Skip to main content

Table 2 AUC results using 4 algorithms, PSA and fPSA/fPSA in the validation cohort

From: Artificial intelligence for the diagnosis of clinically significant prostate cancer based on multimodal data: a multicenter study

AUC(95%CI)

Validation cohort

Changhai cohort

Zhongda cohort

LR

0.816 (0.78–0.85)

0.793 (0.75–0.83)

0.848 (0.80–0.90)

RF

0.779 (0.74–0.81)

0.766 (0.72–0.81)

0.844 (0.79–0.90)

XGBoost

0.795 (0.76–0.83)

0.763 (0.71–0.81)

0.817 (0.76–0.87)

AutoML

0.820 (0.79–0.85)

0.807 (0.76–0.85)

0.850 (0.80–0.89)

PSA

0.616 (0.57–0.66)

0.593 (0.54–0.65)

0.583 (0.51–0.65)

fPSA/PSA

0.675 (0.63–0.72)

0.675 (0.62–0.73)

0.738 (0.67–0.80)

  1. AUC Area under receiver operating characteristic, AutoML Automated machine learning, LR Logistic regression, RF Random forest