Glycemie - Development of a control system for the optimization of glycemia in critically ill patients
From 01-01-2003 to 31-12-2006
Description
Glycemia is the concentration of glucose in the blood. Glycemia control is a complex system in which a lot of factors may play a significant role. This human control system may be interrupted by an absolute or relative shortage of insulin that may result in an elevated glycemia level (hyperglycemia). Recently, an article in The New England Journal of Medicine appeared in which the results of a clinical study about the intensive insulin therapy in critically ill patients were described. Those patients typically need ?intensive care?. It is known insulin resistance and the resulting hyperglycemia frequently appear in these patients, even if they have not had diabetes before. In this clinical study with 1548 patients it is mentioned that normalization of glycemia, by means of intensive administration of insulin, decreased the mortality and morbidity rate by 50 % (!) for patients who stayed for more than 5 days in ICU (Intensive Care Unit). At present, insulin administration is controlled by a labor-intensive and empirical manual protocol in which glycemia is measured every 4 hours or even more frequently in case of complications or during the initial phase. This protocol should result in getting a normal glycemia level, i.e., a glycemia level between 80 and 110 mg/dl. Glycemia levels under 70 mg/dl, the so-called hypoglycemias, should be avoided because of their possible baleful influences. The efficiency of the protocol is complicated due to factors such as supply of calories and drugs, patient profile, etc. In the near future, glycemia sample frequency will probably be increased (e.g., glycemia measurements every 3 minutes) by applying other sensor techniques. In this project, a control system that (semi-)automatically normalizes glycemia of critically ill patients will be developed. It will determine the insulin rate that a certain patient will probably need at each time step. Many different dynamical changes (such as administered calories or drugs) will influence the condition of the patient. Consequently, the control system should be robust to overcome these disturbances. The control system will consist of two parts. On the one hand, a patient model will be constructed. This model will represent a ?mathematical? patient. It will make it possible to predict glycemia of a specific patient after administering a certain amount of insulin, calories, drugs, etc. Factors such as insulin resistance, BMI, etc. will also be important to develop an accurate model. On the other hand, the control system will include the controller itself. The latter will determine the insulin rate that will be administered to the patient for the next time steps. The patient model and controller will both consist of certain structures and parameters that are patient specific. The initial structures and parameter values will be defined using input-output-data, which have been gathered before. The control system should be adaptive in order to account for different types of specific patient behavior. Depending on initial patient features (e.g., BMI) a new patient who is admitted to ICU will belong to a certain patient cluster that will be correlated with a specific control system (e.g., a specific patient model structure, specific model parameter values, specific controller parameter values). During the patient?s stay in ICU this initial control system will be adapted in order to render it more patient-specific, and as a result, more accurate. The final implementation of this control system in hospitals will significantly reduce the workload for nurses and doctors. Consequently, the introduction of a (semi-)automatic glycemia control system will also be feasible in ICU-divisions of hospitals in which staff are less motivated nowadays to apply the manual intensive insulin therapy. Generally, this control system will also optimize glycemia of patients in a more stable way. Subjective manual control will be avoided. The application of this control system in divisions other than ICU might be an opportunity, as well. Finally, there is also the possibility the mortality and/or morbidity rate will decrease further due to the stricter glycemia control. Probably, this will be the case in hospitals where the manual intensive insulin therapy is currently not used.Team
- Bart De Moor, Promoter
- Bert Pluymers, Team member
- Marcelo Rodrigo Espinoza Tapia, Team member
- Tom Van Herpe, Team member
Financing
Funding: FWO - Research Foundation - Flanders
Program/Grant Type: FWO Research Grant - FWO Research Grant
Events
2/09/2024:
PhD defense - Martijn Oldenhof
Machine Learning for Advanced Chemical Analysis and Structure Recognition in Drug Discovery
3/09/2024:
Meet the Jury Igor Tetko on Advanced Machine Learning in Drug Discovery
12/09/2024:
Multimodal analysis of cell-free DNA for sensitive cancer detection in low-coverage and low-sample settings
Seminar by Antoine Passemiers
News
STADIUS Alumni Herman Verrelst – new CEO of Biocartis
08 June 2017
Herman Verrelst, the founder of KU Leuven spin-off Cartagenia, who has been working in Silicon Valley, US for the last few years will be returning to Belgium to follow the steps of Rudi Pauwels as CEO of the Belgian diagnostic company, Biocartis.
Supporting healthcare policymaking via machine learning – batteries included!
29 May 2017
STADIUS takes the lead in the data analytics efforts in an ambitious European Project MIDAS.
Marc Claesen gives an interview about his PhD for the magazine of the Faculty of Engineering Sciences "Geniaal"
10 February 2017
Did you know that in Belgium approximately one third of type 2 diabetes patients are unaware of their condition?
Joos Vandewalle is nieuwe voorzitter KVAB
09 October 2016
Op 5 oktober 2016 heeft de Algemene Vergadering van de Academie KVAB Joos Vandewalle verkozen tot voorzitter van de KVAB.