Skip to main content

Table 6 Performance of previous studies

From: Predicting diabetic retinopathy and identifying interpretable biomedical features using machine learning algorithms

Approaches

Data Sets

AUC

Acc.

Sens.

Spec.

Hosseini et al.

Iran

0.704

NAa

0.603

0.694

Oh et al.

South Korea

0.820

0.752

0.721

0.760

Ogunyemi et al.

United States

0.720

0.735

0.692

0.559

  1. AUC, accuracy, sensitivity, and specificity of the best predictive performance reported in previous studies are summarized
  2. aNA stands for “Not Available” because this evaluation measure was not reported in the study