MODELING DECISION MAKING IN CLINICAL PRACTICE:A COST-EFFECTIVENESS APPROACH

Abstract

Current medical research, focused on understanding the disease from a molecular level is exploring the correlation between
various inflammatory markers (cytokines) and patient survival. Partially observable Markov decision processes ( POMDPs )
have recently been suggested as a suitable Model to formalizing the planning of Clinical Management over a prolonged period
of time. In this paper, we show how the POMDP framework can be used to model and solve the problem of the management
of patients, characterized by hidden disease states, investigative and treatment procedures. This model is significant because it
provides a way to make a tradeoff between choosing the investigative actions and the diagnosis actions. The results in this
paper demonstrate the potential value of inexpensive, accurate testing procedures as well as accurate interpretation of test
results. The reported experiments show that (POMDPs) provide Clinically Reasonable and justifiable solutions