Acquisition et validation de données pour la définition d’un modèle de la gestion et prédiction du glucose
Context and challenges
Biosensors are increasingly being developed to provide clinicians with rapid quantitative diagnostic information to guide patients’ treatments without the need of a centralized laboratory testing. They can also be used in low-resource settings, without highly trained medical staff, thus having the potential to greatly improve patients’ care especially regarding disease management where complex sample handling is undesirable.
Blood glucose monitoring is a key example where technological innovation has responded to a multi-level clinical needs, from the pathology laboratory to the patient’s home. However, despite the recent progress, these methods still remain invasive and uncomfortable for the patients for daily use.
Our approach will be a product of type point-of care and low cost with an objective to be a complementary solution to the existing invasive methods in order to reduce the number of the invasive glucose measurements.
This project’s goal is to conceive and implement a non-invasive glucose monitoring system, in the form of a point-of-care system able to predict an increased risk of abnormal glycemia thus allowing patients with Type I diabetes to manage their disease in a simple and comfortable way.
Partners and funding
Funded by the HES-SO
The project has developed a flexible and extensible patient-side subsystem:
The project is has been building a predictive mathematical model and an implementation of a system that will help to warn the patient about a potential hypo- or hyper glycemic crisis in an easy-to-manage and discreet way which will greatly impact the long-term health condition as well as the daily management of a diabetic patient:
Scientific paper – Freiburghaus, J., Rizzotti-Kaddouri, A., Albertetti, F. A Deep Learning Approach for Blood Glucose Prediction of Type 1 Diabetes.