China
Africa
Explore chapters and articles related to this topic
Knowing What to Do
Published in Bill Runciman, Alan Merry, Merrilyn Walton, Safety and Ethics in Healthcare, 2007
Bill Runciman, Alan Merry, Merrilyn Walton
The point estimate and 95 per cent confidence intervals for each trial’s result (expressed as relative risk, odds ratio or mean difference) is represented as a box with lines. The box size also represents the trial’s sample size. Currently, the major problem is that many articles are published with insufficient data to include in a meta-analysis; publishing a significant P value is often viewed as sufficient. The pooled results of the meta-analysis are displayed at the bottom of the Forest plot. If this result crosses ‘unity’ (i.e. relative risk = 1), it is concluded that no difference has been shown in the amalgamated results. Differences in trial characteristics (heterogeneity) can confound the results of meta-analysis. To some extent, this can be corrected for statistically, but if there are substantial differences, then comparison using meta-analysis is thought not be appropriate. Meta-analysis is a powerful tool for combining the results of similar trials with the same outcomes to identify differences that small, individual trials may not be powerful enough to demonstrate.
Reengineering Data Analytics
Published in Paul Cerrato, John Halamka, Reinventing Clinical Decision Support, 2020
Many clinical studies that compare one or more interventions typically generate a mean result and a variance around that average. Over the years, investigators have used a variety of statistical methods to measure that variance, including the standard deviation, forest plots, and subgroup analysis. But the emergence of several AI/ML–enabled techniques suggests that these older approaches are insufficient because they do not always detect the heterogeneity present in patient populations.
The global epidemiology of Microsporidia infection in birds: A systematic review and meta-analysis
Published in International Journal of Environmental Health Research, 2023
Ali Taghipour, Sahar Ghodsian, Mahdi Jabbari, Vahid Rajabpour, Saeed Bahadory, Narges Malih, Kavous Solhjoo, Mohammad Zibaei, Amir Abdoli
For each included study, the point estimates and their respective 95% confidence intervals were calculated using a random-effects model. The random-effects model allows for a distribution of true effect sizes between published studies. To minimize the bias, using subgroup analyses, the pooled prevalence of Microsporidia infection was estimated according to diagnostic methods (molecular and microscopic methods), bird species, continent, and countries. To visualize possible heterogeneity among the included studies, a forest plot analysis was used. The I2 statistic was performed to assess the heterogeneity between studies and the values of < 50%, 50%–80%, and > 80% were defined as low, moderate, and high heterogeneity, respectively (Taghipour et al. 2020, 2020, 2021). We also used the funnel plot to check the probability of publication bias during the analysis (Egger et al. 1997). All analytical functions were applied by comprehensive meta-analysis software (version 2, BIOSTAT, Englewood, NJ, USA).
Reuse of pacemakers and implantable cardioverter-defibrillators: systematic review, meta-analysis and quality assessment of the body of evidence
Published in Expert Review of Medical Devices, 2021
Eliane Molina Psaltikidis, Eliana Auxiliadora Magalhães Costa, Kazuko Uchikawa Graziano
The meta-analysis was performed with the help of a statistician (Bernardo dos Santos MSc – Research Support Center of the USP Nursing School). A random effects model was used, estimated by restricted maximum likelihood, which groups all the studies together based on the assumption of heteroscedasticity. The odds ratio (OR) and 95% confidence interval were calculated for each variable. An OR < 1 indicated a smaller chance of the outcome with reuse and > 1 a greater likelihood. Forest plots were used to display the results of the individual studies and meta-analysis. The variability of the studies was estimated using the H2 statistical measure and heterogeneity by I [2], with values ≤25%, 50% and ≥75% corresponding to low, moderate and high inconsistency, respectively [21]. The program used was R software version 4.0.3.
The use of meta-analysis in food contact materials risk assessment
Published in Human and Ecological Risk Assessment: An International Journal, 2020
Marzena Pawlicka, Paweł Struciński, Jacek Postupolski
Meta-analysis consists of the following steps: systematic review of primary research, evaluation of heterogeneity between primary studies, collation of relevant primary data, estimation of effect size, calculation of effect size for each study, choice of random-effects or fixed effects model, subgroup specification, calculation of the summary effect (per subgroup and overall), conduct of sensitivity analysis, checking for the presence of publication bias and interpretation of meta-analysis results (Borenstein 2009). Meta-analysis results are commonly displayed graphically as ‘forest plots’. A meta-analysis is often part of a systematic review, but – as mentioned – this is not always possible. Figure 1 presents the steps to be taken in meta-analysis of an animal study proposed by Hooijmans et al. (2014).