Neural Architecture Search for Blood Glucose Prediction in Type-1 Diabetics

For subjects affected with type-1 diabetes mellitus, accurately predicting future blood glucose values helps regulate insulin delivery. This paper introduces a dual Q-network-based neural architecture search approach to develop and train per-sonalized BG prediction models for individuals affected with type-1 diabetes mellitus. Utilizing historical blood glucose data collected via body sensor networks, the proposed model forecasts future blood glucose levels. When evaluated on the OhioTlDM dataset, the proposed approach shows significant improvements over the state-of-the-art, achieving a 46.78% reduction in root mean square error and a 56.05% reduction in mean absolute error while predicting blood glucose values 5 minutes into the future.