An evidence‐splitting approach to evaluation of direct‐indirect evidence inconsistency in network meta‐analysis

Shih, Ming‐Chieh; Tu, Yu–Kang

doi:10.1002/jrsm.1480

Cited by 13 publications

(23 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We evaluated the presence of inconsistency by comparing direct and indirect evidence within each closed loop by applying the separating indirect from direct evidence (SIDE) approach 47,48 . We further compared the goodness of fit for a NMA model assuming consistency with a model allowing for inconsistency in a "design-by-treatment interaction model" framework [49][50][51] , using the decompose.design function in R package netmeta 52 .…”

Section: Discussionmentioning

confidence: 99%

Oral and long‐acting antipsychotics for relapse prevention in schizophrenia‐spectrum disorders: a network meta‐analysis of 92 randomized trials including 22,645 participants

et al. 2022

View full text Add to dashboard Cite

According to current evidence and guidelines, continued antipsychotic treatment is key for preventing relapse in people with schizophrenia‐spectrum disorders, but evidence‐based recommendations for the choice of the individual antipsychotic for maintenance treatment are lacking. Although oral antipsychotics are often prescribed first line for practical reasons, long‐acting injectable antipsychotics (LAIs) are a valuable resource to tackle adherence issues since the earliest phase of disease. Medline, EMBASE, PsycINFO, CENTRAL and CINAHL databases and online registers were searched to identify randomized controlled trials comparing LAIs or oral antipsychotics head‐to‐head or against placebo, published until June 2021. Relative risks and standardized mean differences were pooled using random‐effects pairwise and network meta‐analysis. The primary outcomes were relapse and dropout due to adverse events. We used the Cochrane Risk of Bias tool to assess study quality, and the CINeMA approach to assess the confidence of pooled estimates. Of 100 eligible trials, 92 (N=22,645) provided usable data for meta‐analyses. Regarding relapse prevention, the vast majority of the 31 included treatments outperformed placebo. Compared to placebo, “high” confidence in the results was found for (in descending order of effect magnitude) amisulpride‐oral (OS), olanzapine‐OS, aripiprazole‐LAI, olanzapine‐LAI, aripiprazole‐OS, paliperidone‐OS, and ziprasidone‐OS. “Moderate” confidence in the results was found for paliperidone‐LAI 1‐monthly, iloperidone‐OS, fluphenazine‐OS, brexpiprazole‐OS, paliperidone‐LAI 1‐monthly, asenapine‐OS, haloperidol‐OS, quetiapine‐OS, cariprazine‐OS, and lurasidone‐OS. Regarding tolerability, none of the antipsychotics was significantly worse than placebo, but confidence was poor, with only aripiprazole (both LAI and OS) showing “moderate” confidence levels. Based on these findings, olanzapine, aripiprazole and paliperidone are the best choices for the maintenance treatment of schizophrenia‐spectrum disorders, considering that both LAI and oral formulations of these antipsychotics are among the best‐performing treatments and have the highest confidence of evidence for relapse prevention. This finding is of particular relevance for low‐ and middle‐income countries and constrained‐resource settings, where few medications may be selected. Results from this network meta‐analysis can inform clinical guidelines and national and international drug regulation policies.

show abstract

Section: Discussionmentioning

confidence: 99%

Oral and long‐acting antipsychotics for relapse prevention in schizophrenia‐spectrum disorders: a network meta‐analysis of 92 randomized trials including 22,645 participants

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Inconsistency will be tested for using the node-split model. When P>0.05, the selected studies will be considered to be heterogeneous, and the consistency model will be used for analysis; otherwise, the inconsistency model will be applied (27). Convergence will be measured using the potential scale reduction factor method.…”

Section: Discussionmentioning

confidence: 99%

Acupoint application therapy for diarrhea-predominant irritable bowel syndrome: a protocol for systematic review and network meta-analysis

