The metafor package provides functions for conducting meta-analyses in R. The package includes functions for fitting the meta-analytic fixed- and random-effects models and allows for the inclusion of moderators variables (study-level covariates) in these models. Meta-regression analyses with continuous and categorical moderators can be conducted in this way. Functions for the Mantel-Haenszel and Peto's one-step method for meta-analyses of 2 x 2 table data are also available. Finally, the package provides various plot functions (for example, for forest, funnel, and radial plots) and functions for assessing the model fit, for obtaining case diagnostics, and for tests of publication bias.

Conducting Meta-Analyses in R with the metafor Package

Applied Linear Regression.

© 2016 Hill et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Chronic kidney disease (CKD) is a global health burden with a high economic cost to health systems and is an independent risk factor for cardiovascular disease (CVD). All stages of CKD are associated with increased risks of cardiovascular morbidity, premature mortality, and/or decreased quality of life. CKD is usually asymptomatic until later stages and accurate prevalence data are lacking. Thus we sought to determine the prevalence of CKD globally, by stage, geographical location, gender and age. A systematic review and meta-analysis of observational studies estimating CKD prevalence in general populations was conducted through literature searches in 8 databases. We assessed pooled data using a random effects model. Of 5,842 potential articles, 100 studies of diverse quality were included, comprising 6,908,440 patients. Global mean(95%CI) CKD prevalence of 5 stages 13.4%(11.7-15.1%), and stages 3-5 was 10.6%(9.2-12.2%). Weighting by study quality did not affect prevalence estimates. CKD prevalence by stage was Stage-1 (eGFR>90+ACR>30): 3.5% (2.8-4.2%); Stage-2 (eGFR 60-89+ACR>30): 3.9% (2.7-5.3%); Stage-3 (eGFR 30-59): 7.6% (6.4-8.9%); Stage-4 = (eGFR 29-15): 0.4% (0.3-0.5%); and Stage-5 (eGFR<15): 0.1% (0.1-0.1%). CKD has a high global prevalence with a consistent estimated global CKD prevalence of between 11 to 13% with the majority stage 3. Future research should evaluate intervention strategies deliverable at scale to delay the progression of CKD and improve CVD outcomes.

/pdf/global-prevalence-of-chronic-kidney-disease-a-systematic-r3jpj6fdd1.pdf

Global Prevalence of Chronic Kidney Disease - A Systematic Review and Meta-Analysis.

Meta-analyses have become an essential tool in synthesizing evidence on clinical and epidemiological questions derived from a multitude of similar studies assessing the particular issue. Appropriate and accessible statistical software is needed to produce the summary statistic of interest. 
Metaprop is a statistical program implemented to perform meta-analyses of proportions in Stata. It builds further on the existing Stata procedure metan which is typically used to pool effects (risk ratios, odds ratios, differences of risks or means) but which is also used to pool proportions. Metaprop implements procedures which are specific to binomial data and allows computation of exact binomial and score test-based confidence intervals. It provides appropriate methods for dealing with proportions close to or at the margins where the normal approximation procedures often break down, by use of the binomial distribution to model the within-study variability or by allowing Freeman-Tukey double arcsine transformation to stabilize the variances. Metaprop was applied on two published meta-analyses: 1) prevalence of HPV-infection in women with a Pap smear showing ASC-US; 2) cure rate after treatment for cervical precancer using cold coagulation. The first meta-analysis showed a pooled HPV-prevalence of 43% (95% CI: 38%-48%). In the second meta-analysis, the pooled percentage of cured women was 94% (95% CI: 86%-97%). By using metaprop, no studies with 0% or 100% proportions were excluded from the meta-analysis. Furthermore, study specific and pooled confidence intervals always were within admissible values, contrary to the original publication, where metan was used.

