Efficient SQL based multi-attribute clustering

• US 9,195,732 B2
• Filed: 03/15/2013
• Issued: 11/24/2015
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: Optum Incorporated (UnitedHealth Group Incorporated)
• Original Assignee: Optum Incorporated (UnitedHealth Group Incorporated)
• Inventors: Anderson, David R., Hane, Christopher A.
• Primary Examiner(s): LU, KUEN S
• Application Number:
  US13/843,441
• Publication Number:
  US 20140280309A1
• Time in Patent Office: 984 Days
• Field of Search: 707/769
• US Class Current: 1/1
• CPC Class Codes: G06F 16/211 Schema design and management
• CPC Class Codes: G06F 16/22 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/2452 Query translation
• CPC Class Codes: G06F 16/284 Relational databases
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 40/177 of tables; using ruled lines
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

Efficient SQL based multi-attribute clustering of data attributes may be used to identify the most relevant combination of data attributes to an outcome. A global outcome value may be calculated to represent an average of the outcome. A subset outcome value for each subset of data attributes of a plurality of attributes may be calculated to represent average of the outcome for the subset. For each subset of data attributes, a number of members associated with the subset may be compared to a threshold, and the subsets with less members than the threshold may be removed. The subset outcome value for each subset of data attributes may be compared to the global outcome value, and a report may be generated that identifies each subset for which the corresponding subset outcome value is greater than or less than the global outcome value.

Claims

1. A method, comprising:

receiving a global outcome value, wherein the global outcome value is a global threshold for identifying a plurality of subsets of data attributes;

calculating, in parallel, a plurality of subset outcome values for the plurality of subsets of data attributes, respectively, of a plurality of data attributes, wherein each subset outcome value of a subset of data attributes represents an average value of a data attribute outcome for members that are associated with each of the data attributes of the subset of data attributes;

comparing, for each subset of data attributes, a number of members associated with the subset of data attributes with a size threshold;

removing each subset of data attributes for which the number of members associated with the subset is below the size threshold;

comparing, for each subset of data attributes, the subset outcome value for the subset with the global outcome value as the global threshold for identifying a plurality of subsets of data attributes; and

generating a report that identifies each subset of data attributes for which the corresponding subset outcome value is greater by a first threshold than or less by a second threshold than the global outcome value.

2. The method of claim 1, wherein the method is implemented using a database query language.

3. The method of claim 1, wherein the global outcome value represents an average value of the data attribute outcome for a plurality of members and is calculated based on inputs from a user through a user interface.

4. The method of claim 3, wherein the plurality of members comprise a plurality of patients.

5. The method of claim 1, further comprising receiving the size threshold as an input from a user through a user interface.

6. The method of claim 1, further comprising algorithmically defining the size threshold.

7. The method of claim 1, wherein each subset of data attributes identified in the generated report is input into a regression model to create a predictive model.

8. A system, comprising:

a data storage device configured to store a plurality of data records for a plurality of members, wherein each data record comprises a plurality of data attributes;

a processor in data communication with the data storage device and configured to;

receive a global outcome value, wherein the global outcome value is a global threshold for identifying a plurality of subsets of data attributes;

calculate, in parallel, a subset outcome value for the plurality of subsets of data attributes of a plurality of data attributes, wherein each subset outcome value of a subset of data attributes represents an average value of a data attribute outcome for members that are associated with each of the data attributes of the subset of data attributes;

compare, for each subset of data attributes, a number of members associated with the subset of data attributes with a size threshold;

remove each subset of data attributes for which the number of members associated with the subset is below the size threshold;

compare, for each subset of data attributes, the subset outcome value for the subset with the global outcome value as the global threshold for identifying a plurality of subsets of data attributes; and

generate a report that identifies each subset of data attributes for which the corresponding subset outcome value is greater by a first threshold than or less by a second threshold than the global outcome value.

9. The system of claim 8, wherein the processor is in data communication with the data storage device using a database query language.

10. The system of claim 8, wherein the global outcome value represents an average value of the data attribute outcome for a plurality of members and is calculated based on inputs from a user through a user interface.

11. The system of claim 10, wherein the plurality of members comprise a plurality of patients.

12. The system of claim 8, further comprising receiving the size threshold as an input from a user through a user interface.

13. The system of claim 8, further comprising algorithmically defining the size threshold.

14. The system of claim 8, wherein each subset of data attributes identified in the generated report is input into a regression model to create a predictive model.

15. A computer program product, comprising a non-transitory computer readable medium having computer executable instructions to perform operations comprising:

receiving a global outcome value, wherein the global outcome value is a global threshold for identifying a plurality of subsets of data attributes;

calculating, in parallel, a subset outcome value for the plurality of subsets of data attributes of a plurality of data attributes, wherein each subset outcome value of a subset of data attributes represents an average value of a data attribute outcome for members that are associated with each of the data attributes of the subset of data attributes;

comparing, for each subset of data attributes, a number of members associated with the subset of data attributes with a size threshold;

removing each subset of data attributes for which the number of members associated with the subset is below the size threshold;

comparing, for each subset of data attributes, the subset outcome value for the subset with the global outcome value as the global threshold for identifying a plurality of subsets of data attributes; and

generating a report that identifies each subset of data attributes for which the corresponding subset outcome value is greater by a first threshold than or less by a second threshold than the global outcome value.

16. The computer program product of claim 15, wherein the computer executable instructions are written in a database query language.

17. The computer program product of claim 15, wherein the global outcome value represents an average value of the data attribute outcome for a plurality of members and is calculated based on inputs from a user through a user interface.

18. The computer program product of claim 17, wherein the plurality of members comprise a plurality of patients.

19. The computer program product of claim 15, wherein the medium further comprises computer executable instructions to perform operations comprising receiving the size threshold as an input from a user through a user interface.

20. The computer program product of claim 15, wherein the medium further comprises computer executable instructions to perform operations comprising algorithmically defining the size threshold.

21. The computer program product of claim 15, wherein each subset of data attributes identified in the generated report is input into a regression model to create a predictive model.