China
Africa
Explore chapters and articles related to this topic
Packages for Meta-Analysis
Published in Ding-Geng (Din) Chen, Karl E. Peace, Applied Meta-Analysis with R and Stata, 2021
Ding-Geng (Din) Chen, Karl E. Peace
Fisher’s method is known as Fisher’s combined probability test which was developed to combine statistical p-values from several independent tests of the same hypothesis (H0) using a χ2-distribution. Specifically, suppose pi is the p-value reported from ith study, then the statistic
Choice of Effect Measure and Issues in Extracting Outcome Data
Published in Christopher H. Schmid, Theo Stijnen, Ian R. White, Handbook of Meta-Analysis, 2020
Ian R. White, Christopher H. Schmid, Theo Stijnen
It is possible to avoid the use of an effect measure by performing a meta-analysis of p-values, yielding just a summary p-value. For example, given p-values pi in the ith study (either all one-tailed or all two-tailed), Fisher’s method uses the statistic : if the null hypothesis is true for all studies then this statistic follows the distribution (Fisher, 1934). Meta-analysis of p-values is usually not desirable because it fails to quantify the magnitude of effect, because there is no assessment of heterogeneity, and because p-values are insufficient to tell whether results are scientifically significant—for example, whether treatment reduces risk by a large enough amount to justify its increased burden on the patient. Meta-analysis of p-values is sometimes used in genetics (Chapter 17) and forms part of the “fail-safe N” method for publication bias (Chapter 13).
Controlled Clinical Trials — Necessity and Progress
Published in James L. MacPherson, Duke O. Kasprisin, Therapeutic Hemapheresis, 2019
The study sample will be comprised of two mutually exclusive groups — (1) patients who require dialysis on admission or shortly afterwards, and (2) patients who do not require dialysis. The major response variable for group 1 will be whether or not there is an improvement in renal function to the point that dialysis will no longer be required. The main response variable for group 2 will be the rate of change in serum creatinine over time. The two results will be combined using Fisher’s method for combining independent statistical tests.44 It is estimated that an overall sample size of 160 — 80 in each treatment group — will be required.
Identification and validation of core genes in tumor-educated platelets for human gastrointestinal tumor diagnosis using network-based transcriptomic analysis
Published in Platelets, 2023
Yuhong Jiang, Jun He, Xiaobo Wang, Chao Liu, Weihan Zhou, Dekun Liu, Zhushu Guo, Kuijie Liu
Tables ” option on the NetworkAnalyst website. The merged data of this meta-analysis is listed in Table S2. Figure 2a depicts the whole meta-analysis procedure used in this investigation. The “Fisher’s method” and “Random effect model” were used to produce more consistent and accurate results by taking into account both the direction and magnitude of changes in gene expression. By employing “Fisher’s method” and “Random effect model” meta-analysis methods, we identified 2421 and 775 DEGs, respectively (Combined p < .05 was considered to be significant). Among them, 775 genes were jointly uncovered by both strategies, which is shown in the Venn diagram (Figure 2b). Of these 775 DEGs, 51 genes are significantly up-regulated and 724 are significantly down-regulated in the platelets of tumor patients as compared to the controls. A complete list of the DEGs can be seen in Table S3. Among them, the gene with the greatest upregulation in the three datasets is CD96, while the one with the greatest downregulation is KLRB1. CD96, together with TIGIT and co-stimulatory receptor CD226, are newly discovered immune checkpoints expressed on natural killer (NK) cells and CD8+ T cells and hold great potential as targets for cancer immunotherapy.41,42 A heatmap visualization of the top 10 up- and down-regulated genes across the different studies is displayed in Figure 2c.
Toll-like receptor 2 promotes breast cancer progression and resistance to chemotherapy
Published in OncoImmunology, 2022
Antonino Di Lorenzo, Elisabetta Bolli, Roberto Ruiu, Giuseppe Ferrauto, Enza Di Gregorio, Lidia Avalle, Aurora Savino, Pietro Poggio, Irene Fiore Merighi, Federica Riccardo, Mara Brancaccio, Elena Quaglino, Federica Cavallo, Laura Conti
The expression levels of TLR2 across BC molecular subtypes were obtained from the transcriptomic datasets collected in the MetaGxBreast R package,24 and PAM50 subtyping was performed through the molecular subtyping function of the genefu R package (“pam50” model).25 Since the log-rank tests were two-sided, one-sided p-values were obtained with the two2one function from the metap package, taking the hazard ratio into account, before applying Fisher’s method. A total of 32 datasets had a probe for TLR2 and allowed the inference of the molecular subtype. TLR2 mRNA expression levels in BC patients that responded to adjuvant chemotherapy and those that did not were analyzed using the datasets and tools available;22,26 patients who relapsed within 5 y of treatment were compared with patients who did not, excluding those censored before the 5 y had passed.
Adipose tissue density on CT as a prognostic factor in patients with cancer: a systematic review
Published in Acta Oncologica, 2020
N. D. Kapoor, P. K. Twining, O. Q. Groot, B. J. Pielkenrood, M. E. R. Bongers, E. T. Newman, J. J. Verlaan, J. H. Schwab
We considered a quantitative meta-analysis for pooling HRs to be inappropriate due to the heterogeneity in patient populations, CT protocols, cancer types and outcomes. Providing a pooled HR with the data for different outcomes and types of cancers would result in hazard ratios with minimal clinical validity. To summarize the findings in a quantitative form, the associations between fat density and outcome, and the median HR with 95% confidence interval (CI) was calculated for all studies. Two meta-analysis methods were performed which are commonly used when the data underlying the tests are difficult to combine: binomial sign test and Fisher’s method. The binomial sign test will assess the favorability of one particular direction in repeated measurements by comparing the ratios of positive and negative HRs, irrespective of whether the results are significant [17]. Fisher’s method will test the null hypothesis that all of the separate null hypotheses from each study are true by computing a combined p-value for all available p-values [18].