A Bayesian random-effects model for survival probabilities after acute myocardial infarction


Statistical learning
Health Analytics
A Bayesian random-effects model for survival probabilities after acute myocardial infarction
Saturday 5th June 2010
Guglielmi, Alessandra; Ieva, Francesca; Paganoni, Anna Maria; Ruggeri, Fabrizio
Download link:
Studies of variations in health care utilization and outcome involve the analysis of multilevel clustered data, considering in particular the estimation of a cluster-specific adjusted response, covariates effect and components of variance. Besides reporting on the extent of observed variations, those studies quantify the role of contributing factors including patients and providers characteristics. In addition, they may assess the relationship between health-care process and outcomes. In this article we present a case-study, considering a Bayesian hierarchical generalized linear model, to analyze MOMI2 (MOnth MOnitoring Myocardial Infarction in MIlan) data on patients admitted with ST-Elevation Myocardial Infarction diagnosis, in order to predict survival probabilities. We obtain posterior estimates of the regression parameters, as well as of the random-effects parameters (the grouping factor is the hospital the patients were admitted to), through an MCMC algorithm. The choice of covariates is achieved in a Bayesian fashion as a preliminary step. Some issues about model fitting are discussed through the use of predictive tail probabilities and Bayesian residuals. Keywords: Bayesian hierarchical models, Multilevel data analysis, Bayesian generalized linear mixed models, Logistic regression, Health services research. AMS Subject Classi¯cation: 62F15, 62P10, 62J12
This report, or a modified version of it, has been also submitted to, or published on
Chilean Journal of Statistics, Vol. 3, No. 1, pp: 1-15