Searching an electronic medical record

• US 8,239,216 B2
• Filed: 01/09/2009
• Issued: 08/07/2012
• Est. Priority Date: 01/09/2009
• Status: Active Grant

• Current Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Original Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Inventors: McCallie, David P. Jr., Finn, Christopher S., Kolm, Margaret Cushing
• Primary Examiner(s): Gilligan, Luke
• Assistant Examiner(s): SOREY, ROBERT A
• Application Number:
  US12/351,288
• Publication Number:
  US 20100179827A1
• Time in Patent Office: 1,306 Days
• Field of Search: 705/2, 705/3
• US Class Current: 705/2
• CPC Class Codes: G06F 16/3331 Query processing
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

A method, system, and medium are provided for searching an electronic medical record. Search results are returned in response to a search query. The search query may be one or more designated medical concepts. The search results may be displayed according to a ranking that determines which search results are likely to be the most responsive to a query submitted by a particular clinician based on matching the most important clinical concepts in each document to the most important clinical concepts in the search query.

Claims

1. One or more non-transitory computer-storage media having computer executable instructions embodied thereon that when executed by a computer perform a method of finding information in an electronic medical record, the method comprising:

receiving a search query from a user to search the electronic medical record, wherein the electronic medical record is associated with a patient, and wherein the electronic medical record includes a plurality of electronic documents that describe a medical history for the patient and is stored on the computer-storage media;

identifying one or more components of the electronic medical record that contain text that matches the search query, wherein each of the one or more components is a section of text within the electronic medical record that includes one or more words;

determining a query-responsiveness score for each of the one or more components that match the search query, wherein the query-responsiveness score indicates how responsive an individual component is to the search query, wherein determining the query-responsiveness score of each of the one or more components further comprises;

determining a patient-subject status for each particular-clinical concept recited in the one or more components, wherein the patient-subject status indicates whether the patient is an object of a particular-clinical concept recited in a particular component of the one or more components;

determining a truth status for said each particular-clinical concept recited in the one or more components, wherein the truth status indicates whether said each particular-clinical concept was expressed positively, negatively, ambiguously, or unknown;

determining a clinical-usage context for each particular-clinical concept recited in the one or more components, wherein the clinical-usage context describes how the clinical concept was used in the component;

determining a document-importance factor for each particular-clinical concept recited in the one or more components, wherein the document-importance factor measures the relevance of the particular-clinical concept to the main subject of a particular document by analyzing other clinical concepts that are used in the particular document with the particular-clinical concept;

determining a specificity factor for each particular-clinical concept recited in the one or more components based on a degree of narrowness for a scope of said each particular-clinical concept; and

presenting search results that communicate information describing each of the one or more components, wherein the search results are displayed ordered according to the query-responsiveness score assigned to each of the one or more components.

2. The media of claim 1, wherein the method further includes receiving a selection of a search mode, wherein the search mode is set to match related concepts, and wherein the one or more components of the electronic medical record matches the search query when a clinical concept conveyed by the search query matches at least one related clinical concept recited in the one or more components of the electronic medical record, and wherein the clinical concept describes any aspect of a person'"'"'s health condition.

3. The media of claim 2, wherein determining the query-responsiveness score of each of the one or more components further includes:

wherein the query-responsiveness score for the individual component is increased when the patient-subject status for one or more of the clinical concepts identified within the component is affirmative, when the truth status for one or more of the clinical concepts identified within the component equals positive, when the clinical-usage context for one or more of the clinical concepts identified within the component directly relates to the patient, when the document-importance factor is high, and when the specificity factor for one or more of the clinical concepts identified within the component is high.

4. The media of claim 1, wherein the method further includes displaying one or more filter options that allows the user to filter the search results, wherein the one or more filter options are based on one or more of a clinical-concept in an individual search result, an aggregation of related clinical concepts, a clinical facility associated with the individual search result, and a document class associated with the individual search result.

5. The media of claim 1, wherein the method further includes receiving a selection of a search mode, wherein the search mode is a medical synonym match, wherein the one or more components of the electronic medical record matches the search query when at least a medical synonym of the one or more words in the search query is found within the one or more components of the electronic medical record, and wherein the medical synonyms match search mode includes matching two or more words or phrases that have a similar medical meaning.

6. The media of claim 1, wherein the method further includes:

expanding one or more primary clinical concepts recited in the search query to additional related clinical concepts, thereby generating a plurality of expanded clinical concepts to match with a particular one of the one or more components of the electronic medical record;

assigning a boost factor to each combination of an expanded clinical concept and the particular matching component of the electronic medical record, wherein the boost factor is higher when the expanded clinical concept is close to the one or more primary clinical concepts on a clinical-concept ontology and lower when the expanded clinical concept is remote from the one or more primary clinical concepts; and

wherein the boost factor is used to calculate the query-responsiveness score for said each combination of the expanded clinical concept and the particular-clinical concepts contained within the matching component.

