IP Library Patent Application 19643986
Patent Application
App. No. 19/643,986

Interactive Agent Interface And Optimized Health Plan Ranking

Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US None
App. No.
19/643,986
Abstract

A computing system can obtain health record data of a user from health record sources. The system can generate, on a computing device of a call agent, an interactive agent interface comprising prepopulated data based on the health record data. Based on an interaction between the call agent and the user during a call session, the system can receive input data from the computing device of the call agent. Based on at least one of the health record data or the input data, the system can generate a set of health outcome predictions for the user, and based on the set of health outcome predictions, the input data, and the health record data, the system can generate a set of health care plan rankings for the user.

Claims (82)

1 .- 20 . (canceled)

21 . A method comprising:

communicating, over one or more networks, with I) one or more health record computing systems and II) a computing device of a user, III) a computing system of an agent, and IV) one or more databases having a collection of medical records stored thereon;

detecting initiation of a call session between the agent and the user;

based on the detected initiation of the call session, facilitating generation of an interactive agent user interface on the computing system of the agent over at least one first network of the one or more networks;

obtaining, from the one or more health record computing systems over at least one second network of the one or more networks, multiple health records of the user,

wherein the multiple health records of the user are obtained in a non-standardized format utilizing multiple coding protocols, the multiple coding protocols including two or more of procedural codes, diagnostic codes, treatment codes, prescription codes, provider codes, or any combination thereof;

translating the multiple health records of the user from the non-standardized format to a standardized natural language format;

storing, in the collection of health records on the one or more databases via at least one third network of the one or more networks, the multiple health records of the user in the standardized format;

while the agent is engaged in the call session with the user, obtaining input data related to the user based on one or more interactions of the agent with the interactive agent user interface;

generating, by a machine learning model, a set of health outcome predictions for the user based on the obtained input data and the multiple health records; and

causing, over the at least one first network of the one or more networks, the computing system of the agent to update the interactive agent user interface with the generated set of health outcome predictions.

22 . The method of claim 21 , wherein the machine learning model is customized to generate the set of health outcome predictions for the user based on training data including a corpus of historical health records, associated with other users, paired with known health outcomes for the other users.

23 . The method of claim 21 , wherein the generating, by the machine learning model, the set of health outcome predictions for the user includes:

comparing the multiple health records of the user to multiple historical health records of other users included in the collection of health records stored on the one or more databases;

filtering the multiple historical health records based on the obtained input data related to the user;

identifying a set of matching health records, of the filtered multiple historical health records, having known health outcomes; and

generating the set of health outcome predictions for the user based on the known health outcomes of the identified set of matching health records.

24 . The method of claim 21 , wherein the machine learning model is customized to generate the set of health outcome predictions for the user by identifying a set of correlations with known patients having historical health records similar to the multiple health records of the user.

25 . The method of claim 21 , wherein the machine learning model is customized to generate the set of health outcome predictions for the user by identifying a set of correlations with known patients having personal information similar to the obtained input data related to the user.

26 . The method of claim 21 , wherein the machine learning model is customized to generate the set of health outcome predictions for the user by determining one or more predispositions of the user towards having or not having a particular medical condition based on genetic information of the user included in the obtained input data and/or the multiple health records.

27 . The method of claim 21 , further comprising:

ranking multiple health care plans based on the generated set of health outcome predictions for the user; and

causing, over the at least one first network of the one or more networks, the computing system of the agent to update the interactive agent user interface with the ranked multiple health care plans.

28 . The method of claim 27 , wherein the ranking the multiple health care plans includes:

assigning scores to benefits and/or attributes of each of the multiple health care plans based on the generated set of health outcome predictions for the user;

generating an overall health care plan score, for each of the multiple health care plans, by aggregating the assigned scores for the benefits and/or attributes corresponding to each of the multiple health care plans; and

ordering the multiple health care plans from a first health care plan, of the multiple health care plans, having a highest overall health care plan score, to a last health care plan, of the multiple health care plans, having a lowest overall health care plan score.

29 . The method of claim 27 , further comprising:

obtaining, from the computing system of the agent over the at least one first network of the one or more networks, a request to provide the ranked multiple health care plans to the computing device of the user; and

based on the obtained request, facilitating generation of an interactive patient user interface on the computing device of the user over at least one fourth network of the one or more networks, the interactive patient user interface including the ranked multiple health care plans.

30 . The method of claim 21 , wherein the set of health outcome predictions includes one or more of

A) a health risk of the user,

B) a life expectancy of the user,

C) a mortality risk of the user,

D) a probability of the user requiring a particular medical procedure, or

E) any combination thereof.

31 . The method of claim 21 , wherein the set of health outcomes predictions includes an adverse impact risk between A) one or more current prescriptions of the user, one or more treatments of the user, one or more health risks of the user, one or more current health issues of the user, or any combination thereof, and B) one or more other current prescriptions of the user, one or more other treatments of the user, one or more other health risks of the user, one or more other current health issues of the user, or any combination thereof.

