Predicted time to assess and/or control a glycemic state
View Patent ↗Presented here are techniques for controlling glucose levels of a patient based on predicted time to a target glucose level. One methodology predicts a trajectory of the blood glucose level based on past observations of the blood glucose level, determines a cost expression based on the trajectory, and affects a future command to an infusion pump to affect a cost value according to the cost expression. Another methodology defines a target blood glucose concentration level for the patient, observes a current blood glucose concentration for the patient based on signals received from a blood-glucose sensor, and predicts a duration of time for the patient's blood glucose concentration to reach the target blood glucose concentration level based on the observed current blood glucose concentration.
1. A method comprising:
defining a plurality of different target blood glucose concentration levels for a patient;
assigning a plurality of different threshold time periods to the target blood glucose concentration levels, resulting in a plurality of different time-to-target checkpoints for the target blood glucose concentration levels, each of the plurality of different time-to-target checkpoints having a respective glucose control system operation associated therewith;
observing a current blood glucose concentration for the patient based, at least in part, on signals received from a blood-glucose sensor;
predicting a respective duration of time for the patient's blood glucose concentration to reach each of the target blood glucose concentration levels using the observed current blood glucose concentration;
identifying which of the target blood glucose concentration levels is predicted to be reached first in time, based on the predicting step;
comparing the predicted duration of time for the identified target blood glucose concentration level against the threshold time periods of the plurality of different time-to-target checkpoints of the identified target blood glucose concentration level, to determine an operation of the glucose control system based on the predicted duration of time and the plurality of different time-to-target checkpoints; and
altering a therapy applied to the patient based on the determined operation of the glucose control system.
2. The method of claim 1 , wherein the target blood glucose concentration level is within upper and lower bounds of a target blood glucose concentration range.
3. The method of claim 1 , wherein predicting the duration of time comprises:
predicting the duration of time based, at least in part, on one or more parameters representing a sensitivity of the patient to insulin.
4. The method of claim 1 , wherein predicting the duration of time comprises:
predicting the duration of time based, at least in part, on an expected change in a rate of infusion of insulin.
5. The method of claim 1 , wherein altering the therapy comprises one or more of:
changing a rate of insulin infusion;
transmitting a command signal to an insulin infusion pump; and
administering glucose to the patient.
6. An article comprising:
a non-transitory storage medium comprising machine-readable instructions stored thereon which are executable by a special purpose computing device to:
define a plurality of different target blood glucose concentration levels for a patient;
assign a plurality of different threshold time periods to the target blood glucose concentration levels, resulting in a plurality of different time-to-target checkpoints for the target blood glucose concentration levels, each of the plurality of different time-to-target checkpoints having a respective glucose control system operation associated therewith;
observe a current blood glucose concentration for the patient based, at least in part, on signals received from a blood-glucose sensor;
predict a respective duration of time for the patient's blood glucose concentration to reach each of the target blood glucose concentration levels using the observed current blood glucose concentration;
identify which of the target blood glucose concentration levels is predicted to be reached first in time, based on the predicting;
compare the predicted duration of time for the identified target blood glucose concentration level against the threshold time periods of the plurality of different time-to-target checkpoints of the identified target blood glucose concentration level, to determine an operation of the glucose control system based on the predicted duration of time and the plurality of different time-to-target checkpoints; and
alter a therapy applied to the patient based on the determined operation of the glucose control system.
7. A method comprising:
defining a plurality of different target blood glucose concentration levels for a patient;
observing a current blood glucose concentration for the patient based, at least in part, on signals received from a blood-glucose sensor;
predicting a respective duration of time for the patient's blood glucose concentration to reach each of the target blood glucose concentration levels using the observed current blood glucose concentration;
identifying which of the target blood glucose concentration levels is predicted to be reached first in time, based on the predicting step;
determining an operation of the glucose control system based on the identified target blood glucose concentration level and the predicted duration of time for the identified target blood glucose concentration level; and
altering a therapy applied to the patient based on the determined operation of the glucose control system.