Background: Automated Insulin Delivery (AID) is now integral to the clinical practice of Type 1 diabetes (T1D). The objective of this pilot-feasibility study was to introduce a new regulatory and clinical paradigm - a Neural-Net Artificial Pancreas (NAP) - an encoding of an AID algorithm into a neural network that approximates its action, and assess NAP vs the original AID algorithm.
Methods: The UVA model-predictive control (UMPC) algorithm was encoded into a neural network, creating its NAP approximation. Seventeen AID users with T1D were recruited and 15 participated in two consecutive 20-hour hotel sessions, receiving in random order either NAP or UMPC. Their demographic characteristics were: ages 22-68 years old, duration of diabetes 7-58 years, gender 10/5 female/male, White Non-Hispanic/Black 13/2, and baseline HbA1c 5.4-8.1%.
Results: The time-in-range (TIR) difference between NAP and UMPC, adjusted for entry glucose level, was 1 percentage point, with absolute TIR values of 86% (NAP) and 87% (UMPC). The two algorithms achieved similar times <70 mg/dL of 2.0% vs 1.8% and coefficients of variation of 29.3% (NAP) vs 29.1 (UMPC)%. Under identical inputs, the average absolute insulin-recommendation difference was 0.031 units/hour. There were no serious adverse events on either controller. NAP had 6-fold lower computational demands than UMPC.
Conclusion: In a randomized crossover study, a neural-network encoding of a complex model-predictive control algorithm demonstrated similar performance, at a fraction of the computational demands. Regulatory and clinical doors are therefore open for contemporary machine learning methods to enter the AID field.