G M Weber et al. in the BMJ:

In this study, we build on previous research into the healthcare process model, but on a larger scale. Specifically, we systematically evaluate the ability of 272 laboratory tests to predict three year survival across the full patient populations seen over a year at two large hospitals. We treat laboratory test data in the EHR as having two distinct dimensions. One dimension is the value of the test result, which is a measure of the patient’s pathophysiology. The other is the timing of when the test was ordered, which is a marker of the underlying healthcare processes.

Boils down to doctors have a pretty good sense of who is in trouble, and change behaviors therefore. But that is not the point, the point is that when you are extracting info from big data, the noise may have signal, that you have to control for if you want to look deeper.