# US 2020/0286612 A1 · Autonomous management of a diabetic condition based on mealtime and activity detection

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

- Number: US 2020/0286612 A1
- Document ID: US20200286612A1
- Status: Published application
- Kind: A1
- Application number: 16/291,584
- Filed: 2019-03-04
- Published: 2020-09-10
- Earliest claimed: 2019-03-04
- Assignees: Roche Diabetes Care, Inc.
- Applicants: Roche Diabetes Care, Inc.
- Inventors: Mark Mears
- Web page: https://patentgrep.com/patent/US20200286612A1

## CPC

- G16H 20/60: relating to nutrition control, e.g. diets
- G06V 20/20: in augmented reality scenes
- G16H 20/17: delivered via infusion or injection
- G16H 40/63: for local operation
- G16H 50/30: for calculating health indices; for individual health risk assessment
- H04W 4/029: Location-based management or tracking services
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

Management of a diabetic condition may be performed by detecting a mealtime and/or an increased level of activity associated with a user. The mealtime is detected based one or more mealtime indicators that may indicate a likelihood of an occurrence of a mealtime. Each mealtime indicator provides additional context around the likelihood of a mealtime. To assist in managing the diabetic condition, a user's elevated activity levels may be detected. The activity level of a user is detected based on one or more activity indicators. Each activity indicator provides additional context around the likelihood of an increased level of activity by the user. Management of the diabetic condition may be performed proximate a mealtime or a user exercising to increase the efficacy of management of the diabetic condition.

## Claims

### Claim 1

A method comprising:
determining a mealtime score based on a presence of at least three mealtime detection indicators associated with a user, wherein the mealtime detection indicators associated with the user comprise at least three of:
a predefined meal-time indicator set within a range of estimated mealtimes associated with the user;
a location indicator that indicates a location of a mobile device associated with the user;
a position indicator that indicates the user is in a sitting position;
a blood glucose indicator that indicates a blood-glucose level of the user is below a predefined threshold;
a photograph indicator that indicates a photograph is taken of a plate or food; or
a keyword indicator that indicates a keyword of a pre-scheduled event comprises at least one of a meal-related word or a meal-related location;
providing at least one mealtime alert to the user to assist in treatment of a diabetic condition in response to the mealtime score being above a mealtime threshold; and
controlling a basal rate of an insulin pump after detection of a mealtime based on the mealtime score.

### Claim 2 (depends on 1)

The method of claim 1, wherein the mealtime score is determined based on a weight associated with each of the at least three mealtime detection indicators.

### Claim 3 (depends on 1)

The method of claim 1, wherein the position indicator is based on information from a gyroscope or an accelerometer of the mobile device of the user.

### Claim 4 (depends on 1)

The method of claim 1, wherein the blood glucose indicator is based on information from a glucose meter associated with the user.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
identifying at least one similarity between the photograph taken by a camera of the mobile device and prestored images; and
generating the photograph indicator in response to the at least one similarity being above a predefined threshold, wherein the predefined threshold comprises a number of similarities or a percentage of the photograph that is similar to the prestored images.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
identifying at least one of a distance or an angle between a camera of the mobile device and the plate or food in the photograph based on Exchangeable image file format (Exif) metadata in the photograph; and
generating the photograph indicator in response to the distance being less than a predetermined threshold or to the angle being within a predetermined range.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
detecting an activity level associated with the user is above an activity threshold based on information from the mobile device associated with the user; and
controlling the basal rate of the insulin pump while the activity level is above an activity threshold and the keyword indicator indicates when another keyword of another pre-scheduled event comprises an activity-related word.

### Claim 8 (depends on 1)

The method of claim 1, wherein the keyword is mined from a title or a location of a calendar event or a social media site associated with the user.

### Claim 9 (depends on 8)

The method of claim 8, wherein the keyword comprises the meal-related word mined from the title of the calendar event, the method further comprising:
matching the keyword to a dataset of keywords associated with a mealtime in order to estimate when the mealtime is to occur for the user, wherein the at least one reminder comprises a reminder to the user regarding a food choice for the mealtime or diabetes-related treatment behaviors.

