NEAR REAL-TIME HEALTHCARE FRAUD DETECTION

• US 20130006655A1
• Filed: 06/28/2012
• Published: 01/03/2013
• Est. Priority Date: 06/30/2011
• Status: Abandoned Application

• Current Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Original Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Inventors: VAN ARKEL, John H., WAGNER, James J., SCHWEYEN, Corrine L., MAHONE, Saralyn M., TADA, David D., CURTIS, Terrill J., HAGINS, Scott
• Application Number:
  US13/536,367
• Publication Number:
  US 20130006655A1
• Time in Patent Office: Days
• US Class Current: 705/2
• CPC Class Codes: G06Q 10/10 Office automation; Time management

Abstract

A healthcare fraud management system is configured to store multiple rules for detecting healthcare fraud, receive a healthcare claim involving a provider and a beneficiary, and obtain other healthcare fraud information associated with the provider or the beneficiary. The healthcare fraud management system is further configured to select rules, from the multiple rules, based on information associated with the claim, information associated with the provider or the beneficiary, and the other healthcare fraud information. The healthcare fraud management system is also configured to process the healthcare claim using the selected rules to generate a fraud score, and output, prior to payment of the healthcare claim, information regarding the fraud score to a clearinghouse or a claims processor to assist the clearinghouse or the claims processor in determining whether to accept, deny, or review the healthcare claim.

Claims

1. A method, comprising:

storing, by one or more computer devices of a healthcare fraud management system, a plurality of rules for detecting healthcare fraud;

receiving, by the one or more computer devices, a healthcare claim involving a provider and a beneficiary;

obtaining, by the one or more computer devices, other healthcare fraud information associated with the provider or the beneficiary;

selecting, by the one or more computer devices, rules, from the plurality of rules, based on information associated with the claim, information associated with the provider or the beneficiary, and the other healthcare fraud information;

processing, by the one or more computer devices, the healthcare claim using the selected rules to generate a fraud score; and

outputting, by the one or more computer devices and prior to payment of the healthcare claim, information regarding the fraud score to a clearinghouse or a claims processor to assist the clearinghouse or the claims processor in determining whether to accept, deny, or review the healthcare claim.

2. The method of claim 1, further comprising:

determining a type associated with the healthcare claim; and

selecting the rules from the plurality of rules based on the determined type associated with the healthcare claim.

3. The method of claim 1, further comprising:

generating a profile associated with the healthcare claim based on the other healthcare fraud information and information included in the healthcare claim, meta information associated with the healthcare claim, or historical information associated with the healthcare claim; and

selecting the rules, from the plurality of rules, based on information in the profile.

4. The method of claim 1, where outputting information regarding the fraud score includes:

generating an alert, associated with the claim, based on the fraud score, where the alert indicates that the clearinghouse or the claims processor should accept, deny, or review the claim, and

outputting the alert to the clearinghouse or the claims processor.

5. The method of claim 1, where the plurality of rules include at least one of:

provider-specific rules;

provider type-specific rules;

beneficiary-specific rules;

procedure frequency-specific rules;

geographical dispersion of services-specific rules;

single claim analysis-related rules;

auto summation of provider procedure time-specific rules;

suspect beneficiary ID theft-specific rules;

alert on suspect address-specific rules;

inconsistent relationship-specific rules;

excessive cost-specific rules;

rules that identify fraudulent therapies;

or rules that identify a gang visit fraud scheme.

6. The method of claim 1, where processing the healthcare claim includes:

processing the healthcare claim, in parallel, using the selected rules to generate a plurality of alarms,

sorting the plurality of alarms into a plurality of groups based on attributes of the healthcare claim, where each of one or more of the plurality of groups includes alarms from a plurality of healthcare claims, and

analyzing the plurality of groups to generate the fraud score.

7. The method of claim 6, where sorting the plurality of alarms includes:

aggregating alarms corresponding to healthcare claims associated with a plurality of unaffiliated providers, where the plurality of unaffiliated providers includes the provider, and where the alarms include the plurality of alarms, and

correlating the alarms into the plurality of groups.

