Research Article
[Retracted] Identification of Diabetic Retinopathy through Machine Learning
Table 6
Average performance of the 15 series of experiments with RBM-1000, considering four classes (no DR, light DR, mod/severe, and proliferative).
| RBM-1000 | Machine learning | | Hit % | Specialist | Without DR | With DR | | Absence | Light | Mod/record | Proliferative | |
| Without DR | Absence | 14 | 0 | 0 | 0 | 14/14 (100%) | With DR | Light | 0 | 3 | 1 | 0 | 3/4 (75%) | Mod/record | 1 | 1 | 10 | 0 | 10/12 (83.3%) | Proliferative | 0 | 0 | 0 | 77 7 | 7/7 (100%) |
|
|