Generating a query

• US 10,127,271 B2
• Filed: 09/06/2013
• Issued: 11/13/2018
• Est. Priority Date: 09/06/2012
• Status: Active Grant

• Current Assignee: Koninklijke Philips N.V.
• Original Assignee: Koninklijke Philips N.V.
• Inventors: Barbieri, Mauro, Korst, Johannes Henricus Maria, Dadlani Mahtani, Pavankumar Murli, Aleksovski, Zarko, Peters, Marc Andre
• Primary Examiner(s): Torgrimson, Tyler
• Application Number:
  US14/020,092
• Publication Number:
  US 20140067847A1
• Time in Patent Office: 1,894 Days
• Field of Search: None
• CPC Class Codes: G06F 16/242 Query formulation
• CPC Class Codes: G06F 16/332 Query formulation
• CPC Class Codes: G06F 16/3338 Query expansion
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• 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

A system for generating a query includes a term unit (1) for extracting a term from at least one input document (51), to obtain an extracted term. A category unit (2) is arranged for associating the extracted term with a category that is semantically related with the extracted term. A query unit (3) is arranged for generating a query in dependence on the extracted term and the category. The query unit (3) includes an additional term unit (4) for generating at least one additional search term based on the category, and the query unit (3) is arranged for including the additional search term in the query. A submit unit (5) is arranged for submitting the query to at least one search engine (50), to obtain a plurality of found documents.

Claims

1. A system for generating a query to search educational material to educate a first patient regarding the first patient'"'"'s medical condition, the system comprising:

a term unit executed on one or more processors and configured to extract a term indicative of a medical condition or a medicine from at least one of a medical report or a part of an electronic medical record of the first patient to obtain an extracted term;

a category unit executed on the one or more processors and configured to associate the extracted term with one of a list of categories that is semantically related with the extracted term, the list of categories including at least medical conditions and medicines;

a similarity unit executed on the one or more processors and configured to determine second patient case information, wherein the second patient case information is associated with an electronic medical record of a second patient, wherein similarity is based on at least one of the medical report or the electronic medical record of the first patient, the second patient case information, and predetermined similarity criteria, wherein the second patient case information is associated with second case queries, and the second case queries are associated with levels of usefulness attached to each second query by the second case patient;

a query unit executed on the one or more processors and configured to generate a first query in dependence on the extracted term, the category, and the second patient case information and the associated second case queries with the attached levels of usefulness;

a submit unit executed on the one or more processors and configured to submit the first query to at least one search engine to obtain a plurality of found documents; and

a comparator executed on the one or more processors and configured to compare at least one found document of the plurality of found documents with at least one of the medical report or the patient electronic medical record of the first patient to determine a value representing a relevance of the found document in respect of at least one of the medical report or the patient electronic medical record of the first patient.

2. The system according to claim 1, wherein the query unit comprises an additional term unit configured to generate at least one additional search term based on the category, and wherein the query unit is further configured to include the additional search term in the query.

3. The system according to claim 2, wherein the category includes medicines and the at least one additional search term is indicative of one of effectiveness and side effects.

4. A workstation comprising the system according to claim 1.

5. The system according to claim 1, further including:

a result filter configured to select at least one document of the plurality of found documents, based on a clinical pathway of the patient associated with said at least one of the medical report and the patient electronic medical record; and

a complexity unit configured to determine a complexity of at least one of the found documents.

6. The system according to claim 1, wherein the comparator is configured to rank the found documents including:

representing the medical report or part of the electronic medical record of the patient as a vector in a multi-dimensional space, each dimension of the multi-dimensional space corresponding to a word;

representing each of the found documents as a vector in the multi-dimensional space;

determining angles between the vector representing the medical record or part of the electronic medical record and the vectors representing the found documents;

ranking each found document based on a closeness of angle between the vector of the found document and the vector of the medical report or part of the medical record of the patient.

7. The system according to claim 6, further including a display device, the display device being configured to present the found documents based on the ranking.

8. The system according to claim 6, further including a filter configured to filter the found documents to permit only documents in one or more preselected languages and below a preselected level of linguistic complexity.