### Claim 10 (depends on 8)

The method of claim 8, wherein the keyword comprises the meal-related location mined from the location of the calendar event, the method further comprising:
matching the keyword to a dataset of meal-related words in order to estimate when the mealtime is to occur for the user, wherein the at least one mealtime alert comprises a reminder to the user regarding a food choice for the mealtime or diabetes-related treatment behaviors.

### Claim 11 (depends on 8)

The method of claim 8, wherein the keyword comprises the meal-related word and the meal-related location, wherein the meal-related location comprises a street address, the method comprising:
matching the street address of the calendar event to a dataset of locations; and
matching the meal-related word to a dataset of meal-related words in order to estimate when the mealtime is to occur for the user at the meal-related location, wherein the at least one mealtime alert comprises a reminder to the user regarding a food choice for the mealtime or diabetes-related treatment behaviors based on the meal-related location.

### Claim 12 (depends on 1)

The method of claim 1, further comprising:
cross-referencing the location of the mobile device with a dataset of meal-related locations to determine that the user is at the meal-related location.

### Claim 13 (depends on 1)

The method of claim 1, further comprising:
determining an activity score based on at least one of the activity level, the keyword indicator indicating another keyword of another pre-scheduled event comprising an activity-related word, or the location indicator; and
controlling the basal rate of the insulin pump when the activity score is above an activity threshold.

### Claim 14 (depends on 1)

The method of claim 1, wherein the location indicator is generated based on a GPS location of the mobile device associated with the user being in a location of a known restaurant.

### Claim 15 (depends on 1)

The method of claim 1, wherein the at least one mealtime alert comprises a reminder to take medication, a reminder to take vitamins, a reminder to measure pre-meal blood glucose, a reminder to take post-meal blood glucose, a reminder to record an amount of carbohydrates, or a reminder to record dimensions associated with a meal.

### Claim 16 (depends on 1)

The method of claim 1, further comprising:
detecting, prior to determining the mealtime score, that a current time is at least a predefined period of time since a last mealtime associated with the user.

### Claim 17 (depends on 1)

The method of claim 1, wherein the mobile device comprises a smartphone, a tablet, a wearable device, or a diabetes-related monitoring device.

### Claim 18 (depends on 17)

The method of claim 17, wherein the diabetes-related monitoring device is a glucose meter.

### Claim 19 (depends on 17)

The method of claim 17, wherein the wearable device is a smart watch.

### Claim 20

A method comprising:
determining a mealtime score based on a presence of at least three mealtime detection indicators associated with a user, wherein the mealtime detection indicators associated with the user comprise at least three of: a predefined meal-time indicator set within a range of estimated mealtimes associated with the user, a location indicator that indicates a location of a mobile device associated with the user, a position indicator that indicates the user is in a sitting position, a blood glucose indicator that indicates a blood-glucose level of the user is below a predefined threshold, a photograph indicator that indicates a photograph is taken of a plate or food, or a keyword indicator that indicates a keyword of a pre-scheduled event comprises at least one of a meal-related word or a meal-related location; and
providing at least one mealtime alert to the user to assist in treatment of a diabetic condition in response to the mealtime score being above a mealtime threshold.

### Claim 21

A mobile device comprising:
a communication circuit; and
a processor configured to:
determine a mealtime score based on a presence of at least three mealtime detection indicators associated with a user, wherein the mealtime detection indicators associated with the user comprise at least three of: a predefined meal-time indicator set within a range of estimated mealtimes associated with the user, a location indicator that indicates a location of the mobile device, a position indicator that indicates the user is in a sitting position, a blood glucose indicator that indicates a blood-glucose level of the user is below a predefined threshold, a photograph indicator that indicates a photograph is taken of a plate or food, or a keyword indicator that indicates a keyword of a pre-scheduled event comprises at least one of a meal-related word or a meal-related location;
provide at least one mealtime alert to the user to assist in treatment of a diabetic condition in response to the mealtime score being above a mealtime threshold; and
send, via the communication circuit, a message to control a basal rate of an insulin pump after detection of a mealtime based on the mealtime score.
