From: Early prediction of chronic kidney disease based on ensemble of deep learning models and optimizers
Model | Precision | Sensitivity | F1-score | Accuracy | |
---|---|---|---|---|---|
Individual classifiers in Ensemble model | CNN_Adamax | 0.95 | 0.95 | 0.95 | 0.95 |
LSTM_Adam | 0.96 | 0.96 | 0.96 | 0.96 | |
LSTM-BLSTM_Adamax | 0.97 | 0.97 | 0.97 | 0.97 | |
Ensemble model | 0.98 | 0.98 | 0.98 | 0.98 | |
Results for the previous work [9] | LightGBM [9] | 0.426 | 0.685 | 0.525 | 0.751 |
Logistic [9] | 0.405 | 0.664 | 0.503 | 0.736 | |
Random forest [9] | 0.390 | 0.652 | 0.488 | 0.725 | |
Decision tree [9] | 0.395 | 0.622 | 0.483 | 0.732 |