A comparison of the statistical performance of different meta-analysis models for the synthesis of subgroup effects from randomized clinical trials

Effectiveness and safety of intra-articular interventions for knee and hip osteoarthritis based on large randomized trials: A systematic review and network meta-analysis

OBJECTIVE

To quantify the effectiveness and safety of intra-articular interventions for knee and hip osteoarthritis (OA) through a systematic review and Bayesian random-effects network meta-analysis.

DESIGN

We searched CENTRAL and regulatory agency websites (inception-2023) for large, English-language, randomized controlled trials (RCTs) (≥100 patients/group) examining any intra-articular intervention.

PRIMARY OUTCOME

pain intensity.

SECONDARY OUTCOMES

physical function and safety outcomes. Pain and function outcomes were analyzed at 2, 6, 12, 24, and 52 weeks post-randomization, and presented as standardized mean differences (SMDs) (95% credible intervals, 95% CrI). The prespecified minimal clinically important between-group difference (MID) was -0.37 SMD. Safety outcomes were presented as odds ratios (OR) (95% CrI).

FINDINGS

Among 57 RCTs (22,795 participants) examining 18 intra-articular interventions, usual care or placebo, treatment effects were larger in 35 high-risk-of-bias trials than in 22 low/unclear-risk-of-bias trials. In the main analysis (excluding high-risk-of-bias trials), triamcinolone had the highest probabilities of reaching the MID at weeks 2 and 6 (75.3% and 90%, respectively) with corresponding SMDs of -0.48 (95% CrI,-0.85 to -0.10) and -0.53 (95% CrI,-0.79 to -0.27) compared to placebo (1 trial). The complex homeopathic products Tr14/Ze14 showed therapeutic potential at week 6 compared to placebo (SMD:-0.42, 95% CrI,-0.71 to -0.11, 63.5% probability of reaching the MID, 1 trial). Hyaluronic acid had no effect on pain (SMD:-0.04, 95% CrI,-0.19 to 0.11, 11 trials) but a higher risk of dropouts due to adverse events (OR: 2.01, 95% CrI,1.08 to 3.77) and serious adverse events (OR: 1.86, 95% CrI, 1.16 to 3.03) than placebo.

CONCLUSION

Triamcinolone had the highest probabilities to have a treatment effect beyond the MID at weeks 2-6. Large RCTs with lower risk of bias indicate that the effects of 16 intra-articular interventions in knee or hip OA were smaller than the MID, and that most were consistent with placebo effects. Lack of evidence of long-term effectiveness underscores the need for further research beyond 24 weeks.

Nonlinear effects and effect modification at the participant-level in IPD meta-analysis part 2: methodological guidance is available

OBJECTIVES

To review methodological guidance for nonlinear covariate-outcome associations (NL), and linear effect modification and nonlinear effect modification (LEM and NLEM) at the participant level in individual participant data meta-analyses (IPDMAs) and their power requirements.

STUDY DESIGN AND SETTING

We searched Medline, Embase, Web of Science, Scopus, PsycINFO and the Cochrane Library to identify methodology publications on IPDMA of LEM, NL or NLEM (PROSPERO CRD42019126768).

RESULTS

Through screening 6,466 records we identified 54 potential articles of which 23 full texts were relevant. Nine further relevant publications were published before or after the literature search and were added. Of these 32 references, 21 articles considered LEM, 6 articles NL or NLEM and 6 articles described sample size calculations. A book described all four. Sample size may be calculated through simulation or closed form. Assessments of LEM or NLEM at the participant level need to be based on within-trial information alone. Nonlinearity (NL or NLEM) can be modeled using polynomials or splines to avoid categorization.

CONCLUSION

Detailed methodological guidance on IPDMA of effect modification at participant-level is available. However, methodology papers for sample size and nonlinearity are rarer and may not cover all scenarios. On these aspects, further guidance is needed.

Estimating interactions in individual participant data meta-analysis: a comparison of methods in practice

Medical interventions may be more effective in some types of individuals than others and identifying characteristics that modify the effectiveness of an intervention is a cornerstone of precision or stratified medicine. The opportunity for detailed examination of treatment-covariate interactions can be an important driver for undertaking an individual participant data (IPD) meta-analysis, rather than a meta-analysis using aggregate data. A number of recent modelling approaches are available. We apply these methods to the Perinatal Antiplatelet Review of International Studies (PARIS) Collaboration IPD dataset and compare estimates between them. We discuss the practical implications of applying these methods, which may be of interest to aid meta-analysists in the use of these, often complex models.Models compared included the two-stage meta-analysis of interaction terms and one-stage models which fit multiple random effects and separate within and between trial information. Models were fitted for nine covariates and five binary outcomes and results compared.Interaction terms produced by the methods were generally consistent. We show that where data are sparse and there is low heterogeneity in the covariate distributions across trials, the meta-analysis of interactions may produce unstable estimates and have issues with convergence. In this IPD dataset, varying assumptions by using multiple random effects in one-stage models or using only within trial information made little difference to the estimates of treatment-covariate interaction. Method choice will depend on datasets characteristics and individual preference.

