SAS Software is a powerful and internationally-recognized programming statistical software, which can implement all kinds of meta-analysis, including network meta-analysis. Bayesian statistics is an important statistical method, which uses MCMC (Markov Chain Monte Carlo) arithmetic to conduct various statistical inference. With this idea, we implement network meta-analysis thorough PROC MCMC process and introduce this process in this article based on an example.
ObjectiveTo systematically review the efficacy of different stimulation modalities of repetitive transcranial magnetic stimulation (rTMS) combined with SSRI in improving depressed mood after stroke using network meta-analysis. MethodsThe PubMed, EMbase, Cochrane Library, Web of Science, CNKI, VIP, CBM and WanFang Data databases were electronically searched to collect randomized controlled trials (RCTs) related to the objectives from inception to October 1, 2022. Two reviewers independently screened literature, extracted data and assessed the risk of bias of the included studies. Network meta-analysis was then performed by using R 4.2.1software. ResultsA total of 25 RCTs involving 2 152 patients were included. Four types of rTMS stimulation combined with SSRIs were included: high-frequency stimulation of the left dorsolateral prefrontal (l-DLPFC), low-frequency stimulation of l-DLPFC, low-frequency stimulation of the right dorsolateral prefrontal (r-DLPFC), and low-frequency stimulation of the bilateral DLPFC. The results of the network meta-analysis showed that the effect of combining four stimulation methods with SSRI in treating depression was better than that of SSRI alone (P<0.05). Probability sorting results showed that low-frequency stimulated bilateral DLPFC (88.9%) > low-frequency stimulated l-DLPFC (63.1%) > high-frequency stimulation l-DLPFC (57.1%) > low-frequency stimulation r-DLPFC (40.4%). There was no statistically significant difference in the incidence of adverse reactions between the four stimulation methods combined with SSRI and the use of SSRI alone (P>0.05). Conclusion rTMS combined with SSRIs is better than SSRIs alone in improving depressed mood after stroke. Low-frequency rTMS stimulation of bilateral DLPFC may be the best. Meanwhile, the safety of different stimulation methods is good.
Objective To systematically review the efficacy and safety of different SGLT2 inhibitors in the treatment of heart failure. Methods The Cochrane Library, Web of Science, PubMed and EMbase databases were searched for randomized controlled trials on the efficacy and safety of SGLT2 inhibitors in patients with heart failure from inception to July 2, 2021. Two researchers independently screened literature, extracted data and evaluated the risk of bias of the included studies. Network meta-analysis was then performed using Stata 16.0 software. Results A total of 16 randomized controlled trials, including 15 312 patients, involving 5 interventions, namely dapagliflozin, empagliflozin, canagliflozin, sotagliflozin and ertugliflozin were included. Results of network meta-analysis showed that there was no significant difference in the compound outcome of hospitalization for heart failure or cardiovascular death, hospitalization for heart failure, all-cause mortality, risk of cardiovascular mortality and serious adverse reactions among patients with heart failure among 5 different SGLT2 inhibitors (P>0.05). Compared with placebo, both selective and non-selective SGLT2 inhibitors improved the risk of hospitalization for heart failure, hospitalization for heart failure, or compound cardiovascular mortality (P<0.05), while only selective SGLT2 inhibitors improved the risk of cardiovascular mortality, all-cause mortality, and serious adverse events (P<0.05). However, there was no significant difference between them (P>0.05). The area under the cumulative ordering probability curve of selective and non-selective SGLT2 inhibitors ranked first and second, except for the combined outcome of heart failure or cardiovascular death. Conclusion The current evidence indicates that there is no significant difference in the efficacy and safety of the 5 different SGLT2 inhibitors in the treatment of heart failure, and there is no significant difference between selective SGLT2 inhibitors and non-selective SGLT2 inhibitors. Due to the limited quantity and quality of included studies, more high-quality studies are needed to verify the above conclusion.
