The Length of Hospital Stay in Acute Myocardial Infarction: A Predictive Model with Laboratory and Administrative Data

Introduction: The length of hospital stay (LOS) is an important measure of efficiency in the use of hospital resources. Acute Myocardial Infarction (AMI), as one of the diseases with higher mortality and LOS variability in the OECD countries, has been studied with predominant use of administrative data (AD). This paper presents preliminary results of a predictive model for LOS using both AD and laboratory data (LD) in order to develop a decision support system. Methods: LD and AD of a Portuguese hospital were included, using logistic regression to develop a predictive model for extended LOS. The examples of three individuals were performed to show how model works. Results: A model with three LD and seven AD variables, with excellent discriminative ability and a good calibration, was obtained. Age >= 69, presence of comorbidities and abnormal LD predict a higher probability of extended LOS.