Factors Limiting Subgroup Analysis in Cost-Effectiveness Analysis and a Call for Transparency

The use of population averages in cost-effectiveness analysis may hide important differences across subgroups, potentially resulting in suboptimal resource allocation, reduced population health and/or increased health inequalities. We discuss the factors that limit subgroup analysis in cost-effectiveness analysis and propose more thorough and transparent reporting. There are many issues that may limit whether subgroup analysis can be robustly included in cost-effectiveness analysis, including challenges with prespecifying and justifying subgroup analysis, identifying subgroups that can be implemented (identified and targeted) in practice, resource and data requirements, and statistical and ethical concerns. These affect every stage of the design, development and reporting of cost-effectiveness analyses. It may not always be possible to include and report relevant subgroups in cost effectiveness, e.g. due to data limitations. Reasons for not conducting subgroup analysis may be heterogeneous, and the consequences of not acknowledging patient heterogeneity can be substantial. We recommend that when potentially relevant subgroups have not been included in a cost-effectiveness analysis, authors report this and discuss their rationale and the limitations of this. Greater transparency of subgroup reporting should provide a starting point to overcoming these challenges in future research.

The Use of Tocilizumab in Patients with COVID-19: A Systematic Review, Meta-Analysis and Trial Sequential Analysis of Randomized Controlled Studies

Background: Among the several therapeutic options assessed for the treatment of coronavirus disease 2019 (COVID-19), tocilizumab (TCZ), an antagonist of the interleukine-6 receptor, has emerged as a promising therapeutic choice, especially for the severe form of the disease. Proper synthesis of the available randomized clinical trials (RCTs) is needed to inform clinical practice. Methods: A systematic review with a meta-analysis of RCTs investigating the efficacy of TCZ in COVID-19 patients was conducted. PubMed, EMBASE, and the Cochrane COVID-19 Study Register were searched up until 30 April 2021. Results: The database search yielded 2885 records; 11 studies were considered eligible for full-text review, and nine met the inclusion criteria. Overall, 3358 patients composed the TCZ arm, and 3131 the comparator group. The main outcome was all-cause mortality at 28–30 days. Subgroup analyses according to trials’ and patients’ features were performed. A trial sequential analysis (TSA) was also carried out to minimize type I and type II errors. According to the fixed-effect model approach, TCZ was associated with a better survival odds ratio (OR) (0.84; 95% confidence interval (CI): 0.75–0.94; I²: 24% (low heterogeneity)). The result was consistent in the subgroup of severe disease (OR: 0.83; 95% CI: 0.74–0.93; I²: 53% (moderate heterogeneity)). However, the TSA illustrated that the required information size was not met unless the study that was the major source of heterogeneity was omitted. Conclusions: TCZ may represent an important weapon against severe COVID-19. Further studies are needed to consolidate this finding.

Sodium-Glucose Cotransporter 2 Inhibitors, All-Cause Mortality, and Cardiovascular Outcomes in Adults with Type 2 Diabetes: A Bayesian Meta-Analysis and Meta-Regression

Background

This study aimed to assess the effectiveness of sodium‐glucose cotransporter 2 inhibitors in reducing the incidence of mortality and cardiovascular outcomes in adults with type 2 diabetes.

Methods and Results

We conducted a Bayesian meta‐analysis of randomized controlled trials comparing sodium‐glucose cotransporter 2 inhibitors with placebo. We used meta‐regression to examine the association between treatment effects and control group event rates as measures of cardiovascular baseline risk. Fifty‐three randomized controlled trials were included in our synthesis. Empagliflozin, canagliflozin, and dapagliflozin reduced the incidence of all‐cause mortality (empagliflozin: rate ratio [RR], 0.79; 95% credibility interval [CrI], 0.63–0.97; canagliflozin: RR, 0.86; 95% CrI, 0.69–1.05; dapagliflozin: RR, 0.86; 95% CrI, 0.72–1.01) and cardiovascular mortality (empagliflozin: RR, 0.78; 95% CrI, 0.61–1.00; canagliflozin: RR, 0.83; 95% CrI, 0.63–1.05; dapagliflozin: RR, 0.88; 95% CrI, 0.71–1.08), with a 90.1% to 98.7% probability for the true RR to be <1.00 for both outcomes. There was little evidence for ertugliflozin and sotagliflozin versus placebo for reducing all‐cause and cardiovascular mortality. There was no association between treatment effects for all‐cause and cardiovascular mortality and the control group event rates. There was evidence for a reduction in the incidence of heart failure for empagliflozin, canagliflozin, dapagliflozin, and ertugliflozin versus placebo (probability RR <1.00 of ≥99.3%) and weaker, albeit positive, evidence for acute myocardial infarction for the first 3 agents (probability RR <1.00 of 89.0%–95.2%). There was little evidence of any agent except canagliflozin for reducing the incidence of stroke.

Conclusions

Empagliflozin, canagliflozin, and dapagliflozin reduced the incidence of all‐cause and cardiovascular mortality versus placebo. Treatment effects of sodium‐glucose cotransporter 2 inhibitors versus placebo do not vary by baseline risk.