A Personalized and Adaptive Insulin Bolus Calculator Based on Double Deep Q-Learning to Improve Type 1 Diabetes Management.

Researchers

Journal

Modalities

Models

Abstract

Mealtime insulin dosing is a major challenge for people living with type 1 diabetes (T1D). This task is typically performed using a standard formula that, despite containing some patient-specific parameters, often leads to sub-optimal glucose control due to its poor personalization and lack of adaptation over time to tackle the intra-individual variability. To overcome the previous limitations, in this work we propose an individualized and adaptive mealtime insulin bolus calculator based on double deep Q-learning (DDQ), which is tailored to the patient thanks to a personalization procedure relying on a two-step learning framework. The proposed DDQ-learning bolus calculator was developed and tested using the UVA/Padova T1D simulator, which is equipped with a cohort of 100 diabetic virtual subjects, and able to reliably mimic real-world scenarios, by introducing multiple variability sources impacting glucose metabolism and technology. The learning phase included a long-term training of eight sub-population models, one for each representative subject, selected thanks to a clustering procedure applied to the training set. Then, for each subject of the testing set, a personalization procedure was performed, by initializing the models based on the cluster to which the patient belongs. We evaluated the effectiveness of the proposed bolus calculator on a 60-day simulation, using several metrics representing the goodness of glycemic control, and comparing the results with the standard guidelines for mealtime insulin dosing. The proposed method improved the time in target range from 68.35% to 70.08% and significantly reduced the time in hypoglycemia (from 8.78% to 4.17%). The overall glycemic risk index decreased from 8.2 to 7.3, indicating the benefit of our method when applied for insulin dosing compared to standard guidelines.