Bayesian splines versus fractional polynomials in network meta-analysis
- PDF / 1,791,312 Bytes
- 16 Pages / 595 x 791 pts Page_size
- 113 Downloads / 194 Views
(2020) 20:261
RESEARCH ARTICLE
Open Access
Bayesian splines versus fractional polynomials in network meta-analysis Andreas Heinecke1 , Marta Tallarita2 and Maria De Iorio1,2* Abstract Background: Network meta-analysis (NMA) provides a powerful tool for the simultaneous evaluation of multiple treatments by combining evidence from different studies, allowing for direct and indirect comparisons between treatments. In recent years, NMA is becoming increasingly popular in the medical literature and underlying statistical methodologies are evolving both in the frequentist and Bayesian framework. Traditional NMA models are often based on the comparison of two treatment arms per study. These individual studies may measure outcomes at multiple time points that are not necessarily homogeneous across studies. Methods: In this article we present a Bayesian model based on B-splines for the simultaneous analysis of outcomes across time points, that allows for indirect comparison of treatments across different longitudinal studies. Results: We illustrate the proposed approach in simulations as well as on real data examples available in the literature and compare it with a model based on P-splines and one based on fractional polynomials, showing that our approach is flexible and overcomes the limitations of the latter. Conclusions: The proposed approach is computationally efficient and able to accommodate a large class of temporal treatment effect patterns, allowing for direct and indirect comparisons of widely varying shapes of longitudinal profiles. Keywords: Bayesian evidence synthesis techniques, P-splines, Clinical trials, Evidence-synthesis, Longitudinal studies, Markov chain Monte Carlo methods, Mixed treatment comparison
Background Scientific and technological advances are steadily adding to the number of different healthcare interventions. To fully exploit their potential requires clinicians and healthcare professionals to make informed and objective choices, based on clinical studies, between a possibly large number of treatment options in terms of relative medical efficacy and cost effectiveness [11, 22]. It is generally accepted that randomized controlled trials provide the most rigorous and conclusive evidence on the relative effects of different interventions. For example, the gold standard for directly comparing two treatments A and B is a randomized controlled trial. In practice, however, *Correspondence: [email protected] Yale-NUS College, 16 College Avenue West, 138527 Singapore, Singapore 2 Department of Statistical Science, University College London, Gower Street, WC1E 6BT London, UK 1
evidence from direct comparison trials may be limited and it is often impossible to have head-to-head comparisons for all relevant comparators of an intervention, making it necessary to resort to indirect comparisons [11]. For instance, direct comparison from two different studies on treatment A versus C, and B versus C, might be available and indirect methods exploit the common comparator C to provide an indirect comparis
Data Loading...
