scholarly journals Multivariate meta-analysis of multiple outcomes: characteristics and predictors of borrowing of strength from Cochrane reviews

2021 ◽  
Author(s):  
Miriam Hattle ◽  
Danielle L. Burke ◽  
Thomas Trikalinos ◽  
Christopher H. Schmid ◽  
Yong Chen ◽  
...  
Keyword(s):  
Prediction Model ◽  
Study Design ◽  
Meta Analysis ◽  
Binary Outcomes ◽  
Multiple Outcomes ◽  
Analysis Methods ◽  
Cochrane Reviews ◽  
Meta Analyses

Abstract Objectives Multivariate meta-analysis allows the joint synthesis of multiple outcomes accounting for their correlation. This enables borrowing of strength (BoS) across outcomes, which may lead to greater efficiency and even different conclusions compared to separate univariate meta-analyses. However, multivariate meta-analysis is complex to apply, so guidance is needed to flag (in advance of analysis) when the approach is most useful. Study design and setting We use 43 Cochrane intervention reviews to empirically investigate the characteristics of meta-analysis datasets that are associated with a larger BoS statistic (from 0 to 100%) when applying a bivariate meta-analysis of binary outcomes. Results Four characteristics were identified as strongly associated with BoS: the total number of studies, the number of studies with the outcome of interest, the percentage of studies missing the outcome of interest, and the largest absolute within-study correlation. Using these characteristics, we then develop a model for predicting BoS in a new dataset, which is shown to have good performance (an adjusted R2 of 50%). Applied examples are used to illustrate the use of the BoS prediction model. Conclusions Cochrane reviewers currently use univariate meta-analysis methods, but our prediction model for BoS helps to flag when a multivariate meta-analysis may also be beneficial in Cochrane reviews with multiple binary outcomes. Extension to non-Cochrane reviews and other outcome types is still required.

scholarly journals Beta-binomial models for meta-analysis with binary outcomes: Variations, extensions, and additional insights from econometrics

2021 ◽  
pp. 263208432199622
Author(s):  
Tim Mathes ◽  
Oliver Kuss
Keyword(s):  
Simulation Study ◽  
Count Data ◽  
Negative Binomial ◽  
Meta Analysis ◽  
Negative Binomial Regression ◽  
Binary Outcomes ◽  
Small Scale ◽  
Panel Count Data ◽  
Count Data Models ◽  
Meta Analyses

Background Meta-analysis of systematically reviewed studies on interventions is the cornerstone of evidence based medicine. In the following, we will introduce the common-beta beta-binomial (BB) model for meta-analysis with binary outcomes and elucidate its equivalence to panel count data models. Methods We present a variation of the standard “common-rho” BB (BBST model) for meta-analysis, namely a “common-beta” BB model. This model has an interesting connection to fixed-effect negative binomial regression models (FE-NegBin) for panel count data. Using this equivalence, it is possible to estimate an extension of the FE-NegBin with an additional multiplicative overdispersion term (RE-NegBin), while preserving a closed form likelihood. An advantage due to the connection to econometric models is, that the models can be easily implemented because “standard” statistical software for panel count data can be used. We illustrate the methods with two real-world example datasets. Furthermore, we show the results of a small-scale simulation study that compares the new models to the BBST. The input parameters of the simulation were informed by actually performed meta-analysis. Results In both example data sets, the NegBin, in particular the RE-NegBin showed a smaller effect and had narrower 95%-confidence intervals. In our simulation study, median bias was negligible for all methods, but the upper quartile for median bias suggested that BBST is most affected by positive bias. Regarding coverage probability, BBST and the RE-NegBin model outperformed the FE-NegBin model. Conclusion For meta-analyses with binary outcomes, the considered common-beta BB models may be valuable extensions to the family of BB models.

scholarly journals Methods used to meta-analyse results from interrupted time series studies: A methodological systematic review protocol

