Abstract:
Diabetes type 1 is a chronic disease which is increasing at an alarming rate throughout
the world. Studies reveal that the complications associated with diabetes can be reduced by
proper management of the disease by continuously monitoring and forecasting the blood
glucose level of patients. In the recent past, numerous researches have been carried out to
monitor blood glucose level which suggests the quantity of insulin i.e. artificial pancreas.
Objective: The prior prediction of blood glucose level is necessary to overcome the lag time
for insulin absorption in diabetic type 1 patients. Method: In this research, we use Continuous
Glucose Monitoring (CGM) data to predict future blood glucose level using the previous data
points. We propose optimal nonlinear autoregressive neural networks. We compared optimal
feedforward neural network with optimal nonlinear autoregressive neural networks for blood
glucose prediction 15-30 minutes earlier for diabetic type 1 patients. We validate the
proposed model with 2 diabetic patients using their 24 hours blood glucose level data.
Results: In the prediction horizon (PH) of 15 and 30 minutes, improved results have been
shown for minimal inputs for blood glucose level of a particular subject. Root Mean Square
Error (RMSE) is used for performance calculation. For optimal feedforward neural network,
the RMSE is 0.9984 and 3.78ml/dl and for the optimal nonlinear autoregressive neural
network it reduces the RMSE to 0.60 and 1.12 ml/dl for 15 min and 30 min prediction horizon
respectively for subject 1. Similarly, for subject 2 the optimal feedforward neural network,
RMSE is 1.43 and 3.51ml/dl which is improved using the optimal autoregressive neural
network to 0.7911 and 1.6756 ml/dl for 15 min and 30 min prediction horizon, respectively.
Validation: We further validate our proposed model using UCI machine learning datasets
and it shows improved results on that as well. Conclusion and Future work: The proposed
optimal nonlinear autoregressive neural network model performs better than the feedforward
neural network model for these time series data. In the future, we intend to investigate a
greater collection of patients, and other factors of BGLs.
