Table 8 Comparison of outcome between the existing system and our proposed system
Authors | Algorithms | Dataset | Accuracy (%) | Precision (%) | Recall (%) | F1 score (%) | outcome |
|---|---|---|---|---|---|---|---|
D.C Yadov et al. [33] | bagging boosting, Stacking, and Voting | Chandan Diagnostic Center Sipah Jaunpur | 94.210 | 94.412 | 96.620 | N/A | Predict TD |
L. Aversano et al. [34] | DT, NB, KNN, RF, EXT, MLP, XGB, CB, AB, GB | AOU Federico II | 84 | 85 | 84 | 84 | TD treatment prediction |
T. Alyas et al. [35] | DT, RF, KNN, ANN | UCI | 94.8 | 91 | N/A | N/A | Predict TD |
I.M.D. Maysanjaya et al. [37] | RBF, LVQ, MLP, BPA, AIRS, Perceptron | UCI | 96.74 | 96.8 | 96.7 | 96.8 | Predict TD |
W. Ahmad et al.[38] | LDA, KNN, ANFIS | UCI | 98.5 | 99.7 | 94.7 | N/A | Predict TD |
R. Chaganti et al.[39] | RF, LR, SVM, AD, and GB, LSTM, CNN | UCI | 93 | 94 | 92 | 93 | Predict TD |
S. Shibu et al.[97] | KNN, RF, XGB, and CB | Kaggle | 98.83 | 92.8 | 83.8 | N/A | Predict TD |
Our study | KNN, RF, DT, SVM, AB, and GB | UCI | 99 | 97 | 92 | 95 | Predict TD and identify major risk factors |