32 . The method of claim 21 , further comprising:

communicating, over one or more networks, with V) one or more health care provider computing systems; and

verifying the obtained input data related to the user with the one or more health care provider computing systems over at least one fourth network of the one or more networks.

33 . A computer-readable storage medium storing instructions, the instructions, when executed by a computing system, cause the computing system to:

communicate, over one or more networks, with I) one or more health record computing systems and II) a computing device of a user, III) a computing system of an agent, and IV) one or more databases having a collection of medical records stored thereon;

detect initiation of a call session between the agent and the user;

based on the detected initiation of the call session, facilitate generation of an interactive agent user interface on the computing system of the agent over at least one first network of the one or more networks;

obtain, from the one or more health record computing systems over at least one second network of the one or more networks, multiple health records of the user,

wherein the multiple health records of the user are obtained in a non-standardized format utilizing multiple coding protocols, the multiple coding protocols including two or more of procedural codes, diagnostic codes, treatment codes, prescription codes, provider codes, or any combination thereof;

translate the multiple health records of the user from the non-standardized format to a standardized natural language format;

store, in the collection of health records on the one or more databases via at least one third network of the one or more networks, the multiple health records of the user in the standardized format;

while the agent is engaged in the call session with the user, obtain input data related to the user based on one or more interactions of the agent with the interactive agent user interface;

generate, by a machine learning model, a set of health outcome predictions for the user based on the obtained input data and the multiple health records; and

cause, over the at least one first network of the one or more networks, the computing system of the agent to update the interactive agent user interface with the generated set of health outcome predictions.

34 . The computer-readable storage medium of claim 33 , wherein the machine learning model is customized to generate the set of health outcome predictions for the user based on training data including a corpus of historical health records, associated with other users, paired with known health outcomes for the other users.

35 . The computer-readable storage medium of claim 33 , wherein the generating, by the machine learning model, the set of health outcome predictions for the user includes:

comparing the multiple health records of the user to multiple historical health records of other users included in the collection of health records stored on the one or more databases;

filtering the multiple historical health records based on the obtained input data related to the user;

identifying a set of matching health records, of the filtered multiple historical health records, having known health outcomes; and

generating the set of health outcome predictions for the user based on the known health outcomes of the identified set of matching health records.

36 . The computer-readable storage medium of claim 33 , wherein the machine learning model is customized to generate the set of health outcome predictions for the user by identifying a set of correlations with known patients having historical health records similar to the multiple health records of the user.

37 . A computing system comprising:

one or more processors; and

one or more memories storing instructions that, when executed by the one or more processors, cause the computing system to:

communicate, over one or more networks, with I) one or more health record computing systems and II) a computing device of a user, III) a computing system of an agent, and IV) one or more databases having a collection of medical records stored thereon;

detect initiation of a call session between the agent and the user;

based on the detected initiation of the call session, facilitate generation of an interactive agent user interface on the computing system of the agent over at least one first network of the one or more networks;

obtain, from the one or more health record computing systems over at least one second network of the one or more networks, multiple health records of the user,

wherein the multiple health records of the user are obtained in a non-standardized format utilizing multiple coding protocols, the multiple coding protocols including two or more of procedural codes, diagnostic codes, treatment codes, prescription codes, provider codes, or any combination thereof;

translate the multiple health records of the user from the non-standardized format to a standardized natural language format;

store, in the collection of health records on the one or more databases via at least one third network of the one or more networks, the multiple health records of the user in the standardized format;

while the agent is engaged in the call session with the user, obtain input data related to the user based on one or more interactions of the agent with the interactive agent user interface;

generate, by a machine learning model, a set of health outcome predictions for the user based on the obtained input data and the multiple health records; and

cause, over the at least one first network of the one or more networks, the computing system of the agent to update the interactive agent user interface with the generated set of health outcome predictions.

38 . The computing system of claim 37 , wherein the instructions, when executed by the one or more processors, further cause the computing system to:

rank multiple health care plans based on the generated set of health outcome predictions for the user; and

cause, over the at least one first network of the one or more networks, the computing system of the agent to update the interactive agent user interface with the ranked multiple health care plans.

39 . The computing system of claim 38 , wherein the ranking the multiple health care plans includes:

assigning scores to benefits and/or attributes of each of the multiple health care plans based on the generated set of health outcome predictions for the user;

generating an overall health care plan score, for each of the multiple health care plans, by aggregating the assigned scores for the benefits and/or attributes corresponding to each of the multiple health care plans; and

ordering the multiple health care plans from a first health care plan, of the multiple health care plans, having a highest overall health care plan score, to a last health care plan, of the multiple health care plans, having a lowest overall health care plan score.

40 . The computing system of claim 38 , wherein the instructions, when executed by the one or more processors, further cause the computing system to:

obtain, from the computing system of the agent over the at least one first network of the one or more networks, a request to provide the ranked multiple health care plans to the computing device of the user; and

based on the obtained request, facilitate generation of an interactive patient user interface on the computing device of the user over at least one fourth network of the one or more networks, the interactive patient user interface including the ranked multiple health care plans.