Objective To systematically review the efficacy of eight time-restricted eating strategies on overweight/obese adults using network meta-analysis. MethodsThe Scopus, MEDLINE, Embase, PubMed, Web of Science, and Cochrane Library databases were electronically searched to collect randomized controlled trials (RCTs) on the intervention effects of eight time-restricted eating strategies on overweight/obese adults from inception to September 18, 2024. Two researchers independently screened the literature, extracted data, and assessed the risk of bias of the included studies. Network meta-analysis was performed using ADDIS 1.16.8 and Stata 18.0 software. ResultsA total of 23 RCTs involving 1 306 overweight/obese adults were included. The network meta-analysis revealed that compared with standard diets, the 8-hour time-restricted eating combined with a low-carbohydrate diet (MD=−4.01, 95%CI −5.95 to −2.08, P<0.05) showed better weight reduction effects. Compared with standard diets, the 8-hour time-restricted eating combined with a low-carbohydrate diet (MD=−3.54, 95%CI −5.44 to −1.63, P<0.05) and the 8-hour time-restricted eating combined with a low-sugar diet (MD=−4.19, 95%CI −8.33 to −0.05, P<0.05) significantly improved overall fat mass. Compared with standard diets, the 8-hour time-restricted eating combined with a low-sugar diet (MD=−15.42, 95%CI −29.12 to −1.72, P<0.05) had a better effect on fasting blood glucose control. The 8-hour time-restricted eating combined with high-intensity interval training (MD=−3.68, 95%CI −6.57 to −0.79, P<0.05) showed better results in reducing waist circumference. No statistical significance was found in direct comparisons regarding bone mineral content. The efficacy ranking showed that the 8-hour time-restricted eating combined with a low-carbohydrate diet was most effective for weight reduction; the 8-hour time-restricted eating combined with a low-sugar diet was more effective in reducing overall fat mass and controlling fasting blood glucose; the 8-hour time-restricted eating combined with calorie restriction had significant effects on waist circumference improvement; and the 8-hour time-restricted eating combined with high-intensity interval training was more effective for increasing bone mineral content. ConclusionBased on the results of the network meta-analysis and ranking, different time-restricted eating strategies have specific advantages for the intervention of overweight or obese individuals. The choice of the appropriate strategy should consider individual dietary habits and health conditions. Due to the limited quantity and quality of the included studies, more high-quality studies are needed to verify the above conclusion.
Network meta-analyses (NMA) of survival data often rely on the proportional hazards (PH) assumption, however, this assumption fails when survival curves intersect. With the emergence of innovative therapies such as immunotherapy, the importance of NMA based on non-proportional hazards (non-PH) in the current evidence-based medicine evaluation of oncology drugs has become increasingly prominent. Fractional polynomial (FP) models do not rely on the assumption of PH, which can flexibly capture the characteristics of survival curves, and the corresponding fitting effects are better than those of the PH models. This study introduced a complete workflow in R for NMA using FP models with non-PH.
The goal of JAGS (Just Another Gibbs Sampler) software is to remedy the short of BUGS software that unable to running on a system besides Microsoft Windows, such as Unix or Linux. JAGS owns independent computing function and formula of Bayesian theory; it is mischaracterized with simple user interface, good system compatibility, smoother operation, and good interactivity with other programming software. However, due to the limitations of lacking function for results data reading and unscrambling and graph plotting, the popularization and application of JAGS software is restricted. Calling JAGS software from R software through R2jags package, rjags package, or runjags package can overcome these limitations. The operating principle of these three packages is calling JAGS software in the framework of the R software, they have similar functional structure and all have easy maneuverability, concise command, perfect function of data reading and unscrambling and graph drawing; however, there are some differences among them in practice. This article introduces how to performing network meta-analysis by calling JAGS software from R through these three packages.
ObjectiveTo systematically review the effectiveness and safety of thrombolytics for treating ST-segment elevation myocardial infarction (STEMI) in China by network meta-analysis.MethodsThe PubMed, EMbase, The Cochrane Library, Web of Science, CBM, WanFang Data, and CNKI databases were searched for randomized controlled trials (RCTs) of thrombolytics for Chinese patients with STEMI from inception to October 2016. Two reviewers independently screened literature, extracted data and assessed the risk of bias of included studies. Statistical analysis was performed by WinBUGS 1.4.3 software and R 3.3.1 software.ResultsA total of 32 RCTs involving 3 164 patients with 7 types of thrombolytics were included. The results of network meta-analysis showed: the urokinase had lower reperfusion rate than tenecteplase (rhTNK-tPA), reteplase, alteplase, and pro-urokinase (all P values <0.05), however, had higher mortality or major adverse cardiovascular events rates than rhTNK-tPA, reteplase, alteplase, and pro-urokinase (all P values <0.05), and higher incidence of non-intracranial hemorrhage than those of alteplase and pro-urokinase (both P values <0.05). The incidence of intracranial hemorrhage had no statistical differences among different thrombolytics (all P values >0.05). The results of area under the cumulative ranking curve which ranked effectiveness of all thrombolytics showed that rhTNK-tPA had the best effectiveness and urokinase had the relative worst effectiveness among different thrombolytics.ConclusionsThe current evidence shows that domestic rhTNK-tPA may be effective in thrombolytic treatment. Due to limited quality and quantity of the included studies, more high-quality studies are needed to verify the above conclusion.
