# US 2023/0058548 A1 · System and method for predicting blood-glucose concentration

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0058548 A1
- Document ID: US20230058548A1
- Status: Published application
- Kind: A1
- Application number: 17/889,611
- Filed: 2022-08-17
- Published: 2023-02-23
- Earliest claimed: 2021-08-18
- Assignees: University of Houston System
- Applicants: University of Houston System
- Inventors: Marzia Cescon; Mehrad Jaloli
- Web page: https://patentgrep.com/patent/US20230058548A1

## CPC

- G16H 20/17: delivered via infusion or injection
- A61M 5/1723: {using feedback of body parameters, e.g. blood sugar or pressure}
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- A61M 2230/201: Glucose concentration
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- A61M: DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY (introducing media into or onto the bodies of animals A61D7/00; means for inserting tampons A61F13/26; devices for administering food or medicines orally A61J; containers for collecting, storing or administering blood or medical fluids A61J1/05); DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY (surgery A61B; chemical aspects of surgical articles A61L); DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR {(Electrotherapy, e.g. producing anaesthesia by the use of alternating or intermittent currents A61N1/36021)}

## Abstract

A system for predicting blood-glucose concentration includes a blood-glucose monitoring device including a sensor configured to capture blood-glucose levels, a processor, and a memory. The memory includes instructions, which, when executed by the processor, cause the system to: access data of meal intake for a person with type 1 diabetes, data of insulin doses administered to the person, data corresponding to a physical activity of the person, and data of blood-glucose levels in the person, captured by the sensor; predict by a deep learning network blood-glucose concentration levels for the person at predetermined time intervals based on the accessed data of meal intake, data of insulin doses, data corresponding to the physical activity, and data of blood-glucose levels in the person; and determine an insulin administration schedule based on the predicted blood-glucose concentration levels for the person, the insulin administration schedule including a dosing schedule.

## Claims

### Claim 1

A system for predicting blood-glucose concentration, comprising:
a blood-glucose monitoring device including at least one sensor configure to capture blood-glucose levels, a processor, and a memory storing instructions, which, when executed by the processor, cause the system to:
access data of meal intake for a person with type 1 diabetes;
access data of insulin doses administered to the person;
access data corresponding to a physical activity of the person;
access data of blood-glucose levels in the person, captured by the sensor;
predict by a deep learning network blood-glucose concentration levels for the person at a plurality of predetermined time intervals based on the accessed data of meal intake, the accessed data of insulin doses, the accessed data corresponding to the physical activity, and the accessed data of blood-glucose levels in the person, wherein the deep learning network may include a convolutional neural network feeding a long short-term memory network or at least two long short-term memory networks; and
determine an insulin administration schedule based on the predicted blood-glucose concentration levels for the person, the insulin administration schedule including a dosing schedule.

### Claim 2 (depends on 1)

The system of claim 1, further including an insulin pump,
wherein the instructions, when executed by the processor, further cause the system to:
cause the insulin pump to administer insulin according to the insulin administration schedule to the person.

### Claim 3 (depends on 1)

The system of claim 1, wherein the instructions, when executed by the processor, further cause the system to communicate the insulin administration schedule to the person.

### Claim 4 (depends on 1)

The system of claim 1, wherein the instructions, when executed by the processor, further cause the system to:
detect real-time blood glucose concentrations in the person during the insulin administration schedule and modifying the insulin administration schedule based on the detected real-time blood glucose concentrations in the person.

### Claim 5 (depends on 1)

The system of claim 1, wherein the data of meal intake accessed by the processor includes data of lipid, carbohydrate, and protein intake.

### Claim 6 (depends on 1)

The system of claim 1, wherein the instructions, when executed by the processor, further cause the system to:
predict blood-glucose concentration levels for the person at about 30-minute, about 60-minute, and about 90-minute time intervals.

### Claim 7 (depends on 1)

The system of claim 1, wherein the instructions, when executed by the processor, further cause the system to:
receive historical glucose metabolism data for the person and include the historical glucose metabolism data as a further input to the deep learning network.

### Claim 8 (depends on 1)

The system of claim 1, wherein the instructions, when executed by the processor, further cause the system to:
receive data of bolus doses and correction doses received by the person during a predetermined time period.

### Claim 9 (depends on 1)

The system of claim 1, further including at least one of a smartphone, tablet computer, or cloud-based application in communication with the blood-glucose monitoring device.

### Claim 10 (depends on 1)

The system of claim 1, wherein the deep learning network may include a convolutional neural network and a long short-term memory network.

### Claim 11

A computer-implemented method for predicting blood-glucose concentration, comprising:
accessing data of meal intake for a person with type 1 diabetes;
accessing data of insulin doses administered to the person;
accessing data corresponding to a physical activity of the person;
accessing data of blood-glucose levels in the person;
predicting by a deep learning network blood-glucose concentration levels for the person at a plurality of predetermined time intervals based on the accessed data of meal intake, the accessed data of insulin doses, the accessed data corresponding to the physical activity, and the accessed data of blood-glucose levels in the person, wherein the deep learning network may include a convolutional neural network feeding a long short-term memory network or at least two long short-term memory networks; and
determining an insulin administration schedule based on the predicted blood-glucose concentration levels for the person, the insulin administration schedule including a dosing schedule.

### Claim 12 (depends on 11)

The computer-implemented method of claim 11, further including administering insulin to the person according to the determined insulin administration schedule.

### Claim 13 (depends on 12)

The computer-implemented method of claim 12, wherein the insulin administered to the person is administered by an insulin pump.

### Claim 14 (depends on 12)

The computer-implemented method of claim 12, further including communicating the insulin administration schedule to the person.

### Claim 15 (depends on 12)

The computer-implemented method of claim 12, further including detecting real-time blood glucose concentrations in the person during the insulin administration schedule and modifying the insulin administration schedule based on the detected real-time blood glucose concentrations in the person.

### Claim 16 (depends on 11)

The computer-implemented method of claim 11, wherein the data of meal intake includes data of lipid, carbohydrate, and protein intake.

### Claim 17 (depends on 11)

The computer-implemented method of claim 11, wherein the plurality of predetermined time intervals includes about 30-minute, about 60-minute, and about 90-minute time intervals.

### Claim 18 (depends on 11)

The computer-implemented method of claim 11, further including providing historical glucose metabolism data for the person and including the historical glucose metabolism data as a further input to the deep learning network.

### Claim 19 (depends on 11)

The computer-implemented method of claim 11, wherein the data of insulin doses administered to the person include data of bolus doses and correction doses received by the person during a predetermined time period.

### Claim 20

A non-transitory computer-readable medium storing instructions which, when executed by a processor, cause the processor to perform a computer-implemented method for predicting blood-glucose concentration, comprising:
accessing data of meal intake for a person with type 1 diabetes;
accessing data of insulin doses administered to the person;
accessing data corresponding to a physical activity of the person;
accessing data of blood-glucose levels in the person;
predicting by a deep learning network blood-glucose concentration levels for the person at a plurality of predetermined time intervals based on the accessed data of meal intake, the accessed data of insulin doses, the accessed data corresponding to the physical activity, and the accessed data of blood-glucose levels in the person, wherein the deep learning network may include a convolutional neural network feeding a long short-term memory network or at least two long short-term memory networks; and
determining an insulin administration schedule based on the predicted blood-glucose concentration levels for the person, the insulin administration schedule including a dosing schedule.
