Optimal Assignment of Treatments to??Health States Using a Markov Decision Model

摘要: Assessing the cost effectiveness of a new health intervention often requires modelling to estimate impact on cost, survival and quality life over lifetime cohort patients. Markov is methodology that commonly employed these long-term costs benefits. As used, models assume patients continue get treatments assigned regardless change in states. In this paper, we describe an extension approach, called decision modelling. Such model starts with set states optimally assigns each A can be used identify optimal treatment strategy not just for initial disease state, but also as state changes time. We present dynamic programming approach identifying assignment treatments, illustrate using example. The provides efficient way states, but, like standard model, may limited use when probabilities future events depend past history complex fashion. Even its limitations, offer opportunity economists inform healthcare decision-makers how modify current pathways incorporate they become available.