Related Experiment Video
Updated: Jun 23, 2026
Establishing a Competing Risk Regression Nomogram Model for Survival Data
Published on: October 23, 2020
Comparison of 19 pre-operative risk stratification models in open-heart surgery
Johan Nilsson1, Lars Algotsson, Peter Höglund
1Department of Cardiothoracic Surgery, Heart and Lung Centre, Lund University Hospital, Sweden. johan.nilsson@thorax.lu.se
Insights
The European System for Cardiac Operative Risk Evaluation (EuroSCORE) and Cleveland Clinic risk scores demonstrated the highest accuracy in predicting mortality after cardiac surgery. These models also showed reasonable 1-year mortality prediction capabilities.
Area of Science:
- Cardiology
- Surgical Outcomes
- Risk Prediction Modeling
Background:
- Accurate prediction of mortality after cardiac surgery is crucial for patient management and risk stratification.
- Numerous risk score algorithms exist, but their comparative validity for predicting short- and long-term mortality after cardiac surgery requires evaluation.
Purpose of the Study:
- To compare the predictive validity of 19 different risk score algorithms for 30-day and 1-year mortality following cardiac surgery.
- To identify the most accurate risk scores for general cardiac surgery and for coronary artery bypass grafting (CABG)-only procedures.
Main Methods:
- A prospective cohort study of 6222 patients undergoing cardiac surgery between 1996 and 2001.
- Utilized Receiver Operating Characteristic (ROC) curves to assess the performance and accuracy of 19 risk score algorithms.
- Obtained 30-day and 1-year survival data and cause of death for all included patients.
Main Results:
- The European System for Cardiac Operative Risk Evaluation (EuroSCORE) logistic and additive models, along with the Cleveland Clinic and Magovern scoring systems, exhibited the highest discriminatory power for both 30-day (0.84) and 1-year (0.77) mortality.
- No significant difference in predictive power was observed for the remaining 15 risk algorithms compared to these top four.
- For CABG-only surgery, EuroSCORE, New York State (NYS), and Cleveland Clinic risk scores were the most accurate predictors of 30-day and 1-year mortality.
Conclusions:
- The EuroSCORE, Cleveland Clinic, and Magovern risk algorithms demonstrated superior performance and accuracy in predicting mortality after open-heart surgery.
- EuroSCORE, NYS, and Cleveland Clinic risk scores were particularly effective for CABG-only procedures.
- The evaluated risk models, though primarily designed for early mortality prediction, also provided reasonably accurate predictions for 1-year mortality.
Aims:
To compare 19 risk score algorithms with regard to their validity to predict 30-day and 1-year mortality after cardiac surgery.
Methods And Results:
Risk factors for patients undergoing heart surgery between 1996 and 2001 at a single centre were prospectively collected. Receiver operating characteristics (ROC) curves were used to describe the performance and accuracy. Survival at 1 year and cause of death were obtained in all cases. The study included 6222 cardiac surgical procedures. Actual mortality was 2.9% at 30 days and 6.1% at 1 year. Discriminatory power for 30-day and 1-year mortality in cardiac surgery was highest for logistic (0.84 and 0.77) and additive (0.84 and 0.77) European System for Cardiac Operative Risk Evaluation (EuroSCORE) algorithms, followed by Cleveland Clinic (0.82 and 0.76) and Magovern (0.82 and 0.76) scoring systems. None of the other 15 risk algorithms had a significantly better discriminatory power than these four. In coronary artery bypass grafting (CABG)-only surgery, EuroSCORE followed by New York State (NYS) and Cleveland Clinic risk score showed the highest discriminatory power for 30-day and 1-year mortality.
Conclusion:
EuroSCORE, Cleveland Clinic, and Magovern risk algorithms showed superior performance and accuracy in open-heart surgery, and EuroSCORE, NYS, and Cleveland Clinic in CABG-only surgery. Although the models were originally designed to predict early mortality, the 1-year mortality prediction was also reasonably accurate.
