The Extreme Gradient Boosting (XGBoost) model outperformed traditional logistic regression in predicting heart failure events among hemodialysis patients, achieving an AUC of 0.814 versus 0.722.
Cohort (n=353)
Yes
Does an XGBoost machine learning model improve the prediction of heart failure events in hemodialysis patients compared to traditional logistic regression?
An XGBoost-based machine learning model accurately predicts heart failure events in hemodialysis patients, outperforming traditional logistic regression and identifying novel risk factors like platelet count.
Absolute Event Rate: 0.814% vs 0.722%
Background: Heart failure (HF) is the main cause of mortality in hemodialysis (HD) patients. However, it is still a challenge for the prediction of HF in HD patients. Therefore, we aimed to establish and validate a prediction model to predict HF events in HD patients. Methods: A total of 355 maintenance HD patients from two hospitals were included in this retrospective study. A total of 21 variables, including traditional demographic characteristics, medical history, and blood biochemical indicators, were used. Two classification models were established based on the extreme gradient boosting (XGBoost) algorithm and traditional linear logistic regression. The performance of the two models was evaluated based on calibration curves and area under the receiver operating characteristic curves (AUCs). Feature importance and SHapley Additive exPlanation (SHAP) were used to recognize risk factors from the variables. The Kaplan–Meier curve of each risk factor was constructed and compared with the log-rank test. Results: Compared with the traditional linear logistic regression, the XGBoost model had better performance in accuracy (78.5 vs. 74.8%), sensitivity (79.6 vs. 75.6%), specificity (78.1 vs. 74.4%), and AUC (0.814 vs. 0.722). The feature importance and SHAP value of XGBoost indicated that age, hypertension, platelet count (PLT), C-reactive protein (CRP), and white blood cell count (WBC) were risk factors of HF. These results were further confirmed by Kaplan–Meier curves. Conclusions: The HF prediction model based on XGBoost had a satisfactory performance in predicting HF events, which could prove to be a useful tool for the early prediction of HF in HD.
Wang et al. (Tue,) conducted a cohort in End-stage renal disease on hemodialysis (n=353). Extreme Gradient Boosting (XGBoost) model vs. Traditional linear logistic regression was evaluated on Area under the receiver operating characteristic curve (AUC) for predicting heart failure. The Extreme Gradient Boosting (XGBoost) model outperformed traditional logistic regression in predicting heart failure events among hemodialysis patients, achieving an AUC of 0.814 versus 0.722.