DYNAMIC DECISION MAKING FOR CLINICAL PATIENT MANAGEMENT WITH PARKINSON�S DISEASE
Markov models are a powerful and appropriate technique for medical treatment decisions. Parkinson�s disease (PD) is one of the most common disabling neurological disorders and results in substantial burdens for patients, their families and society in terms of increased health resource use and poorer quality of life. For all stages of PD, drug therapy is the medical treatment of choice. Also two options for surgical intervention are ablative surgery and deep brain stimulation (DBS). In this paper we applied a Markov decision process (MDP) formulation to the problem of treating patients with Parkinson�s disease. The purpose of this paper is to address the challenge of effectively managing PD therapies, with a goal of maximizing a patient�s total expected lifetime or quality-adjusted lifetime. We framed this problem as an infinite-horizon discounted model that seeks a treatment strategy that minimizes total lifetime costs (where the costs incorporate duration of life, quality of life, and monetary costs). To solve this problem we used a procedure that takes advantage of special problem structure, and we provide optimal policies to stochastic and dynamic decisions naturally arise in finding optimal disease treatment plans.
OR in health services, Markov processes, dynamic programming, stochastic optimal control, medical decision making.