7. The media of claim 1, wherein the method further includes increasing the query-responsiveness score when a role of the user who submitted the search query is in the same category as the role of a person that created a matching component.

8. One or more non-transitory computer-storage media having computer executable instructions embodied thereon that when executed by a computer perform for performing a method of searching an electronic medical record for clinical concepts, the method comprising:

receiving a search query that includes a clinical concept from a user to search the electronic medical record, wherein the clinical concept is an aspect related to a person'"'"'s health, wherein the electronic medical record is associated with a patient, and wherein the electronic medical record includes a plurality of electronic documents that describe a medical history for the patient and is stored on the computer-storage media;

identifying one or more uses of the clinical concept in the electronic medical record, wherein a use of a clinical concept is a single occurrence of the clinical concept within the electronic medical record, wherein the documents in the electronic medical record describe the patient'"'"'s medical history, and wherein the electronic medical record is stored on the computer-storage media;

determining a clinical-importance score for each of the one or more uses of the clinical concept, wherein the clinical-importance score quantifies how important each use of the clinical concept is likely to be to the user querying the electronic medical record, and wherein the clinical-importance score is calculated based on the use of the clinical concept within the electronic medical record and without reference to any specific search query;

determining at least one boost factor for each of the one or more uses of the clinical concept, wherein the at least one boost factor is based on the search query and the user, wherein the at least one boost factor includes a role-boost factor, wherein each role-boost factor is based on a role of the user that submitted the search query and a role of a person that generated the particular use of the clinical concept in the electronic medical record, and wherein the particular role-boost factor is increased when the role of the user is in the same category as the role of the person associated with the use of the clinical concept within the electronic medical record;

calculating a query-responsiveness score for each document within the electronic medical record in which the clinical concept is used by combining the one or more clinical-importance scores with the one or more boost factors; and

presenting search results based on the query-responsiveness score associated with each said document within the electronic medical record in which the one or more uses of a clinical concept was identified, wherein the search results are displayed ordered according to the query-responsiveness score.

9. The media of claim 8, wherein the method further includes:

determining a clinical-usage context for each use of the clinical concept in the electronic medical record, wherein the clinical-usage context describes how the clinical concept was used in each document of the electronic medical record;

determining a truth status for each use of the clinical concept in the electronic medical record, wherein the truth status indicates whether the clinical concept was expressed in as one of positively, negatively, ambiguously, and unknown; and

wherein the clinical-importance score for said each of the one or more uses of the clinical concept is based on the clinical-usage context and the truth status for said each of the one or more uses of the clinical concept.

10. The media of claim 9, wherein the method further includes:

determining a patient-subject status for each use of the clinical concept in the documents of the electronic medical record, wherein the patient-subject status indicates whether or not the patient is an object of the particular use of the clinical concept; and

wherein the clinical-importance score for said each of the one or more uses of the clinical concept in said each of the one or more documents in the electronic medical record is based on the clinical-usage context, the truth status, and the patient-subject status for said each of the one or more uses of the clinical concept.

11. The media of claim 10, wherein the method further includes:

determining a specificity factor for the particular use of the clinical concept based on a degree of narrowness for a scope of the particular use of the clinical concept;

determining a document-importance factor for the particular use of the clinical concept, wherein the document-importance factor measures the relevance of the particular use of the clinical concept to the main subject of a particular document by analyzing other clinical concepts that are used in the particular document with the particular use of the clinical concept;

and

wherein the clinical-importance score for said each of the one or more uses of the clinical concept is based on the clinical-usage context, the truth status, the patient-subject status, the document-importance factor, and the specificity factor for the particular use.

12. The media of claim 8, wherein the at least one boost factor includes a clinical-facility-boost factor, wherein the clinical-facility-boost factor is based on a clinical facility associated with the user that submitted the search query and the clinical facility associated with a use of the clinical concept in the electronic medical record, and wherein a clinical-facility-boost factor is increased for the use of the clinical concept in the electronic medical record when the use of the clinical concept in the electronic medical record is in a portion of the electronic medical record that is associated with the clinical facility from which the user submitted the search query.

13. The media of claim 8, wherein the method further includes:

expanding the clinical concept recited in the search query into additional related clinical concepts, thereby generating a plurality of expanded clinical concepts to match to each of the uses of the plurality of expanded clinical concepts within documents in the electronic medical record;

assigning a closeness-boost factor to each combination of an expanded-clinical concept and a matching use of the expanded-clinical concept within a document in the electronic medical record, wherein the closeness-boost factor is higher when the expanded-clinical concept is close to the clinical concept on a clinical-concept ontology and lower when the expanded clinical concept is remote from the clinical concept; and

wherein the at least one boost factor includes the closeness-boost factor.