Machine learning algorithms that predict the risk of prostate cancer based on metabolic syndrome and sociodemographic characteristics: a prospective cohort study

Table 2 Performance of models

Models	C-index	IBS	D-index
Cox	0.816 (0.815鈥�0.818)	0.010	5.60 (3.48-9.00)
Random survival forest	0.808 (0.806鈥�0.809)	0.010	5.57 (3.44-9.00)
Survival support vector machine	0.806 (0.804鈥�0.808)	-	5.66 (3.49鈥�9.16)
Survival trees	0.795 (0.793鈥�0.797)	0.010	5.01 (3.10鈥�8.08)
Gradient boosting	0.808 (0.806鈥�0.810)	0.010	5.26 (3.30鈥�8.38)
Extra survival trees	0.767 (0.765鈥�0.769)	0.010	4.36 (2.68鈥�7.09)

Note: C-index was estimated based on 100 bootstrapped data samples. Integrated brier score (IBS) applies for models that can estimate a survival function. Thus, it is impossible to estimate the integrated brier score for Survival Support Vector Machine

ISSN: 1471-2458