Research on the development of an intelligent prediction model for blood pressure variability during hemodialysis

BMC Nephrology

Table 4 IDHTN machine learning results

	XGBoost	SVM	KNN	DT	RF	LR	NB	AdaBoost	LightGBM	CatBoost
ROC-AUC	0.89	0.87	0.84	0.72	0.89	0.79	0.74	0.81	0.88	0.89
PR-AUC	0.78	0.76	0.72	0.66	0.78	0.60	0.55	0.62	0.77	0.79
accuracy	0.85	0.82	0.81	0.76	0.83	0.76	0.71	0.77	0.83	0.84
precision	0.77	0.76	0.72	0.59	0.75	0.63	0.50	0.64	0.76	0.77
recall	0.64	0.54	0.59	0.61	0.62	0.42	0.59	0.46	0.59	0.62
F1-score	0.70	0.63	0.65	0.60	0.68	0.50	0.54	0.54	0.67	0.69

XGBoost: Extreme Gradient Boosting; SVM: Support Vector Machine; KNN: K-Nearest Neighbors; DT: Decision Tree; RF: Random Forest; LR: Logistic Regression; NB: Naive Bayes; AdaBoost: Adaptive Boosting; LightGBM: Light Gradient Boosting Machine; CatBoost: Categorical Boosting; ROC-AUC: Receiver Operating Characteristic - Area Under the Curve; PR-AUC: Precision-Recall - Area Under the Curve

ISSN: 1471-2369