F1000Research ◽  
2020 ◽  
Vol 9 ◽  
pp. 110
Author(s):  
Elizabeth Korevaar ◽  
Amalia Karahalios ◽  
Andrew B. Forbes ◽  
Simon L. Turner ◽  
Steve McDonald ◽  
...  
Keyword(s):  
Public Health ◽  
Time Series ◽  
Systematic Reviews ◽  
Data Extraction ◽  
Meta Analysis ◽  
Interrupted Time Series ◽  
Analysis Methods ◽  
Study Selection ◽  
The Individual ◽  
Meta Analyses

Background: Systematic reviews are used to inform healthcare decision making. In reviews that aim to examine the effects of organisational, policy change or public health interventions, or exposures, evidence from interrupted time series (ITS) studies may be included. A core component of many systematic reviews is meta-analysis, which is the statistical synthesis of results across studies. There is currently a lack of guidance informing the choice of meta-analysis methods for combining results from ITS studies, and there have been no studies examining the meta-analysis methods used in practice. This study therefore aims to describe current meta-analysis methods used in a cohort of reviews of ITS studies. Methods: We will identify the 100 most recent reviews (published between 1 January 2000 and 11 October 2019) that include meta-analyses of ITS studies from a search of eight electronic databases covering several disciplines (public health, psychology, education, economics). Study selection will be undertaken independently by two authors. Data extraction will be undertaken by one author, and for a random sample of the reviews, two authors. From eligible reviews we will extract details at the review level including discipline, type of interruption and any tools used to assess the risk of bias / methodological quality of included ITS studies; at the meta-analytic level we will extract type of outcome, effect measure(s), meta-analytic methods, and any methods used to re-analyse the individual ITS studies. Descriptive statistics will be used to summarise the data. Conclusions: This review will describe the methods used to meta-analyse results from ITS studies. Results from this review will inform future methods research examining how different meta-analysis methods perform, and ultimately, the development of guidance.

scholarly journals 0820 Meta-Analysis of the Association of Age and Actigraphy-Assessed Sleep Across the Lifespan

SLEEP ◽  
2020 ◽  
Vol 43 (Supplement_1) ◽  
pp. A312-A313
Author(s):  
M A Bowman ◽  
D J Buysse ◽  
A L Marsland ◽  
A G Wright ◽  
J Foust ◽  
...  
Keyword(s):  
Data Collection ◽  
Sleep Duration ◽  
Study Design ◽  
Meta Analysis ◽  
Sleep Efficiency ◽  
Behavioral Measure ◽  
Poor Sleep ◽  
Sleep Quantity ◽  
Sleep Timing ◽  
Meta Analyses

Abstract Introduction Sleep quantity and continuity vary across the lifespan. Actigraphy is reliable, ecologically valid, and is the most widely-used behavioral measure of sleep in research and personal health monitoring. The extent to which age is associated with actigraphy-assessed sleep has not been evaluated across the lifespan. The aim of this meta-analysis was to evaluate the associations between age and actigraphy-assessed sleep in relatively healthy individuals. Methods A systematic search of PubMed, Embase.com, Cochrane CENTRAL, and PsycINFO using “actigraphy” and “sleep” terms provided 7,079 titles/abstracts, which were screened to exclude studies of only individuals with mental health disorders, medical conditions, sleep disorders, or shift workers. We evaluated 1,379 full-text articles for reports on the association between age and actigraphy-assessed sleep duration, efficiency, timing, and/or regularity. Overall, 88 articles met these criteria (182 effect sizes; N=18,443). Four meta-analyses were conducted, examining sleep duration (k=86), sleep efficiency (k=58), bedtime (k=27), and wake-up time (k=11). There were insufficient numbers of studies (less than 5) to evaluate sleep midpoint or sleep regularity. We tested continent of the study, study design, actigraphy device type, and number of nights of data collection as moderators of meta-analytic associations. Results With increasing age, sleep duration was shorter (r = -0.13) and sleep efficiency was lower (r = -0.06). Bedtime was later with age for ages 6-21 (r = 0.31) and earlier for ages 22 and up (r = -0.65). Wake-up time was not associated with age for ages 6-21 (r = 0.20) but was earlier with increasing age for ages 22 and up (r = -0.71). The strength of these associations was modified by continent and study design, but not by type of actigraphy device or number of nights of data collection. Conclusion Weak associations between age and actigraphy-assessed duration and efficiency suggest that inadequate sleep quantity or poor sleep continuity should not be dismissed as typical consequences of aging. Large associations between age and sleep timing, despite a small literature, highlights a promising area for further study, particularly to determine the age at which sleep timing shifts from delaying to advancing. Support MAB was supported by T32 HL07560.

