Table 1 Diagnostic performance of DLHD.

From: Impact of a deep learning-based brain CT interpretation algorithm on clinical decision-making for intracranial hemorrhage in the emergency department

Test characteristics

Value (95% CI)

Sensitivity

70.81 (66.65–74.97)

Specificity

86.72 (85.10–88.34)

Accuracy

83.32 (81.74–84.90)

AUROC

0.788 (0.765–0.810)

Positive predictive value

59.20 (55.09–63.31)

Negative predictive value

91.61 (90.25–92.97)

  1. DLHD, deep learning-based assistive intracranial hemorrhage detection algorithm; AUROC, area under the receiver operating characteristic curve.
Back to article page