/pdf/metaprop-a-stata-command-to-perform-meta-analysis-of-14g7ulsnr6.pdf

Metaprop: a Stata command to perform meta-analysis of binomial data

Background 
Pancreatic cancer has an extremely poor prognosis and prolonged survival is achieved only by resection with macroscopic tumor clearance. There is a strong rationale for a neoadjuvant approach, since a relevant percentage of pancreatic cancer patients present with non-metastatic but locally advanced disease and microscopic incomplete resections are common. The objective of the present analysis was to systematically review studies concerning the effects of neoadjuvant therapy on tumor response, toxicity, resection, and survival percentages in pancreatic cancer.
Methods and Findings 
Trials were identified by searching MEDLINE, EMBASE, and the Cochrane Central Register of Controlled Trials from 1966 to December 2009 as well as through reference lists of articles and proceedings of major meetings. Retrospective and prospective studies analyzing neoadjuvant radiochemotherapy, radiotherapy, or chemotherapy of pancreatic cancer patients, followed by re-staging, and surgical exploration/resection were included. Two reviewers independently extracted data and assessed study quality. Pooled relative risks and 95% confidence intervals were calculated using random-effects models. Primary outcome measures were proportions of tumor response categories and percentages of exploration and resection. A total of 111 studies (n = 4,394) including 56 phase I–II trials were analyzed. A median of 31 (interquartile range [IQR] 19–46) patients per study were included. Studies were subdivided into surveys considering initially resectable tumors (group 1) and initially non-resectable (borderline resectable/unresectable) tumors (group 2). Neoadjuvant chemotherapy was given in 96.4% of the studies with the main agents gemcitabine, 5-FU (and oral analogues), mitomycin C, and platinum compounds. Neoadjuvant radiotherapy was applied in 93.7% of the studies with doses ranging from 24 to 63 Gy. Averaged complete/partial response probabilities were 3.6% (95% CI 2%–5.5%)/30.6% (95% CI 20.7%–41.4%) and 4.8% (95% CI 3.5%–6.4%)/30.2% (95% CI 24.5%–36.3%) for groups 1 and 2, respectively; whereas progressive disease fraction was estimated to 20.9% (95% CI 16.9%–25.3%) and 20.8% (95% CI 14.5%–27.8%). In group 1, resectability was estimated to 73.6% (95% CI 65.9%–80.6%) compared to 33.2% (95% CI 25.8%–41.1%) in group 2. Higher resection-associated morbidity and mortality rates were observed in group 2 versus group 1 (26.7%, 95% CI 20.7%–33.3% versus 39.1%, 95% CI 29.5%–49.1%; and 3.9%, 95% CI 2.2%–6% versus 7.1%, 95% CI 5.1%–9.5%). Combination chemotherapies resulted in higher estimated response and resection probabilities for patients with initially non-resectable tumors (“non-resectable tumor patients”) compared to monotherapy. Estimated median survival following resection was 23.3 (range 12–54) mo for group 1 and 20.5 (range 9–62) mo for group 2 patients.
Conclusions 
In patients with initially resectable tumors (“resectable tumor patients”), resection frequencies and survival after neoadjuvant therapy are similar to those of patients with primarily resected tumors and adjuvant therapy. Approximately one-third of initially staged non-resectable tumor patients would be expected to have resectable tumors following neoadjuvant therapy, with comparable survival as initially resectable tumor patients. Thus, patients with locally non-resectable tumors should be included in neoadjuvant protocols and subsequently re-evaluated for resection.

Please see later in the article for the Editors' Summary

/pdf/preoperative-neoadjuvant-therapy-in-pancreatic-cancer-a-31hum8qmaw.pdf

Preoperative/Neoadjuvant Therapy in Pancreatic Cancer: A Systematic Review and Meta-analysis of Response and Resection Percentages

The use of transformations to stabilize the variance of binomial or Poisson data is familiar(Anscombe [1], Bartlett [2, 3], Curtiss [4], Eisenhart [5]). The comparison of transformed binomial or Poisson data with percentage points of the normal distribution to make approximate significance tests or to set approximate confidence intervals is less familiar. Mosteller and Tukey [6] have recently made a graphical application of a transformation related to the square-root transformation for such purposes, where the use of "binomial probability paper" avoids all computation. We report here on an empirical study of a number of approximations, some intended for significance and confidence work and others for variance stabilization. For significance testing and the setting of confidence limits, we should like to use the normal deviate $K$ exceeded with the same probability as the number of successes $x$ from $n$ in a binomial distribution with expectation $np$, which is defined by $\frac{1}{2\pi} \int^K_{-\infty} e^{-\frac{1}{2}t^2} dt = \operatorname{Prob} \{x \leq k |mid \operatorname{binomial}, n, p\}.$ The most useful approximations to $K$ that we can propose here are $N$ (very simple), $N^+$ (accurate near the usual percentage points), and $N^{\ast\ast}$ (quite accurate generally), where $N = 2 (\sqrt{(k + 1)q} - \sqrt{(n - k)p)}.$ (This is the approximation used with binomial probability paper.) $N^+ = N + \frac{N + 2p - 1}{12\sqrt{E}},\quad E = \text{lesser of} np \text{and} nq, N^\ast = N + \frac{(N - 2)(N + 2)}{12} \big(\frac{1}{\sqrt{np + 1}} - \frac{1}{\sqrt{nq + 1}}\big), N^{\ast\ast} = N^\ast + \frac{N^\ast + 2p - 1}{12 \sqrt{E}}\cdot\quad E = \text{lesser of} np \text{and} nq.$ For variance stabilization, the averaged angular transformation $\sin^{-1}\sqrt{\frac{x}{n + 1}} + \sin^{-1} \sqrt{\frac{x + 1}{n+1}}$ has variance within $\pm 6%$ of $\frac{1}{n + \frac{1}{2}} \text{(angles in radians)}, \frac{821}{n + \frac{1}{2}} \text{(angles in degrees)},$ for almost all cases where $np \geq 1$. In the Poisson case, this simplifies to using $\sqrt{x} + \sqrt{x + 1}$ as having variance 1.

/pdf/transformations-related-to-the-angular-and-the-square-root-33vntd00by.pdf

Murray F. Freeman

Papers

Transformations Related to the Angular and the Square Root