Table 3 Performance of the proposed models reported using various metrics of evaluation including accuracy, sensitivity, specificity, precision, C-value, and area under the curve
References | Best performing model | Accuracy (%) | Sensitivity (%) | Specificity (%) | Precision (%) | Area under the curve |
|---|---|---|---|---|---|---|
[31] | XGBoost | NA | 71.00 ± 23.85 | NA | NA | 71.13 ± 11.69 |
Gradient Boosting Machine | NA | 79.1 | 55.8 | NA | 0.69–0.825 | |
[29] | Hybrid Wavelet Neural Network (HWNN) | 83.04 ± 8.22 | 29.50 ± 23.15 | 87.30 ± 9.73 | NA | 67.64 ± 15.09 |
[30] | XGBoost | 84.5 | 85 | NA | 84.5 | NA |
[13] | Ensembles of ANN | 80.20 | NA | NA | NA | 0.849 |
[33] | Knowledge Learning Symbiosis (KLS) | NA | NA | NA | NA | NA |
[28] | Neural network | 87.50 | 88.06 | 87.23 | 76.6 | 0.91 |
[35] | Logistic regression, support vector machine | 83.33 | 83.33 | 83.33 | 83.33 | 0.81 |
[36] | Support vector machine | 96.93 | 92.87 | NA | 94.44 | NA |