ObjectiveTo compare the efficacy of different family-based interventions on reducing screen-based exposure among children and adolescents using a network meta-analysis method. MethodsThe CNKI, WanFang Data, CBM, VIP, PubMed, Web of Science, Embase, Cochrane Library databases were electronically searched to collect randomized controlled trials (RCTs) related to the objectives from inception to September 11, 2024. Two reviewers independently screened literature, extracted data and assessed the risk of bias of the included studies. Network meta-analysis was then performed by using Stata and R software. ResultsA total of 17 RCTs involving 2 490 participants were included. The results of the network meta-analysis showed that compared with waiting lists, health education, alternative behavior combined with screen exposure-restricted environment and rule-setting, behavior monitoring combined with health education, and physical activity combined with alternative behavior could reduce total screen time. The intervention effect of alternative behavior combined with behavior monitoring in reducing total screen time was superior to other intervention measures. Increasing exercise could reduce TV/DVD viewing time. Compared with health education, behavior monitoring combined with health education could reduce weekend screen time. ConclusionThe current evidence indicates that health education, alternative activities combined with screen exposure-restricted environment and rule-setting, behavior monitoring combined with health education, physical activity combined with alternative activities, physical activity alone, alternative activities combined with behavior monitoring have certain advantages in reducing screen-based exposure among children and adolescents.
ObjectiveTo systematically review the survival rate of different vascularized bone flaps in mandibular defect repair and reconstruction by Bayesian network meta-analysis. MethodsThe PubMed, EBSCO, Scopus, Web of Science, Cochrane Library, WanFang Data and CNKI databases were electronically searched to collect clinical studies related to the objectives from inception to February 2024. Two reviewers independently screened literature, extracted data and assessed the risk of bias of the included studies. The Bayesian network meta-analysis was carried out applying R software. ResultsA total of 24 studies involving 1 615 patients were included. The results of meta-analysis showed that the respective survival rates of fibula free flap (FFF), deep circumferential iliac artery flap (DCIA), scapula flap, and osteocutaneous radial forearm flap (ORFF) were 95.62%, 94.09%, 98.16%, and 93.75%. Moreover, the network meta-analysis failed to show a statistically significant difference between all comparators. Conclusion Current evidence shows that different vascularized bone flaps have similar survival rates in mandibular defect repair and reconstruction. Due to the limited quality and quantity of the included studies, more high quality studies are needed to verify the above conclusion.
Objective To systematically review the efficacy and safety of 3-month sustained releasing gonadotropin-releasing hormone agonist (GnRHa) (GnRHa 3M) and 1-month sustained releasing GnRHa (GnRHa 1M) in the treatment of pre-menopausal females with hormone receptor-positive breast cancer. Methods Databases including CNKI, WanFang Data, PubMed, EMbase and Web of Science were electronically searched to collect randomized controlled trials(RCTs) of GnRHa in the treatment of hormone receptor-positive breast cancer from inception to May 18th, 2021. Two reviewers independently screened literature, extracted data, and assessed the risk of bias of the included studies. The gemtc software package in R 3.6.1 software and Stata 15.0 software were used for network meta-analysis. Results A total of 11 RCTs including 7 484 patients were included. The network meta-analysis results showed that there was no significant difference between GnRHa 3M and GnRHa 1M in E2 level (MD=−1.3, 95%CI −13 to 9.6), DFS (HR=1.2, 95%CI 0.88 to 1.7) and OS (HR=2.0, 95%CI 0.75 to 4.9). For safety, there was no significant difference between the two groups (RR=1.0, 95%CI 0.25 to 4.2). Conclusion Current evidence shows that the efficacy and safety of GnRHa 3M is similar to that of GnRHa 1M. Due to the limited quality and quantity of the included studies, more high-quality studies are needed to verify the above conclusions.