Hemorrhagic and thrombotic events in oncology patients treated with antiangiogenic therapy: Impact of study design on the results assessed by meta-analysis.

2017 ◽  
Vol 35 (15_suppl) ◽  
pp. e14058-e14058
Author(s):  
Jane-Chloe Trone ◽  
Céline Chapelle ◽  
Edouard Ollier ◽  
Laurent Bertoletti ◽  
Michel Cucherat ◽  
...  
Keyword(s):  
Clinical Trials ◽  
Cancer Patients ◽  
Study Design ◽  
Fixed Effects ◽  
Meta Analysis ◽  
Antiangiogenic Therapy ◽  
Solid Cancer ◽  
Increasing Risk ◽  
Meta Analyses ◽  
The Impact

e14058 Background: Antiangiogenic (AA) therapies emerge as a new cornerstone for cancer treatment, but carry their own particular risk profile. Several previous meta-analyses have showed increasing risk of bleeding and paradoxically thrombosis in cancer patients receiving antiangiogenic. The aim of the meta-analysis is to investigate the impact of studies design (open or double blind (DB)), on the incidence and the occurrence of bleeding, venous thrombotic events (VTE) and arterial thrombotic events (ATE) in cancer patients treated by AA therapies. Methods: We searched Medline, Cochrane, ClinicalTrial databases, meeting abstracts of the American Society of Clinical Oncology and the European Society of Medical Oncology for relevant clinical trials. We included prospective phase II and III clinical trials that randomly assigned patients with solid cancer to AA therapy or control. Statistical analyses were conducted to calculate the summary incidence, ORs, and 95% CIs, using random-effects or fixed-effects models based on the heterogeneity of included studies. Results: A total of 166 trials (72,024 patients) were included. For bleeding events, comparison on AA treatment versus control yielded an OR of 2.41 (95% CI 2.07 to 2.71; p < 0.001) with an exaggeration of treatment effects by 68% (95% CI, 33 to 113) in open-label studies compared with DB trials. Concerning VTE, an OR of 1.18 (95% CI 1.04 to 1.35; p = 0.0115) was noted, with a significant enhancement of 53% (95% CI, 19 to 96) of treatment side effects with open trials compared with DB trials. AA don’t increase significantly the frequency of VTE when considering only DB trials. For ATE, an OR of 1.59 (95% CI 1.30 to 1.94; p < 0.001) was observed, associated with a significant exaggeration of 65% (95% CI, 13 to 143) with open trials compared with DB trials. Conclusions: The present meta-analysis showed a significant interaction of study design for the tolerance assessment in the AA therapies in cancers. The increasing risk of hemorrhagic events, VTE and ATE appear to have been overestimated in the previous meta-analyses. In the future, meta-analyses should be restricted to DB trials for analysis of toxicity profile.

scholarly journals Reproducibility of systematic literature reviews on food, nutrition, physical activity and endometrial cancer

2008 ◽  
Vol 11 (10) ◽  
pp. 1006-1014 ◽  
Author(s):  
RL Thompson ◽  
EV Bandera ◽  
VJ Burley ◽  
JE Cade ◽  
D Forman ◽  
...  
Keyword(s):  
Physical Activity ◽  
Endometrial Cancer ◽  
Study Design ◽  
Systematic Reviews ◽  
Meta Analysis ◽  
Case Series ◽  
Case Control Studies ◽  
Food Nutrition ◽  
Search And Selection ◽  
Meta Analyses

