AUTHOR=Xavier Joana , Seringa Joana , Pinto Fausto José , Magalhães Teresa 

TITLE=Decision-making support systems on extended hospital length of stay: Validation and recalibration of a model for patients with AMI

JOURNAL=Frontiers in Medicine

VOLUME=Volume 10 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2023.907310

DOI=10.3389/fmed.2023.907310

ISSN=2296-858X

ABSTRACT=Background: Cardiovascular diseases are still a significant cause of death and hospitalization. In 2019, circulatory diseases were responsible for 29.9% of deaths in Portugal (1). These diseases have an important impact on the length of stay. Length of stay predictive models are an efficient way to aid decision-making in health. The aim of this study was to validate a predictive model on extended length of stay (LOSE) in patients with AMI at the time of admission.
Methods: An analysis was carried out to test and recalibrate a previously developed model in the prediction of prolonged length of stay for a different population. The study was conducted based on administrative and laboratory data of patients admitted for AMI events from an NHS hospital in Portugal from 2013 to 2015.
Results: After validation and recalibration of the predictive model of LOSE, reasonable validation measures have been found. Comorbidities such as shock, complicated diabetes, dysrhythmia, pulmonary edema and respiratory infections were the common variables found between the anterior model and the validated and recalibrated one for AMI.
Conclusion: Predictive models of LOSE can be applied in clinical practice, provided they are recalibrated and modeled to the population characteristics.