Table 5.
Related work for BC studies with miRNA as biomarkers.
| Reference | Function/Purpose | Methods | Accuracy of Model |
|---|---|---|---|
| [97] | Cancer Classification | Gradient Boosting | Accuracy 93.59% |
| RF | Accuracy 93.24% | ||
| LR | Accuracy 92.37% | ||
| Passive Aggressive | Accuracy 88.31% | ||
| SGD | Accuracy 90.35% | ||
| SVM | Accuracy 91.54% | ||
| Ridge | Accuracy 83.05% | ||
| Bagging | Accuracy 91.1% | ||
| [98] | Cancer Classification | NB | Accuracy 94.9% |
| [99] | Cancer detection | RF | AUC 99.5–99.9% |
| SVM | AUC 93.8–99.6% | ||
| ANN | Accuracy 97.3% | ||
| KNN | Accuracy 99.2% | ||
| SVM | Accuracy 96.3% | ||
| LR | Accuracy 95.8% | ||
| [100] | Cancer Classification | Tree-based model | NIA |
| [101] | Cancer Classification | DT | Accuracy 99.12% |
| NB | Accuracy 93.86% | ||
| ANN | Accuracy 100% | ||
| DL | Accuracy 100% |
Abbreviations: BC: breast cancer; SVM: Support Vector Machine; LR: Logistic Regression; KNN: k-Nearest Neighbor; NB: Naïve Bayes; WBCD: Wisconsin Breast Cancer Diagnostic dataset; RF: Random Forest; SGD: Stochastic Gradient Descent; ANN: Artificial Neural Network; DT: Decision Tree; DL: Deep Learning; NIA: no information available.