Table 4.
Relative ranks of MLa models for predicting BGb levels in PHc=30 minutes.
| ML model | SUCRAd | Relative rank |
| NNMe | 52.0 | 14.4 |
| ARMf | 39.6 | 17.9 |
| ARJNNg | 79.5 | 6.8 |
| RFh | 6.9 | 27.1 |
| SVMi | 73.3 | 8.5 |
| One symbolic model (SAX) | 0.4 | 28.9 |
| Recurrent neural network (RNN) | 19.0 | 23.7 |
| One neural network model (NARX) | 3.9 | 27.9 |
| Jump neural network (JNN) | 36.0 | 18.9 |
| Delayed feed-forward neural network model (DFFNN) | 15.8 | 24.6 |
| Gradually connected neural network (GCN) | 41.1 | 17.5 |
| Fully connected (FC [neural network]) | 58.1 | 12.7 |
| Light gradient boosting machine (LGBM) | 69.3 | 9.6 |
| DRNNj | 99.1 | 1.2 |
| Autoregressive moving average (ARMA) | 54.3 | 13.8 |
| Autoregressive integrated moving average (ARIMA) | 46.6 | 16.0 |
| Feed-forward neural network (fNN) | 86.3 | 4.8 |
| Long short-term memory (LSTM) | 69.1 | 9.7 |
| GluNet | 96.4 | 2.0 |
| Latent variable with exogenous input (LVX) | 75.2 | 7.9 |
| Neural network–linear prediction algorithm (NN-LPA) | 60.0 | 12.2 |
| Convolutional recurrent neural network multitask learning (CRNN-MTL) | 77.5 | 7.3 |
| Convolutional recurrent neural network multitask learning glycemic variability (CRNN-MTL-GV) | 77.2 | 7.4 |
| Convolutional recurrent neural network transfer learning (CRNN-TL) | 71.8 | 8.9 |
| Convolutional recurrent neural network single-task learning (CRNN-STL) | 52.0 | 14.4 |
| k-Nearest neighbor (kNN) | 26.0 | 21.7 |
| DTk | 16.2 | 24.5 |
| AdaBoost | 18.0 | 24.0 |
| XGBoostl | 29.2 | 20.8 |
aML: machine learning.
bBG: blood glucose.
cPH: prediction horizon.
dSUCRA: surface under the cumulative ranking.
eNNM: neural network model.
fARM: autoregression model.
gARJNN: ARTiDe jump neural network.
hRF: random forest.
iSVM: support vector machine.
jDRNN: dilated recurrent neural network.
kDT: decision tree.
lXGBoost: Extreme Gradient Boosting.