Table 18 Comparative analysis with existing state-of-the-art research and proposed model.
References | Model | Accuracy (%) | Sensitivity (%) | Specificity (%) | Precision (%) | AUC (%) | F1 Score (%) | Cohen’s Kappa (κ) |
|---|---|---|---|---|---|---|---|---|
Ellis et al.1 | Deep Learning Risk Prediction | 88.5 | 90.0 | 87.0 | 89.0 | 0.91 | 89.5 | 0.80 |
Mahmood et al.2 | Radiomics + Deep Learning | 91.2 | 92.5 | 90.0 | 90.8 | 0.93 | 91.1 | 0.82 |
Laghmati et al.4 | ML + PCA | 85.0 | 84.0 | 86.0 | 85.5 | 0.87 | 84.8 | 0.72 |
Rahman et al.5 | Deep Learning | 87.0 | 85.0 | 88.5 | 86.0 | 0.90 | 85.5 | 0.75 |
Ahmad, Jawad, et al.7 | Deep Learning | 92.0 | 94.0 | 90.0 | 91.0 | 0.95 | 92.0 | 0.85 |
Gullo et al.9 | AI-enhanced MRI | 89.5 | 88.0 | 91.0 | 90.0 | 0.92 | 89.0 | 0.78 |
Liu et al.11 | Multi-modal Fusion Network | 90.5 | 91.0 | 89.0 | 90.0 | 0.94 | 90.5 | 0.80 |
Ray et al.12 | Advanced ML Models | 93.0 | 92.0 | 94.0 | 93.5 | 0.96 | 92.7 | 0.87 |
Xiao et al.17 | CNN | 88.0 | 86.5 | 89.5 | 87.0 | 0.89 | 86.8 | 0.74 |
Naz et al.18 | Deep Learning + IoMT | 85.5 | 84.0 | 87.0 | 86.0 | 0.88 | 85.0 | 0.70 |
Wang et al.14 | Deep Sample Clustering | 91.5 | 92.0 | 91.0 | 90.5 | 0.94 | 91.2 | 0.83 |
Yan et al.20 | CNN with Attention Modules | 92.5 | 93.0 | 92.0 | 91.5 | 0.95 | 92.3 | 0.86 |
Abimouloud et al.21 | Vision Transformer + CNN | 90.0 | 89.0 | 91.5 | 90.0 | 0.92 | 89.5 | 0.79 |
Ignatov et al.8 | Morphology Aware DNN | 91.0 | 92.0 | 90.0 | 91.0 | 0.93 | 91.0 | 0.84 |
Proposed hybrid model | CNN-Bi-LSTM | 99.00 | 95.00 | 99.50 | 98.00 | 0.99 | 96.33 | 0.95 |
