System for evaluating potential claim outcomes using related historical data

• US 8,457,984 B2
• Filed: 01/11/2012
• Issued: 06/04/2013
• Est. Priority Date: 05/14/2009
• Status: Active Grant

• Current Assignee: Hartford Fire Insurance Company (The Hartford Financial Services Group, Inc.)
• Original Assignee: Hartford Fire Insurance Company (The Hartford Financial Services Group, Inc.)
• Inventors: Hu, Wangyang, Maurer, Kathleen E., McLaughlin, Kelly J.
• Primary Examiner(s): BURGESS, JOSEPH D
• Application Number:
  US13/348,175
• Publication Number:
  US 20120116801A1
• Time in Patent Office: 510 Days
• Field of Search: 705 2- 4
• US Class Current: 705/2
• CPC Class Codes: G06Q 10/06375 Prediction of business process outcome or impact based on a proposed change
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

A computer system includes a data storage device. The data storage module receives, stores, and provides access to historical claim data. A categorical aggregation component comprising program instructions stored in a program memory provides categorized and aggregated historical claim data by identifying claim categories based on the historical claim data, each of the one or more claim categories associated with a respective set of claim characteristics, identifying claims of the historical claim data associated with one of the claim categories, assigning each identified claim to one of a plurality of total severity ranges based on the total severity of the identified claim, and determining an average cost per claim year for claims of each total severity range when executed by a computer processor.

Claims

1. A computer system comprising:

a data storage device for receiving, storing, and providing access to historical claim data;

a computer processor for executing program instructions and for retrieving the historical claim data from the data storage device;

a memory, coupled to the computer processor, for storing program instructions for execution by the computer processor;

a categorical aggregation component comprising program instructions stored in the memory for providing categorized and aggregated historical claim data by determining a first set of claim characteristics, identifying first claims of the historical claim data which exhibit the first set of claim characteristics, determining whether a number of the first claims exceeds a statistical significance threshold, in response to a determination that the number of the first claims exceeds a statistical significance threshold, determining a total severity statistical profile based on a total severity of each of the first claims, determining whether the total severity statistical profile meets predefined profile criteria, and, in response to determining that the total severity statistical profile meets the predefined profile criteria, associating the first set of claim characteristics with a first claim category, identifying claims of the historical claim data associated with the first claim category, assigning each identified claim associated with the first claim category to one of a plurality of total severity ranges based on the total severity of the identified claim, and determining an average cost per claim year divided amongst a plurality of expense categories for claims of each total severity range when executed by the computer processor; and

a communication device, coupled to the computer processor, to output categorized and aggregated historical claim data including the average cost per claim year for claims of each total severity range.

2. A system according to claim 1, wherein the program instructions of the categorical aggregation component are for providing categorized and aggregated historical claim data further by:

determining a second set of claim characteristics, the second set of claim characteristics being a subset of the first set of claim characteristics;

identifying second claims of the historical claim data which exhibit the second set of claim characteristics, the second claims being a subset of the first claims;

determining whether the number of the second claims exceeds the statistical significance threshold;

in response to a determination that the number of the second claims exceeds the statistical significance threshold, determining a second total severity statistical profile based on a total severity of each of the second claims;

determining whether the second total severity statistical profile meets the predefined profile criteria; and

in response to a determination that the second total severity statistical profile meets the predefined profile criteria, associating the second set of claim characteristics with a second claim category, the second claim category being a subcategory of the first claim category.

3. A system according to claim 1, wherein the first set of claim characteristics comprises at least one of:

one or more medical billing codes, a minimum annual spend rate in one or more medical expense categories, one or more co-morbidities, and a disability duration.

4. A system according to claim 3, wherein the one or more co-morbidities comprise at least one of:

obesity, psychiatric issues, and alcohol use.

5. A system according to claim 1, wherein the one or more claim categories comprise one or more of:

non-traumatic cervical surgery without fusion, non-traumatic lumbar surgery without fusion, non-traumatic lumbar fusion surgery, and non-traumatic cervical fusion surgery.

6. A system according to claim 1, further comprising:

filtering the historical claim data based on one or more characteristics prior to identifying the claim categories.

