System for retrieval of information from data structure of medical records

• US 6,438,533 B1
• Filed: 10/29/1999
• Issued: 08/20/2002
• Est. Priority Date: 10/30/1998
• Status: Expired due to Fees

• Current Assignee: International Health Terminology Standards Development Organisation
• Original Assignee: College of American Pathologists (College)
• Inventors: Spackman, Kent A., Campbell, Keith E.
• Primary Examiner(s): Davis, George B.
• Application Number:
  US09/431,291
• Time in Patent Office: 1,026 Days
• Field of Search: 706/45, 706/46, 600/300, 705/3
• US Class Current: 706/45
• 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
• CPC Class Codes: G16H 70/00 ICT specially adapted for the handling or processing of medical references
• CPC Class Codes: Y02A 90/10 Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Abstract

An apparatus and system are provided for retrieving electronic records from a database of records, preferably in the form of medical records. The apparatus utilizes a knowledge base in the form of a data structure set forth in a description language. The knowledge base includes representations of a plurality of concepts hierarchically linked with other concepts within a plurality of classes, and non-hierarchically linked with concepts in other classes. A query manager receives a user query and translates the query into the description language. A records analyzer is coupled to the query manager, database and knowledge base. The records analyzer analyzes the records in the database based on the user query and the classes and the hierarchical and non-hierarchical relationships in the knowledge base.

Claims

1. An apparatus for retrieving electronic records from a database of medical records, comprising:

a database of medical records;

a knowledge base having a data structure set forth in a description language, said knowledge base including a plurality of classes having a plurality of concepts, each of said classes comprising a nomenclature for medical terminology, each of said concepts in a first class being vertically linked to another of said concepts in said first class by a hierarchical relationship, each of said concepts in a second class being vertically linked to another of said concepts in said second class by a hierarchical relationship, each of said concepts in a third class being vertically linked to another of said concepts in said third class by a hierarchical relationship;

said hierarchical relationships including parent relationships, child relationships, “

is-a”

relationships and “

part-of”

relationships;

said nomenclature for said classes being selected from one or more of the group of;

(a) diseases/diagnoses, (b) morphology, (c) living organisms, (d) physical agents, activities and forces, (e) chemicals, drugs, and biological products, (f) social context, (g) topography, h) human bodily function, (i) treatment procedures, (j) etiology, (k) spatial relationships, and (l) occupations;

a plurality of said concepts in said first class being horizontally linked to a plurality of said concepts in said second class by non-hierarchical relationships, a plurality of said concepts in said first class being horizontally linked to a plurality of said concepts in said third class by non-hierarchical relationships;

each of said non-hierarchical relationships further comprises a role relationship;

a query manager that receives a user query and translates said query into a description language; and

a records analyzer coupled to said query manager, said database and said knowledge base;

said records analyzer analyzing said records in said database based on said user query and said classes and said hierarchical and said non-hierarchical relationships in said knowledge base.

2. The apparatus of claim 1 wherein each of a plurality of said concepts of said second class are horizontally linked to each of a plurality of said concepts of said third class,

said knowledge base having a fourth class, said fourth class including a plurality of concepts vertically linked with one another in hierarchical relationships,

each of a plurality of said concepts of said third class being horizontally linked to each of a plurality of said concepts of said fourth class.

3. The apparatus of claim 2 wherein said class of diseases/diagnoses has one or more associated role relationships with one or more of the group of:

(a) etiology, (b) morphology, (c) topography, (d) course, and (e) severity.

4. The apparatus of claim 3 wherein said class of topography has one or more associated role relationships with one or more of the group of:

(a) part-of, (b) branch-of, and (c) tributary-of.

5. A method for retrieving electronic records from a database of medical records, comprising the steps of:

forming a knowledge base having a data structure set forth in a description language, said knowledge base including representations of a plurality of concepts within a plurality of classes, each of said classes comprising a nomenclature for medical terminology, each of said concepts in a first class being vertically linked to another of said concepts in said first class by a hierarchical relationship, each of said concepts in a second class being vertically linked to another of said concepts in said second class by a hierarchical relationship, each of said concepts in a third class being vertically linked to another of said concepts in said third class by a hierarchical relationship;

said hierarchical relationships including parent relationships, child relationships, “

is-a”

relationships and “

part-of”

relationships;

said nomenclature for said classes being selected from one or more of the group of;

