Mark Baillie presents examples for visualisations of heterogeneity in a meta-analysis combining data of seven studies. The objective of the studies was to show reduction in hypertension. Additional interest was in prognostic or predictive factors.
The first three visualisations were interactive apps. A forest plot with bands displayed the overlaps of the confidence intervals. The Subgroup Explorer enabled the comparison of different outcomes across all baseline factors and studies side by side or as bubble plot. A multistep meta-analysis app included a prognostic model and displayed the interaction within all combinations of studies allowing for interactive selection of studies and predictors.
Examples for static plots were different kinds of multiplots. Two were combining joyplots either of the baseline factors plotting all studies or of the studies plotting the treatment groups. The scatter plot at the end finale revealed the secret in the data.
The new challenge was introduced and will be about visualisation of a prediction model for a binary outcome.
Wonderful Wednesdays are brought to you by the Visualisation SIG. The Wonderful Wednesday team includes: Bodo Kirsch, Alexander Schacht, Mark Baillie, Daniel Saure, Zachary Skrivanek, Lorenz Uhlmann, Rachel Phillips, Markus Vogler, David Carr, Steve Mallett, Abi Williams, Julia Igel.