Glucose level management based on fat content of meals
Techniques for glucose level management are disclosed. In some examples, the techniques may involve obtaining an estimated protein value for a meal and determining an equivalent carbohydrate value for the meal based on the estimated protein value. In some examples, the techniques may involve obtaining an estimated fat value for a meal and determining, based on the estimated fat value, a glucose absorption rate resulting from consumption of the meal. In some examples, the equivalent carbohydrate value and/or the glucose absorption rate may be used to determine an amount of insulin to deliver to a patient to counteract a glucose level increase caused by consumption of the meal. The techniques may further involve generating an output indicative of the amount of insulin to deliver to the patient to counteract the glucose level increase caused by consumption of the meal.
1. A system comprising:
an insulin infusion device;
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:
obtaining an estimated fat value for a meal;
determining, based on the estimated fat value, a glucose absorption rate resulting from consumption of the meal by using a patient-specific parameter to determine the glucose absorption rate that is scaled between two values;
predicting, using a patient-specific physiological simulator and based on the glucose absorption rate, amounts of glucose to be absorbed in a bloodstream of the patient and a glucose level increase over a period of time that is caused by the consumption of the meal;
determining, based on the predicted amounts of glucose to be absorbed in the bloodstream of the patient and the predicted glucose level increase over the period of time, an amount of insulin to deliver to a patient that counteracts the predicted glucose level increase over the period of time that is caused by consumption of the meal;
generating an output indicative of the amount of insulin to deliver to the patient to counteract the glucose level increase caused by consumption of the meal; and
delivering, by the insulin infusion device, the determined amount of insulin to the patient based on the output.
2. The system of claim 1 , wherein determining the amount of insulin to deliver to the patient comprises:
determining, based on the predicted amounts of glucose to be absorbed into the bloodstream, a bolus dosage of insulin to deliver to the patient.
3. The system of claim 2 , wherein determining the amount of insulin to deliver to the patient comprises:
prior to determining the bolus dosage, obtaining an amount of a basal dosage of insulin previously delivered to the patient, and wherein determining the bolus dosage is further based on the amount of the basal dosage of insulin.
4. The system of claim 2 , wherein determining the bolus dosage comprises:
identifying a plurality of candidate dosages;
for each candidate dosage of the plurality of candidate dosages, predicting a respective amount of time within a target range for the patient's glucose levels; and
selecting a candidate dosage that corresponds to a maximum amount of time within the target range.
5. The system of claim 1 , wherein determining the glucose absorption rate comprises:
determining an absorption rate tuning factor for approximating an effect of fat on the glucose absorption rate, wherein the absorption rate tuning factor is the patient-specific parameter; and
determining the glucose absorption rate based on the estimated fat value for the meal and the absorption rate tuning factor.
6. The system of claim 5 , wherein the absorption rate tuning factor is determined based on historical meal data for the patient and further based on historical glucose level data for the patient.
7. The system of claim 1 , wherein determining the amount of insulin to deliver to the patient comprises:
determining, based on the glucose absorption rate, a peak of the glucose level increase caused by consumption of the meal; and
determining, based on the peak, the amount of insulin to deliver to the patient.
8. The system of claim 1 , wherein determining the amount of insulin to deliver to the patient comprises:
determining, based on the glucose absorption rate, a timing for a peak of the glucose level increase caused by consumption of the meal; and
determining, based on the timing for the peak, the amount of insulin to deliver to the patient.
9. A processor-implemented method comprising:
obtaining an estimated fat value for a meal;
determining, based on the estimated fat value, a glucose absorption rate resulting from consumption of the meal by using a patient-specific parameter to determine the glucose absorption rate that is scaled between two values;
predicting, using a patient-specific physiological simulator and based on the glucose absorption rate, amounts of glucose to be absorbed in a bloodstream of the patient and a glucose level increase over a period of time that is caused by the consumption of the meal;
determining, based on the predicted amounts of glucose to be absorbed in the bloodstream of the patient and the predicted glucose level increase over the period of time, an amount of insulin to deliver to a patient that counteracts the predicted glucose level increase over the period of time that is caused by consumption of the meal;
generating an output indicative of the amount of insulin to deliver to the patient to counteract the glucose level increase caused by consumption of the meal; and
delivering, by an insulin infusion device, the determined amount of insulin to the patient based on the output.
