Title: Multiple-outcome network meta-analysis and personalized treatment ranking
Authors: Yong Chen - Univ. of Pennsylvania (United States) [presenting]
Abstract: Network Meta-analysis (NMA), also known as multiple treatments meta- analysis (MTM), expands the scope of conventional pairwise meta-analysis by simultaneously synthesizing both direct comparisons of interventions within randomized clinical trials and indirect comparisons across trials. Network meta-analysis has been shown to have the advantage of providing broader, objective and inclusive view of available evidence for comparative effectiveness reviews. While network meta-analysis allows integrating information from clinical trials comparing different interventions, it also brings additional model assumptions and complexity. Furthermore, trials typically measure multiple outcomes, such as drug efficacy and safety. Simultaneously modeling all the outcomes allows borrowing information across outcomes since they are not only correlated but are also of interest for clinicians and patients. Therefore, considering the multivariate network meta-analysis is a necessity for aggregating all the existing evidence for comparative effectiveness reviews. We will introduce a simple but robust method for conducting multivariate NMA, as well as its implications to personalized treatment ranking.