System and method for rapid assessment of lab value distributions

• US 8,429,186 B2
• Filed: 05/05/2010
• Issued: 04/23/2013
• Est. Priority Date: 05/05/2009
• Status: Active Grant

• Current Assignee: Optuminsight, Inc. (UnitedHealth Group Incorporated)
• Original Assignee: Optuminsight, Inc. (UnitedHealth Group Incorporated)
• Inventors: Anderson, David R.
• Primary Examiner(s): HO, BINH VAN
• Application Number:
  US12/774,270
• Publication Number:
  US 20100287190A1
• Time in Patent Office: 1,084 Days
• Field of Search: 707/769
• US Class Current: 707/769
• CPC Class Codes: G16H 10/40 for data related to laboratory analysis, e.g. patient specimen analysis
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

System and methods for rapid assessment of lab value distributions are provided. In one embodiment, the system includes a data storage device and a server. The data storage device may be configured to store a database comprising one or more records, wherein the records are identified by one or more test codes. The server may receive a medical code, search the database to obtain a first group of records associated with individuals having the medical code, wherein each record of the first group of records is identified by a test code, search the database to obtain a second group of records associated with a control population, wherein each record of the second group of records is identified by the test code, and generate an output comprising a distribution graph on a shared scale from the first and second group of records.

Claims

1. A method for comparing two groups of records comprising:

receiving a medical code;

searching a database stored on a data storage device to obtain a first group of records associated with individuals having the medical code, wherein each record of the first group of records includes a plurality of test codes, and wherein each of the test codes comprises one or more lab values;

searching the database to obtain a second group of records associated with a control population, wherein each record of the second group of records includes the plurality of test codes; and

evaluating a first percentile lab value for each test code of the first group of records representative of each of the one or more lab values of each test code;

evaluating a second percentile lab value for each test code of the second group of records representative of each of the one or more lab values of each test code, wherein each test code for which a second percentile lab value is evaluated is also a test code in the first group of records;

determining a relevancy of each test code to the medical code based on the first percentile lab value for each test code and the second percentile lab value for each test code;

comparing a first percentile lab value representing a particular test code in the first group of records and a second percentile lab value representing the same particular test code in the second group of records; and

generating an output comprising a distribution graph on a shared scale from the first and second group of records, wherein the output displays the relevancy of each test code to the medical code.

2. The method of claim 1, further comprising interpolating each of the one or more lab values of a particular test code of the plurality of test codes in the first group of records to obtain the first percentile lab value and interpolating each of the one or more lab values of the particular test code of the plurality of test codes in the second group of records to obtain the second percentile lab value, wherein the first and second percentile lab values are associated with a shared percentile lab value.

3. The method of claim 1, wherein generating the output further comprises counting distinct records in the first group of records and the second group of records.

4. The method of claim 1, wherein generating the output further comprises aggregating records from the first group and from the second group according to a selected attribute.

5. The method of claim 4, wherein generating the output further comprises computing a probability in response to a ratio of a number of records in the first group having the selected attribute and a number of records in the second group having the selected attribute.

6. The method of claim 1, further comprising selecting the first group of records from within a time interval.

7. The method of claim 1, wherein the record comprises an average, a first reading or a last reading of a test.

8. The method of claim 1, further comprising selecting records in the first group and in the second group according to a limiting criterion.

9. A system comprising:

a data storage device configured to store a database comprising one or more records, wherein the records include a plurality of test codes, and wherein each of the test codes comprises one or more lab values;

a server in data communication with the data storage device, suitably programmed to;

receive a medical code;

search the database to obtain a first group of records associated with individuals having the medical code, wherein each record of the first group of records includes a plurality of test codes, wherein each of the test codes comprises one or more lab values;

search the database to obtain a second group of records associated with a control population, wherein each record of the second group of records includes the plurality of test codes;

evaluate a first percentile lab value for each test code of the first group of records representative of each of the one or more lab values of each test code;

evaluate a second percentile lab value for each test code of the second group of records representative of each of the one or more lab values of each test code, wherein each test code for which a second percentile lab value is evaluated is also a test code in the first group of records;

determine a relevancy of each test code to the medical code based on the first percentile lab value for each test code and the second percentile lab value for each test code;

wherein the server is further configured to compare a first percentile lab value representing a particular test code in the first group of records and a second percentile lab value representing the same particular test code in the second group of records; and

generate an output comprising a distribution graph on a shared scale from the first and second group of records, wherein the output displays the relevancy of each test code to the medical code.

10. The system of claim 9, wherein the server is further configured to interpolate each of the one or more lab values of a particular test code of the plurality of test codes in the first group of records to obtain the first percentile lab value and to interpolate each of the one or more lab values of the particular test code of the plurality of test codes in the second group of records to obtain the second percentile lab value, wherein the first and second percentile lab values are associated with a shared percentile lab value.

11. The system of claim 9, wherein the server is further configured to count distinct records in the first group of records and the second group of records.

12. The system of claim 9, wherein the server is further configured to aggregate records from the first group and from the second group according to a selected attribute.

13. The system of claim 12, wherein the server is further configured to compute a probability in response to a ratio of a number of records in the first group having the selected attribute and a number of records in the second group having the selected attribute.

14. The system of claim 9, wherein the server is further configured to select the first group of records from within a time interval.

15. The system of claim 9, wherein the server is further configured to select records in the first group and in the second group according to a limiting criterion.

16. A computer program product comprising a non-transitory computer readable medium having computer usable program code executable to perform operations comprising:

receiving a medical code;

searching a database stored on a data storage device to obtain a first group of records associated with individuals having the medical code, wherein each record of the first group of records includes a plurality of test codes, and wherein each of the test codes comprises one or more lab values;

searching the database to obtain a second group of records associated with a control population, wherein each record of the second group of records is identified by includes the plurality of test codes; and

evaluating a first percentile lab value for each test code of the first group of records representative of each of the one or more lab values of each test code;

evaluating a second percentile lab value for each test code of the second group of records representative of each of the one or more lab values of each test code, wherein

each test code for which a second percentile lab value is evaluated is also a test code in the first group of records;

determining a relevancy of each test code to the medical code based on the first percentile lab value for each test code and the second percentile lab value for each test code;

comparing a first percentile lab value representing a particular test code in the first group, of records and a second percentile lab value representing the same particular test code in the second group of records; and

generating an output comprising a distribution graph on a shared scale from the first and second group of records, wherein the output displays the relevancy of each test code to the medical code.

17. The computer program product of claim 16, further comprising interpolating each of the one or more lab values of a particular test code of the plurality of test codes in the first group of records to obtain the first percentile lab value and interpolating each of the one or more lab values of the particular test code of the plurality of test codes in the second group of records to obtain the second percentile lab value, wherein the first and second percentile lab values are associated with a shared percentile lab value.

18. The computer program product of claim 16, further comprising counting distinct records in the first group of records and the second group of records.

19. The computer program product of claim 16, further comprising aggregating records from the first group and from the second group according to a selected attribute.

20. The computer program product of claim 19, further comprising computing a probability in response to a ratio of a number of records in the first group having the selected attribute and a number of records in the second group having the selected attribute.

21. The computer program product of claim 16, further comprising selecting the first group of records from within a time interval.

22. The computer program product of claim 16, further comprising selecting records in the first group and in the second group according to a limiting criterion.