Health lending system and method using probabilistic graph models

• US 10,417,379 B2
• Filed: 01/20/2016
• Issued: 09/17/2019
• Est. Priority Date: 01/20/2015
• Status: Active Grant

• Current Assignee: Change Healthcare Holdings, LLC (UnitedHealth Group Incorporated)
• Original Assignee: Change Healthcare Holdings, LLC (UnitedHealth Group Incorporated)
• Inventors: Tanner, Jr., Theodore C., Alstad, Colin Erik
• Primary Examiner(s): Tomaszewski, Michael
• Application Number:
  US15/001,703
• Publication Number:
  US 20160210423A1
• Time in Patent Office: 1,336 Days
• Field of Search: None
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 40/03 Credit; Loans; Processing thereof
• CPC Class Codes: G16H 40/20 for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment

Abstract

A system and method for health lending using a probabilistic graph model are described. The system and method may generate a health credit score (“HICO”). The HICO is a score that is a risk measure placed on all entities of a healthcare transaction in which a company that owns or operates the system may have an interest or a company that utilizes the HICO score for its risk assessment.

Claims

1. A system, comprising:

a first computer system having a processor and a memory;

a computer system that stores claims and benefits data for a payor;

a computer system that stores provider data for a health care transaction provider;

a computer system that stores consumer data about a consumer of a health care service;

the first computer system hosting an input processor configured to receive data from the computer systems that store claims and benefits data for the payor, provider data and consumer data about a health service transaction and process the data about the health care transaction using an ETL process;

the first computer system hosting a graph model engine that receives the data about the health care transaction and programmatically generates a bayes graph for the payor using the claims and benefits data to generate a payor risk associated with the health care transaction, a bayes graph for the provider using the provider data to generate a provider risk associated with the health care transaction and a bayes graph for the consumer using the consumer data and the claims and benefits data to generate a consumer risk associated with the health care transaction; and

the computer system configured to generate a risk measure for the health service transaction using the payor risk, provider risk and consumer risk generated using the bayes graphs for each entity that is part of the health service transaction.

6. The system of claim 1, wherein the processor is configured to generate a risk score for an entity involved in the health service transaction.

7. The system of claim 6, wherein the entity is one of a health service consumer, a health service provider and a health service payer.

8. The system of claim 1, wherein the risk measure is a risk score.

2. The system of 1, wherein the processor is configured to use a probabilistic graph model to generate the risk measure.

3. The system of claim 2, wherein the processor is configured to generate a payor bayes graph, a provider bayes graph and a consumer bayes graph.

4. The system of claim 3, wherein the processor is configured to generate the risk measure by combining the payor bayes graph, the provider bayes graph and the consumer bayes graph.

5. The system of claim 2, wherein the processor is configured to use a stepwise belief network to generate the probabilistic graph model.

9. A method, comprising:

providing a computer system having a processor, memory and a plurality of lines of computer code configured to;

receive and process data about a health service transaction using an ETL process, the data about the health care transaction including claims and benefits data for a payor, provider data for a health care transaction provider and consumer data about a consumer of a health care service;

generate a bayes graph for the payor using the claims and benefits data to generate a payor risk associated with the health care transaction, a bayes graph for the provider using the provider data to generate a provider risk associated with the health care transaction and a bayes graph for the consumer using the consumer data and the claims and benefits data to generate a consumer risk associated with the health service transaction; and

generate a risk measure for the health service transaction using the payor risk, provider risk and consumer risk generated using the bayes graphs for each entity that is part of the health service transaction.

14. The method of claim 9 further comprising generating a risk score for an entity involved in the health service transaction.

15. The method of claim 14, wherein the entity is one of a health service consumer, a health service provider and a health service payer.

16. The method of claim 9, wherein the risk measure is a risk score.

10. The method of 9, wherein generating the risk measure further comprises using a probabilistic graph model to generate the risk measure.

11. The method of claim 10, wherein using the probabilistic graph model further comprises generating a payor bayes graph, generating a provider bayes graph and generating a consumer bayes graph.

12. The method of claim 11, wherein generating the risk measure further comprises combining the payor bayes graph, the provider bayes graph and the consumer bayes graph to generate the risk measure.

13. The method of claim 10, wherein using the probabilistic graph model further comprises using a stepwise belief network to generate the probabilistic graph model.

17. An apparatus, comprising:

a processor;

a memory;

the processor configured to receive and process data about a health service transaction using an ETL process, the data about the health care transaction including claims and benefits data for a payor, provider data for a health care transaction provider and consumer data about a consumer of a health care service; and

the processor configured to generate a bayes graph for the payor using the claims and benefits data to generate a payor risk associated with the health care transaction, a bayes graph for the provider using the provider data to generate a provider risk associated with the health care transaction and a bayes graph for the consumer using the consumer data and the claims and benefits data to generate a consumer risk associated with the health care transaction and to generate a risk measure for the health service transaction using the payor risk, provider risk and consumer risk generated using the bayes graphs for each entity that is part of the health service transaction.

22. The apparatus of claim 17, wherein the processor is configured to generate a risk score for an entity involved in the health service transaction.

23. The apparatus of claim 22, wherein the entity is one of a health service consumer, a health service provider and a health service payer.

24. The apparatus of claim 17, wherein the risk measure is a risk score.

18. The apparatus of 17, wherein the processor is configured to use a probabilistic graph model to generate the risk measure.

19. The apparatus of claim 18, wherein the processor is configured to generate a payor bayes graph, a provider bayes graph and a consumer bayes graph.

20. The apparatus of claim 19, wherein the processor is configured to generate the risk measure by combining the payor bayes graph, the provider bayes graph and the consumer bayes graph.

21. The apparatus of claim 18, wherein the processor is configured to use a stepwise belief network to generate the probabilistic graph model.