8. The method of claim 1, further comprising:

analyzing the fraud score with respect to first and second thresholds, where the first threshold is less than the second threshold;

classifying the healthcare claim as a safe claim when the fraud score is less than the first threshold; and

classifying the healthcare claim as an unsafe claim when the fraud score is greater than the second threshold;

where outputting information regarding the fraud score includes;

outputting, to the clearinghouse or the claims processor, information regarding whether the healthcare claim has been classified as a safe claim or an unsafe claim.

9. The method of claim 1, further comprising:

prioritizing the fraud score in relation to other fraud scores generated for other healthcare claims.

10. The method of claim 1, where the information regarding the fraud score is outputted to the clearinghouse or the claims processor in near real-time.

11. A system, comprising:

one or more memory devices to store a plurality of rules for detecting healthcare fraud; and

one or more processors to;

receive a healthcare claim involving a provider and a beneficiary;

obtain other healthcare fraud information associated with the provider or the beneficiary;

select a subset of rules, of the plurality of rules, based on information associated with the healthcare claim, information associated with the provider or the beneficiary, and the other healthcare fraud information;

process the healthcare claim using the subset of rules to generate a plurality of alarms;

process the plurality of alarms to generate a fraud score for the healthcare claim; and

output information regarding the fraud score to a clearinghouse or a claims processor to assist the clearinghouse or the claims processor in determining whether to accept, deny, or review the healthcare claim.

12. The system of claim 11, where the one or more processors are further to:

determine a type associated with the healthcare claim; and

selecting the subset of rules from the plurality of rules based on the determined type associated with the healthcare claim.

13. The system of claim 11, where the one or more processors are further to:

flag the healthcare claim for review by a human analyst based on the fraud score.

14. The system of claim 11, where the one or more processors are further to:

prioritize the fraud score in relation to other fraud scores generated for other healthcare claims.

15. The system of claim 11, where, when processing the healthcare claim using the subset of rules, the one or more processors are to:

generate an alarm score for each alarm of the plurality of alarms; and

where, when processing the plurality of alarms to generate the fraud score, the one or more processors are to;

sort the plurality of alarms into a plurality of groups based on attributes of the healthcare claim, where each of the plurality of groups includes at least one alarm from the plurality of alarms,

generate a group score for each group, of the plurality of groups, based on the alarm score for the at least one alarm in the group, and

generate the fraud score based on one or more of the group scores.

16. The system of claim 15,

where one or more of the plurality of groups include alarms corresponding to a plurality of healthcare claims associated with a plurality of unaffiliated providers, and

where the provider is one of the plurality of unaffiliated providers.

17. The system of claim 11, where the one or more processors are further to:

generate a profile associated with the healthcare claim based on the other healthcare fraud information and information included in the healthcare claim, meta information associated with the healthcare claim, or historical information associated with the healthcare claim; and

select rules, for the subset of rules, based on information in the profile.

18. The system of claim 11, where, when outputting information regarding the fraud score, the one or more processors are to:

determine policies associated with the clearinghouse or the claims processor,

generate an alert, associated with the healthcare claim, based on the fraud score and the determined policies, where the alert indicates that the clearinghouse or the claims processor should accept, deny, or review the healthcare claim, and

output the alert to the clearinghouse or the claims processor.

19. The system of claim 11, where, when processing the plurality of alarms, the one or more processors are to:

aggregate alarms associated with a plurality of healthcare claims, where the alarms include the plurality of alarms,

sort the alarms into a plurality of groups based on attributes of the healthcare claim, where each of the plurality of groups includes at least one of the alarms,

generate a group score for each group, of the plurality of groups, based on the at least one of the alarms in the group, and

generate the fraud score based on one or more of the group scores.

20. A computer-readable medium, comprising:

one or more instructions that, when executed by at least one processor of a healthcare fraud management system, cause the at least one processor to;

store a plurality of rules for detecting healthcare fraud,

receive a healthcare claim involving a provider and a beneficiary,

obtain other healthcare fraud information associated with the provider or the beneficiary,

select a subset of rules, of the plurality of rules, based on information associated with the healthcare claim, information associated with the provider or the beneficiary, and the other healthcare fraud information,

process the healthcare claim using the subset of rules to generate a plurality of alarms,

process the plurality of alarms to generate a fraud score for the healthcare claim, and

output, prior to payment of the healthcare claim, information regarding the fraud score to a clearinghouse or a claims processor to assist the clearinghouse or the claims processor in determining whether to accept, deny, or review the healthcare claim.