Techniques to compute attribute relationships utilizing a leveling operation in a computing environment

• US 9,529,649 B2
• Filed: 10/22/2015
• Issued: 12/27/2016
• Est. Priority Date: 10/23/2014
• Status: Active Grant

• Current Assignee: SAS Institute Incorporated
• Original Assignee: SAS Institute Incorporated
• Inventors: Boyle, Walter, Berry, Cindy Ann
• Primary Examiner(s): Wathen, Brian W
• Application Number:
  US14/920,264
• Publication Number:
  US 20160117205A1
• Time in Patent Office: 432 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/23 Updating
• CPC Class Codes: G06F 9/542 Event management; Broadcasting; Multicasting; Notifications
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

Various embodiments include a system having interfaces, storage devices, memory, and processing circuitry. The system may be coupled with one or more storage devices and may receive episode information for a patient from a storage device via one or more wired or wireless links, the episode information includes a plurality of episodes associated with the patient, each of the plurality of episodes is a specific instance of a medical condition. The system may generate a candidate episode pairs list comprising a plurality of candidate episode pairs. Embodiments may also include the system generating a transition list comprising episode pairs from the plurality of candidate episode pairs in the candidate episode pairs list and determining attribute relationships between the plurality of episodes for the patient based on episode pairs in the transition list, the attribute relationships used to attribute items between the plurality of episodes.

Claims

1. An apparatus, comprising:

processing circuitry;

memory coupled with the processing circuitry;

a candidate component having instructions storable in the memory and operable on the processing circuitry, the candidate component to;

receive episode information for a patient from a storage device via one or more links, the episode information comprising a plurality of episodes associated with the patient, each of the plurality of episodes is a specific instance of a medical condition, and

generate a candidate episode pairs list comprising a plurality of candidate episode pairs by;

performing a Cartesian merge of the plurality of episodes, and

comparing each of the candidate episode pairs with association information defining related medical conditions,

each of the candidate episode pairs having a different association level and each of the candidate episode pairs define a parent-child relationship,

each of the association levels define a relative strength between episodes in each of the candidate episode pairs;

a transition component having instructions storable in the memory and operable on the processing circuitry, the transition component to generate a transition list comprising episode pairs from the plurality of candidate episode pairs in the candidate episode pairs list; and

a leveling component having instructions storable in the memory and operable on the processing circuitry to determine attribute relationships between the plurality of episodes for the patient based on episode pairs in the transition list, the attribute relationships used to attribute items between the plurality of episodes.

2. The apparatus of claim 1, the candidate component to remove candidate episode pairs not defined as related medical conditions from candidate episode pairs lists based on the comparison with the association information.

3. The apparatus of claim 1, the candidate component to:

determine whether episodes of a particular candidate episode pair overlap in time; and

remove the particular candidate episode pair from the candidate episode pairs list based on determining that the particular candidate episode pair does not include episodes that overlap in time.

4. The apparatus of claim 1, the candidate component to adjust an association level for a first candidate episode pair having a parent episode that is a child episode in a second candidate episode pair by performing an offset operation or a stacking operation.

5. The apparatus of claim 1, the transition component to:

iteratively add candidate episode pairs from the candidate episode pairs list to the transition list starting with candidate episode pairs with a lowest association level;

remove each remaining candidate episode pairs from the candidate episode pairs list having a same child episode of an episode pair in the transition list;

after each iteration, increase to a next lowest association level associated with candidate episode pairs and repeat the add and remove operations until no candidate episode pair remain in the candidate episode pair list; and

add identity episode pairs to the transition list for each episode already in the transition list.

6. The apparatus of claim 1, the relative strength between episodes to indicate a likelihood of one episode causing another episode, a lower association level for the relative strength to indicate a higher likelihood than a higher association level.

7. The apparatus of claim 1, the leveling component to determine the attribute relationships by iteratively performing a leveling operation for each episode pairs in the transition list, the leveling operation to determine a parent episode for each child episode of each episode pair in the transition list at a particular association level.

