Add cohort comparison tables

[firste]

Is your feature request related to a problem? Please describe

Understanding how a site's patient population differs from the model training or local population is important during pre-procurement validation and post-implementation monitoring. This should be done across the various cohort attributes present in the dataset.

Describe the solution you'd like

Build a configuration pattern to include cohort breakdown data provided by the model developer from training sites or for a health system to include local population breakdowns.

Build an analysis that plot these comparisons into a table and highlight significant differences.

Describe alternatives you've considered

This could be implemented manually in each notebook, but given that this is an need for all models and much of the necessary inference time data is already present, it should be added as a default analysis.

Additional context

After this is implemented, the UX could be enhanced with this additional configuration.