US 12,263,021 B2
Glucose monitoring method and system
Xiali Hei, Lafayette, LA (US); and Yazhou Tu, Lafayette, LA (US)
Assigned to University of Louisiana at Lafayette, Lafayette, LA (US)
Filed by University of Louisiana at Lafayette, Lafayette, LA (US)
Filed on Nov. 19, 2020, as Appl. No. 16/952,692.
Claims priority of provisional application 62/937,319, filed on Nov. 19, 2019.
Prior Publication US 2021/0145370 A1, May 20, 2021
Int. Cl. A61B 5/00 (2006.01); A61B 5/11 (2006.01); A61B 5/145 (2006.01)
CPC A61B 5/746 (2013.01) [A61B 5/11 (2013.01); A61B 5/14532 (2013.01); A61B 5/4806 (2013.01); A61B 5/681 (2013.01); A61B 5/6887 (2013.01); A61B 5/725 (2013.01); A61B 2562/0219 (2013.01); A61B 2562/0247 (2013.01)] 7 Claims
OG exemplary drawing
 
1. A system for determining a false alarm in a continuous glucose monitor comprising:
a. a patient physiological signal detector, wherein said signal detector continuously monitors a plurality of patient physiological signals selected from the group consisting of heart rate, galvanic skin response, skin tremor, and heart rate variability, and wherein said signal detector outputs said monitored patient physiological signals;
b. a continuous glucose sensor, wherein said glucose sensor outputs measured patient glucose levels;
c. an insulin pump operably connected to said continuous glucose sensor, wherein said insulin pump injects the patient with insulin based on said measured patient glucose levels;
d. a receiver operably connected to said continuous glucose sensor, said patient physiological signal detector, and said insulin pump, wherein said receiver continuously receives and outputs to a processor said patient physiological signals and said measured patient glucose levels, wherein said processor continuously applies a stacked LSTM (Long Short-Term Memory) Based Deep Recurrent Neural Network to said patient physiological signals and said measured patient glucose levels to predict a patient's predicted blood glucose level and compares said predicted blood glucose level to said measured patient glucose level to calculate a confidence score and actuates an alarm when said confidence score is less than a predetermined threshold level.