Adaptive hybrid reasoning decision support system

• US 8,504,514 B2
• Filed: 08/13/2012
• Issued: 08/06/2013
• Est. Priority Date: 05/05/2008
• Status: Active Grant

• Current Assignee: University Of Massachusetts
• Original Assignee: University Of Massachusetts
• Inventors: Fortier, Paul J., Dluhy, Nancy, Mitsa, Theophano
• Primary Examiner(s): Jami, Hares
• Application Number:
  US13/584,380
• Publication Number:
  US 20120310947A1
• Time in Patent Office: 358 Days
• Field of Search: 707/603, 707/705, 707/736, 707/741, 707/999.1
• US Class Current: 707/603
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records

Abstract

A method for indexing a plurality of nodes using a computer system is provided. The computer system includes data storage and a processor coupled to the data storage. The method includes acts of storing the plurality of nodes in the data storage, each of the plurality of nodes having a hit count, a link count and an outcome, creating a qualitative index ordering a plurality of nodes according to the hit count, the link count and the outcome of each node and storing the qualitative index in the data storage. The hit count of each node indicates a number of times a case attribute associated with the node is presented to a user. The link count of each node indicates a number of times the case attribute associated with the node is affirmed as useful. The outcome of each node indicates a desirability of the outcome.

Claims

1. A method for indexing a plurality of nodes using a computer system, the computer system including data storage and a processor coupled to the data storage, the method comprising:

storing the plurality of nodes in the data storage, each of the plurality of nodes having a hit count, a link count and an outcome, the hit count of each node indicating a number of times a case attribute associated with the node is presented to a user, the link count of each node indicating a number of times the case attribute associated with the node is affirmed as useful, the outcome of each node indicating a desirability of the outcome;

creating a qualitative index ordering the plurality of nodes according to the hit count, the link count and the outcome of each node; and

storing the qualitative index in the data storage, wherein storing the plurality of nodes includes storing a plurality of cases, and wherein storing the plurality of cases includes storing a hit count of each case indicating a number of times a rule associated with the case was presented to the user.

2. The method according to claim 1, wherein storing the plurality of nodes includes storing a tree of nodes.

3. The method according to claim 1, wherein creating the qualitative index includes ordering the plurality of nodes in descending order.

4. The method according to claim 1, further comprising:

creating a semantic index ordering the plurality of nodes according to a diagnosis-related group associated with each node;

creating a quantitative index ordering the plurality of nodes according to a plurality of patient data values associated with each node;

creating an ontological index ordering the plurality of nodes according to at least one clinical term taxonomy;

creating a temporal index ordering the plurality of nodes according to a time period associated with each node;

creating a temporal-ontological index ordering the plurality of nodes according to a time period associated with each node and the at least one clinical term taxonomy; and

storing the semantic index in the data storage.

5. The method according to claim 4, further comprising:

receiving a first case from the user, the first case including a patient history, a patient characteristic, a diagnosis and an intervention;

determining, using the diagnosis, a semantic similarity between the first case and a plurality of cases associated with at least one of the plurality of nodes;

determining, using the patient characteristic and the intervention, a quantitative similarity between the first case and the plurality of cases; and

determining, using the patient history, a temporal similarity between the first case and the plurality of cases.

6. The method according to claim 5, further comprising:

determining a similarity vote based at least in part on the semantic similarity, the quantitative similarity and the temporal similarity, the similarity vote indicating a second case of the plurality of cases; and

presenting the second case to the user.

7. The method according to claim 6, further comprising:

adjusting the hit count of any of the plurality of nodes when a case attribute associated with a node is presented to the user; and

adjusting the link count of any of the plurality of nodes when the case attribute associated with the node is affirmed as useful.

8. A system for indexing a plurality of nodes comprising:

a storage medium; and

a processor coupled to the storage medium and configured to;

store the plurality of nodes on the storage medium, each of the plurality of nodes having a hit count, a link count and an outcome, the hit count of each node indicating a number of times a case attribute associated with the node is presented to a user, the link count of each node indicating a number of times the case attribute associated with the node is affirmed as useful, the outcome of each node indicating a desirability of the outcome;

create a qualitative index ordering the plurality of nodes according to the hit count, the link count and the outcome of each node; and

store the qualitative index in the data storage, wherein the processor configured to store the plurality of nodes is further configured to store a plurality of cases, and wherein the processor configured to store the plurality of cases is further configured to store a hit count of each case indicating a number of times a rule associated with the case was presented to the user.

9. The system according to claim 8, wherein the processor configured to store the plurality of nodes is further configured to store a tree of nodes.

10. The system according to claim 8, wherein the processor configured to create the qualitative index is further configured to order the plurality of nodes in descending order.

11. The system according to claim 8, wherein the processor is further configured to:

create a semantic index ordering the plurality of nodes according to a diagnosis-related group associated with each node;

create a quantitative index ordering the plurality of nodes according to a plurality of patient data values associated with each node;

create an ontological index ordering the plurality of nodes according to at least one clinical term taxonomy;

create a temporal index ordering the plurality of nodes according to a time period associated with each node;

create a temporal-ontological index ordering the plurality of nodes according to a time period associated with each node and the at least one clinical term taxonomy; and

store the semantic index in the data storage.

12. The system according to claim 11, wherein the processor is further configured to:

receive a first case from the user, the first case including a patient history, a patient characteristic, a diagnosis and an intervention;

determine, using the diagnosis, a semantic similarity between the first case and a plurality of cases associated with at least one of the plurality of nodes;

determine, using the patient characteristic and the intervention, a quantitative similarity between the first case and the plurality of cases; and

determine, using the patient history, a temporal similarity between the first case and the plurality of cases.

13. The system according to claim 12, wherein the processor is further configured to:

determine a similarity vote based at least in part on the semantic similarity, the quantitative similarity and the temporal similarity, the similarity vote indicating a second case of the plurality of cases; and

present the second case to the user.

14. The system according to claim 13, wherein the processor is further configured to:

adjust the hit count of any of the plurality of nodes when a case attribute associated with a node is presented to the user; and

adjust the link count of any of the plurality of nodes when the case attribute associated with the node is affirmed as useful.

15. A non-transitory computer readable medium storing sequences of instruction for indexing a plurality of nodes, the sequences of instruction including instructions that instruct at least one processor to:

store the plurality of nodes in the data storage, each of the plurality of nodes having a hit count, a link count and an outcome, the hit count of each node indicating a number of times a case attribute associated with the node is presented to a user, the link count of each node indicating a number of times the case attribute associated with the node is affirmed as useful, the outcome of each node indicating a desirability of the outcome;

create a qualitative index ordering the plurality of nodes according to the hit count, the link count and the outcome of each node; and

store the qualitative index in the data storage, wherein the instructions to store the plurality of nodes include instructions to store a plurality of cases, and wherein the instructions to store the plurality of cases include instructions to store a hit count of each case indicating a number of times a rule associated with the case was presented to the user.