In this document we describe a new method for the real-time detection of failures in the so-called “augmented pump” (or “smart pump”), a medical system for Type-1 diabetes therapy composed by a continuous glucose monitoring (CGM) sensor and a continuous subcutaneous insulin infusion (CSII) pump. The new method is fed by CGM readings and CSII injection data. By exploiting a model of the glucose-insulin system (provided externally or individualized on patient data), single- or multi-step ahead real-time predictions of future glucose concentrations are obtained. The predicted glucose concentrations are then compared to measured CGM data by means of a statistical analysis block. Finally, a failure alert is generated if CGM measurements are not consistent with glucose predictions.
Method to Improve Safety Monitoring in Type-1 Diabetic Patients by Detecting in Real-Time Failures of the Glucose Sensor-Insulin Pump System
FACCHINETTI, ANDREA;DEL FAVERO, SIMONE;SPARACINO, GIOVANNI;COBELLI, CLAUDIO
2012
Abstract
In this document we describe a new method for the real-time detection of failures in the so-called “augmented pump” (or “smart pump”), a medical system for Type-1 diabetes therapy composed by a continuous glucose monitoring (CGM) sensor and a continuous subcutaneous insulin infusion (CSII) pump. The new method is fed by CGM readings and CSII injection data. By exploiting a model of the glucose-insulin system (provided externally or individualized on patient data), single- or multi-step ahead real-time predictions of future glucose concentrations are obtained. The predicted glucose concentrations are then compared to measured CGM data by means of a statistical analysis block. Finally, a failure alert is generated if CGM measurements are not consistent with glucose predictions.
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
