Safeguarding measures for a closed-loop insulin infusion system

Abstract

Processor-implemented methods of controlling an insulin infusion device for a user are provided here. A first method obtains a current insulin on board (IOB) value that estimates active insulin in the user, and compensates a calculated insulin infusion rate in response to the obtained IOB value. A second method supervises the operation of a glucose sensor by obtaining and processing insulin-delivered data and glucose sensor data for the user. An alert is generated if the second method determines that a current glucose sensor value has deviated from a predicted sensor glucose value by at least a threshold amount.

What is claimed is: 
     
         1 . A system comprising:
 one or more processors; and   one or more processor-readable media storing instructions which, when executed by the one or more processors, cause performance of:
 generating a model for predicting physiological values based on a plurality of measured physiological values obtained during a plurality of sampling periods; 
 operating a fluid infusion device in an automatic mode for automatically delivering fluid based on one or more physiological values; 
 obtaining a measured physiological value corresponding to a sampling period excluded from the plurality of sampling periods; 
 determining, based on the model, a predicted physiological value for the sampling period; and 
 switching operation of the fluid infusion device from the automatic mode to a manual mode when a difference between the measured physiological value and the predicted physiological value exceeds a threshold error amount. 
   
     
     
         2 . The system of  claim 1 , wherein the fluid infusion device is an insulin infusion device comprising an insulin reservoir for insulin to be delivered from the insulin infusion device. 
     
     
         3 . The system of  claim 1 , wherein:
 the measured physiological value comprises a sensor glucose value; and   the predicted physiological value comprises a predicted sensor glucose value.   
     
     
         4 . The system of  claim 3 , wherein the one or more processor-readable media further store instructions which, when executed by the one or more processors, cause performance of:
 estimating plasma insulin for the user based on current insulin-delivered data, historical insulin-delivered data, and an insulin basal rate for the user; and   obtaining predicted sensor glucose values based at least in part on the estimated plasma insulin.   
     
     
         5 . The system of  claim 1 , wherein the one or more processor-readable media further store instructions which, when executed by the one or more processors, cause performance of:
 generating an alert when the difference between the measured physiological value and the predicted physiological value exceeds the threshold error amount.   
     
     
         6 . The system of  claim 1 , wherein:
 a recent history period corresponds to a period of time from a begin-prediction sampling period to a most recent sampling period, inclusive;   a distant history period corresponds to a period of time from a begin-training sampling period to an end-training sampling period, inclusive;   the distant history period occurred before the recent history period; and   the model obtains predicted physiological values as a function of a bounded initial condition that is influenced by a baseline measured physiological value obtained during the distant history period.   
     
     
         7 . The system of  claim 6 , wherein the baseline sensor glucose value is obtained during the begin-training sampling period. 
     
     
         8 . A processor-implemented method comprising:
 generating a model for predicting physiological values based on a plurality of measured physiological values obtained during a plurality of sampling periods;   operating a fluid infusion device in an automatic mode for automatically delivering fluid based on one or more physiological values;   obtaining a measured physiological value corresponding to a sampling period excluded from the plurality of sampling periods;   determining, based on the model, a predicted physiological value for the sampling period; and   switching operation of the fluid infusion device from the automatic mode to a manual mode when a difference between the measured physiological value and the predicted physiological value exceeds a threshold error amount.   
     
     
         9 . The method of  claim 8 , wherein the fluid infusion device is an insulin infusion device comprising an insulin reservoir for insulin to be delivered from the insulin infusion device. 
     
     
         10 . The method of  claim 8 , wherein:
 the measured physiological value comprises a sensor glucose value; and   the predicted physiological value comprises a predicted sensor glucose value.   
     
     
         11 . The method of  claim 10 , further comprising:
 estimating plasma insulin for the user based on current insulin-delivered data, historical insulin-delivered data, and an insulin basal rate for the user; and   obtaining predicted sensor glucose values based at least in part on the estimated plasma insulin.   
     
     
         12 . The method of  claim 8 , further comprising:
 generating an alert when the difference between the measured physiological value and the predicted physiological value exceeds the threshold error amount.   
     
     
         13 . The method of  claim 8 , wherein:
 a recent history period corresponds to a period of time from a begin-prediction sampling period to a most recent sampling period, inclusive;   a distant history period corresponds to a period of time from a begin-training sampling period to an end-training sampling period, inclusive;   the distant history period occurred before the recent history period; and   the model obtains predicted physiological values as a function of a bounded initial condition that is influenced by a baseline measured physiological value obtained during the distant history period.   
     
     
         14 . The method of  claim 13 , wherein the baseline sensor glucose value is obtained during the begin-training sampling period. 
     
     
         15 . One or more non-transitory processor-readable media storing instructions which, when executed by one or more processors, cause performance of:
 generating a model for predicting physiological values based on a plurality of measured physiological values obtained during a plurality of sampling periods;   operating a fluid infusion device in an automatic mode for automatically delivering fluid based on one or more physiological values;   obtaining a measured physiological value corresponding to a sampling period excluded from the plurality of sampling periods;   determining, based on the model, a predicted physiological value for the sampling period; and   switching operation of the fluid infusion device from the automatic mode to a manual mode when a difference between the measured physiological value and the predicted physiological value exceeds a threshold error amount.   
     
     
         16 . The one or more non-transitory processor-readable media of  claim 15 , wherein:
 the measured physiological value comprises a sensor glucose value; and   the predicted physiological value comprises a predicted sensor glucose value.   
     
     
         17 . The one or more non-transitory processor-readable media of  claim 16 , further storing instructions which, when executed by the one or more processors, cause performance of:
 estimating plasma insulin for the user based on current insulin-delivered data, historical insulin-delivered data, and an insulin basal rate for the user; and   obtaining predicted sensor glucose values based at least in part on the estimated plasma insulin.   
     
     
         18 . The one or more non-transitory processor-readable media of  claim 15 , further storing instructions which, when executed by the one or more processors, cause performance of:
 generating an alert when the difference between the measured physiological value and the predicted physiological value exceeds the threshold error amount.   
     
     
         19 . The one or more non-transitory processor-readable media of  claim 15 , wherein:
 a recent history period corresponds to a period of time from a begin-prediction sampling period to a most recent sampling period, inclusive;   a distant history period corresponds to a period of time from a begin-training sampling period to an end-training sampling period, inclusive;   the distant history period occurred before the recent history period; and   the model obtains predicted physiological values as a function of a bounded initial condition that is influenced by a baseline measured physiological value obtained during the distant history period.   
     
     
         20 . The one or more non-transitory processor-readable media of  claim 19 , wherein the baseline sensor glucose value is obtained during the begin-training sampling period.