Development and validation of a clinic machine-learning nomogram for the prediction of risk stratifications of prostate cancer based on functional subsets of peripheral lymphocyte

Table 3 Logistic regression for predicting risk stratifications of PCa based on predictions of five ML algorithms

ML Models	Univariate logistic regression		Multivariate logistic regression
ML Models	OR (95% CL)	p-value	OR (95% CL)	p-value
AdaBoost	2.535 (2.358–2.726)	0.000*	1.154 (1.090–1.222)	0.000 ^*
Decision Tree	2.667 (2.563–2.774)	0.000*	1.554 (1.438–1.680)	0.000 ^*
Random Forest	2.449 (2.286–2.622)	0.000*	1.150 (1.088–1.214)	0.000 ^*
SVM	1.906 (1.681–2.162)	0.000*	1.014 (0.980–1.050)	0.419
XGBoost	2.577 (2.462–2.696)	0.000*	1.354 (1.260–1.455)	0.000 ^*

*p < 0.05. Values in bold indicate independent predictors in the multivariate logistic regression

ISSN: 1479-5876