9. A system for generating a query to search educational material to educate a patient regarding the patient'"'"'s medical condition, the system comprising:

one or more computers programmed to;

extract a term regarding the patient'"'"'s medical condition or a medicine from an electronic medical record in an electronic medical records database to obtain an extracted term, wherein the electronic medical record includes at least one of a medical report or a medical record;

associate the extracted term with one of a list of medical categories that is semantically related with the extracted term, the list including medical conditions and medicines, the categories being indicative of one or more of body structure, chemical substance, and clinical finding;

generate an additional term that is indicative of one or more of side effects, dosage, price, alternatives, and survival rates;

generate a query in dependence on the extracted term, the additional term, and at least one category in the list of medical categories;

submit the query to at least one search engine to obtain a plurality of found documents;

compare at least one found document of the plurality of found documents with at least one of the medical report or the patient'"'"'s medical record to determine a relevance of the found document to at least one of the medical report or the patient'"'"'s medical record;

rank the documents by representing each document as a vector in multi-dimensional space, where each dimension corresponds to a word in a given dictionary;

represent the patient'"'"'s electronic medical record as a vector in the multi-dimensional space;

determine angles between the vector representing the medical record or part of the electronic medical record and the vectors representing the found documents;

compare the angles between the document and electronic medical record vectors to determine similarity;

determine textual difficulty of each document; and

present documents to the patient based on the determined relevance, the determined similarity, and the determined textual difficulty.

10. The system according to claim 9, wherein the one or more computers are further configured to:

compare a portion of the patient'"'"'s electronic medical record with electronic medical records of other patients;

determine a similarity of corresponding portions of the other patient'"'"'s electronic medical records to the portion of the patient'"'"'s electronic medical record; and

generate the query further based on information from a similar patient record of another patient.

11. The system according to claim 9, wherein the one or more computers are further configured to:

review electronic medical records for other patients to determine patients with a similar medical condition; and

wherein generating the query includes incorporating search terms which were useful in a prior query for a patient with the similar medical condition.

12. The system according to claim 9, wherein the patient'"'"'s electronic medical record includes at least one of a diagnosis report, pathology, co-morbidity report, and practitioner referral letters.

13. The system according to claim 9, wherein the one or more computers are further configured to:

determine a relevance of each found document to where the patient is in a patient pathway based on clinical guidelines.

14. The system according to claim 9, wherein the one or more computers are further programmed to:

select at least one document of the plurality of found documents, based on a clinical pathway of the patient associated with said at least one of the medical report and the patient electronic medical record.

15. The system according to claim 9, wherein the extracted term is selected based on an ontology and the extracted term is associated with the one of the list of categories based on the ontology.

16. A system for generating a query to search educational material to educate a patient regarding the patient'"'"'s medical condition, the system comprising:

one or more computers programmed to;

extract a term regarding the patient'"'"'s medical condition or a medicine from an electronic medical record in an electronic medical records database to obtain an extracted term, wherein the electronic medical record includes at least one of a medical report or a medical record;

associate the extracted term with one of a list of medical categories that is semantically related with the extracted term, the list including medical conditions and medicines, the categories being indicative of one or more of body structure, chemical substance, and clinical finding;

generate an additional term that is indicative of one or more of side effects, dosage, price, alternatives, and survival rates;

generate a query in dependence on the extracted term, the additional term, and at least one category in the list of medical categories;

submit the query to at least one search engine to obtain a plurality of found documents;

compare at least one found document of the plurality of found documents with at least one of the medical report or the patient'"'"'s medical record to determine a relevance of the found document to at least one of the medical report or the patient'"'"'s medical record;

rank the documents by representing each document as a vector in multi-dimensional space, where each dimension corresponds to a word in a given dictionary;

represent the patient'"'"'s electronic medical record as a vector in the multi-dimensional space;

determine angles between the vector representing the medical record or part of the electronic medical record and the vectors representing the found documents;

compare the angles between the document and electronic medical record vectors to determine similarity;

determine textual difficulty of each document; and

present documents to the patient based on the determined relevance, the determined similarity, and the determined textual difficulty;

an electronic medical records database configured to store the medical records of the patient; and

a display apparatus configured to present the documents to the medical report or the patient'"'"'s medical record to the patient.

17. The system according to claim 16, wherein the presented documents are more relevant than a selected relevance threshold, more similar than a selected similarity threshold, and textually simpler than a selected textual difficulty threshold.