Table 5.

Results on the hybrid validation for the two best models

	Hybrid validation: centre C
Train_MAN + Val_AUTO	0.69 (60–89)	75 (53–88) [21/28]	80 (50–95) [12/15]	69 (37–90) [9/13]	75 (54–86) [9/12]	75 (55–83) [12/16]
Train_AUTO + Val_MAN	0.62 (52–73)	64 (44–81) [18/28]	47 (21–73) [7/15]	85 (55–98) [11/13]	58 (45–70) [11/19]	78 (47–93) [7/9]

Hybrid validation: centre C

AUC
(95% CI)

ACC %
(95% CI)
[rate]

SE %
(95% CI)
[rate]

SP %
(95% CI)
[rate]

NPV %
(95% CI)
[rate]

PPV %
(95% CI)
[rate]

Train_MAN + Val_AUTO

0.69

(60–89)

(53–88)

[21/28]

(50–95)

[12/15]

(37–90)

[9/13]

(54–86)

[9/12]

(55–83)

[12/16]

Train_AUTO + Val_MAN

0.62

(52–73)

(44–81)

[18/28]

(21–73)

[7/15]

(55–98)

[11/13]

(45–70)

[11/19]

(47–93)

[7/9]

AUC Area under the curve, ACC Accuracy, NPV Negative predictive value, PPV Positive predictive value, SE Sensitivity, SP Specificity