U. Pielmeier, S. Andreassen (Denmark), and J.G. Chase (New Zealand)
Control Systems, Medical Decision Support, Physiological Modelling, Critical Care, Model-based Control, Hypergly caemia
Model-based control systems provide better glycaemic control in intensive care than ad-hoc protocols, but de pend on predictive accuracy and facilitation of clinical rou tines. A general method to customize and visualize model based blood glucose predictions is presented. Customiza tion is based on admission type and diabetic status of pa tients. Blood glucose concentrations of 14 critically ill pa tients from two intensive care units were retrospectively predicted. Relative prediction errors were found to be high est for diabetic I and II patients, and lowest for non-diabetic trauma and head-injured patients. Standard deviations of mean relative prediction errors are proposed to be used for display of accuracy of model-based blood glucose predic tions in prospectively controlled patients. The method pro vides for an optimized timing of blood sampling to facili tate tight glucose management in the ICU.
Important Links:
Go Back
