Table 3 Multivariate logistic regression model.

From: Integrating radiological and clinical data for clinically significant prostate cancer detection with machine learning techniques

Variable

OR (95% C.I.)

p-value

Age (years)

1.059 (1.048,1.071)

< 0.001

rcs(PSA, 5) PSA

1.579 (1.355,1.850)

< 0.001

rcs(PSA, 5) PSA’

2.150 × 10− 7 (1.662 × 10− 11,2.425 × 10− 3)

0.001

rcs(PSA, 5) PSA’’

3.449 × 1015 (7.171 × 104,2.148 × 1026)

0.004

rcs(PSA, 5) PSA’’’

1.111 × 10− 10 (7.608 × 10− 19,1.464 × 10− 2)

0.016

PV

0.974 (0.971, 0.977)

< 0.001

DRE (suspicious)

2.599 (2.133,3.170)

< 0.001

FH (yes)

1.673 (1.227,2.278)

0.001

PNB (yes)

0.696 (0.579,0.835)

< 0.001

PI-RADS 2:1

1.279 (0.690,2.301)

0.421

PI-RADS 3:1

1.839 (1.288,2.662)

< 0.001

PI-RADS 4:1

6.755 (4.882,9.520)

< 0.001

PI-RADS 5:1

18.758 (12.994,27.515)

< 0.001

  1. rcs restricted cubic spline, PSA prostate specific antigen, PV prostate volume, PSAD PSA density, DRE digital rectal exam findings, FH family history of PCa, PNB previous negative biopsy.
Back to article page