METHOD AND SYSTEM FOR RECOMMENDING A SET OF INSULIN DOSAGES FOR A PATIENT

• US 20170263156A1
• Filed: 03/08/2016
• Published: 09/14/2017
• Est. Priority Date: 03/08/2016
• Status: Abandoned Application

• Current Assignee: Quattro Folia Oy
• Original Assignee: Quattro Folia Oy
• Inventors: Lnnroth, Pekka, Sinisalo, Ari, Okkonen, Harri, Visnen, Petteri, Carpelan, Paulus
• Application Number:
  US15/063,893
• Publication Number:
  US 20170263156A1
• Time in Patent Office: Days
• CPC Class Codes: G09B 19/0092 Nutrition
• CPC Class Codes: G09B 23/28 for medicine
• CPC Class Codes: G16H 20/17 delivered via infusion or injection
• CPC Class Codes: G16H 40/63 for local operation

Abstract

Disclosed is a method and system for recommending a set of insulin dosages for a patient. The method estimates a blood glucose level of the patient using a physiological glucose-insulin module based on a set of patient-related information. Thereafter, an insulin dosage calculator calculates the set of insulin dosages based on an output of the physiological glucose-insulin module and contextual information associated with the patient. Finally, the set of insulin dosages are presented to the patient.

Claims

1. A computer implemented method for recommending a set of insulin dosages for a patient, the computer implemented method comprising:

estimating a blood glucose level of the patient using a physiological glucose-insulin module, the physiological glucose-insulin module estimating the continuous blood glucose level based on a set of patient-related information;

calculating the set of insulin dosages using an insulin dosage calculator based on an output of the physiological glucose-insulin module and contextual information associated with the patient; and

presenting the set of insulin dosages for the patient.

2. The computer implemented method of claim 1, wherein the set of insulin dosages comprises at least one of a basal insulin, bolus insulin and correction insulin.

3. The computer implemented method of claim 1, wherein the patient-related information comprises at least one of Self-Monitor Blood Glucose (SMBG) values, a meal plan and an activity plan.

4. The computer implemented method of claim 1, wherein the contextual information associated with the patient comprises at least one of general health details, a stress level, an activity plan of the patient'"'"'s social network connections, weather forecast, and presence of allergens.

5. The computer implemented method of claim 1, wherein at least one parameter of the physiological glucose-insulin module is automatically defined for each patient.

6. The computer implemented method of claim 1, wherein the insulin dosage calculator uses a heuristic search algorithm for calculating the set of insulin dosages, the heuristic search algorithm being one of a Monte Carlo Tree Search (MCTS), a genetic algorithm and a combination of the MCTS and the genetic algorithm.

7. The computer implemented method of claim 6 further comprising:

monitoring at least one of an actual meal consumed by the patient in a day, an actual activity performed by the patient in a day and actual events occurred in a day; and

storing the actual meal consumed by the patient in the day, the actual activity performed by the patient in the day, actual events occurred in the day and the set of insulin dosages recommended for the day in a daily routine database.

8. The computer implemented method of claim 7, wherein the insulin dosage calculator uses at least a part of data from the daily routine database to further refine calculation of the set of insulin dosages.

9. The computer implemented method of claim 1, wherein the physiological glucose-insulin module is based on an artificial intelligence system comprising at least one of a back propagation artificial neural network, fuzzy logic system, and combination of the back propagation artificial neural network and fuzzy logic system forming a hybrid intelligent system (‘

Neuro-Fuzzy’

).

10. The computer implemented method of claim 1, wherein the presenting the set of insulin dosages comprises at least one of:

displaying the set of insulin dosages to the patient; and

rendering the set of insulin dosages as one of an audio message, a visual message and an audiovisual message to the patient.

11. The computer implemented method of claim 1 further comprising transmitting the set of insulin dosages to an administering unit configured to administer the insulin dosage to the patient.

12. The computer implemented method of claim 1, wherein the set of insulin dosages is recommended for a period of 24 hours.

13. A system for recommending a set of insulin dosages for a patient, the system comprising:

a data acquisition unit, wherein the data acquisition unit is configured to acquire a set of patient-related information and contextual information with the patient; and

a physiological glucose-insulin module, wherein the physiological glucose-insulin module is configured to continuously estimate a blood glucose level of the patient based on the set of patient-related information;

an insulin dosage calculator, wherein the insulin dosage calculator is configured to calculate the set of insulin dosages based on an output of the physiological glucose-insulin module and the contextual information associated with the patient; and

a presentation unit configured to present the set of insulin dosages for the patient.

14. The system of claim 13, wherein the insulin dosage calculator uses a heuristic search algorithm for calculating the set of insulin dosages, the heuristic search algorithm being one of a Monte Carlo Tree Search (MCTS), a genetic algorithm and a combination of the MCTS and the genetic algorithm.

15. The system of claim 13, wherein the data acquisition unit is further configured to:

monitor at least one of an actual meal consumed by the patient in a day, an actual activity performed by the patient in a day and actual events occurred in a day; and

store the actual meal consumed by the patient in the day, the actual activity performed by the patient in the day, actual events occurred in the day and the set of insulin dosages recommended for the day in a daily routine database.

16. A non-transitory computer readable medium storing a computer program for causing a computing device to perform a method of recommending a set of insulin dosages for a patient, the method comprising;

estimating a blood glucose level of the patient using a physiological glucose-insulin module, the physiological glucose-insulin module estimating the continuous blood glucose level based on a set of patient-related information;

calculating the set of insulin dosages using an insulin dosage calculator based on an output of the physiological glucose-insulin module and contextual information associated with the patient; and

presenting the set of insulin dosages for the patient.