8. The apparatus of claim 7, the leveling operation to start with one or more identity episode pairs in the transition list and add each episode pair to a table, evaluate each episode pair at each association level, and increase by association level until no episode pairs remain in the transition list.

9. The apparatus of claim 7, the leveling operation to determine a number of times each episode is a child episode at the particular level, and calculate a weighted level value for each episode pair used to determine the attribute relationships between episodes, the attribute relationships comprising a cost association for the episodes.

10. The apparatus of claim 1, comprising:

an interface coupled with the memory and the processing circuitry, the interface to receive the episode information from a remote device or a local device.

11. The apparatus of claim 1, comprising:

an interface coupled with the memory and the processing circuitry, the interface to receive the association information from a remote device or a local device.

12. At least one non-transitory computer-readable storage medium comprising instructions that when executed cause processing circuitry to:

identify episode information for a patient, the episode information comprising a plurality of episodes associated with the patient, each of the plurality of episodes is a specific instance of a medical condition;

generate a candidate episode pairs list comprising a plurality of candidate episode pairs by;

performing a Cartesian merge of the plurality of episodes, and

comparing each of the candidate episode pairs with association information defining related medical conditions,

each of the candidate episode pairs having a particular association level and each of the candidate episode pairs define a parent-child relationship,

each of the particular association levels define a relative strength between episodes in each of the candidate episode pairs;

generate a transition list comprising episode pairs from candidate episode pairs in the candidate episode pairs list; and

determine attribute relationships between the plurality of episodes for the patient based on the episode pairs in the transition list, the attribute relationships used to attribute items between the plurality of episodes.

13. The non-transitory computer-readable storage medium of claim 12, comprising instructions that when executed cause the processing circuitry to remove candidate episode pairs not defined as related medical conditions from the candidate episode pairs list.

14. The non-transitory computer-readable storage medium of claim 12, comprising instructions that when executed cause the processing circuitry to:

determine whether episodes of a particular candidate episode pair overlap in time; and

remove the particular candidate episode pair from the candidate episode pairs list based on determining that the particular candidate episode pair does not include episodes that overlap in time.

15. The non-transitory computer-readable storage medium of claim 12, comprising instructions that when executed cause the processing circuitry to adjust an association level for a first candidate episode pair having a parent episode that is a child episode in a second candidate episode pair by performing an offset operation or a stacking operation.

16. The non-transitory computer-readable storage medium of claim 12, comprising instructions that when executed cause the processing circuitry to generate the transition list, the instructions further causing the processing circuitry to:

iteratively add candidate episode pairs from the candidate episode pairs list to the transition list starting with candidate episode pairs with a lowest association level;

remove each remaining candidate episode pair from the candidate episode pairs list having a same child episode an episode pair in the transition list;

after each iteration, increase to a next lowest association level associated with candidate episode pairs and repeat the add and remove operations until no candidate episode pairs remain in the candidate episode pairs list; and

add identity episode pairs for each episode in the transition list.

17. The non-transitory computer-readable storage medium of claim 12, the relative strength between episodes to indicate a likelihood of one episode causing another episode, a lower association level for the relative strength to indicate a higher likelihood than a higher association level.

18. The non-transitory computer-readable storage medium of claim 12, comprising instructions that when executed cause the processing circuitry to determine the attribute relationships, the instructions further causing the processing circuitry to:

iteratively perform a leveling operation for each episode pair in the transition list, the leveling operation to determine a final parent episode for each child episode of each episode pair in the transition list, the final parent episode determined at a particular level.

19. The computer-readable storage medium of claim 18, the leveling operation to start with one or more identity episode pairs in the transition list and add each episode pair to a table, evaluate each episode pair at each association level, and increase by association level until no episode pairs remain in the transition list.

20. The computer-readable storage medium of claim 18, the leveling operation to determine a number of times each episode is a child episode at the particular level, and calculate a weighted level value for each episode pair for each child episode used to determine the attribute relationships between episodes, the attribute relationships comprising a cost association for the episodes.

