Table 1.
State of the Art.
| Author | Year | Methods/Classifiers | Datasets | Evaluation Parameters |
Highest Accuracy% |
|---|---|---|---|---|---|
| [36] | 2022 | LR, NB, RF REP, M5P Tree, J48, JRIP | Hungarian and Statlog (heart) dataset | RMSE, MAE | RF 99.81% |
| [37] | 2021 | RF, DT, LR | UCI Cleveland database | Accuracy | LR 92.10% |
| [38] | 2021 | AB, ET, LR, MNB, CART, LDA, SVM, RF, XGB | Heart Dataset (UCI repository) |
Accuracy | AB 90% |
| [39] | 2021 | SVM, NB, DT | Heart Dataset (UCI repository) |
Accuracy | DT 90% |
| [40] | 2022 | KNN, DT, LR, NB, SVM | Heart Dataset (UCI repository) |
Accuracy, Specificity, Sensitivity, F1-Score | LR 92% |
| [41] | 2022 | RF into fetal echocardiography | Congenital heart disease database of 3910 Singleton Fetuses | Sensitivity, Specificity | sensitivity 0.85, specificity 0.88, |
| [42] | 2022 | LR, Evimp functions, Multivariate adaptive regression | DiScRi dataset | Accuracy, Sensitivity, Specificity | 94.09% |
| [43] | 2022 | LR, KNN, SVM, RF | Pathogen, Host feature | Accuracy | RF 99% |
| [44] | 2022 | DT, LR, XGB, NB, GB, RF, SVM, PEM | Cardiovascular disease dataset (Mendeley Data Center) | Accuracy | EM 96.75% |
| [45] | 2021 | NB, LM, LR, DT, RF, SVM, HRFLM | Heart Cleveland (UCI repository) |
Accuracy, Precision, Specificity, Sensitivity, F-Measure | HRFLM 88.4% |
| [47] | 2021 | RF, LR, KNN, SVM, DT, XGB | Public Health Dataset | Accuracy, Specificity, Sensitivity | SVM 84% |
| [48] | 2022 | K-NN, DT, RF, MLP, NB, L-SVM, | IoT based Produced Data | Accuracy | L-SVM 92.30%, RF 92.30% |
| [49] | 2022 | DT, NB, KNN, RF, ANN, Ada, GBA | Heart Disease (Kaggle Repository) | Accuracy, Precision, recall, f1-score | RF 86.89% |
| In our Proposed Scheme | |||||
| Proposed Methodology | 2022 | LR, SVM, NB, RF, XGB, DT, NN, RBF, KNN, GBT, MLP | Heart Disease (UCI Repository) | Accuracy, Precision (specificity), Recall (sensitivity), F-Measure | RF 96.28% |