We track the path sick individuals take through "disease space" to learn how to prevent, reduce and recover from symptoms. Our approach is to use simple descriptions of tolerance and resilience from ecology to predict the trajectory of a system as it is perturbed and then recovers. We need less data to test our ideas than to use machine learning and determine disease trajectories from scratch. We then explore our predictions experimentally, using a combination of models ranging from bacteria infected fruit flies to Plasmodium infected mice and humans. Our current work focuses on mapping and manipulating the metabolic changes that occur during a malaria infection to improve outcomes. With respect to the PHIND Center, the maps we produce of disease space and the trajectories that sick individuals take through this space provide a simple graphical description of the differences between precision health and precision medicine.