Based upon some googling it would appear that I need to run a logistic regression on our data to determine the probability that a patient will not show for their appointment.
I am a statistics noob and so I definitely have no clue.
Will I be able to use a Python Analysis transform (once all the packages are loaded) to perform this trick on the fly?
Or is this something I will need to do with MS SQL and Python outside of BI?
You should indeed be able to use a python analysis transform for this - as long as you can bring the data in from the database to feed the transform and the data is structured in such a way that you should be able to perform the modeling/calculations you would like on it, you should be good to go - you can import pretty much any python package you’d like into the transform.
You can also use R to perform this type of statistical modeling, as an alternative (although I’d imagine you are more familiar with Python).