AbstractObjectiveDespite the increasing dependence on systematic reviews to summarise the literature and to issue public health recommendations, the formal assessment of the reliability of conclusions emerging from systematic reviews has received little attention. The main goal of the present study was to evaluate whether two independent centres, in two continents, draw similar conclusions regarding the association of food, nutrition and physical activity and endometrial cancer, when provided with the same general instructions and with similar resources.DesignThe assessment of reproducibility concentrated on four main areas: (1) paper search and selection; (2) assignment of study design; (3) inclusion of ‘key’ papers; and (4) individual studies selected for meta-analysis and the summary risk estimate obtained.ResultsIn total 310 relevant papers were identified, 166 (54 %) were included by both centres. Of the remaining 144 papers, 72 (50 %) were retrieved in the searches of one centre and not the other (54 in centre A, 18 in centre B) and 72 were retrieved in both searches but regarded as relevant by only one of the centres (52 in centre A, 20 in centre B). Of papers included by both centres, 80 % were allocated the same study design. Agreement for inclusion of cohort-type and case–control studies was about 63 % compared with 50 % or less for ecological and case series studies. The agreement for inclusion of 138 ‘key’ papers was 87 %. Summary risk estimates from meta-analyses were similar.ConclusionsTransparency of process and explicit detailed procedures are necessary parts of a systematic review and crucial for the reader to interpret its findings.

scholarly journals Meta-Analysis of Proptosis Response in Thyroid Eye Disease: Efficacy of EUGOGO Recommended Treatment Regimen With IV Methylprednisolone

2021 ◽  
Vol 5 (Supplement_1) ◽  
pp. A842-A842
Author(s):  
Raymond S Douglas ◽  
Ryan Batten ◽  
Rana A Qadeer ◽  
Chris Cameron
Keyword(s):  
Study Design ◽  
Observational Studies ◽  
Meta Analysis ◽  
Thyroid Eye Disease ◽  
Recommended Dose ◽  
Sensitivity Analyses ◽  
Controlled Study ◽  
Eye Disease ◽  
Primary Analysis ◽  
Meta Analyses

Abstract Background: The European Group on Graves’ Orbitopathy (EUGOGO) recommends intravenous methylprednisolone (IVMP) as the first line treatment for moderate-to-severe active thyroid eye disease (TED). While many studies with varying doses of IVMP have reported improvements in inflammation, via clinical activity score (CAS) reduction, the reported improvements in the major progressive outcome of TED, proptosis, vary widely. A reduction in proptosis of ≥2 millimeter (mm) is considered by clinicians and EUGOGO as clinically meaningful. A meta-analysis of existing literature on use of IVMP in TED management, specifically proptosis response, was conducted. Methods: PubMed and Embase were searched for relevant randomized controlled trials (RCTs) and observational studies that included patients with moderate-to-severe active TED receiving treatment with the EUGOGO recommended dose of IVMP (4.5-5g over 12 weeks) from the inception of the databases to date of search (October 2020); regular alerts were established to capture any recent studies. The outcome of interest was change from baseline to week 12 in proptosis in mms. Single-arm meta-analyses were conducted for IVMP using the DerSimonian-Laird random-effects models and forest plots were generated. Pooled means and corresponding 95% confidence intervals (CIs) were calculated. The primary analysis included all identified studies. Sensitivity analyses were conducted based on study design, study characteristics (smoking status), and methodologies (weighted Bayesian meta-analyses based on study design). Results: The search retrieved 12 studies (10 single-center, 8 RCTs, 4 observational studies: 7 from China, 4 from EU, 1 from Turkey), reporting proptosis for 498 patients that were used for the meta-analysis. No placebo-controlled study with the EUGOGO recommended dose of IVMP was found. All studies included patients who were 18 years or older with moderate-to-severe TED and most (n=11) studies included patients with CAS of ≥3. For studies that reported this data, the mean or median (if mean not reported) age ranged from 35 to 52 years and duration of TED symptoms ranged from 4 to 13.6 months. Treatment with IVMP resulted in a reduction of 0.94 mm (95% CI: -1.57 to -0.32) in proptosis from baseline to week 12. The results from the sensitivity analyses were aligned with those from the primary analysis. Conclusions: Among patients with moderate-to-severe TED, this meta-analysis found the EUGOGO-recommended dose of IVMP may result in modest, but not clinically meaningful, improvements in proptosis. However, these results should be interpreted with caution given the paucity of published data and the lack of risk/benefit analyses with glucocorticoid use as compared to the recently FDA-approved therapy, teprotumumab, for the treatment of TED.

