Using an Online Disturbance Rejection and Anticipation System to Reduce Hyperglycemia in a Fully Closed-Loop Artificial Pancreas System

Abstract

Introduction: Hyperglycemia following meals is a recurring challenge for people with type 1 diabetes, and even the most advanced available automated systems currently require manual input of carbohydrate amounts. To progress toward fully automated systems, we present a novel control system that can automatically deliver priming boluses and/or anticipate eating behaviors to improve postprandial full closed-loop control. Methods: A model predictive control (MPC) system was enhanced by an automated bolus system reacting to early glucose rise and/or a multistage MPC (MS-MPC) framework to anticipate historical patterns. Priming was achieved by detecting large glycemic disturbances, such as meals, and delivering a fraction of the patient’s total daily insulin (TDI) modulated by the disturbance’s likelihood (bolus priming system [BPS]). In the anticipatory module, glycemic disturbance profiles were generated from historical data using clustering to group days with similar behaviors; the probability of each cluster is then evaluated at every controller step and informs the MS-MPC framework to anticipate each profile. We tested four configurations: MPC, MPC + BPS, MS-MPC, and MS-MPC + BPS in simulation to contrast the effect of each controller module. Results: Postprandial time in range was highest for MS-MPC + BPS: 60.73 ± 25.39%, but improved with each module: MPC + BPS: 56.95±25.83 and MS-MPC: 54.83 ± 26.00%, compared with MPC: 51.79 ± 26.12%. Exposure to hypoglycemia was maintained for all controllers (time below 70 mg/dL <0.5%), and improvement came primarily from a reduction in postprandial time above range (MS-MPC + BPS: 39.10 ± 25.32%, MPC + BPS: 42.99 ± 25.81%, MS-MPC: 45.09 ± 25.96%, MPC: 48.18 ± 26.09%). Conclusions: The BPS and anticipatory disturbance profiles improved blood glucose control and were most efficient when combined.

Artificial Pancreas: A Review of Meal Detection and Carbohydrates Counting Techniques

“…More details are available in the literature [ 26 ]. Examples of MPC for diabetes also are reported in the literature [ 25 ]. For this approach the author presents a control system that automatically delivers priming boluses and/or anticipates eating behaviors to improve post-prandial full closed-loop control.…”

Enabling fully automated insulin delivery through meal detection and size estimation using Artificial Intelligence

“…Sensitivity varies greatly depending on the datasets used and the study protocols, reaching values greater than 90% in some cases, though the sensitivity and specificity of many of previously published algorithms have been validated only in silico. For example, the automated meal detection algorithm presented by Corbett et al 16 used a clustering method to estimate the probability of a meal occurring based on prior meal patterns. The algorithm recognizes a meal pattern and doses a priming dose, demonstrating an improvement in time in range from 52 to 57%; however, these results are only provided for an in silico trial.…”

New Contributions Towards Meal and Exercise Announcement-Free Artificial Pancreas Systems

“…The consensus of MPC problems in the optimization depends on the probability that the specific disturbance profile represents the actual disturbance. In silico validations of the system with the full version of the UVa/Padova simulator showed a %time in 70-180 mg/dL higher than 70 % (Corbett et al 2022). However, compared with a single MPC that delivers bolus after detecting meals, the multistage MPC led to slight inferior results (Corbett et al 2022).…”

“…Other methods use information from behavioral meal patterns to confirm a meal occurrence (Cameron et al 2012;Villeneuve et al 2020). Lastly, classification algorithms have also been used to discern the meal events, such as logistic regression (Garcia-Tirado et al 2021c;Garcia-Tirado et al 2021b;Corbett et al 2022), linear discriminant analysis (Kölle et al 2017;Kölle et al 2020), extended isolation forest (Zheng et al 2020), fuzzy logic (Samadi et al 2017), or recursive neural networks (Askari et al 2022).…”

“…Another technique featured with meal anticipation capabilities was presented in Corbett et al (2020) and extended later in Corbett et al (2022). The core of the system is a multistage MPC.…”