Yin

Ouyang

et al. 2022

Ann Palliat Med

View full text Add to dashboard Cite

Background: Irritable bowel syndrome is a chronic functional gastrointestinal disease, of which diarrheapredominant irritable bowel syndrome (IBS-D) is a common subtype. In China, acupoint application therapy is currently widely used as an effective complementary therapy for IBS-D. In the clinical management of IBS-D, acupoint application is usually combined with other therapies, including acupuncture, moxibustion, and Chinese herbal and Western medicine. However, at present, evidence regarding the most effective options for treating IBS-D is insufficient. Therefore, this protocol proposes a systematic review and network meta-analysis for evaluating the effectiveness of acupoint application and its combination therapies in treating IBS-D, and for identifying the acupoint application-related treatments with the highest probability of being the best intervention.Methods: Six English electronic databases (PubMed, Ovid MEDLINE, Scopus, Web of Science, the Cochrane Library, and EMBASE), four Chinese electronic databases [China National Knowledge Infrastructure (CNKI), China Science and Technology Journal Database (CQVIP), WanFang, and SinoMed), and one Japanese medical database (Citation Information by National Institute of Informatics (CiNii)] will be searched for eligible randomized controlled trials from their inception to June 1, 2022. The efficacy and safety of acupoint application therapy and its combination therapies for patients with IBS-D will be evaluated. The STATA 14.0 (StataCorp, USA) software package will be used for the meta-analysis.A Bayesian NMA will be performed using R (version 4.0.2) and Aggregate Data Drug Information System (ADDIS, version 1.16.8) software packages. Bias risk will be assessed using the Cochrane Collaboration's risk of bias tool; specifically, publication bias will be evaluated using Egger's test and funnel plots. The rank probabilities of various outcomes for each intervention will be calculated, clustered, and ranked using the cumulative ranking curve method. The Grading of Recommendations Assessment, Development, and Evaluation (GRADE) method will be employed to assess the certainty of evidence for NMA outcomes.Discussion: This study will aim to determine the clinical efficacy of acupoint application therapy and its combined therapy in the treatment of IBS-D and provide an evidence-based foundation for identifying the best acupoint application program.

show abstract

“…Several methods have been suggested to evaluate the consistency assumption that can be broadly categorized into local and global methods. Local methods evaluate consistency either in every loop or comparison in the network for which we have both direct and indirect evidence 4‐9 . Global methods include approaches where inconsistency factors are added to the NMA model and evaluated simultaneously, 10‐12 employing the generalized Cochran's Q statistic, 13 fitting the NMA model using integrated nested Laplace approximations, 14 and treating the comparisons as independent parameters for estimation 15 .…”

Section: Introductionmentioning

confidence: 99%

“…Local methods have an increased probability of false positives for large networks, while global methods suffer from lack of power 10 . Moreover, local methods in which for each comparison we contrast direct evidence and indirect effect estimates (node‐splitting, symmetric side‐splitting, separate indirect from direct design evidence SIDDE), have been shown in the presence of multi‐arm trials to disregard the principle of independence between direct and indirect evidence and as a result, may lead to false conclusions 8 …”

Section: Introductionmentioning

confidence: 99%

“…Local methods evaluate consistency either in every loop or comparison in the network for which we have both direct and indirect evidence. [4][5][6][7][8][9] Global methods include approaches where inconsistency factors are added to the NMA model and evaluated simultaneously, [10][11][12] employing the generalized Cochran's Q statistic, 13 fitting the NMA model using integrated nested Laplace approximations, 14 and treating the comparisons as independent parameters for estimation. 15 Local methods have an increased probability of false positives for large networks, while global methods suffer from lack of power.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Inconsistency identification in network meta‐analysis via stochastic search variable selection

Seitidis,

Nikolakopoulos,

Ntzoufras

et al. 2023

Statistics in Medicine

View full text Add to dashboard Cite

The reliability of the results of network meta‐analysis (NMA) lies in the plausibility of the key assumption of transitivity. This assumption implies that the effect modifiers' distribution is similar across treatment comparisons. Transitivity is statistically manifested through the consistency assumption which suggests that direct and indirect evidence are in agreement. Several methods have been suggested to evaluate consistency. A popular approach suggests adding inconsistency factors to the NMA model. We follow a different direction by describing each inconsistency factor with a candidate covariate whose choice relies on variable selection techniques. Our proposed method, stochastic search inconsistency factor selection (SSIFS), evaluates the consistency assumption both locally and globally, by applying the stochastic search variable selection method to determine whether the inconsistency factors should be included in the model. The posterior inclusion probability of each inconsistency factor quantifies how likely is a specific comparison to be inconsistent. We use posterior model odds or the median probability model to decide on the importance of inconsistency factors. Differences between direct and indirect evidence can be incorporated into the inconsistency detection process. A key point of our proposed approach is the construction of a reasonable “informative” prior concerning network consistency. The prior is based on the elicitation of information derived historical data from 201 published network meta‐analyses. The performance of our proposed method is evaluated in two published network meta‐analyses. The proposed methodology is publicly available in an R package called ssifs, published on CRAN and developed and maintained by the authors of this work.

show abstract

An evidence‐splitting approach to evaluation of direct‐indirect evidence inconsistency in network meta‐analysis

Cited by 13 publications

References 19 publications

Oral and long‐acting antipsychotics for relapse prevention in schizophrenia‐spectrum disorders: a network meta‐analysis of 92 randomized trials including 22,645 participants

Oral and long‐acting antipsychotics for relapse prevention in schizophrenia‐spectrum disorders: a network meta‐analysis of 92 randomized trials including 22,645 participants

Acupoint application therapy for diarrhea-predominant irritable bowel syndrome: a protocol for systematic review and network meta-analysis

Inconsistency identification in network meta‐analysis via stochastic search variable selection

Contact Info

Product

Resources

About