Hospital performance in a large urban acute myocardial infarction emergency care system: Tokyo Cardiovascular Care Unit network

Abstract

Background: An ideal urban network system for improving regional acute myocardial infarction (AMI) outcomes should be geographically balanced and uniform according to regional population in performance of participating hospitals. The objective of our study is to evaluate whether there is a major difference in risk-adjusted in-hospital mortality between the Tokyo Cardiovascular Care Unit (CCU) network hospitals, which cover the whole population of large cities.

Methods: The study subjects were all AMI patients without cardiac arrest on arrival admitted to the Tokyo CCU network hospitals from 2009 to 2017. Risk-adjusted in-hospital mortality rates (RAMRs) were compared between the categories of each hospital-level factor. A hospital-level multivariable linear regression was modeled to analyze the association between RAMRs and hospital-level factors. A funnel plot was constructed by plotting RAMRs against hospital volumes.

Results: From 2009 to 2017, there were 42,123 hospitalizations for AMI in Tokyo CCU network hospitals (n=72, as of December, 2017). There were no significant differences in RAMRs in the comparison of hospital backgrounds. Each hospital background was not significantly associated with the RAMR. Considering the 99% CI in funnel plots, only five hospitals (7.2%) were located outside the control limits.

Conclusions: There was no major difference in the RAMRs between the participating hospitals within the Tokyo CCU network, despite the different hospital backgrounds.

Keywords: Acute myocardial infarction; Hospital network; Hospital performance; Hospital variation; Mortality.