Monitoring and treatment dosage prediction system

• US 10,657,224 B2
• Filed: 06/02/2016
• Issued: 05/19/2020
• Est. Priority Date: 09/25/2015
• Status: Active Grant

• Current Assignee: Accenture Global Solutions Limited (Accenture PLC)
• Original Assignee: Accenture Global Solutions Limited (Accenture PLC)
• Inventors: Hoglund, Jonas, Johansson, Henrik, Mbanefo, Primrose, O'Kane, Matthew
• Primary Examiner(s): Morgan, Robert W
• Assistant Examiner(s): Coleman, Charles P
• Application Number:
  US15/171,813
• Publication Number:
  US 20170091419A1
• Time in Patent Office: 1,447 Days
• Field of Search: 705 2, 705 3, 705 20
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 20/13 delivered from dispensers
• CPC Class Codes: G16H 20/17 delivered via infusion or injection
• CPC Class Codes: G16H 20/30 relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
• CPC Class Codes: G16H 20/60 relating to nutrition control, e.g. diets
• CPC Class Codes: G16H 20/70 relating to mental therapies, e.g. psychological therapy or autogenous training
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders

Abstract

A device may receive lifestyle information corresponding to an individual with a medical condition. The device may create a lifestyle timeline, associated with the individual, that includes a plurality of items of lifestyle information, included in the lifestyle information, arranged in a chronological order. The device may generate, based on the lifestyle timeline, a recommendation or a prediction associated with a metric related to the medical condition. The recommendation may be generated based on one or more of the plurality of items of lifestyle information. The prediction may be generated using a prediction model that uses one or more of the plurality of items of lifestyle information as input, and generates the prediction using the prediction model. The device may provide information associated with the recommendation or the prediction to identify a dosage associated with treating or managing the medical condition.

Claims

1. A method, comprising:

receiving, by a device and from at least one of a sensor of a user device or a server device via a network, lifestyle information corresponding to a user, of the user device, with a medical condition;

creating, by the device and based on receiving the lifestyle information, a lifestyle timeline associated with the user,

the lifestyle timeline;

including a plurality of items of lifestyle information, included in the lifestyle information, and having the plurality of items of lifestyle information arranged in a chronological order;

generating, by the device and based on receiving the lifestyle timeline, a recommendation or a prediction associated with a metric related to the medical condition,

the recommendation being generated based on one or more of the plurality of items of lifestyle information, or

the prediction being generated using a prediction model that uses one or more of the plurality of items of lifestyle information as input;

receiving, by the device and from another device via the network, transaction information associated with a purchase of food by the user;

receiving, by the device via the network, location information associated with the user;

generating, by the device and based on the transaction information and the location information, an updated recommendation regarding insulin dosage; and

providing, by the device and to an insulin device via the network, the updated recommendation,

upon receipt of the updated recommendation, the insulin device adjusting an amount of insulin to a recommended dosage identified by the updated recommendation after the updated recommendation is accepted via a user interface of the insulin device, and

the insulin device administering the amount of insulin to the user after the updated recommendation is accepted via the user interface of the insulin device.

2. The method of claim 1, further comprising:

determining a set of predictive factors associated with the medical condition,

a predictive factor, of the set of predictive factors, being a factor or an amount by which the metric is predicted to be affected by an item of lifestyle information of the plurality of items of lifestyle information; and

where generating the recommendation or the prediction associated with the metric comprises;

generating the recommendation or the prediction based on the set of predictive factors.

3. The method of claim 1, where the plurality of items of lifestyle information includes a combination of historical items of lifestyle information, current items of lifestyle information, and future items of lifestyle information.

4. The method of claim 1, where receiving the lifestyle information comprises:

receiving the lifestyle information based on user input via the user device.

5. The method of claim 1, where receiving the lifestyle information comprises:

automatically receiving the lifestyle information from the user device.

18. The method of claim 1, where the location information includes at least one of:

information that identifies a geographic location of the user,

information indicating whether the user is indoors or outdoors, or

information indicating that the user is at a particular place.

19. The method of claim 1, where a notification is provided by the user device based on the updated recommendation.

6. A device, comprising:

a memory; and

one or more processors to;

receive, from at least one of a sensor of a user device or a server device via a network, lifestyle information corresponding to a user, of the user device, with a medical problem;

create, based on receiving the lifestyle information, a lifestyle timeline associated with the user,

the lifestyle timeline;

including a plurality of items of lifestyle information included in the lifestyle information, and having the plurality of items of lifestyle information arranged in a chronological order;

generate, based on receiving the lifestyle timeline, a recommendation or a prediction associated with a health metric related to the medical problem,

the recommendation including a recommended dosage of a treatment associated with the health metric and being generated based on one or more of the plurality of items of lifestyle information, or

the prediction including a predicted value of the health metric at a future time and being generated by a prediction model that uses one or more items of the plurality of items of lifestyle information as input;

receive, from another device via the network, transaction information associated with a purchase of food by the user;

receive, via the network, location information associated with the user;

generate, based on the transaction information and the location information, an updated recommendation regarding insulin dosage; and

provide, to an insulin device via the network, the updated recommendation,

upon receipt of the updated recommendation, the insulin device adjusting an amount of insulin to a recommended dosage identified by the updated recommendation after the updated recommendation is accepted via a user interface of the insulin device, and

the insulin device administering the amount of insulin to the user after the updated recommendation is accepted via the user interface of the insulin device.

