All data of this meta-analysis were analyzed in RevMan (version 5.4) and Stata (version 15.1). For all included studies, the risk ratio (RR) and 95% confidence interval (Cl) were used to measure the correlation between the TSH, FT3, and FT4 levels and the mortality and severity of COVID-19 patients. The I2 value and P value were used to evaluate heterogeneity. If the I2 was less than 50% and if the P value was less than 0.05, there was no heterogeneity in the included studies. In addition, sensitivity analyses were used to ensure that the method we adopted was scientific (Supplementary Figures 1 10
Revman version 5.4
Manufactured by StataCorp
Sourced in United States
RevMan (version 5.4) is a software application designed for creating and maintaining Cochrane systematic reviews. It provides tools for authors to manage the entire review process, including protocol development, data extraction, and meta-analysis.
Automatically generated - may contain errors
5 protocols using revman version 5.4
1
COVID-19 Mortality and Severity Predictors
2
Meta-analysis on Asthma-COPD Overlap
Check if the same lab product or an alternative is used in the 5 most similar protocols
+ Expand
The meta-analysis was performed by Review Manager (RevMan) Version 5.4 and Stata/MP version 16.0. Due to differences in testing methods of some indicators, the pooled standardized mean differences (SMDs) with 95% confidence intervals (CIs) were calculated, with a p-value <0.05 implying a statistically significant difference, and random-effects models were used to evaluate the pooled effects. Heterogeneity was assessed by the I-squared (I2) test, when I2 >50% indicating substantial heterogeneity, in which case multivariate meta-regression and subgroup analyses by year of publication, total sample size (n <200 or ≥200), study type, and quality score were conducted to explore sources of heterogeneity. The leave-one-out sensitivity analyses were performed to evaluate the stability of the pooled results. Funnel plots as well as begg’s and egger’s tests were adopted to assess publication bias when at least ten studies were included. Since the diagnostic criteria of ACO were not consistent in the included studies, linkage bias analyses based on the different populations in these studies, were conducted to explore the influence of such inconsistency on the pooled results.17 (link)
3
Statistical Analysis Techniques in Meta-Analysis
Check if the same lab product or an alternative is used in the 5 most similar protocols
+ Expand
Cochrane Review Manager software (RevMan, version 5.4) and STATA software (version 16.0) were utilized for statistical analysis. For dichotomous outcomes, results were expressed as a risk ratio (RR) with 95% confidence intervals (CI). The mean difference (MD) for continuous scales was used to assess treatment effects or the standardized mean difference (SMD) if different scales were used. Graded outcome data was analyzed by Generic Inverse Variance. The meaning of HR values was determined according to different outcome indicators. A p < 0.05 was considered statistically significant. Heterogeneity was assessed using the Q test and I2 statistics. A chi-squared p < 0.1 or an I2 statistic >50% was regarded as heterogeneity. When heterogeneity existed, we performed a sensitivity analysis to remove research with a higher risk of bias or used a random-effect model for data pooling; otherwise, a fixed-effects model can ensure the robustness of the model chosen and susceptibility to outliers was adopted. Forest plots indicated the results of the meta-analysis and a funnel plot was utilized to assess publication bias.
4
Meta-analysis of Dichotomous Outcomes
Check if the same lab product or an alternative is used in the 5 most similar protocols
+ Expand
The pooled proportions were computed using a random-effect method with an inverse variance approach [16 (link)]. Prior to statistical analysis, a continuity correction of 0.5 was applied when the incidence of an outcome was zero in a study. Dichotomous variables were analyzed using the odds ratio (OR) and MantelHaenszel test. The heterogeneity was assessed by I2 and the p-value of heterogeneity. A P-value of < 0.10 was taken as statistically significant while I2 values of 25%, 50%, and 75% were considered as cutoffs for low, moderate, and considerable heterogeneity, respectively [17 (link)]. The assessment of publication bias was done by evaluating the asymmetry of the funnel plot and quantified using Egger’s test. Sensitivity analysis was performed by analyzing prevalence data based on continent and study design and by leave-one-out meta-analysis. Meta-regression was used to explore heterogeneity induced by the relationship between moderators and study effect sizes. All statistical analyses were performed using RevMan version 5.4 and STATA software version 17 (StataCorp., College Station, TX, USA).
5
Meta-analysis Statistical Methodology
Check if the same lab product or an alternative is used in the 5 most similar protocols
+ Expand
Review Manager (RevMan) version 5.4 and Stata 16.0 were used for data analysis. Continuous variables were evaluated by the weighted mean difference (WMD) with a 95% confidence interval (95% CI), and dichotomous variables were evaluated using the odds ratios (OR) with 95% CI. Heterogeneity was assessed using X2 and the I2 index. The fixed-effect model (FEM) and random effect model (REM) were used based on the value of I2. Low, moderate, and high heterogeneity were considered for levels of I2 values of 25–49%, 50–74%, and above 75%, respectively [11 (link)]. If I2 was > 50%, we considered it to have significant heterogeneity and a REM was adopted, then, a sensitivity analysis was performed to explore potential sources. p < 0.05 was considered statistically significant. Egger’s test was used to assess the publication bias of the included studies [12 (link)]. If there was a publication bias, a trim and fill analysis was further used to evaluate the impact of it on the pooled results.
About PubCompare
Our mission is to provide scientists with the largest repository of trustworthy protocols and intelligent analytical tools, thereby offering them extensive information to design robust protocols aimed at minimizing the risk of failures.
We believe that the most crucial aspect is to grant scientists access to a wide range of reliable sources and new useful tools that surpass human capabilities.
However, we trust in allowing scientists to determine how to construct their own protocols based on this information, as they are the experts in their field.
Ready to get started?
Sign up for free.
Registration takes 20 seconds.
Available from any computer
No download required
Revolutionizing how scientists
search and build protocols!