Blood glucose regulation with stochastic optimal control for insulin-dependent diabetic patients

Acikgoz, Saadet Ulas; Diwekar, Urmila M.

doi:10.1016/j.ces.2009.09.077

Cited by 37 publications

(19 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the carbohydrate content in the diet increases (see Figs. 24 and 25), the optimal insulin profile found by Acikgoz and Diwekar [34] is not capable of controlling glycemic variability whereas * II 0.25 is always able to maintain BG levels within soft thresholds (green lines). It can be argue that better results can be obtained for the optimal insulin profile if it is specifically derived for each meal routine.…”

Section: Stochastic Optimal Controlmentioning

confidence: 93%

“…This value has been recommended in the literature [34] to account for different source of intra-and inter-patient variability in stochastic optimal control. Results obtained using the learned optimal policies * Fig.…”

Section: Simulation Study #3mentioning

confidence: 97%

“…The policy * II 0.25 exhibits exceedingly better performance in controlling glycemic variability when compared to the optimal insulin profile for the three meal routines considered. For low carbohydrate intakes, the insulin profile developed by Acikgoz and Diwekar [34] is yet able to maintain BG concentration within the hard thresholds (red lines) but the amplitude of glycemic excursions are quite high. As the carbohydrate content in the diet increases (see Figs.…”

Section: Stochastic Optimal Controlmentioning

confidence: 98%

“…To end this section, a comparison of the proposed approach is made against an optimal insulin profile obtained in the work of Acikgoz and Diwekar [34]. A worthy comparison is thus made Table 6 Summary of percentages of time in each glycemic zone for each simulation study of the sensitivity of the optimal control policy.…”

Section: Stochastic Optimal Controlmentioning

confidence: 99%

“…Based on the deterministic physiological dynamic model developed by Lehmann and Deutsch [32] (Eqs. (1)-(3)), Acikgoz and Diwekar [34] proposed that different sources of time-dependent uncertainties could be represented by introducing stochastic processes in this deterministic model. By superimposing an Ito's stochastic process to represent the variability in plasma glucose concentration Eq.…”

Section: Modeling Glycemic Variabilitymentioning

confidence: 99%

See 4 more Smart Citations

Controlling blood glucose variability under uncertainty using reinforcement learning and Gaussian processes

Paula

Ávila

Martínez

2015

Applied Soft Computing

View full text Add to dashboard Cite

Section: Stochastic Optimal Controlmentioning

confidence: 93%

Section: Simulation Study #3mentioning

confidence: 97%

Section: Stochastic Optimal Controlmentioning

confidence: 98%

Section: Stochastic Optimal Controlmentioning

confidence: 99%

Section: Modeling Glycemic Variabilitymentioning

confidence: 99%

See 3 more Smart Citations

Controlling blood glucose variability under uncertainty using reinforcement learning and Gaussian processes

Paula

Ávila

Martínez

2015

Applied Soft Computing

View full text Add to dashboard Cite

A grid-based tool for optimal performance monitoring of a glycemic regulator

Ávila

Martínez

2015

Optim. Control Appl. Meth.

View full text Add to dashboard Cite

Summary Recent technology breakthroughs towards a fully automated artificial pancreas give rise to the need of new monitoring tools aiming at increasing both reliability and performance of a closed‐loop glycemic regulator. Based on error grid analysis, an insightful monitoring tool is proposed to assess if a given closed‐loop implementation respects its specification of an optimally performing glycemic regulator under uncertainty. The optimal behavior specification is obtained using linearly solvable Markov decision processes, whereby the Bellman optimality equation is made linear through an exponential transformation that allows obtaining the optimal control policy in an explicit form. The specification for the desired glucose dynamics is learned using Gaussian processes for state transitions in an optimally performing artificial pancreas. By means of the proposed grid, the specification is vis‐à‐vis compared with glucose sensor readings so that any significant deviation from the expected closed‐loop performance under abnormal or faulty scenarios can be detected. Copyright © 2015 John Wiley & Sons, Ltd.

show abstract

Inverse problems from biomedicine

August

Koeppl

2012

J. Math. Biol.

View full text Add to dashboard Cite

Many complex diseases that are difficult to treat cannot be mapped onto a single cause, but arise from the interplay of multiple contributing factors. In the study of such diseases, it is becoming apparent that therapeutic strategies targeting a single protein or metabolite are often not efficacious. Rather, a systems perspective describing the interaction of physiological components is needed. In this paper, we demonstrate via examples of disease models the kind of inverse problems that arise from the need to infer disease mechanisms and/or therapeutic strategies. We identify the challenges that arise, in particular the need to devise strategies that are robust against variable physiological states and parametric uncertainties.

show abstract

Blood glucose regulation with stochastic optimal control for insulin-dependent diabetic patients

Cited by 37 publications

References 23 publications

Controlling blood glucose variability under uncertainty using reinforcement learning and Gaussian processes

Controlling blood glucose variability under uncertainty using reinforcement learning and Gaussian processes

A grid-based tool for optimal performance monitoring of a glycemic regulator

Inverse problems from biomedicine

Contact Info

Product

Resources

About