SYSTEMS AND METHODS FOR MEDICAL INFORMATION ANALYSIS WITH DEIDENTIFICATION AND REIDENTIFICATION

• US 20130124523A1
• Filed: 10/19/2012
• Published: 05/16/2013
• Est. Priority Date: 09/01/2010
• Status: Active Grant

• Current Assignee: Apixio LLC
• Original Assignee: Jehoshua Bruck
• Inventors: Rogers, Robert Derward, Dastmalchi, Shahram Shawn, Chaudhri, Imran N., Campana, Mary Ellen, Sethumadhavan, Vishnuvyas, Schulte, Darren Matthew
• Granted Patent: US 8,898,798 B2
• Time in Patent Office: Days
• US Class Current: 707/737
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records

Abstract

A medical information navigation engine is useful in association with at least one electronic health record system. The engine decouples identifying information from clinical data from electronic health records. The clinical data includes clinical narrative having discrete data and textual data. The identifying information is stored. Additionally, the identifying information is associated with a token in the clinical data. The clinical data may then be indexed. The discrete data and the textual data in the clinical data may then be mined. Mining includes extracting at least one relevant event from the discrete data and the textual data. Next, the clinical data and identifying information may be reintegrated using the token. The event associated with the mined discrete data and textual data may then be exported. The system may also provide a validation tool for users, including clinicians, to search and view clinical data. The exported event may be used to alter treatment of a patient.

Claims

1. In a medical information navigation engine, a method for quality optimization useful in association with at least one electronic health record system, the method comprising:

decoupling identifying information from clinical data from at least one electronic health record system, wherein the clinical data includes clinical narrative having discrete data and textual data;

storing the identifying information, wherein the identifying information is associated with a token in the clinical data;

indexing the clinical data;

mining the discrete data and the textual data, wherein the mining includes extracting at least one relevant event from the discrete data and the textual data; and

reintegrating the clinical data with the identifying information using the token.

2. The method of claim 1 further comprising providing a validation tool for users, including clinicians, to search and view clinical data.

3. The method of claim 1 further comprising at least one of:

exporting the at least one relevant event associated with the mined discrete data and textual data;

altering treatment of a patient in response to the exported at least one relevant event;

meta-tagging information in the clinical data of a specific patient; and

adding additional information to the clinical data of the specific patient.

4. The method of claim 1 wherein the at least one relevant event comprises at least one of relevant quality measure, concepts and facts about the patient such as conditions or biometric values or facts about clinical services performed for the patient such as surgical procedures or from the discrete data and the textual data, used for the computation of eligibility for a clinical quality or performance measure, or disease management cohort.

5. The method of claim 1 further comprising aggregating billing data from at least one data source, including an electronic health record system.

6. The method of claim 1 wherein the decoupled identifying information from clinical data is encrypted on a per-patient per organization basis.

7. The method of claim 4 further comprising applying at least one terminology code for at least one of relevant discrete and textual data and fact mined and extracted from the clinical narrative for the purposes of computing either eligibility for or compliance with a quality or performance measure.

8. The method of claim 7 further comprising providing a validation tool for users, including care providers, coders, and care managers, to view the source clinical data from which a fact is mined and extracted and provide feedback regarding the accuracy of the extraction result.

9. The method of claim 1 further comprising providing a view including at least one of patient disease, patient condition, patient risk stratification, patient care quality measure compliance, and patient actionable care gap.

10. The method of claim 9 wherein the patient risk stratification includes co-morbidities associated with at least one of the plurality of patients.

11. The method of claim 1 further comprising identifying at least one coding opportunity associated with at least one patient condition mined from unstructured clinical data, wherein the at least one patient condition has not yet been associated with one of the patient claims.

12. The method of claim 11 further comprising presenting at least one optimized target billing code associated with the at least one patient condition.

13. The method of claim 1 further comprising decoupling the identifying information from the clinical data for a plurality of electronic health records for a cohort of patients and encrypting the identifying information for the cohort using a single encryption scheme.

14. The method of claim 13 wherein the cohort includes at least one of demographics, genotype, and phenotype.

15. A medical information navigation engine, useful in association with at least one electronic health record system, the medical information navigation engine comprising:

a processor configured to decouple identifying information from clinical data from at least one electronic health record system, wherein the clinical data includes clinical narrative having discrete data and textual data;

a database configured to store the identifying information, wherein the identifying information is associated with a token in the clinical data;

an indexor configured to index the clinical data;

the processor further configured to mine the discrete data and the textual data, wherein the mining includes extracting at least one relevant event from the discrete data and the textual data; and

the processor further configured to reintegrate the clinical data with the identifying information using the token.

16. The system of claim 15 further comprising a validator configured to provide a validation tool for users, including clinicians, to search and view clinical data.

17. The system of claim 15 wherein the at least one relevant event comprises at least one of relevant quality measure, concepts and facts about the patient such as conditions or biometric values or facts about clinical services performed for the patient such as surgical procedures or from the discrete data and the textual data, used for the computation of eligibility for a clinical quality or performance measure, or disease management cohort.

18. The system of claim 15 wherein the aggregator is further configured to aggregate billing data from at least one data source, including an electronic health record system.

19. The system of claim 17 further comprising a mapper configured to apply at least one terminology code for at least one of relevant discrete and textual data and fact mined and extracted from the clinical narrative for the purposes of computing either eligibility for or compliance with a quality or performance measure.

20. The system of claim 19 further comprising a validator configured to provide a validation tool for users, including care providers, coders, and care managers, to view the source clinical data from which a fact is mined and extracted and provide feedback regarding the accuracy of the extraction result.

21. The system of claim 15 further comprising a visualizer configured to provide a view including at least one of patient disease, patient condition, patient risk stratification, patient care quality measure compliance, and patient actionable care gap.

22. The system of claim 21 wherein the patient risk stratification includes co-modalities associated with at least one of the plurality of patients.

23. The system of claim 15 further comprising identifying at least one coding opportunity associated with at least one patient condition mined from unstructured clinical data, wherein the at least one patient condition has not yet been associated with one of the patient claims.

24. The system of claim 23 further comprising an optimizer configured to present at least one optimized target billing code associated with the at least one patient condition.

25. The system of claim 15 further comprising an interface configured to export the relevant event associated with the mined discrete data and textual data.