Diabetes management therapy advisor
A method includes obtaining training data for a plurality of patients of a patient population. The training data includes training blood glucose history data including treatment doses of insulin administered by the patients of the patient population and one or more outcome attributes associated with each treatment dose. The method also includes identifying, for each patient of the patient population, one or more optimum treatment doses of insulin from the treatment doses yielding favorable outcome attributes. The method also includes receiving patient-state information for the treated patient, determining a next recommended treatment dose of insulin for the treated patient based on one or more of the identified optimum treatment doses associated with the patients of the patient population having training patient-state information similar to the patient-state information for the treated patient, and transmitting the next recommended treatment dose to a portable device associated with the treated patient.
1. A computer-implemented method executed on data processing hardware that causes the data processing hardware to perform operations comprising:
obtaining training data for a plurality of patients of a patient population from memory hardware in communication with the data processing hardware, the training data comprising, for each particular patient of the patient population:
one or more ADM dose-combinations administered to the particular patient;
a corresponding outcome attribute associated with each of the one or more ADM dose-combinations administered to the particular patient; and
corresponding training patient-state information;
processing the training data for each of the plurality of patients of the patient population to train a predictive model capable of predicting ADM dose-combinations for a patient being treated;
for each particular patient of the patient population, identifying, using the trained predictive model, a corresponding optimum ADM dose-combination that yields a corresponding outcome attribute associated with bringing and maintaining a corresponding glucose level of the particular patient closest to a glucose target center of a glucose target range;
receiving patient-state information for the patient being treated;
identifying a subset of the patients of the patient population having corresponding training patient-state information similar to the received patient-state information for the patient being treated;
determining a recommended ADM dose-combination for the patient being treated based on the corresponding optimum ADM dose-combinations identified for the identified subset of the patients, the ADM dose-combination comprising a particular dosage of a particular ADM; and
transmitting instructions to an administration device associated with the patient to administer the recommended ADM dose-combination to the patient being treated, the instructions, when received by the administration device, causing the administration device to administer the recommended ADM dose-combination to the patient being treated.
2. The method of claim 1 , wherein obtaining the training data comprises obtaining the training data periodically at an end of a re-occurring configurable time interval.
3. The method of claim 1 , wherein obtaining the training data comprises obtaining the training data immediately in response to a user input selecting an immediate start button displayed upon a display in communication with the data processing hardware.
4. The method of claim 1 , wherein obtaining the training data comprises obtaining the training data on a selected date.
5. The method of claim 1 , wherein the corresponding outcome attributes associated with the one or more ADM dose-combinations administered to the particular patient comprises a glycated hemoglobin measurement associated with the one or more ADM dose-combinations administered to the particular patient.
6. The method of claim 5 , wherein the operations further comprise:
receiving a glycated hemoglobin measurement for the patient being treated,
wherein determining the recommended ADM dose-combination for the patient being treated is further based on the glycated hemoglobin measurement for the patient being treated.
7. The method of claim 1 , wherein the recommended ADM dose-combination comprises a non-insulin dose-combination.
8. The method of claim 1 , wherein the recommended ADM dose-combination comprises a dual- or triple-therapy including insulin and at least one non-insulin ADM.
9. The method of claim 1 , wherein at least one of the ADM dose-combinations for at least one corresponding patient of the patient population comprises a dual-therapy including an ADM dose-combination comprising two ADMs.
10. The method of claim 1 , wherein at least one of the ADM dose-combinations for at least one corresponding patient of the patient population comprises a triple-therapy including a ADM dose-combination comprising two ADMs.
11. The method of claim 1 , wherein the patient being treated is diagnosed with Type 2 diabetes mellitus.
12. The method of claim 1 , wherein the patient-state information for a patient comprises a plurality of patient-state attributes associated with the patient, the patient-state attributes including one or more of an age, a gender, a medical history, a body mass index, a medical history, risk factors, and/or financial attributes.
13. A system comprising:
a dosing controller including data processing hardware and memory hardware in communication with the data processing hardware, the memory hardware storing instructions that, when executed by the data processing hardware, cause the dosing controller to perform operations comprising:
obtaining training data for a plurality of patients of a patient population from memory hardware in communication with the data processing hardware, the training data comprising, for each particular patient of the patient population:
one or more ADM dose-combinations administered to the particular patient;
a corresponding outcome attribute associated with each of the one or more ADM dose-combinations administered to the particular patient; and
corresponding training patient-state information;
processing the training data for each of the plurality of patients of the patient population to train a predictive model capable of predicting ADM dose-combinations for a patient being treated;
for each particular patient of the patient population, identifying, using the trained predictive model, a corresponding optimum ADM dose-combination that yields a corresponding outcome attribute associated with bringing and maintaining a corresponding glucose level of the particular patient closest to a glucose target center of a glucose target range;
receiving patient-state information for the patient being treated;
identifying a subset of the patients of the patient population having corresponding training patient-state information similar to the received patient-state information for the patient being treated;
determining a recommended ADM dose-combination for the patient being treated based on the corresponding optimum ADM dose-combinations identified for the identified subset of the patients, the ADM dose-combination comprising a particular dosage of a particular ADM; and
transmitting instructions to an administration device associated with the patient to administer the recommended ADM dose-combination to the patient being treated, the instructions, when received by the administration device, causing the administration device to administer the recommended ADM dose-combination to the patient being treated.
14. The system of claim 13 , wherein obtaining the training data comprises obtaining the training data periodically at an end of a re-occurring configurable time interval.
15. The system of claim 13 , wherein obtaining the training data comprises obtaining the training data immediately in response to a user input selecting an immediate start button displayed upon a display in communication with the data processing hardware.
16. The system of claim 13 , wherein obtaining the training data comprises obtaining the training data on a selected date.
17. The system of claim 13 , wherein the corresponding outcome attributes associated with the one or more ADM dose-combinations administered to the particular patient comprises a glycated hemoglobin measurement associated with the one or more ADM dose-combinations administered to the particular patient.
18. The system of claim 17 , wherein the operations further comprise:
receiving a glycated hemoglobin measurement for the patient being treated,
wherein determining the recommended ADM dose-combination for the patient being treated is further based on the glycated hemoglobin measurement for the patient being treated.
19. The system of claim 13 , wherein the recommended ADM dose-combination comprises a non-insulin dose-combination.
20. The system of claim 13 , wherein the recommended ADM dose-combination comprises a dual- or triple-therapy including insulin and at least one non-insulin ADM.
21. The system of claim 13 , wherein at least one of the ADM dose-combinations for at least one corresponding patient of the patient population comprises a dual-therapy including an ADM dose-combination comprising two ADMs.
22. The system of claim 13 , wherein at least one of the ADM dose-combinations for at least one corresponding patient of the patient population comprises a triple-therapy including a ADM dose-combination comprising two ADMs.
23. The system of claim 13 , wherein the patient being treated is diagnosed with Type 2 diabetes mellitus.
24. The system of claim 13 , wherein the patient-state information for a patient comprises a plurality of patient-state attributes associated with the patient, the patient-state attributes including one or more of an age, a gender, a medical history, a body mass index, a medical history, risk factors, and/or financial attributes.