The accuracy of Continuous Glucose Monitoring (CGM) devices has been observed to be affected during exercise periods. The accuracy of glucose measurement is of great importance for the correct performance of AP devices, since it drives the decision making of the algorithms behind it. Physical activity has been linked to changes in glucose trends and variability in patients with diabetes. It is one the most promising solutions to the complications of T1D, and several prototypes have been under development over the last few years, including commercially-available devices. A simpler one-input model using only “Mets” is also viable for a more immediate implementation of this correction into market devices.Īn Artificial Pancreas (AP) is a device that feeds continuous glucose measurements into an insulin pump in real time and continuously adjusts insulin dosage delivered to the patient.
Statplus cross tabulation error skin#
The signals identified as optimal inputs for the model are “Mets” (Metabolic Equivalent of Tasks) from the Fitbit Charge HR device, which is a normalized measurement of energy expenditure, and the skin temperature reading provided by the Microsoft Band 2 device. The CGM error is not worsened in periods without physical activity. 13.8%, p < 0.005) to the magnitude of the baseline error level (13.61%). A simple two-input model can reduce CGM error during physical activity (17.46% vs. Linear regression models were used in this work to evaluate the correction capabilities of each of the wearable signals and propose a model for CGM correction during exercise. The viability of an array of physical activity signals provided by three different wearable devices was considered. The use of readily-available exercise monitoring devices opens new possibilities for accuracy enhancement during these periods. Current Continuous Glucose Monitors (CGM) exhibit increased estimation error during periods of aerobic physical activity.
0 kommentar(er)
