Network Meta-analysis: Users' Guide for Surgeons: Part II - Certainty

Abstract

In the previous article (Network Meta-analysis: Users' Guide for Surgeons-Part I, Credibility), we presented an approach to evaluating the credibility or methodologic rigor of network meta-analyses (NMA), an innovative approach to simultaneously addressing the relative effectiveness of three or more treatment options for a given medical condition or disease state. In the second part of the Users' Guide for Surgeons, we discuss and demonstrate the application of criteria for determining the certainty in effect sizes and directions associated with a given treatment option through an example pertinent to clinical orthopaedics.

Fig. 1

In the forest plot comparing unreamed intramedullary nailing and external fixation (based on data from the open tibial shaft NMA [7]), initial visual assessment indicates that heterogeneity is low, as odds ratios are similar and CIs are widely overlapping.

Fig. 2

A rankogram plots the probability of each rank for each treatment. In this hypothetical figure, THA (green solid line) has a higher likelihood of being the best treatment compared with either monopolar (red dashed line) or bipolar (blue dotted line) hemiarthroplasty. Through visual depiction, ranks are shown as probabilities rather than absolute values.