INFUSION SYSTEMS AND RELATED PERSONALIZED BOLUSING METHODS
Techniques for contextual adjustment of insulin adjustment curves are provided. In some embodiments, the techniques may involve identifying a reference insulin absorption parameter for a patient based on demographic information. The techniques may further involve determining an adjusted insulin absorption parameter based on the reference insulin absorption parameter and context of the patient. The techniques may further involve delivering insulin to the patient based on the adjusted insulin absorption parameter.
1 . A processor-implemented method comprising:
identifying a reference insulin absorption parameter for a patient based on demographic information;
determining an adjusted insulin absorption parameter based on the reference insulin absorption parameter and context of the patient; and
delivering insulin to the patient based on the adjusted insulin absorption parameter.
2 . The method of claim 1 , wherein determining the adjusted insulin absorption parameter is based at least in part on relationships between historical insulin on board (IOB) data and prior bolus events.
3 . The method of claim 1 , wherein determining the adjusted insulin absorption parameter comprises:
providing the reference insulin absorption parameter as input to an insulin absorption model; and
determining the adjusted insulin absorption parameter based on the insulin absorption model.
4 . The method of claim 3 , wherein the insulin absorption model is derived based on relationships between historical insulin on board (IOB) time series data, historical contextual adjustment factor data, and historical reference insulin absorption curves associated with prior bolus events.
5 . The method of claim 4 , wherein the historical IOB time series data is optimized based on minimizing cumulative differences between simulated glucose levels and historical glucose measurement data of the patient.
6 . The method of claim 1 , wherein the reference insulin absorption parameter is associated with a patient cluster corresponding to the demographic information.
7 . The method of claim 1 , further comprising:
determining a contextual adjustment factor by providing the context for the patient as input to a model for predicting how the context will affect an insulin absorption rate of the patient; and
identifying the contextual adjustment factor based on the model.
8 . The method of claim 1 , wherein the context for the patient includes at least one of a group comprising a time of day, a day of the week, a geographic location, and an activity level of the patient.
9 . A system comprising:
one or more processors; and
one or more processor-readable storage media storing instructions which, when executed by the one or more processors, cause performance of:
identifying a reference insulin absorption parameter for a patient based on demographic information;
determining an adjusted insulin absorption parameter based on the reference insulin absorption parameter and context of the patient; and
delivering insulin to the patient based on the adjusted insulin absorption parameter.
10 . The system of claim 9 , wherein determining the adjusted insulin absorption parameter is based at least in part on relationships between historical insulin on board (IOB) data and prior bolus events.
11 . The system of claim 9 , wherein determining the adjusted insulin absorption parameter comprises:
providing the reference insulin absorption parameter as input to an insulin absorption model; and
determining the adjusted insulin absorption parameter based on the insulin absorption model.
12 . The system of claim 11 , wherein the insulin absorption model is derived based on relationships between historical insulin on board (IOB) time series data, historical contextual adjustment factor data, and historical reference insulin absorption curves associated with prior bolus events.
13 . The system of claim 12 , wherein the historical IOB time series data is optimized based on minimizing cumulative differences between simulated glucose levels and historical glucose measurement data of the patient.
14 . The system of claim 9 , wherein the reference insulin absorption parameter is associated with a patient cluster corresponding to the demographic information.
15 . The system of claim 9 , wherein the instructions further cause performance of:
determining a contextual adjustment factor by providing the context for the patient as input to a model for predicting how the context will affect an insulin absorption rate of the patient; and
identifying the contextual adjustment factor based on the model.
16 . The system of claim 9 , wherein the context for the patient includes at least one of a group comprising a time of day, a day of the week, a geographic location, and an activity level of the patient.
17 . A processor-implemented method comprising:
determining an insulin absorption parameter based on a reference insulin absorption parameter and context of a patient;
determining a bolus insulin dosage based on the insulin absorption parameter; and
delivering insulin to the patient based on the determined bolus insulin dosage.
18 . The method of claim 17 , wherein the insulin absorption parameter is based on an estimate of the insulin on board (IOB) at a time the bolus insulin dosage is to be delivered.
19 . The method of claim 17 , wherein the reference insulin absorption parameter is based on demographic data associated with the patient.
20 . The method of claim 19 . wherein the insulin absorption parameter is determined using a model that relates demographic variables of the demographic data to insulin absorption metrics.