Multi-State Markov Chain Modeling of Health Insurance Claims and Cost Prediction

Abstract

Health care costs have increased significantly in the past few decades due to a cost-per- service incentive structure, which compensates physicians for quantity, not quality, of treatments. Accordingly, predicting health insurance costs of multi-visit conditions with accuracy is a problem of wide-reaching importance for insurance companies. This thesis focuses on modeling health insurance claims of episodic, recurring health prob- lems as Markov Chains, estimating cycle length and cost, and then pricing associated health insurance premiums and setting forth a framework for the risk-management of a health insurance portfolio. The cost and cycle-length estimations modeled in this thesis affords health insurance companies a way to compare physician treatment effectiveness and cost effectiveness, to inform them of which physicians to cover.