CLINICALLY RELEVANT MEDICAL CONCEPT CLUSTERING

• US 20170193185A1
• Filed: 01/06/2016
• Published: 07/06/2017
• Est. Priority Date: 01/06/2016
• Status: Active Grant

• Current Assignee: Merative US LP
• Original Assignee: International Business Machines Corporation
• Inventors: Devarakonda, Murthy V., Barker, Kenneth J., Tsou, Ching-Huei
• Granted Patent: US 10,839,947 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/353 into predefined classes
• 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

The present invention embodiments are directed to methods, systems, and computer programs for identifying relations, within at least one taxonomy, between taxonomy categories and concepts extracted from electronic content. The relations represent semantic similarities for the concepts. The concepts are clustered based on the identified relations within the at least one taxonomy.

Claims

1. A computer implemented method comprising:

identifying, within at least one taxonomy, relations between taxonomy categories and concepts extracted from electronic content, wherein the relations represent semantic similarities for the concepts; and

clustering the concepts based on the identified relations within the at least one taxonomy.

2. The method of claim 1, further comprising:

performing named-entity recognition and disambiguation on the concepts, which includes concept identification, named-entity detection, and linking of each identified concept to a meaning.

3. The method of claim 2, further comprising:

identifying the concepts from structured information within the electronic record.

4. The method of claim 2, further comprising:

identifying the concepts from unstructured information within the electronic record.

5. The method of claim 1, wherein identifying relations between taxonomy categories and concepts comprises:

mapping each of the concepts the least one taxonomy;

generating, based on the mapping, concept vectors relating each of the concepts to each of the taxonomy categories; and

determining a similarity measure between each of the concept vectors.

6. The method of claim 5, further comprising:

generating a similarity matrix relating the concepts based on the similarity measures; and

clustering the concepts based on the similarity measures.

7. The method of claim 5, wherein concepts not found in the at least one taxonomy are mapped to the at least one taxonomy using relationships identified in one or more other taxonomies.

8. The method of claim 1, wherein the taxonomy categories represent a feature space for clustering of the concepts, and wherein the method further comprising:

performing dimensionality reduction on the feature space to reduce processing time.

9. The method of claim 1, wherein the semantic similarities for the concepts represent relative relationships of the concepts to the taxonomy categories such that the concepts are clustered based on identified relevance.

10. The method of claim 1, wherein the concepts are medical concepts and wherein the electronic content is an electronic medical record.

11. A computer program product for clustering concepts extracted from electronic content, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:

identify, within at least one taxonomy, relations between taxonomy categories and the concepts extracted from the electronic content, wherein the relations represent semantic similarities for the concepts; and

cluster the concepts based on the identified relations within the at least one taxonomy.

12. The computer program product of claim 11, wherein the program instructions further cause the processor to:

perform named-entity recognition and disambiguation on the concepts, which includes concept identification, named-entity detection, and linking of each identified concept to a meaning.

13. The computer program product of claim 12, wherein the program instructions further cause the processor to:

identify the concepts from both structured information and unstructured information within the electronic content.

14. The computer program product of claim 11, wherein the program instructions that cause the processor to identify relations between taxonomy categories and concepts further cause the processor to:

map the concepts to the least one taxonomy;

generate, based on the mapping, concept vectors relating each of the concepts to each of the taxonomy categories; and

determine a similarity measure between each of the concept vectors.

15. The computer program product of claim 11, wherein the taxonomy categories represent a feature space for clustering of the concepts, and wherein the program instructions further cause the processor to:

perform dimensionality reduction on the feature space to reduce processing time.

16. The computer program product of claim 11, wherein the concepts are medical concepts and wherein the electronic content is an electronic medical record.

17. A system comprising:

at least one processor configured to;

identify within at least one taxonomy, relations between taxonomy categories and concepts extracted from electronic content, wherein the relations represent semantic similarities for the concepts; and

cluster the concepts based on the identified relations within the at least one taxonomy.

18. The system of claim 17, wherein the concepts are medical concepts and wherein the electronic content is an electronic medical record.

19. The system of claim 17, wherein the processor is further configured to:

identify the concepts from both structured information and unstructured information within the electronic content.

20. The system of claim 17, wherein to identify relations between taxonomy categories and concepts, the processor is configured to:

map each of the concepts the least one taxonomy;

generate based on the mapping, concept vectors relating each of the concepts to each of the taxonomy categories; and

determine a similarity measure between each of the concept vectors.