10. The method of claim 9 , wherein determining the amount of insulin to deliver to the patient comprises:
determining, based on the predicted amounts of glucose to be absorbed into the bloodstream, a bolus dosage of insulin to deliver to the patient.
11. The method of claim 10 , wherein determining the amount of insulin to deliver to the patient comprises:
prior to determining the bolus dosage, obtaining an amount of a basal dosage of insulin previously delivered to the patient, and wherein determining the bolus dosage is further based on the amount of the basal dosage of insulin.
12. The method of claim 10 , wherein determining the bolus dosage comprises:
identifying a plurality of candidate dosages;
for each candidate dosage of the plurality of candidate dosages, predicting a respective amount of time within a target range for the patient's glucose levels; and
selecting a candidate dosage that corresponds to a maximum amount of time within the target range.
13. The method of claim 9 , wherein determining the glucose absorption rate comprises:
determining an absorption rate tuning factor for approximating an effect of fat on the glucose absorption rate, wherein the absorption rate tuning factor is the patient-specific parameter; and
determining the glucose absorption rate based on the estimated fat value for the meal and the absorption rate tuning factor.
14. The method of claim 13 , wherein the absorption rate tuning factor is determined based on historical meal data for the patient and further based on historical glucose level data for the patient.
15. The method of claim 9 , wherein determining the amount of insulin to deliver to the patient comprises:
determining, based on the glucose absorption rate, a peak of the glucose level increase caused by consumption of the meal; and
determining, based on the peak, the amount of insulin to deliver to the patient.
16. The method of claim 9 , wherein determining the amount of insulin to deliver to the patient comprises:
determining, based on the glucose absorption rate, a timing for a peak of the glucose level increase caused by consumption of the meal; and
determining, based on the timing for the peak, the amount of insulin to deliver to the patient.
17. One or more non-transitory processor-readable storage media storing instructions which, when executed by one or more processors, cause performance of:
obtaining an estimated fat value for a meal;
determining, based on the estimated fat value, a glucose absorption rate resulting from consumption of the meal by using a patient-specific parameter to determine the glucose absorption rate that is scaled between two values;
predicting, using a patient-specific physiological simulator and based on the glucose absorption rate, amounts of glucose to be absorbed in a bloodstream of the patient and a glucose level increase over a period of time that is caused by the consumption of the meal;
determining, based on the predicted amounts of glucose to be absorbed in the bloodstream of the patient and the predicted glucose level increase over the period of time, an amount of insulin to deliver to a patient that counteracts the predicted glucose level increase over the period of time that is caused by consumption of the meal;
generating an output indicative of the amount of insulin to deliver to the patient to counteract the glucose level increase caused by consumption of the meal; and
delivering, by an insulin infusion device, the determined amount of insulin to the patient based on the output.
18. The one or more non-transitory processor-readable storage media of claim 17 , wherein determining the glucose absorption rate comprises:
determining an absorption rate tuning factor for approximating an effect of fat on the glucose absorption rate, wherein the absorption rate tuning factor is the patient-specific parameter; and
determining the glucose absorption rate based on the estimated fat value for the meal and the absorption rate tuning factor.
19. The one or more non-transitory processor-readable storage media of claim 18 , wherein the absorption rate tuning factor is determined based on historical meal data for the patient and further based on historical glucose level data for the patient.
20. The one or more non-transitory processor-readable storage media of claim 17 , wherein determining the amount of insulin to deliver to the patient comprises:
determining, based on the glucose absorption rate, a timing for a peak of the glucose level increase caused by consumption of the meal; and
determining, based on the timing for the peak, the amount of insulin to deliver to the patient.