Balancing prescriptions with constraint solvers

Abstract

Clinical guidelines are evidence-based care plans which detail the essential steps to be followed when caring for patients with a specific clinical problem, usually a chronic disease (e.g. diabetes, cardiovascular disease, chronic kidney disease, cancer, chronic obstructive pulmonary disease, and so on). Recommendations for chronic diseases include the medications (or group of medications) to be given at different stages of the treatment plan. We present an automated approach which combines constraint solvers and theorem provers to find the best solutions for treatment according to different criteria, and avoiding adverse drug reactions as much as possible. We extended the approach here to further refine the choice(s) to avoid dangerous or undesirable side effects.