I found this post about science without theories to be fascinating.
"It may turn out that tremendously large volumes of data are sufficient
to skip the theory part in order to make a predicted observation."
This correlative science is discussed as part of medical care further down in the article. Perhaps this should be the biggest motivation to comprehensive, vast electronic medical records capable of providing such large data sets that useful information can come from patient encounters.
"…computers can extract patterns in this ocean of data that no human could ever possibly detect."