Table 9 Comparison with state-of-the-art algorithms.

From: Diagnostics of diabetic retinopathy based on fundus photos using machine learning methods with advanced feature engineering algorithms

Reference

Method

Number of datasets

Results

17

Convolutional neural networks

1

Acc: 75%

18

SVM

1

Acc: 85.9%

21

Inception-ResNet-v2

2

Acc: 72.33% and 82.18%

26

Ensemble learning + CNN

1

F1-score: 80.8%

23

Modified Xception Architecture

1

Acc: 83.09

This study

Random Forest + advanced feature engineering

9

Acc: 80.4