Key result
An XGBoost machine learning risk model predicted early mortality after surgery for infective endocarditis with an external validation AUC of 0.812 (95% CI, 0.606-0.956), outperforming EuroSCORE II.
Why the study?
Early mortality following surgery for infective endocarditis is high, and most existing risk-scoring systems are inaccurate or inconvenient.
Does an XGBoost machine learning-based risk model accurately predict early mortality after surgery for infective endocarditis compared to existing models?
Observational (n=476)
Yes
Does an XGBoost machine learning-based risk model accurately predict early mortality after surgery for infective endocarditis compared to existing models?
A novel XGBoost machine learning model using 8 clinical variables accurately predicts early mortality after infective endocarditis surgery, outperforming EuroSCORE II.
Answers are grounded in this paper and cite their sources.
May aid preoperative risk stratification in IE surgery; leaves open need for prospective validation.
Background The early mortality after surgery for infective endocarditis is high. Although risk models help identify patients at high risk, most current scoring systems are inaccurate or inconvenient. The objective of this study was to construct an accurate and easy‐to‐use prediction model to identify patients at high risk of early mortality after surgery for infective endocarditis. Methods and Results A total of 476 consecutive patients with infective endocarditis who underwent surgery at 2 centers were included. The development cohort consisted of 276 patients. Eight variables were selected from 89 potential predictors as input of the XGBoost model to train the prediction model, including platelet count, serum albumin, current heart failure, urine occult blood ≥(++), diastolic dysfunction, multiple valve involvement, tricuspid valve involvement, and vegetation >10 mm. The completed prediction model was tested in 2 separate cohorts for internal and external validation. The internal test cohort consisted of 125 patients independent of the development cohort, and the external test cohort consisted of 75 patients from another center. In the internal test cohort, the area under the curve was 0.813 (95% CI, 0.670–0.933) and in the external test cohort the area under the curve was 0.812 (95% CI, 0.606–0.956). The area under the curve was significantly higher than that of other ensemble learning models, logistic regression model, and European System for Cardiac Operative Risk Evaluation II (all, P <0.01). This model was used to develop an online, open‐access calculator ( http://42.240.140.58:1808/ ). Conclusions We constructed and validated an accurate and robust machine learning–based risk model to predict early mortality after surgery for infective endocarditis, which may help clinical decision‐making and improve outcomes.
No takes yet. Share an insight, caveat, or question.
Luo et al. (2022) conducted an observational in Infective endocarditis (n=476). XGBoost machine learning-based risk model vs. Logistic regression and EuroSCORE II was evaluated on Early mortality (predictive accuracy measured by AUC) (AUC 0.812, 95% CI 0.606-0.956, p=<0.01). An XGBoost machine learning risk model predicted early mortality after surgery for infective endocarditis with an external validation AUC of 0.812 (95% CI, 0.606-0.956), outperforming EuroSCORE II.
Synapse has enriched 10 related papers. Consider them for comparative context: