It has been suggested that machine learning algorithms (also Watson) can help with finding disease in patient images and optimize scans. Also that deep learning algorithms show promise for every type of digital imaging.
How does exactly deep learning algorithms exactly can find suspicious patterns in the body’s biochemistry?
I wouldn't focus only on "deep learning" unless you have some specific reason for doing so. There may be other techniques which could be as effective, or more effective.
One approach I've seen used for something similar was Inductive Logic Programming. For one example of using ILP to reason about elements of biochemistry, see this paper
That's not exactly about detecting disease, but it does sort of illustrate the broad idea of reasoning about states and reactions involving metabolic pathways in biochemistry, using ILP. Possibly the basic idea could be adapted more towards detecting disease.
