Now, let's quickly click on the field named Do you use recreational drugs in the visualization and change it to one of our other suspected prediction drivers: Do you smoke. The following screenshot shows you how to do this:

Another, perhaps more curious, visualization will be presented to us, as shown in the following screenshot:

There doesn't seem to be any material difference in the number of illnesses recorded for those who smoke and those who do not. Either way, let's go ahead and add this visualization to our collection (by clicking the Collect icon at the bottom left of the page, as we did for the previous visualization).

Now, at this point, another interesting thought will occur to us: What about the patient's response to the question of alcohol use? If we change the column name again, we will see the following visualization:

This seems more in-line with the common belief that a regular user of alcohol might indeed be ill more often. This theory seems to jump out at us from the visualization quite quickly, given the contrast between the number of illnesses displayed for those answering Yes and those answering No.

Let's go ahead and add this visualization to our collection as well.