Prediction of Patient Length of Stay on the Intensive Care Unit Following Cardiac Surgery: A Logistic Regression Analysis Based on the Cardiac Operative Mortality Risk Calculator, EuroSCORE.

OBJECTIVE

The aim of this study was to develop a statistical model based on patient parameters to predict the length of stay (LOS) in the intensive care unit (ICU) following cardiac surgery in a single center.

DESIGN

Data were collected from patients admitted to the ICU following cardiac surgery over a 10-year period (2006-2016). Both the additive and logistic EuroSCORE were calculated, and logistic regression analysis was carried out to formulate a model relating the predicted LOS to the EuroSCORE. This model was used to stratify patients into short stay (less than 48 hours) or long stay (more than 48 hours).

SETTING

ICU at Papworth Hospital, Cambridgeshire.

PARTICIPANTS

A total of 18,377 consecutive patients who had been in ICU following cardiac surgery (coronary graft bypass surgery, valve surgery, or a combination of both).

INTERVENTIONS

This was an observational study.

MEASUREMENTS AND MAIN RESULTS

The authors have shown that both the additive and logistic EuroSCORE can be used to stratify cardiac surgical patients in various predicted LOS in ICU. Further adjustments can be made to increase the number of patients correctly identified as either short stay or long stay. Comparison of the model predictions to the data demonstrated a high overall accuracy of 79.77%, and receiver operating characteristic curve analysis showed the area under the curve to be 0.7296.

CONCLUSION

This analysis of an extensive data set shows that patient LOS in ICU after cardiac surgery in a single center can be predicted accurately using the simple cardiac operative risk scoring tool EuroSCORE. Using such predictions has the potential to improve ICU resource management.