Event Detection and Control of Blood Glucose Levels Using Deep Neural Network

Govindaraju, Divya; Shree, Ramya; Priyanka, S.; Porkodi, S.; Subbian, Sutha

doi:10.1007/978-981-16-2674-6_18

Cited by 1 publication

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Improved control algorithms have driven recent advances in APS performance. Traditional control algorithms such as proportional integral derivative (PID) [38], model predictive control (MPC) [62], and fuzzy logic [53] have given way to machine learning based techniques such as deep neural networks [34,60] and reinforcement learning [22,74], which offer more powerful insights into relationships in sensor data. However, machine learning techniques are far more intractable than traditional algorithms, so they must be rigorously tested before deployment to ensure the ML controller performs accurately in any possible scenario.…”

Section: Introductionmentioning

confidence: 99%

Design and Validation of an Open-Source Closed-Loop Testbed for Artificial Pancreas Systems

Xugui¹,

Kouzel²,

Ren³

et al. 2022

Preprint

View full text Add to dashboard Cite

The development of a fully autonomous artificial pancreas system (APS) to independently regulate the glucose levels of a patient with Type 1 diabetes has been a long-standing goal of diabetes research. A significant barrier to progress is the difficulty of testing new control algorithms and safety features, since clinical trials are timeand resource-intensive. To facilitate ease of validation, we propose an open-source APS testbed by integrating APS controllers with two state-of-the-art glucose simulators and a novel fault injection engine. The testbed is able to reproduce the blood glucose trajectories of real patients from a clinical trial conducted over six months. We evaluate the performance of two closed-loop control algorithms (OpenAPS and Basal Bolus) using the testbed and find that more advanced control algorithms are able to keep blood glucose in a safe region 93.49% and 79.46% of the time on average, compared with 66.18% of the time for the clinical trial. The fault injection engine simulates the real recalls and adverse events reported to the U.S. Food and Drug Administration (FDA) and demonstrates the resilience of the controller in hazardous conditions. We used the testbed to generate 2.5 years of synthetic data representing 20 different patient profiles with realistic adverse event scenarios, which would have been expensive and risky to collect in a clinical trial. The proposed testbed is a valid tool that can be used by the research community to demonstrate the effectiveness of different control algorithms and safety features for APS. CCS CONCEPTS• Computer systems organization → Embedded and cyberphysical systems; Dependable and fault-tolerant systems and networks; • Applied computing → Life and medical sciences.

show abstract