Granted Patent B2

US 12,730,828 · App. 18/411,920 · Granted Sep 8, 2026

Inventors: Anthony Terrence O'Brien Villate, Jr. (Brookline, MA); Ali Azari (Rockville, MD); Emily Francine Kipping (New York, NY)

Assignee: CVS Pharmacy, Inc.

G06F16/285G16H10/60

Abstract

Claims (108)

1 . A system comprising one or more memory devices having instructions stored thereon, that, when executed by one or more processors, cause the one or more processors to:

receive data of dimensions of a plurality of patients from one or more data sources;

select a portion of the dimensions based on a level at which the dimensions predict that a patient will stop a treatment;

determine a plurality of segments, wherein the plurality of segments describe at least one of an attitude towards healthcare or an independence relative to a healthcare provider;

classify the plurality of patients into the plurality of segments based on execution of a model trained based on a machine learning process and based on the data of the selected portion of the dimensions;

construct a database;

update the database to store classifications of the plurality of patients into the plurality of segments;

construct output data based on the classifications of the plurality of patients into the plurality of segments stored in the database;

select a software application from a plurality of software applications for the patient based on a segment into which the model classified the patient;

generate at least one credential for the patient to access the software application;

construct a message to access the software application, the message comprising the at least one credential or a link to accessing the software application with the at least one credential; and

transmit the message to a device of the patient.

2 . The system of claim 1 , wherein the instructions cause the one or more processors to:

generate a training data set based on the data, the training data set comprising:

a plurality of sets of the data for a portion of the plurality of patients; and

segments that the portion of the plurality of patients are classified into; and

train the model by execution of the machine learning process on the training data set.

3 . The system of claim 1 , wherein the instructions cause the one or more processors to:

retrieve, from the database, a classification of a first patient of the plurality of patients into a first segment of the plurality of segments;

retrieve, from the database, a classification of a second patient of the plurality of patients into a second segment of the plurality of segments;

generate first output data for the first patient based on the classification of the first patient into the first segment; and

generate second output data for the second patient based on the classification of the second patient into the second segment, wherein the first output data is different than the second output data.

4 . The system of claim 1 , wherein the instructions cause the one or more processors to:

retrieve, from the database, a classification of the patient of the plurality of patients into the segment of the plurality of segments;

select the software application for the patient from the database, the software application linked to the segment;

generate the output data to provide the patient access to the software application; and

transmit the output data to the device of the patient.

5 . The system of claim 1 , wherein the instructions cause the one or more processors to:

execute a second machine learning process based on the data to identify a level that the dimensions of the data stored in the database predict that the patient will stop the treatment;

identify the portion of the dimensions associated with levels greater than a threshold; and

construct the plurality of segments based on the portion of the dimensions.

6 . The system of claim 1 , wherein the instructions cause the one or more processors to:

construct the database to include a plurality of sections;

save first data of the data describing the plurality of patients in a first section of the plurality of sections linked to a first segment of the plurality of segments;

store at least one identifier of the first segment in the database to label the first data stored in the first section;

save second data of the data describing the plurality of patients in a second section of the plurality of sections linked to a second segment of the plurality of segments; and

store at least one identifier of the second segment in the database to label the second data stored in the second section.

7 . The system of claim 6 , wherein the instructions cause the one or more processors to:

receive a request to generate an output for patients classified into the first segment;

query the database based on the at least one identifier for the first segment;

receive the first data responsive to the query; and

execute an operation to generate the output for the patients based on the first data received from the database.

8 . A method, comprising:

receiving, by one or more processing circuits, data of dimensions of a plurality of patients from one or more data sources;

executing, by the one or more processing circuits, a first machine learning process based on the data to identify a level that the dimensions of the plurality of patients of the data predict that patients will stop a treatment;

selecting, by the one or more processing circuits, a portion of the dimensions associated with levels greater than a threshold;

constructing, by the one or more processing circuits, a plurality of segments based on the portion of the dimensions, wherein the plurality of segments describe at least one of an attitude towards healthcare or an independence relative to a healthcare provider;

classifying, by the one or more processing circuits, the plurality of patients into the plurality of segments based on execution of a model trained based on a second machine learning process and based on the data of the selected portion of the dimensions;

constructing, by the one or more processing circuits, a database;

updating, by the one or more processing circuits, the database to store classifications of the plurality of patients into the plurality of segments; and

constructing, by the one or more processing circuits, output data based on the classifications of the plurality of patients into the plurality of segments stored in the database.

9 . The method of claim 8 , comprising:

generating, by the one or more processing circuits, a training data set based on the data, the training data set comprising:

a plurality of sets of the data for a portion of the plurality of patients; and

segments that the portion of the plurality of patients are classified into; and

training, by the one or more processing circuits, the model by execution of the second machine learning process on the training data set.