scholarly journals Study design guidelines

2020 ◽  
Vol 10 (3) ◽  
pp. 353-368
Author(s):  
Andrey P. Sereda ◽  
Marina A. Andrianova
Keyword(s):  
Study Design ◽  
Meta Analysis ◽  
Good Reason ◽  
Case Series ◽  
Scientific Publication ◽  
Design Guidelines ◽  
Copyright Holder ◽  
Case Control Studies ◽  
Meta Analyses ◽  
Key Aspects

Complying with certain requirements or, more precisely, following the guidelines for the design of a scientific publication helps to make it not only more comprehensible for reviewers and readers, but actually enhances the quality of work. For example, even if some aspects in design logic were fulfilled but not described, other researchers doing meta-analysis may wrongly but for a good reason downgrade such publication and exclude it from the analysis. understanding of the guidelines for study design ensures not only the proper description of the results but the initial planning of work. The CARE guidelines were established for reporting of clinical cases, STROBE for reporting observational studies (cohort and case-control studies), CONSORT for reporting randomized studies (these guidelines are often used also for other comparative and case series studies), STARD for reporting diagnostic studies, and PRISMa for reporting of systematic reviews and meta-analyses. The present paper describes the key aspects of those guidelines and provides templates for graphic display of study design in form of flow charts. evidently, we should not forget that each study is unique and there is always a place for a reasonable compromise between requirements and the real logic of the research in place. The article is the reprint published with the permission of the copyright holder. Original article: Sereda AP, Andrianova MA. Study Design Guidelines. Traumatology and Orthopedics of Russia. 2019;25(3):165-184. doi: 10.21823/2311-2905-2019-25-3-165-184

scholarly journals Borrowing of strength and study weights in multivariate and network meta-analysis

2015 ◽  
Vol 26 (6) ◽  
pp. 2853-2868 ◽  
Author(s):  
Dan Jackson ◽  
Ian R White ◽  
Malcolm Price ◽  
John Copas ◽  
Richard D Riley
Keyword(s):  
Risk Factor ◽  
Meta Analysis ◽  
Multiple Risk Factor ◽  
Score Statistic ◽  
Multiple Outcomes ◽  
Informal Assessment ◽  
Multiple Treatments ◽  
Definition Of ◽  
Meta Analyses ◽  
Mathematical Definitions

Multivariate and network meta-analysis have the potential for the estimated mean of one effect to borrow strength from the data on other effects of interest. The extent of this borrowing of strength is usually assessed informally. We present new mathematical definitions of ‘borrowing of strength’. Our main proposal is based on a decomposition of the score statistic, which we show can be interpreted as comparing the precision of estimates from the multivariate and univariate models. Our definition of borrowing of strength therefore emulates the usual informal assessment. We also derive a method for calculating study weights, which we embed into the same framework as our borrowing of strength statistics, so that percentage study weights can accompany the results from multivariate and network meta-analyses as they do in conventional univariate meta-analyses. Our proposals are illustrated using three meta-analyses involving correlated effects for multiple outcomes, multiple risk factor associations and multiple treatments (network meta-analysis).

scholarly journals Methodological Quality Assessment of Systematic Review or Meta-Analysis Using AMSTAR-2: the Long-Term Effectiveness or Efficacy of Opioids for Chronic Non-Cancer Pain