21. A computer-implemented method, comprising:

identifying, by processing circuitry, episode information for a patient, the episode information comprising a plurality of episodes associated with the patient, each of the plurality of episodes is a specific instance of a medical condition;

generating, by the processing circuitry, a candidate episode pairs list comprising a plurality of candidate episode pairs by;

performing a Cartesian merge of the plurality of episodes, and

comparing each of the candidate episode pairs with association information defining related medical conditions,

each of the candidate episode pairs having an association level and each of the candidate episode pairs define a parent-child relationship,

each of the association levels define a relative strength between episodes in each of the candidate episode pairs;

generating, by the processing circuitry, a transition list comprising one or more episode pairs from the candidate episode pairs in the candidate episode pairs list; and

determining, by the processing circuitry, attribute relationships between the plurality of episodes for the patient based on the episode pairs in the transition list, the attribute relationships used to attribute items between the plurality of episodes.

22. The computer-implemented method of claim 21, comprising removing, by the processing circuitry, candidate episode pairs not defined as related medical condition from candidate episode pairs lists.

23. The computer-implemented method of claim 21, comprising:

determining, by the processing circuitry, whether episodes of a particular candidate episode pair overlap in time; and

removing the particular candidate episode pair from the candidate episodes pairs list based on determining that the particular candidate episode pair does not include episodes that overlap in time.

24. The computer-implemented method of claim 21, comprising:

adjusting the association level for a first candidate episode pair having a parent episode that is a child episode in a second candidate episode pair by performing an offset operation or a stacking operation.

25. The computer-implemented method of claim 21, comprising:

generating the transition list comprising;

iteratively adding candidate episode pairs from the candidate episode pairs list to the transition list starting with candidate episode pairs with a lowest association level;

removing each remaining candidate episode pairs from the candidate episode pairs list having a same child episode of an episode pair in the transition list; and

after each iteration, increasing to a next lowest association level associated with candidate episode pairs and repeating the adding and removing operations until no candidate episode pair remain in the candidate episode pair list; and

adding identity episode pairs for each episode in the transition list.

26. The computer-implemented method of claim 21, the relative strength between episodes to indicate a likelihood of one episode causing another episode, a lower association level for the relative strength to indicate a higher likelihood than a higher association level.

27. The computer-implemented method of claim 21, the determining the attribute relationships comprising iteratively performing a leveling operation for each episode pair in the transition list, the leveling operation to determine a parent episode for each child episode of each episode pair in the transition list at a particular association level.

28. The computer-implemented method of claim 27, the leveling operation comprising starting with identity episode pairs in the transition list and add each episode pair to a table, evaluating each episode pair at each association level, and increasing by association level until no episode pair remain in the transition list.

29. The computer-implemented method of claim 27, the leveling operation comprising determining a number of times each episode is a child episode at the particular level, and calculating a weighted level value for each episode pair used to determine the attribute relationships between episodes, the attribute relationships comprising cost associations between the episodes.

30. A system, comprising:

a storage device;

an interface coupled with the storage device;

processing circuitry coupled with the storage device and interface;

memory coupled with the processing circuitry, the storage device, and the interface;

a candidate component having instructions storable in the memory and operable on the processing circuitry, the candidate component to;

receive episode information for a patient from a storage device via one or more links, the episode information comprising a plurality of episodes associated with the patient, each of the plurality of episodes is a specific instance of a medical condition, and

generate a candidate episode pairs list comprising a plurality of candidate episode pairs by;

performing a Cartesian merge of the plurality of episodes, and

comparing each of the candidate episode pairs with association information defining related medical conditions,

each of the candidate episode pairs having a different association level and each of the candidate episode pairs define a parent-child relationship,

each of the association levels define a relative strength between episodes in each of the candidate episode pairs;

a transition component having instructions storable in the memory and operable on the processing circuitry, the transition component to generate a transition list comprising episode pairs from the plurality of candidate episode pairs in the candidate episode pairs list; and

a leveling component having instructions storable in the memory and operable on the processing circuitry to determine attribute relationships between the plurality of episodes for the patient based on episode pairs in the transition list, the attribute relationships used to attribute items between the plurality of episodes.