10 . The method of claim 9 , comprising:

selecting, by the one or more processing circuits, a software application from a plurality of software applications for a patient based on a segment into which the model classified the patient;

generating, by the one or more processing circuits, at least one credential for the patient to access the software application;

constructing, by the one or more processing circuits, a message to access the software application, the message comprising the at least one credential or a link to accessing the software application with the at least one credential; and

transmitting, by the one or more processing circuits, the message to a device of the patient.

11 . The method of claim 8 , comprising:

retrieving, by the one or more processing circuits, from the database, a classification of a first patient of the plurality of patients into a first segment of the plurality of segments;

retrieving, by the one or more processing circuits, from the database, a classification of a second patient of the plurality of patients into a second segment of the plurality of segments;

generating, by the one or more processing circuits, first output data for the first patient based on the classification of the first patient into the first segment; and

generating, by the one or more processing circuits, second output data for the second patient based on the classification of the second patient into the second segment, wherein the first output data is different than the second output data.

12 . The method of claim 8 , comprising:

retrieving, by the one or more processing circuits, from the database, a classification of a patient of the plurality of patients into a segment of the plurality of segments;

selecting, by the one or more processing circuits, at least one software application for the patient from the database, the at least one software application linked to the segment;

generating, by the one or more processing circuits, the output data to provide the patient access to the at least one software application; and

transmitting, by the one or more processing circuits, the output data to a device of the patient.

13 . The method of claim 9 , comprising:

constructing, by the one or more processing circuits, the database to include a plurality of sections;

saving, by the one or more processing circuits, first data of the data describing the plurality of patients in a first section of the plurality of sections linked to a first segment of the plurality of segments;

storing, by the one or more processing circuits, at least one identifier of the first segment in the database to label the first data stored in the first section;

saving, by the one or more processing circuits, second data of the data describing the plurality of patients in a second section of the plurality of sections linked to a second segment of the plurality of segments; and

storing, by the one or more processing circuits, at least one identifier of the second segment in the database to label the second data stored in the second section.

14 . The method of claim 13 , comprising:

receiving, by the one or more processing circuits, a request to generate an output for patients classified into the first segment;

querying, by the one or more processing circuits, the database based on the at least one identifier for the first segment;

receiving, by the one or more processing circuits, the first data responsive to the query; and

executing, by the one or more processing circuits, an operation to generate the output for the patients based on the first data received from the database.

15 . One or more storage media having instructions stored thereon, that, when executed by one or more processors, cause the one or more processors to:

receive data of dimensions of a plurality of patients from one or more data sources;

select a portion of the dimensions based on a level at which the dimensions predict that a patient will stop a treatment;

determine a plurality of segments, wherein the plurality of segments describe at least one of an attitude towards healthcare or an independence relative to a healthcare provider;

classify the plurality of patients into the plurality of segments based on execution of a model trained based on a machine learning process and based on the data of the selected portion of the dimensions;

construct a database, the database including a plurality of sections;

update the database to store classifications of the plurality of patients into the plurality of segments by:

saving first data of the data describing the plurality of patients in a first section of the plurality of sections linked to a first segment of the plurality of segments;

storing at least one identifier of the first segment in the database to label the first data stored in the first section;

saving second data of the data describing the plurality of patients in a second section of the plurality of sections linked to a second segment of the plurality of segments; and

storing at least one identifier of the second segment in the database to label the second data stored in the second section; and

construct output data based on the classifications of the plurality of patients into the plurality of segments stored in the database.

16 . The one or more storage media of claim 15 , wherein the instructions cause the one or more processors to:

generate a training data set based on the data, the training data set comprising:

a plurality of sets of the data for a portion of the plurality of patients; and

segments that the portion of the plurality of patients are classified into; and

train the model by execution of the machine learning process on the training data set.

17 . The one or more storage media of claim 15 , wherein the instructions cause the one or more processors to:

select a software application from a plurality of software applications for a patient based on a segment into which the model classified the patient;

generate at least one credential for the patient to access the software application;

construct a message to access the software application, the message comprising the at least one credential or a link to accessing the software application with the at least one credential; and

transmit the message to a device of the patient.

18 . The one or more storage media of claim 15 , wherein the instructions cause the one or more processors to:

execute a second machine learning process based on the data to identify a level that the dimensions of the data stored in the database predict that the patient will stop the treatment;

identify the portion of the dimensions associated with levels greater than a threshold; and

construct the plurality of segments based on the portion of the dimensions.

Assignments (1)

Continuity (2)

References Cited (30)