Table 6 Evaluation Metrics for Health-FedNet with Statistical Validation.
Metric | Description | Formula/Method |
|---|---|---|
Accuracy | Measures overall correctness of predictions | \({\text{Accuracy}}\,{ = }\,\frac{TP + TN}{{TP + TN + FP + FN}}\) |
Precision | Correctness of positive predictions | \({\text{Precision}} = \frac{TP}{{TP + FP}}\) |
Recall (Sensitivity) | Ability to detect true positives | \({\text{Recall}} = \frac{TP}{{TP + FN}}\) |
F1-Score | Harmonic mean of precision and recall | \({\text{F}}1 = 2 \cdot \frac{{{\text{Precision}}\,{\text{Recall}}}}{{\text{Precision + Recall}}}\) |
AUC-ROC | Measures discriminatory ability | AUC computed from ROC curve us- ing trapezoidal rule |
Privacy Budget (\(\varepsilon\)) | Differential privacy leakage bound | \(\varepsilon \,{ = }\,{\text{q}}\frac{{2{\text{In(1}}{.25/}\delta {)}}}{{\sigma^{2} }}\) |
Communication efficiency | Bandwidth + computation over-head | Bandwidth (MB), Convergence Time (sec) |
Robustness | Performance under noisy/heterogeneous data | Accuracy under Gaussian noise and imbalanced partitions |
Statistical Significance | Validates experimental repeatability | Paired t-test (p < 0.05) and 95% CI across 5 runs |
