Intra-institutional prediction of outcome after cardiac surgery: comparison between a locally derived model and the EuroSCORE

Objective: To construct models for predicting mortality, morbidity and leng th of intensive care unit (ICU) stay after cardiac surgery and to compare t he performance of these models with that of the EuroSCORE in two independen t validation databases. Methods: Clinical data on 4592 cardiac surgery pati ents operated between 1992 and 1996 were retrospectively collected. In orde r to derive predictive models and to validate them, the patient population was randomly divided into a derivation database (n = 3061) and a validation database (n = 1531). Variables that were significant in univariate analyse s were entered into a backward stepwise logistic regression model. The outc ome was defined as mortality within 30 days after surgery, predefined morbi dity, and the length of ICU stay lasting >2 days. In addition to the retros pective database, the models were validated also in a prospectively collect ed database of cardiac surgical patients operated in 1998-1999 (n = 821). T he EuroSCORE was tested in two validation databases, i.e. the retrospective and prospective one. Hosmer-Lemeshow goodness-of-fit was used to study the calibration of the predictive models. Area under the receiver operating ch aracteristic (ROC) curve was used to study the discrimination ability of th e models. Results: The overall mortality in the retrospective and the prosp ective data was 2 and 1%, and morbidity 22 and 18%, respectively. The creat ed predictive models fitted well in the validation databases. Our models an d the EuroSCORE were equally good in discriminating patients. Thus, in the prospective validation database, the mean areas under the ROC curve for our models and for the EuroSCORE were similar, i.e. 0.84 and 0.77 for mortalit y, 0.74 and 0.74 for morbidity, and 0.81 and 0.79 for the length of intensi ve care unit stay lasting for 2 days or more, respectively. Conclusions: Ou r models and the EuroSCORE were equally good in discriminating the patients in respect to outcome. However, our model provided also well calibrated es timation of the probability of prolonged ICU stay for each patient. As was originally suggested, the EuroSCORE may be an appropriate tool in categoriz ing cardiac surgical patients into various subgroups in interinstitutional comparisons. Our models may have additive value especially in resource allo cation and quality assurance purposes for local use. (C) 2000 Elsevier Scie nce B.V. All rights reserved.