Skip to main content

Table 3 Areas under the curves (AUC), specificities at 95% sensitivity and sensitivities at 95% specificity with the respective confidence intervals (in parenthesis) for the parameters tPSA, %fPSA, PSAD§, PSAV, ANN and ANNV$ for all patients (n = 199)

From: Artificial neural network (ANN) velocity better identifies benign prostatic hyperplasia but not prostate cancer compared with PSA velocity

Parameter

AUC

(Confidence Intervals)

P-values and significance levels§

Specificity at 95% Sensitivity

P-values and significance levels§

Sensitivity at 95% Specificity

P-values and significance levels$

PSA

0.69

(0.61–0.77)

0.0001**

27.3

(21.4–34)

<0.0001***

14.3

(7–25.4)

0.008**

%fPSA

0.70

(0.71–0.78)

0.007**

17.3

(12.5–23.3)

<0.0001***

20.4

(11.6–32.3)

0.44

PSAD

0.76

(0.69–0.83)

-

44

(37.1–51.7)

-

16.3

(8.5–27.7)

0.013*

PSAV

0.76

(0.67–0.84)

0.835

4.7

(2.2–8.7)

<0.0001***

16.3

(8.5–27.7)

0.023*

ANN

0.66

(0.57–0.75)

0.001**

10

(6.3–15.1)

<0.0001***

18.4

(10–30)

0.023*

ANNV

0.56

(0.44–0.68)

<0.0001***

1.3

(0.2–4.3)

<0.0001***

32.7

(21.7–45.4)

-

  1. §PSAD with largest AUC and highest specificity at 95% sensitivity, all others compared to PSAD
  2. $ANNV with highest sensitivity at 95% specificity, all others compared to ANNV
  3. *P < 0.05
  4. **P < 0.01
  5. ***P < 0.0001