Table 3 Results of CBR and DT RBR on the early-stage diabetes risk prediction dataset
From: Building an enhanced case-based reasoning and rule-based systems for medical diagnosis
Approach | Accuracy | Precision | Recall | F1-Score |
|---|---|---|---|---|
Cosine similarity | 95.19% | 91% | 94% | 92.5% |
Euclidean distance | 91.35% | 79% | 100% | 88% |
Manhattan distance | 92.31% | 80% | 100% | 89% |
Hamming distance | 50.96% | 47% | 51% | 49.25% |
Pearson correlation coefficient | 92.31% | 84% | 94% | 89% |
Jaccard similarity | 94.23% | 89% | 94% | 91.5% |
Dice coefficient | 94.23% | 89% | 94% | 91.5% |
logistic regression similarity | 91.35% | 82% | 94% | 87% |
random forest similarity | 99.04% | 97% | 100% | 98.5% |
GaussianNB similarity | 94.23% | 86% | 97% | 91% |
DT RBR | 96% | 95% | 96% | 95% |
FFNN-TSA [10] | 96.15% | 95.86% | 96.03% | N/A |
FFNN-CSA [10] | 99.04% | 99.03% | 99% | N/A |