From: Early prediction of chronic kidney disease based on ensemble of deep learning models and optimizers
Optimizer | Precision | Sensitivity | F1-score | Accuracy | |||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
CKD | Non-CKD | Macro avg | Weighted avg | CKD | Non-CKD | Macro avg | Weighted avg | CKD | Non-CKD | Macro avg | Weighted avg | ||
CNN model | |||||||||||||
Adamax | 0.91 | 0.95 | 0.93 | 0.93 | 0.95 | 0.91 | 0.93 | 0.93 | 0.93 | 0.93 | 0.93 | 0.93 | 0.93 |
Adam | 0.90 | 0.94 | 0.92 | 0.92 | 0.94 | 0.90 | 0.92 | 0.92 | 0.92 | 0.92 | 0.92 | 0.92 | 0.92 |
SGD | 0.72 | 0.81 | 0.77 | 0.77 | 0.84 | 0.68 | 0.76 | 0.76 | 0.78 | 0.74 | 0.76 | 0.76 | 0.76 |
Adadelta | 0.64 | 0.81 | 0.73 | 0.73 | 0.88 | 0.52 | 0.70 | 0.70 | 0.74 | 0.63 | 0.69 | 0.69 | 0.70 |
Adagrad | 0.70 | 0.86 | 0.78 | 0.78 | 0.89 | 0.62 | 0.76 | 0.76 | 0.78 | 0.72 | 0.75 | 0.75 | 0.76 |
LSTM model | |||||||||||||
Adamax | 0.91 | 0.96 | 0.94 | 0.94 | 0.96 | 0.91 | 0.94 | 0.94 | 0.94 | 0.94 | 0.94 | 0.94 | 0.94 |
Adam | 0.93 | 0.98 | 0.96 | 0.96 | 0.98 | 0.93 | 0.95 | 0.95 | 0.96 | 0.95 | 0.95 | 0.95 | 0.95 |
SGD | 0.55 | 0.69 | 0.62 | 0.62 | 0.85 | 0.33 | 0.59 | 0.59 | 0.67 | 0.45 | 0.56 | 0.56 | 0.59 |
Adadelta | 0.53 | 0.69 | 0.61 | 0.61 | 0.90 | 0.22 | 0.56 | 0.56 | 0.67 | 0.34 | 0.50 | 0.50 | 0.56 |
Adagrad | 0.62 | 0.74 | 0.68 | 0.68 | 0.82 | 0.52 | 0.67 | 0.66 | 0.71 | 0.61 | 0.66 | 0.66 | 0.66 |
LSTM-BLSTM model | |||||||||||||
Adamax | 0.94 | 0.98 | 0.96 | 0.96 | 0.99 | 0.94 | 0.96 | 0.96 | 0.96 | 0.96 | 0.96 | 0.96 | 0.96 |
Adam | 0.94 | 0.99 | 0.96 | 0.96 | 0.99 | 0.93 | 0.96 | 0.96 | 0.96 | 0.96 | 0.96 | 0.96 | 0.96 |
SGD | 0.63 | 0.72 | 0.67 | 0.67 | 0.77 | 0.56 | 0.67 | 0.66 | 0.69 | 0.63 | 0.66 | 0.66 | 0.66 |
Adadelta | 0.58 | 0.73 | 0.66 | 0.66 | 0.85 | 0.39 | 0.62 | 0.62 | 0.69 | 0.51 | 0.60 | 0.60 | 0.62 |
Adagrad | 0.60 | 0.75 | 0.67 | 0.67 | 0.85 | 0.44 | 0.65 | 0.64 | 0.70 | 0.56 | 0.63 | 0.63 | 0.64 |