Process indicators and outcome measures in the treatment of Acute Myocardial Infarction patients

In this chapter, clinical registries are used to model in-hospital survival of acute myocardial infarction patients, in order to classify providers' performances and to enable healthcare governance to better manage resources. The chapter aims at quantifying the magnitude of the variations in healthcare providers and assessing the role of contributing factors, including patients' and providers' characteristics, on survival outcome. Data on healthcare utilization have a 'natural' multilevel structure, usually with patients at the lower level and hospitals forming the upper-level clusters. Within this formulation, the main goal is to derive estimates of providers' effects; that is, differences between hospitals. The chapter also aims at clustering hospitals according to their performance in patients' care. Hierarchical regression modelling from a Bayesian non-parametric perspective provides a framework that can accomplish the above mentioned goals. Dataset, performed analyses and results are discussed and future work is presented.