(a) diseases/diagnoses, (b) morphology, (c) living organisms, (d) physical agents, activities and forces, (e) chemicals, drugs, and biological products, (f) social context, (g) topography, (h) human bodily function, (i) treatment procedures, (j) etiology, k) spatial relationships, and (l) occupations;

a plurality of said concepts in said first class being horizontally linked to a plurality of said concepts in said second class by non-hierarchical relationships, a plurality of said concepts in said first class being horizontally linked to a plurality of said concepts in said third class by non-hierarchical relationships;

inputting a user query into a query manager and translating said query into a description language in said query manager;

accessing a database of encoded medical records; and

analyzing said records in said database with a records analyzer based on said user query and said classes and said hierarchical and said non-hierarchical relationships in said knowledge base.

6. The method of claim 5 wherein each of a plurality of said concepts of said second class are horizontally linked to each of a plurality of said concepts of said third class,

said knowledge base having a fourth class, said fourth class including a plurality of concepts vertically linked with one another in hierarchical relationships,

each of a plurality of said concepts of said third class being horizontally linked to each of a plurality of concepts of said fourth class.

7. The method of claim 6 wherein said class of diseases/diagnoses has one or more associated role relationships from one or more of the group of:

(a) etiology, (b) morphology, (c) topography, (d) course, and (e) severity.

8. The method of claim 7 wherein said class of topography has one or more associated role relationships with one or more of the group of:

(a) part-of, (b) branch-of, and (c) tributary-of.

9. An apparatus for retrieving electronic records from a database of medical records, comprising:

a database of medical records, said medical records being encoded in a description language;

a knowledge base having a data structure set forth in said description language, said knowledge base including a plurality of classes having a plurality of concepts, each of said classes comprising a nomenclature for medical terminology, each of said concepts in a first class being vertically linked to another of said concepts in said first class by a hierarchical relationship, each of said concepts in a second class being vertically linked to another of said concepts in said second class by a hierarchical relationship, each of said concepts in a third class being vertically linked to another of said concepts in said third class by a hierarchical relationship;

said hierarchical relationships including parent relationships, child relationships, “

is-a”

relationships and “

part-of”

relationships;

said nomenclature for said classes including;

(a) diseases/diagnoses, (b) morphology, (c) living organisms, (d) physical agents, activities and forces, (e) chemicals, drugs, and biological products, (f) social context, (g) topography, (h) human bodily function, (i) treatment procedures, (j) etiology, (k) spatial relationships, and (l) occupations;

a plurality of said concepts in said first class being horizontally linked to a plurality of said concepts in said second class by non-hierarchical relationships, a plurality of said concepts in said first class being horizontally linked to a plurality of said concepts in said third class by non-hierarchical relationships;

each of said non-hierarchical relationships further comprises a role relationship;

a query manager that receives a user query and translates said query into a description language, said query seeking records from said database including classes or concepts identified in said query; and

a records analyzer coupled to said query manager, said database and said knowledge base;

said records analyzer analyzing said records in said database based on said user query and said non-hierarchical relationships in said knowledge base;

said records analyzer providing an identification of records in said database having coded representations corresponding to said user query from one or more of said classes and corresponding to each of said hierarchical relationships and each of said non-hierarchical relationships in said knowledge base, said identified records thereby including all of said records in said database having coded representations of concepts that are linked to the concepts specified in said user query by either hierarchical or non-hierarchical relationships.

10. The apparatus of claim 9 wherein said class of diseases/diagnoses has one or more associated non-hierarchical relationships with one or more of the group of:

(a) etiology, (b) morphology, (c) topography, (d) course, and (e) severity.

11. The apparatus of claim 10 wherein said class of treatment procedure has one or more associated non-hierarchical relationships with one or more of the group of:

(a) administered substance, (b) topography, (c) object of a procedure, and (d) equipment used to accomplish a procedure.

12. The apparatus of claim 11 wherein said class of treatment procedure has one or more associated non-hierarchical relationships with one or more laboratory test roles from the group of:

(a) has-measured-component, said component being the substance or thing or physiological or physical function being measured, (b) has-method, said method being the method by which a procedure is performed, (c) has-property, said property being the kind of quantity being measured, (d) has-scale-type, said scale being the result of an observation of a diagnostic test, (e) has-specimen, said specimen being the bodily source, (f) has-subject-of-observation, said observation distinguishes observations or actions on the patient from observations or actions on non-patient materials that relate to the patient, and (g) has-time-aspect, said aspect being definitional temporal relationships for a procedure.