Table 2 Diagnostic performance of AI model at different endpoints.

From: Early screening of colorectal cancer using feature engineering with artificial intelligence-enhanced analysis of nanoscale chromatin modifications

Dataset

Data split

AUC

Se

Sp

Control + DA vs NDA + AA + HNPCC + Cancer

(148, 108)

0.85 (± 0.07)

0.80 (± 0.08)

0.86 (± 0.07)

Control + DA vs AA

(148, 74)

0.90 (± 0.06)

0.88 (± 0.07)

0.85 (± 0.08)

Control vs AA

(135, 74)

0.90 (± 0.06)

0.86 (± 0.08)

0.86 (± 0.09)

Control + DA + NDA vs AA

(163, 74)

0.87 (± 0.07)

0.85 (± 0.07)

0.82 (± 0.08)

  1. AUC, area under the curve; Se: sensitivity; Sp, specificity.
Back to article page