A new and feasible model for predicting operative risk

Abstract

Background: Although the POSSUM (Physiological and Operative Severity Score for the enumeration of Mortality and Morbidity) score can be used to calculate operative risk, its complexity makes its use unfeasible in the immediate clinical setting. The aim of this study was to create a new model, based on ASA status, to predict mortality.

Methods: Data were collected in two hospitals. All types of surgery were included except for cardiac surgery and Caesarean delivery. Age, sex and preoperative information, including the presence of cardiocirculatory and/or lung disease, renal failure, diabetes mellitus, hepatic disease, cancer, Glasgow Coma Score, ASA grade, surgical diagnosis, severity of the procedure and type of surgery (elective, urgent or emergency), were recorded for each patient. The model was developed using a data set incorporating data from 1936 surgical patients, and validated using data from a further 1849 patients. Forward stepwise logistic regression was used to build the model. Goodness of fit was examined using the Hosmer-Lemeshow test and receiver operating characteristic (ROC) curve analyses were performed on both data sets to test calibration and discrimination. In the validation data set, the new model was compared with POSSUM and P-POSSUM for both calibration and discrimination, and with ASA alone to compare discrimination.

Results: The following variables were included in the new model: ASA status, age, type of surgery (elective, urgent, emergency) and degree of surgery (minor, moderate or major). Calibration and discrimination of the new model were good in both development and validation data sets. This new model was better calibrated in the validation data set (Hosmer-Lemeshow goodness-of-fit test: chi(2)=6.8017, P=0.7440) than either P-POSSUM (chi(2)=14.4643, P=0.1528) or POSSUM, which was not calibrated (chi(2)=31.8147, P=0.0004). POSSUM and P-POSSUM had better discrimination than the new model, although this was not statistically significant. Comparing the two ROC curves, the new model had better discrimination than ASA alone (difference between areas, 0.077, SE 0.034, 95% confidence interval 0.012-0.143, P=0.021).

Conclusions: This new, ASA status-based model is simple to use and can be performed routinely in the operating room to predict operative risk for both elective and emergency surgery.