A Model-Based System Engineering Framework for Healthcare Management with Application to Diabetes Mellitus

We describe a framework for Health Care Management Systems using modern Model-Based Systems Engineering methodologies and apply it to Diabetes Mellitus. We describe the desired architecture of such systems. We include a Controlled Hidden Markov Chain model for diabetes disease progression with three states, three diagnostic tests, ten interventions, three types of patients. We develop three methods for computing tradeoffs between health care cost and health care quality. One is an exhaustive Monte Carlo simulation and the other two use multi-criteria optimization with full and partial disease state information. The latter obtain similar results at a fraction of the time of the first. We demonstrate the powerful capabilities of such a framework via examples and problems of practical healthcare significance.