Table 6.

Relative ranks of ML^a models for predicting BG^b levels in PH^c=15 minutes.

ML model	SUCRAd	Relative rank
NNMe	84.4	3.0
ARMf	86.8	2.7
ARJNNg	99.1	1.1
RFh	64.6	5.6
SVMi	20.9	11.3
One symbolic model (SAX)	0.3	14.0
Recurrent neural network (RNN)	45.9	8.0
One neural network model (NARX)	11.8	12.5
Jump neural network (JNN)	62.2	5.9
Delayed feed-forward neural network model (DFFNN)	39.6	8.9
k-Nearest neighbor (kNN)	53.7	7.0
DTj	33.3	9.7
AdaBoost	36.8	9.2
XGBoostk	60.8	6.1

^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.

^jDT: decision tree.

^kXGBoost: Extreme Gradient Boosting.