Blood Glucose Prediction Using Artificial Neural Networks Trained with the AIDA Diabetes Simulator: A Proof-of-Concept Pilot Study

Table 1

Incremental progression of the input vectors, current time-step, and BGL prediction used for ANN training.

			Input vectors		Current time step		Prediction
Time (hrs)	18.25	18.50	18.75	19.00	19.25	19.50	19.75	20.00	20.25
BGL (mmol/L)	11.4	11.2	11.0	10.6	10.1	8.8	7.5	6.3	5.3
Meal (grams of carbohydrates)	0	0	0	90	0	0	0	0	0
Short-acting insulin	7	0	0	0	0	0	0	0	0
Long-acting insulin	0	0	0	0	0	0	0	0	5
				Input vectors		Current time step		Prediction
Time (hrs)	18.25	18.50	18.75	19.00	19.25	19.50	19.75	20.00	20.25
BGL (mmol/L)	11.4	11.2	11.0	10.6	10.1	8.8	7.5	6.3	5.3
Meal (grams of carbohydrates)	0	0	0	90	0	0	0	0	0
Short-acting insulin	7	0	0	0	0	0	0	0	0
Long-acting insulin	0	0	0	0	0	0	0	0	5