Committed Moving Horizon Estimation for Meal Detection and Estimation in Type 1 Diabetes

Chen, Hongkai; Paoletti, Nicola; Smolka, Scott A.; Lin, Shan

doi:10.23919/acc.2019.8814868

Cited by 5 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As such, the quality of the estimate directly depends on the accuracy of the predictive model and the quality of the measurements. Details of the MHE optimization problem for the AP can be found in (Chen et al, 2019). Alternative SE methods include Kalman filters and particle filters (Rawlings, 2013), but these are subject to the same kinds of estimation errors as MHE.…”

Section: Background On Mpc For the Apmentioning

confidence: 99%

MPC-guided Imitation Learning of Bayesian Neural Network Policies for the Artificial Pancreas

Chen

Paoletti

Smolka

et al. 2021

2021 60th IEEE Conference on Decision and Control (CDC)

Self Cite

View full text Add to dashboard Cite

Even though model predictive control (MPC) is currently the main algorithm for insulin control in the artificial pancreas (AP), it usually requires complex online optimizations, which are infeasible for resource-constrained medical devices. MPC also typically relies on state estimation, an error-prone process. In this paper, we introduce a novel approach to AP control that uses Imitation Learning to synthesize neural-network insulin policies from MPC-computed demonstrations. Such policies are computationally efficient and, by instrumenting MPC at training time with full state information, they can directly map measurements into optimal therapy decisions, thus bypassing state estimation. We apply Bayesian inference via Monte Carlo Dropout to learn policies, which allows us to quantify prediction uncertainty and thereby derive safer therapy decisions. We show that our control policies trained under a specific patient model readily generalize (in terms of model parameters and disturbance distributions) to patient cohorts, consistently outperforming traditional MPC with state estimation.

show abstract

Section: Background On Mpc For the Apmentioning

confidence: 99%

MPC-guided Imitation Learning of Bayesian Neural Network Policies for the Artificial Pancreas

Chen

Paoletti

Smolka

et al. 2021

2021 60th IEEE Conference on Decision and Control (CDC)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The artificial pancreas (AP) is used to control blood glucose (BG) levels in Type 1 diabetes patients through automated delivery of insulin. We use the linear plant model of [6] to describe the physiological state of the patient. The main state variable of interest is G, which is the difference between the reference BG (7.8 mmol/L) and the patient's BG.…”

Section: Artificial Pancreasmentioning

confidence: 99%

Neural Simplex Architecture

Phan

Grosu

Jansen

et al. 2020

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

We present the Neural Simplex Architecture (NSA), a new approach to runtime assurance that provides safety guarantees for neural controllers (obtained e.g. using reinforcement learning) of autonomous and other complex systems without unduly sacrificing performance. NSA is inspired by the Simplex control architecture of Sha et al., but with some significant differences. In the traditional approach, the advanced controller (AC) is treated as a black box; when the decision module switches control to the baseline controller (BC), the BC remains in control forever. There is relatively little work on switching control back to the AC, and there are no techniques for correcting the AC's behavior after it generates a potentially unsafe control input that causes a failover to the BC. Our NSA addresses both of these limitations. NSA not only provides safety assurances in the presence of a possibly unsafe neural controller, but can also improve the safety of such a controller in an online setting via retraining, without overly degrading its performance. To demonstrate NSA's benefits, we have conducted several significant case studies in the continuous control domain. These include a targetseeking ground rover navigating an obstacle field, and a neural controller for an artificial pancreas system.

show abstract

“…6 Unannounced meals do not provide the luxury of feedforward knowledge but use of a meal disturbance model paired with meal detection can improve postprandial predictions. [7][8][9][10][11][12][13][14][15][16][17][18][19] MPC relies on accurate predictions by design, so improved predictions lead to improved control.…”

Section: Introductionmentioning

confidence: 99%

A New Meal Absorption Model for Artificial Pancreas Systems

Diamond

Cameron

Bequette

2021

J Diabetes Sci Technol

View full text Add to dashboard Cite

Background: Artificial pancreas (AP) systems reduce the treatment burden of Type 1 Diabetes by automatically regulating blood glucose (BG) levels. While many disturbances stand in the way of fully closed-loop (automated) control, unannounced meals remain the greatest challenge. Furthermore, different types of meals can have significantly different glucose responses, further increasing the uncertainty surrounding the meal. Methods: Effective attenuation of a meal requires quick and accurate insulin delivery because of slow insulin action relative to meal effects on BG. The proposed Variable Hump (VH) model adapts to meals of varying compositions by inferring both meal size and shape. To appropriately address the uncertainty of meal size, the model divides meal absorption into two disjoint regions: a region with coarse meal size predictions followed by a fine-grain region where predictions are fine-tuned by adapting to the meal shape. Results: Using gold-standard triple tracer meal data, the proposed VH model is compared to three simpler second-order response models. The proposed VH model increased model fit capacity by 22% and prediction accuracy by 12% relative to the next best models. A 47% increase in the accuracy of uncertainty predictions was also found. In a simple control scenario, the controller governed by the proposed VH model provided insulin just as fast or faster than the controller governed by the other models in four out of the six meals. While the controllers governed by the other models all delivered at least a 25% excess of insulin at their worst, the VH model controller only delivered 9% excess at its worst. Conclusions: The VH Model performed best in accuracy metrics and succeeded over the other models in providing insulin quickly and accurately in a simple implementation. Use in an AP system may improve prediction accuracy and lead to better control around mealtimes.

show abstract

Committed Moving Horizon Estimation for Meal Detection and Estimation in Type 1 Diabetes

Cited by 5 publications

References 23 publications

MPC-guided Imitation Learning of Bayesian Neural Network Policies for the Artificial Pancreas

MPC-guided Imitation Learning of Bayesian Neural Network Policies for the Artificial Pancreas

Neural Simplex Architecture

A New Meal Absorption Model for Artificial Pancreas Systems

Contact Info

Product

Resources

About