Related Experiment Video
Updated: May 27, 2026
Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia
Published on: September 22, 2020
An In-Hospital Mortality Risk Model for Patients Undergoing Coronary Artery Bypass Grafting Based on Machine
Kun Zhu1, Wenyuan Lu1, Shui Liu2
1Cardiac Surgery Centre, Fuwai Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
Insights
A new machine learning model using Extreme Gradient Boosting (XGBoost) accurately predicts in-hospital mortality after coronary artery bypass grafting (CABG). This AI tool outperforms existing risk scores, offering better risk stratification for cardiac surgery patients.
Area of Science:
- Cardiovascular Surgery
- Medical Informatics
- Machine Learning in Healthcare
Background:
- Ischemic heart disease is a leading global cause of death, with coronary artery bypass grafting (CABG) as the primary surgical intervention.
- Existing models for predicting postoperative mortality after CABG lack sufficient accuracy and broad applicability.
Purpose of the Study:
- To develop and validate a machine learning-based system for predicting in-hospital mortality in patients undergoing CABG.
- To compare the performance of the developed model against established risk assessment tools: EuroSCORE II and SinoSCORE.
Main Methods:
- Utilized data from 21,443 patients in the Chinese Cardiac Surgery Registry (2017-2020), randomly divided into training and testing cohorts.
- Employed machine learning algorithms, including Extreme Gradient Boosting (XGBoost), addressing class imbalance with SMOTE and hyperparameter optimization.
- Evaluated model performance using AUC, Brier score, and decision curve analysis, comparing against EuroSCORE II and SinoSCORE.
Main Results:
- The XGBoost model demonstrated superior predictive performance with an AUC of 0.782 in the independent test cohort, significantly outperforming EuroSCORE II (AUC=0.722) and SinoSCORE (AUC=0.726).
- The model showed excellent discrimination and calibration (P<.05) compared to traditional risk scores.
- Overall in-hospital mortality in the study cohort was 2.1%.
Conclusions:
- A machine learning model, specifically XGBoost, provides a more accurate prediction of in-hospital mortality post-CABG in a Chinese population.
- Locally calibrated models like XGBoost may offer improved risk stratification for specific patient demographics compared to generalized scores.
- A 7-variable web calculator derived from the model can aid bedside risk stratification, warranting further prospective validation for clinical decision-making.
Background:
Ischemic heart disease remains the leading cause of death worldwide. Coronary artery bypass grafting (CABG) remains the primary surgical treatment for ischemic heart disease. There is currently a lack of highly accurate and widely applicable models for assessing the risk of postoperative mortality following CABG.
Objective:
This study aimed to develop and validate an in-hospital mortality risk prediction system for patients undergoing coronary artery bypass grafting (CABG) by using machine learning algorithms and to compare its performance with the European System for Cardiac Operative Risk Evaluation II (EuroSCORE II) and Sino System for Coronary Operative Risk Evaluation (SinoSCORE).
Methods:
Between January 2017 and December 2020, 21,443 patients undergoing CABG in the Chinese Cardiac Surgery Registry were included. Patients were randomly divided into training (n=17,753) and test (n=3690) cohorts. We addressed class imbalance using the synthetic minority oversampling technique (SMOTE) and optimized hyperparameters via grid search. Fifteen machine learning algorithms were developed to predict in-hospital mortality. Performance was evaluated using the area under the receiver operating characteristic curve (AUC), calibration metrics (Brier score), and decision curve analysis, and was compared against EuroSCORE II and SinoSCORE.
Results:
A total of 21,443 patients were included. Overall, in-hospital mortality was 2.1% (n=450). The Extreme Gradient Boosting (XGBoost) model achieved the best performance with an AUC of 0.850 in the training cohort and 0.782 in the independent test cohort (this cohort was independent and not involved in model construction). While EuroSCORE II showed an AUC of 0.722 and SinoSCORE showed an AUC of 0.726 in the test cohort, the XGBoost model demonstrated superior discrimination and calibration (P<.05).
Conclusions:
Our study developed and validated a machine learning-based risk prediction model for in-hospital mortality after CABG by using a large-scale Chinese multicenter registry. Among the algorithms tested, the XGBoost model demonstrated superior discrimination and calibration compared with the traditional EuroSCORE II and SinoSCORE, suggesting that locally calibrated models may better capture the risk profile of Chinese patients. The derived 7-variable web calculator may serve as an exploratory auxiliary tool to provide a preliminary reference for bedside risk stratification, though its direct impact on surgical decision-making requires further prospective validation. Future research should focus on independent test cohorts across diverse hospital tiers to ensure broad generalizability.
