Method and System for Extracting Data From a Plurality of Electronic Data Stores of Patient Data to Provide Provider and Patient Data Similarity Scoring

• US 20180121604A1
• Filed: 10/28/2016
• Published: 05/03/2018
• Est. Priority Date: 10/28/2016
• Status: Active Grant

• Current Assignee: Intelligent Medical Objects, Inc.
• Original Assignee: Intelligent Medical Objects, Inc.
• Inventors: Naeymi-Rad, Frank, Cardwell, Matthew, DeCaro, Michael, Paul, Erina, Wang, Yiqing, Thompson, James, Kanter, Andrew
• Granted Patent: US 11,915,803 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 40/205 Parsing
• 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

Abstract

A system and method for extracting data from an electronic health record to provide provider and patient data similarity scoring includes: encoding a problem list for a plurality of patients with concepts from a common electronic health record ontology. In one aspect, the patients have electronic health records maintained by a plurality of providers. The system and method then may parse the concepts into a plurality of clusters or categories and determining, for each of the providers, a total number of patients that have at least one problem in a cluster or category or determining, for each patient, which of the plurality of clusters or categories correspond to at least one concept encoded in the patient'"'"'s problem list. The system and method then may calculate for each pair of providers or patients, a distance between the providers or patients.

Claims

1. A method for extracting data from a plurality of electronic data repositories to provide provider and patient data similarity scoring, comprising:

encoding a problem list for a plurality of patients with concepts from a common electronic health record ontology, wherein the plurality of electronic data repositories are maintained by a plurality of providers;

parsing the concepts into a plurality of clusters or categories;

determining, for each of the providers, a total number of patients that have at least one problem in a cluster or category;

iterating the determining step for each of the remaining clusters or categories; and

calculating, for each pair of providers, a distance between the providers.

2. The method of claim 1, wherein the calculating step includes calculating a Minkowski distance of order 2 between each pair of providers.

3. The method of claim 1, wherein the calculating step includes normalizing the results of the determining and iterating steps by dividing those results by a respective provider'"'"'s total number of patients.

4. The method of claim 1, wherein the common electronic health record ontology is an interface terminology.

5. The method of claim 4, wherein the problem list also is encoded, directly or indirectly, with a health record ontology selected from the group consisting of the Systematized Nomenclature of Medicine and the International Classification of Disease.

6. The method of claim 1, wherein the calculating step uses both the results of the determining and iterating steps as well as exact problem list matches as inputs.

7. The method of claim 6, wherein the results of the determining and iterating steps and the exact problem list matches are weighted equally.

8. The method of claim 6, wherein the results of the determining and iterating steps are weighted more heavily than the exact problem list matches.

9. The method of claim 6, where the exact problem list matches are weighted more heavily than the results of the determining and iterating steps.

10. The method of claim 1, wherein at least one of the electronic data repositories is an electronic health record repository.

11. The method of claim 1, wherein at least one of the electronic data repositories is a problem list log repository.

12. A method for extracting data from an electronic data repository to provide provider and patient data similarity scoring, comprising:

encoding a problem list for a plurality of patients with concepts from a common electronic health record ontology;

parsing the concepts into a plurality of clusters or categories;

determining, for each patient, which of the plurality of clusters or categories correspond to at least one concept encoded in the patient'"'"'s problem list; and

calculating, for each pair of patients, a distance between the patients.

13. The method of claim 12, wherein the calculating step includes calculating a Minkowski distance of order 2 between each pair of patients.

14. The method of claim 12, wherein the calculating step includes normalizing the results of the determining step by dividing those results by a respective patient'"'"'s total number of problems.

15. The method of claim 12, wherein the common electronic health record ontology is an interface terminology.

16. The method of claim 15, wherein the problem list also is encoded, directly or indirectly, with a health record ontology selected from the group consisting of the Systematized Nomenclature of Medicine and the International Classification of Disease.

17. The method of claim 12, wherein the calculating step uses both the results of the determining step as well as exact problem list matches as inputs.

18. The method of claim 17, wherein the results of the determining step and the exact problem list matches are weighted equally.

19. The method of claim 17, wherein the results of the determining step are weighted more heavily than the exact problem list matches.

20. The method of claim 17, where the exact problem list matches are weighted more heavily than the results of the determining step.

21. The method of claim 12, wherein the electronic data repository is an electronic health record repository.

22. The method of claim 12, wherein the electronic data repository is a problem list log repository.