Methods, data structures, systems and computer program products for identifying obsure patterns in healthcare related data

• US 20070174091A1
• Filed: 01/26/2006
• Published: 07/26/2007
• Est. Priority Date: 01/26/2006
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Friedlander, Robert, Kraemer, James
• Application Number:
  US11/339,932
• Publication Number:
  US 20070174091A1
• Time in Patent Office: Days
• US Class Current: 705/3
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: G16H 50/80 for detecting, monitoring or modelling epidemics or pandemics, e.g. flu

Abstract

Methods, data structures, systems and computer program products are provided for identifying patterns in available healthcare related data. A triggering observation in the available healthcare related data is hierarchically related to at least one additional observation in the available healthcare related data based on a possible relationship between the triggering observation and the at least one additional observation in a computer database environment.

Claims

1. A method of identifying patterns in available healthcare related data comprising hierarchically relating a triggering observation in the available healthcare related data with at least one additional observation in the available healthcare related data based on a possible relationship between the triggering observation and the at least one additional observation in a computer database environment.

2. The method of claim 1, further comprising:

receiving a request specifying the triggering observation at the computer database environment; and

providing the at least one additional observation possibly associated with the specified triggering observation responsive to the request.

3. The method of claim 2, further comprising:

determining a likelihood that the triggering observation and the at least one additional observation indicate a possible problem exceeds a predetermined threshold; and

generating an alert indicating that the predetermined threshold has been exceeded if it is determined that the predetermined threshold has been exceeded.

4. The method of claim 1, wherein the at least one additional observation comprises observations of events in the data of interest, the events occurring at different times within a specified time period and/or a specified location.

5. The method of claim 1, further comprising identifying the triggering observation based on at least one identified pattern defining healthcare events.

6. The method of claim 5, further comprising fine tuning the identified patterns and/or adding identified patterns to the computer database environment based on the triggering observation and/or the at least one additional observation.

7. The method of claim 6, further comprising automatically fine tuning the identified patterns and/or adding the identified patterns based on normal patterns, the normal patterns including season of the year, month of the year, day of the week, time of day, holidays, cultural and sporting events, geographic location, climatic norms and/or environmental norms and abnormalities.

8. A data structure for identifying patterns in available healthcare related data in a computer database environment embodied in a computer readable medium, comprising:

a triggering observation object at a first level of hierarchy in a computer database environment; and

at least one additional observation object at a second level of the hierarchy in the computer database environment that is lower than the first level of the hierarchy, wherein the at least one additional observation objects are identified based on a possible relationship between the triggering observation object and the at least one additional observation object.

9. The data structure of claim 8, wherein the at least one additional observation object comprises observations of events in the data of interest, the events occurring at different times within a specified time period and/or a specified location.

10. A system for identifying patterns in available healthcare related data comprising:

a database environment configured to store a triggering observation object at a first level of hierarchy in a computer database environment and at least one additional observation object at a second level of the hierarchy in the computer database environment that is lower than the of the first level of the hierarchy, wherein the at least one additional observation object is identified based on a possible relationship between the triggering observation object and the at least one additional observation object; and

a processor circuit configured to hierarchically relate the triggering observation object to the at least one additional observation object.

11. The system of claim 10, wherein the processor circuit is further configured to receive a request specifying the triggering observation object and provide the at least one additional observation object possibly associated with the specified triggering observation object responsive to the request.

12. The system of claim 10, wherein the processor is further configured to determine a likelihood that the triggering observation object and the at least one additional observation object are related exceeds a predetermined threshold and generate an alert indicating that the predetermined threshold has been exceeded if it is determined that the predetermined threshold has been exceeded.

13. The system of claim 10, wherein the at least one additional observation comprises observations of events in the data of interest, the events occurring at different times within a specified time period and/or a specified location.

14. The system of claim 10, wherein the processor is further configured to identify the triggering observation object based on at least one identified pattern defining healthcare events.

15. The system of claim 14, wherein the processor is further configured to fine tune the identified patterns and/or add identified patterns to the database environment based on the triggering observation object and/or the at least one additional observation object.

16. A computer program product for identifying patterns in available healthcare related data, the computer program product comprising:

computer readable storage medium having computer readable program code embodied in said medium, the computer readable program code comprising;

computer readable program code configured to hierarchically relate a triggering observation in the available healthcare related data with at least one additional observation in the available healthcare related data based on a possible relationship between the triggering observation and the at least one additional observation in a computer database environment.

17. The computer program product of claim 16, further comprising:

computer readable program code configured to receive a request specifying the triggering observation at the computer database environment; and

computer readable program code configured to provide the at least one additional observation possibly associated with the specified triggering observation responsive to the request.

18. The computer program product of claim 17, further comprising:

computer readable program code configured to determine a likelihood that the triggering observation and the at least one additional observation indicate a possible problem exceeds a predetermined threshold; and

computer readable program code configured to generate an alert indicating that the predetermined threshold has been exceeded if it is determined that the predetermined threshold has been exceeded.

19. The computer program product of claim 16, wherein the at least one additional observation comprises observations of events in the data of interest, the events occurring at different times within a specified time period and/or a specified location.

20. The computer program product of claim 16, further comprising computer readable program code configured to identify the triggering observation based on at least one identified pattern defining healthcare events.

21. The computer program product of claim 20, further comprising computer readable program code configured to fine tune the identified patterns and/or add identified patterns to the computer database environment based on the triggering observation and/or the at least one additional observation.

22. The computer readable program product of claim 21, further comprising computer readable program code configured to automatically fine tune the identified patterns and/or add the identified patterns based on normal patterns, the normal patterns including season of the year, month of the year, day of the week, time of day, holidays, cultural and sporting events, geographic location, climatic norms and/or environmental norms and abnormalities.