoko Horikoshi ◽  
Minoru Iwata ◽  
...  
Keyword(s):  
Type 2 Diabetes ◽  
Diabetic Retinopathy ◽  
Association Studies ◽  
Meta Analysis ◽  
Japanese Patients ◽  
Genome Wide Association ◽  
Genome Wide Association Studies ◽  
Genome Wide ◽  
Stage 1

Abstract Several reports have suggested that genetic susceptibility contributes to the development and progression of diabetic retinopathy. We aimed to identify genetic loci that confer susceptibility to diabetic retinopathy in Japanese patients with type 2 diabetes. We analysed 5 790 508 single nucleotide polymorphisms (SNPs) in 8880 Japanese patients with type 2 diabetes, 4839 retinopathy cases and 4041 controls, as well as 2217 independent Japanese patients with type 2 diabetes, 693 retinopathy cases, and 1524 controls. The results of these two genome-wide association studies (GWAS) were combined with an inverse variance meta-analysis (Stage-1), followed by de novo genotyping for the candidate SNP loci (p < 1.0 × 10−4) in an independent case–control study (Stage-2, 2260 cases and 723 controls). After combining the association data (Stage-1 and -2) using meta-analysis, the associations of two loci reached a genome-wide significance level: rs12630354 near STT3B on chromosome 3, p = 1.62 × 10−9, odds ratio (OR) = 1.17, 95% confidence interval (CI) 1.11–1.23, and rs140508424 within PALM2 on chromosome 9, p = 4.19 × 10−8, OR = 1.61, 95% CI 1.36–1.91. However, the association of these two loci were not replicated in Korean, European, or African American populations. Gene-based analysis using Stage-1 GWAS data identified a gene-level association of EHD3 with susceptibility to diabetic retinopathy (p = 2.17 × 10−6). In conclusion, we identified two novel SNP loci, STT3B and PALM2, and a novel gene, EHD3, that confers susceptibility to diabetic retinopathy; however, further replication studies are required to validate these associations.

scholarly journals Fibroblast Growth Factor 20 Gene Polymorphism in Parkinson’s Disease in Asian Population: A Meta-Analysis

Genes ◽  
2021 ◽  
Vol 12 (5) ◽  
pp. 674
Author(s):  
Han-Lin Chiang ◽  
Yih-Ru Wu ◽  
Yi-Chun Chen ◽  
Hon-Chung Fung ◽  
Chiung-Mei Chen
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Meta Analysis ◽  
Lewy Bodies ◽  
Asian Population ◽  
Protective Role ◽  
Lewy Neurites ◽  
Chinese Populations ◽  
Study Results

Parkinson’s disease (PD) is a neurodegenerative disease with the pathological hallmark of Lewy bodies and Lewy neurites composed of α-synuclein. The SNP rs591323 is one of the risk loci located near the FGF20 gene that has been implicated in PD. The variation of FGF20 in the 3′ untranslated region was shown to increase α-synuclein expression. We examined the association of rs591323 with the risk of PD in a Taiwanese population and conducted a meta-analysis, including our study and two other studies from China, to further confirm the role of this SNP in Taiwanese/Chinese populations. A total of 586 patients with PD and 586 health controls (HCs) were included in our study. We found that the minor allele (A) and the AA + GA genotype under the dominant model are significantly less frequent in PD than in controls. The meta-analysis consisted of 1950 patients with PD and 2073 healthy controls from three studies. There was significant association between rs591323 and the risk of PD in the additive (Z = −3.96; p < 0.0001) and the dominant models (Z = −4.01; p < 0.0001). Our study results and the meta-analysis support the possible protective role of the rs591323 A allele in PD in Taiwanese/Chinese populations.

Sign in / Sign up

Export Citation Format

Share Document