11. A method according to claim 1, further comprising:

filtering the historical claim data based on one or more characteristics prior to identifying the first claim category.

7. A method of operating a categorical aggregation component, the method comprising:

receiving historical claim data from a data warehouse;

determining a first set of claim characteristics;

identifying, via a processor, first claims of the historical claim data which exhibit the first set of claim characteristics;

determining, via the processor, whether a number of the first claims exceeds a statistical significance threshold;

in response to a determination that the number of the first claims exceeds a statistical significance threshold, determining, via the processor, a total severity statistical profile based on a total severity of each of the first claims;

determining, via the processor, whether the total severity statistical profile meets predefined profile criteria; and

in response to a determination that the total severity statistical profile meets the predefined profile criteria, associating, via the processor, the first set of claim characteristics with a first claim category;

identifying, via the processor, claims of the historical claim data associated with the first claim category;

assigning, via the processor, each identified claim associated with the first claim category to one of a plurality of total severity ranges based on the total severity of the identified claim;

determining, via the processor, an average cost per claim year divided amongst a plurality of expense categories for claims of each total severity range; and

outputting, to a file server, categorized and aggregated historical claim data including the average cost per claim year for claims of each total severity range.

8. A method according to claim 7, wherein the first set of claim characteristics comprises at least one of:

one or more medical billing codes, a minimum annual spend rate in one or more medical expense categories, one or more co-morbidities, and a disability duration.

9. A method according to claim 8, wherein the one or more co-morbidities comprise at least one of:

obesity, psychiatric issues, and alcohol use.

10. A method according to claim 7, wherein the first claim category comprises one or more of:

non-traumatic cervical surgery without fusion, non-traumatic lumbar surgery without fusion, non-traumatic lumbar fusion surgery, and non-traumatic cervical fusion surgery.

12. A non-transitory medium storing processor-executable program code, the program code executable by a device to:

receive historical claim data from a data warehouse;

determine a first set of claim characteristics;

identify first claims of the historical claim data which exhibit the first set of claim characteristics;

determine whether a number of the first claims exceeds a statistical significance threshold;

in response to a determination that the number of the first claims exceeds a statistical significance threshold, determine a total severity statistical profile based on a total severity of each of the first claims;

determine whether the total severity statistical profile meets predefined profile criteria; and

in response to a determination that the total severity statistical profile meets the predefined profile criteria, associate the first set of claim characteristics with a first claim category;

identify claims of the historical claim data associated with the first claim category;

assign each identified claim associated with the first claim category to one of a plurality of total severity ranges based on the total severity of the identified claim;

determine an average cost per claim year divided amongst a plurality of expense categories for claims of each total severity range; and

output, to a file server, categorized and aggregated historical claim data including the average cost per claim year for claims of each total severity range.

13. A medium according to claim 12, the program code executable by a device to output categorized and aggregated historical claim data comprising program code executable by a device to:

determine a second set of claim characteristics, the second set of claim characteristics being a subset of the first set of claim characteristics;

identify second claims of the historical claim data which exhibit the second set of claim characteristics, the second claims being a subset of the first claims;

determine whether the number of the second claims exceeds the statistical significance threshold;

in response to a determination that the number of the second claims exceeds the statistical significance threshold, determine a second total severity statistical profile based on a total severity of each of the second claims;

determine whether the second total severity statistical profile meets the predefined profile criteria; and

in response to a determination that the second total severity statistical profile meets the predefined profile criteria, associate the second set of claim characteristics with a second claim category, the second claim category being a subcategory of the first claim category.

14. A medium according to claim 12, wherein the first set of claim characteristics comprises at least one of:

one or more medical billing codes, a minimum annual spend rate in one or more medical expense categories, one or more co-morbidities, and a disability duration.

15. A medium according to claim 14, wherein the one or more co-morbidities comprise at least one of:

obesity, psychiatric issues, and alcohol use.

16. A medium according to claim 12, wherein the first claim category comprises one or more of:

non-traumatic cervical surgery without fusion, non-traumatic lumbar surgery without fusion, non-traumatic lumbar fusion surgery, and non-traumatic cervical fusion surgery.

17. A medium according to claim 12, the program code further executable by a device to:

filter the historical claim data based on one or more characteristics prior to identifying the first claim category.