7. The device of claim 6, where the one or more processors are further to:

determine, based on the lifestyle timeline, a current state associated with the user; and

identify, using a nearest neighbor analysis, a historical state similar to the current state; and

where the one or more processors, when generating the recommendation or the prediction, are to;

generate the recommendation or the prediction based on a historical recommendation or a historical prediction corresponding to the historical state.

8. The device of claim 6, where the one or more processors, when receiving the lifestyle information, are to:

receive the lifestyle information from the server device,

the server device having access to the lifestyle information.

9. The device of claim 6, where the one or more processors are further to:

merge, combine, or normalize the lifestyle information to create converted lifestyle information,

the converted lifestyle information being formatted to permit creation of the lifestyle timeline; and

where the one or more processors, when creating the lifestyle timeline, are to;

create the lifestyle timeline based on the converted lifestyle information.

10. The device of claim 6, where the one or more processors are further to:

determine, based on the lifestyle information, a current value associated with the health metric; and

where the one or more processors, when generating the recommendation or the prediction, are to;

generate the recommendation or the prediction based on the current value of the health metric.

11. The device of claim 6, where the one or more processors, when receiving the lifestyle information, are to:

receive the lifestyle information from the user device,

the user device being a device that is worn by the user.

12. The device of claim 6, where the lifestyle information includes at least one of:

event information from a schedule or calendar associated with the user;

sleep information associated with the user;

information associated with an activity in which the user has participated, is participating in, or is to participate;

information associated with a diet of the user;

biological information associated with the user;

information associated with an emotional state of the user;

medical information, associated with treating the medical problem, corresponding to the user;

information associated with a location of the user;

environmental information associated with the user;

or

information associated with one or more transactions associated with the user.

13. A non-transitory computer-readable medium storing instructions, the instructions comprising:

one or more instructions that, when executed by one or more processors, cause the one or more processors to;

receive, from at least one of a sensor of a user device or a server device via a network, lifestyle information corresponding to a user, of the user device, with a medical problem;

create, based on receiving the lifestyle information, a lifestyle timeline associated with the user,

the lifestyle timeline;

including a plurality of items of lifestyle information included in the lifestyle information, and having the plurality of items of lifestyle information arranged in a chronological order;

determine, based on receiving the lifestyle information, a current value of a metric associated with the medical problem;

generate, based on receiving the lifestyle timeline and the current value of the metric, a recommendation or a prediction associated with the metric,

the recommendation being generated based on a first set of the plurality of items of lifestyle information, or

the prediction being generated using a predictive model that uses a second set of the plurality of items of lifestyle information as input;

receive, from another device via the network, transaction information associated with a purchase of food by the user;

receive, via the network, location information associated with the user;

generate, based on the transaction information and the location information an updated recommendation regarding an insulin dosage; and

provide, to an insulin device via the network, the updated recommendation,

upon receipt of the updated recommendation, the insulin device adjusting an amount of insulin to a recommended dosage identified by the updated recommendation after the updated recommendation is accepted via a user interface of the insulin device, and

the insulin device administering the amount of insulin to the user after the updated recommendation is accepted via the user interface of the insulin device.

14. The non-transitory computer-readable medium of claim 13, where the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:

receive updated lifestyle information corresponding to the user,

the updated lifestyle information being different from the lifestyle information; and

update the lifestyle timeline, based on the updated lifestyle information, to create an updated lifestyle timeline; and

where the one or more instructions, that cause the one or more processors to generate the updated recommendation, cause the one or more processors to;

generate, based on the updated lifestyle timeline, the updated recommendation.

15. The non-transitory computer-readable medium of claim 13, where the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:

determine a set of predictive factors associated with the medical problem,

a predictive factor, of the set of predictive factors, being a factor or an amount by which the metric is predicted to be affected by an item of lifestyle information of the plurality of items of lifestyle information; and

where the one or more instructions, that cause the one or more processors to generate the recommendation or the prediction, cause the one or more processors to;

generate the recommendation or the prediction further based on the set of predictive factors.

16. The non-transitory computer-readable medium of claim 13, where the updated recommendation identifies a recommended time at which the recommended dosage should be administered.

17. The non-transitory computer-readable medium of claim 13, where the plurality of items of lifestyle information includes at least two of:

historical items of lifestyle information;

current items of lifestyle information;

or

future items of lifestyle information.

20. The non-transitory computer-readable medium of claim 13, where the transaction information includes at least one of:

an amount of a transaction,

information that identifies items associated with the transaction, or

information associated with a digital receipt.