2019 ◽  
Author(s):  
Qian Li ◽  
Ke Deng ◽  
Xiaoyuan Jiang ◽  
Huan Tao ◽  
Hui Liu ◽  
...  
Keyword(s):  
Cancer Pain ◽  
Systematic Reviews ◽  
Methodological Quality ◽  
Meta Analysis ◽  
Risk Of Bias ◽  
Cochrane Central Register ◽  
Cochrane Reviews ◽  
Meta Analyses

Abstract Background：Systematic review or meta-analysis, the strong study design of high quality evidence, give inconsistent conclusion of long-term effectiveness or efficacy of opioids for chronic non-cancer pain. We appraised the methodological quality of systematic reviews or meta-analyses. Methods: We found the relevant systematic reviews or meta-analyses by searching Medline, EMBASE, the Cochrane Database of Systematic Reviews, the Cochrane Central Register of Controlled Trials, the International prospective register of systematic reviews, Psyc ARTICLES/OVID, the Chinese Bio-Medical Literature Database, the China National Knowledge Infrastructure, and the Wan Fang Data and VIP Database on March 1st, 2019. The methodological quality was assessed by A Measurement Tool to Assess Systematic Reviews-2(AMSTAR-2). Spearman correlation analysis and non-parametric tests were used to assess the association between quality and factors. Results: Twenty-one systematic reviews or meta-analyses were included in our study. One has no individual study. In terms of methodological quality, twelve reviews were critically low in overall confidence, four reviews were low, two reviews were moderate, two reviews were high. When referring to the systematic reviews or meta-analyses of relatively better methodological quality with more credible results and conclusions, the effectiveness or efficacy of opioids was small to questionable. Cochrane reviews performed better than non-Cochrane reviews in establishing prior protocol (100% vs 17%, P<0.05), providing an excluded studies list (100% vs 50%, P<0.05) and taking risk of bias into account when interpreting the results of the review (100% vs 75%, P<0.05). There was a strong correlation (ρ=0.526, P<0.05) between the impact factor of systematic reviews or meta-analyses in published journals and methodological quality. Conclusion The methodological quality of the included systematic reviews or meta-analyses is far from satisfactory and needs improvement, especially in establishing prior protocol and justifying significant deviations from the protocol, providing an excluded primary studies list, reporting the funding information of primary studies, and assessing the potential impact of risk of bias on individual studies.

scholarly journals Twenty years review of probiotic meta-analyses articles: Effects on disease prevention and treatment

2021 ◽  
Author(s):  
Kajal Farahmandi ◽  
Sadegh Sulaimany ◽  
Kambiz Kalhor
Keyword(s):  
Meta Analysis ◽  
Age Effect ◽  
Disease Type ◽  
Positive Effects ◽  
Cochrane Reviews ◽  
Online Databases ◽  
Keywords Probiotics ◽  
Prevention And Treatment ◽  
Meta Analyses ◽  
Probiotic Effect

The study of the probiotic effect in the prevention or treatment of diseases has long attracted the attention of many researchers. Here, we collected close to 300 meta-analysis articles for 20 years, investigating the effect of probiotics in the prevention and treatment of diseases. The goal of this study is to provide an overview of all meta-analysis articles of the effects of probiotics on various human diseases. For this purpose, different online databases, Pubmed, ScienceDirect, and Google Scholar, were searched with the keywords "probiotics" + "disease" + "meta-analysis" in the title, abstract, and keywords. Papers studied and categorized and investigated in order to present valuable insights for researchers in the field. Some of main categories are based on publication year, publishing journals, gender, age, effect type, disease type, contradicting reports and etc. According to the results, most meta-analyses indicated probiotics were 79% effective in preventing or treating the diseases. Some articles have also reported no positive effects, but there is not any paper in our study confirming the detrimental influence of probiotic effect on human health. For the future works, Cochrane reviews, meta-analysis including dozens of articles (as e.g. for NEC and AAD) may be investigated.

Sign in / Sign up

Export Citation Format

Share Document