Systems and methods for mining aggregated clinical documentation using concept associations

1. In a Medical Information Navigation Engine (“MINE”), a computerized method for computing concept associations by mining patient documentation in the aggregate, the method comprising:

assembling a plurality of patient documents for a single patient;

identifying pairs and triples of clinical concepts in the plurality of patient documents by codes for the clinical concept in a standardized coding system, using the computerized MINE;

computing associations between the pairs and triples of clinical concepts using co-occurrences within at least one of the plurality of patient documents by computing degrees of correlation between any two of the pairs and triples of clinical concepts, using the computerized MINE;

filtering out random associations from the computed associations by taking a ratio of a probability of associations as observed with probability of association due to randomness, using the computerized MINE;

repeating the above steps for each of a plurality of patients;

storing the filtered computed associations for all of the plurality of patients in an association matrix where protected health information for any given patient is not exposed;

receiving a plurality of query concepts from a user query directed to a specific patient, wherein the specific patient is not part of the plurality of patients;

extracting a plurality of clinical concepts from patient documents belonging to the specific patient;

generating a candidate list by cross referencing the plurality of clinical concepts belonging to the specific patient to the plurality of query concepts using the association matrix;

ranking the candidate list in order of expected payout for the concept based upon a lookup table;

selecting the candidates in the ranked candidate list above a rank threshold; and

providing the selected candidates to the user.

2. The method of claim 1 wherein the assembling of the plurality of patient documents include aggregating patient data from the plurality of patient documents.

3. The method of claim 1 wherein the filtering out of the random associations include comparing a probability of concurrent occurrences.

4. The method of claim 1 wherein the plurality of query concepts is identified in accordance with a standard coding system.

5. The method of claim 1 wherein the ranking the candidate list is processed in a knowledge exchange and the processing includes recording whether the processed ranked candidate list were selected by the user.

6. The method of claim 1 wherein the ranking of the candidate list is based on at least one of recency, risk, strength of association, source of data and user context.

7. The method of claim 1 wherein the ranked candidate list is provided to the user within a workflow of the user, and wherein the workflow includes one of at least a billing system and a case management system.

8. A computerized Medical Information Navigation Engine (“MINE”) configured to compute concept associations by mining patient documentation in the aggregate, the MINE comprising:

a medical processor configured to:

assemble a plurality of patient documents for a single patient;

identify pairs and triples of clinical concepts in the plurality of patient documents by codes for the clinical concept in a standardized coding system;

compute associations between the pairs and triples of clinical concepts using co-occurrences within at least one of the plurality of patient documents by computing degrees of correlation between any two of the pairs and triples of clinical concepts; and

filter out random associations from the computed associations by taking a ratio of a probability of associations as observed with probability of association due to randomness; and

repeating the above steps for each of a plurality of patients; and

an association matrix configured to store the filtered computed associations for all of the plurality of patients where protected health information for any given patient is not exposed; and

a query system configured to:

receive a plurality of query concepts from a user query directed to a specific patient, wherein the specific patient is not part of the plurality of patients;

extract a plurality of clinical concepts from patient documents belonging to the specific patient;

generate a candidate list by cross referencing the plurality of clinical concepts belonging to the specific patient to the plurality of query concepts using the association matrix;

rank the candidate list in order of expected payout for the concept based upon a lookup table;

select the candidates in the ranked candidate list above a rank threshold; and

providing the selected candidates to the user.

9. The MINE of claim 8 wherein the associations are computed using aggregate patient data from the at least one of the plurality of patient document thereby reducing risk of exposing protected health information (PHI).

10. The MINE of claim 8 wherein the plurality of query concepts is identified in accordance with a standard coding system.

11. The MINE of claim 8 wherein the ranked candidate list is processed in a knowledge exchange of the knowledge provider and wherein the knowledge exchange is configured to record whether the processed ranked candidate list were selected by the user.

12. The MINE of claim 8 wherein the ranking of the candidate list is based on at least one of recency, risk, strength of association, source of data and user context.

13. The MINE of claim 8 wherein the ranked candidate list is provided to the user within a workflow of the user, and wherein the workflow includes one of at least a billing system and a case management system.

14. The MINE of claim 8 further comprising automatically reconciling redundant data thereby maximizing delivery of meaningful information based on intent interpretation of user query.