Table 1 A comparison with state-of-the-art for several studies.

Nanglia et al.⁴

SVM with Feed-Forward Back Propagation Neural Network and GA optimization

Accuracy: 98.08%

Precision: 98.17%

Recall: 96.5%

F-Score: 97%

Mohamed et al.⁹

Hybrid CNN and Ebola Optimization Search Algorithm (EOSA)

Accuracy: 93.21%

Specificity:

- Normal: 79.41%

- Malignant: 93.28%

- Benign: 97.95%

Sensitivity:

- Normal: 90.38%

- Malignant: 90.71%

- Benign: 13.33%

Ren et al.¹⁰

Deep Convolutional GAN and VGG-DF model with regularization and transfer learning

Accuracy: 99.84% ± 0.156%

Precision: 99.84% ± 0.153%

Sensitivity: 99.84% ± 0.156%

F1-Score: 99.84% ± 0.156%

Bhattacharjee et al.¹¹

Random Forest classifier with K-means visualization

10-Fold Cross-Validation Accuracy: 92.14%

Inertia Score: 16.21 (lowest)

Silhouette Score: 0.815 (highest)

Vijh et al.¹²

Whale Optimization Algorithm with SVM

Accuracy: 95%

Sensitivity: 100%

Specificity: 92%

Shakeel et al.¹³

Discrete AdaBoost optimized ensemble learning generalized neural network

Error Rate: 0.0212

Prediction Rate: 99.48%

Nancy et al.¹⁴

Particle Swarm Optimization with SVM

Accuracy: 97.6%

Specificity: 99%

Joshi et al.¹⁵

SMOCS (Cuckoo Search followed by Spider Monkey Optimization) and CSSMO (Spider Monkey Optimization followed by Cuckoo Search)

Accuracy: 100%

Saxena et al.¹⁶

A chaotic algorithm based on Marine Predator Algorithm (MPA) called Marine Predator Chaotic Algorithm (MPCA)

The proposed MPCA algorithm demonstrates the best graphical visualizations and statistical analysis

Yaqoob et al.¹⁷

Harris hawks optimization and cuckoo search algorithm (HHOCSA)

The proposed HHOCSA algorithm gives the best results when compared to another methods