Machine learning algorithms for the prediction of adverse prognosis in patients undergoing peritoneal dialysis

Table 3 Basic performance indicators of the five complete models

Model name	AUC (CI)	ACC (CI)	F1 score (CI)	PRC (CI)
Cat Boost Classifier	0.8	0.78	0.57	0.52
Cat Boost Classifier	[0.76, 0.83]	[0.72, 0.83]	[0.50, 0.64]	[0.45, 0.60]
Logistic Regression	0.76	0.71	0.48	0.45
Logistic Regression	[0.73, 0.80]	[0.64, 0.77]	[0.44, 0.52]	[0.39, 0.52]
Light Gradient Boosting	0.72	0.74	0.42	0.44
Light Gradient Boosting	[0.68, 0.77]	[0.68, 0.81]	[0.35, 0.48]	[0.36, 0.50]
Gradient Boosting	0.72	0.76	0.41	0.35
Gradient Boosting	[0.70, 0.79]	[0.70, 0.82]	[0.34, 0.51]	[0.31, 0.43]
Random Forest	0.72	0.65	0.41	0.41
Random Forest	[0.62, 0.75]	[0.58, 0.72]	[0.37, 0.45]	[0.34, 0.48]

ACC Accuracy, AUC Area under the curve, CI Confidence interval, F1 F1 score, PRC Precision recall curve, CI Confidence interval

ISSN: 1472-6947