Table 1 Literature review state-of-art method (metric comparison).
Year | Author Name | Online Database | Classification Type | Performance Metric | Accuracy |
|---|---|---|---|---|---|
2022 | IoT based data | K-NN, DT, RF, MLP, NB, L-SVM | Accuracy, sensitivity, F1 score | 96.12 | |
2022 | Di-ScRi database | Evimp functions, Multivariate adaptive regression | Accuracy, Specificity, Sensitivity, F1 score | 91.2 | |
2022 | Hungarian-Statlog database | LR, NB, RF REP, M5P Tree, J48, JRIP | RMSE, MAE | 89.7 | |
2022 | UCI repository | KNN, DT, LR, NB, SVM | Accuracy, Sensitivity, F1-Score, Specificity | 93.23 | |
2022 | Congenital heart disease database of 3910 Singleton | RF-fetal echocardiography | RMSE, MAE | 95.02 | |
2022 | Pathogen, Host feature | LR, KNN, SVM, RF | Accuracy, sensitivity, F1 score | 94.08 | |
2022 | Heart Disease (Kaggle Repository) | KNN, RF, ANN, Ada, GBA | RMSE, MAE | 90.91 | |
2021 | Heart Cleveland (UCI repository) | LR, DT, RF, SVM, HRFLM | Accuracy, Sensitivity, F1-Score, Specificity | 96.22 | |
2021 | UCI Cleveland database | RF, DT, LR | Accuracy, sensitivity, F1 score | 94.21 | |
2021 | UCI repository | SVM, NB, DT | Sensitivity, accuracy | 94.11 |
