English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Effective postprandial glucose control is important to glucose management forsubjects with diabetes mellitus. In this work, a data-driven meal bolusdecision method is proposed without the need of subject-specific glucosemanagement parameters. The postprandial glucose dynamics is learnt usingGaussian process regression. Considering the asymmetric risks of hyper- andhypoglycemia and the uncertainties in the predicted glucose trajectories, anasymmetric risk-sensitive cost function is designed. Bayesian optimization isutilized to solve the optimization problem, since the gradient of the costfunction is unavailable. The proposed approach is evaluated using the 10-adultcohort of the FDA-accepted UVA/Padova T1DM simulator and compared with thestandard insulin bolus calculator. For the case of announced meals, theproposed method achieves satisfactory and similar performance in terms of meanglucose and percentage time in [70, 180] mg/dL without increasing the risk ofhypoglycemia. Similar results are observed for the case without the mealinformation (assuming that the patient follows a consistent diet) and the caseof basal rate mismatches. In addition, advisory-mode analysis is performedbased on clinical data, which indicates that the method can determine safe andreasonable meal boluses in real clinical settings. The results verify theeffectiveness and robustness of the proposed method and indicate thefeasibility of achieving improved postprandial glucose regulation through adata-driven optimal control method.

Bayesian Optimization Assisted Meal Bolus Decision Based on Gaussian Processes Learning and Risk-Sensitive Control