Method and System for Ontology Based Analytics

• US 20130096945A1
• Filed: 03/14/2012
• Published: 04/18/2013
• Est. Priority Date: 10/13/2011
• Status: Abandoned Application

• Current Assignee: Board of Trustees of the Leland Stanford Junior University (Stanford Management Co.)
• Original Assignee: Board of Trustees of the Leland Stanford Junior University (Stanford Management Co.)
• Inventors: Shah, Nigam, Musen, Mark A., LePendu, Paea
• Application Number:
  US13/420,402
• Publication Number:
  US 20130096945A1
• Time in Patent Office: Days
• US Class Current: 705/3
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: G16H 70/60 relating to pathologies

Abstract

The present invention provides a mechanism to use terminologies and ontologies for the purpose of indexing, annotating and semantically marking up existing collections of datasets. The invention further provides a system for incorporating terminologies, ontologies, and contextual annotation in specific domains, such as utilizing biomedical concept hierarchies in data analytics. The resulting rich structure supports specific mechanisms for data mining and machine learning.

Claims

1. A computer-implemented method for de-identifying digital information records, comprising:

receiving a list of terms of interest that may exist within digital information records, wherein the list of terms do not include terms that uniquely identify an individual;

receiving at least one digital information record corresponding to at least one individual, wherein the at least one digital information record includes information that uniquely identifies at least one individual;

identifying an occurrence within the at least one digital information record of terms from the list of terms; and

collecting the occurrence of terms as a set of terms, wherein the set of terms does not include information that uniquely identifies the at least one individual.

2. The method of claim 1, wherein the digital information record is a digital medical record.

3. The method of claim 2, wherein the list of terms of interest is a list of descriptive patient features.

4. The method of claim 3, wherein the list of descriptive patient features is based on at least one of drug, disease, or anatomy ontologies.

5. The method of claim 1, further comprising identifying a negated occurrence within the at least one digital information record of terms from the list of terms.

6. The method of claim 1, further comprising analyzing the collected set of terms.

7. The method of claim 1, further comprising collecting information associated with at least some of the terms from the list of terms.

8. The method of claim 7, wherein the collected information includes a frequency of occurrence for at least one term of interest.

9. The method of claim 7, wherein the collected information includes syntactic information for at least one term of interest.

10. The method of claim 7, wherein the collected information includes semantic information for at least one term of interest.

19. The computer-readable medium of claim 7, wherein the collected information includes syntactic information for at least one term of interest.

11. A computer-readable medium including instructions that, when executed by a processing unit, causes the processing unit to de-identify digital information records, by performing the steps of:

receiving a list of terms of interest that may exist within digital information records, wherein the list of terms do not include terms that uniquely identify an individual;

receiving at least one digital information record corresponding to at least one individual, wherein the at least one digital information record includes information that uniquely identifies at least one individual;

identifying an occurrence within the at least one digital information record of terms from the list of terms; and

collecting the occurrence of terms as a set of terms, wherein the set of terms does not include information that uniquely identifies the at least one individual.

12. The computer-readable medium of claim 11, wherein the digital information record is a digital medical record.

13. The computer-readable medium of claim 12, wherein the list of terms of interest is a list of descriptive patient features.

14. The computer-readable medium of claim 13, wherein the list of descriptive patient features is based on at least one of drug, disease, or anatomy ontologies.

15. The computer-readable medium of claim 11, further comprising identifying a negated occurrence within the at least one digital information record of terms from the list of terms.

16. The computer-readable medium of claim 11, further comprising analyzing the collected set of terms.

17. The computer-readable medium of claim 11, further comprising collecting information associated with at least some of the terms from the list of terms.

18. The computer-readable medium of claim 17, wherein the collected information includes a frequency of occurrence for at least one term of interest.

20. The computer-readable medium of claim 17, wherein the collected information includes semantic information for at least one term of interest.

21. A computing device comprising:

a data bus;

a memory unit coupled to the data bus;

a processing unit coupled to the data bus and configured to

receive a list of terms of interest that may exist within digital information records, wherein the list of terms do not include terms that uniquely identify an individual;

receive at least one digital information record corresponding to at least one individual, wherein the at least one digital information record includes information that uniquely identifies at least one individual;

identify an occurrence within the at least one digital information record of terms from the list of terms; and

collect the occurrence of terms as a set of terms, wherein the set of terms does not include information that uniquely identifies the at least one individual.