System and method for patient identification for clinical trials using content-based retrieval and learning

• US 20050210015A1
• Filed: 03/17/2005
• Published: 09/22/2005
• Est. Priority Date: 03/19/2004
• Status: Abandoned Application

• Current Assignee: Siemens Medical Solutions USA Incorporated (Siemens AG)
• Original Assignee: Siemens Medical Solutions USA Incorporated (Siemens AG)
• Inventors: Zhou, Xiang Sean, Comaniciu, Dorin, Zahlmann, Gudrun
• Application Number:
  US11/082,570
• Publication Number:
  US 20050210015A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G16H 10/20 for electronic clinical trials or questionnaires
• 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 method for selecting a subject for a clinical study includes providing a criteria for selecting one or more subjects from a database, performing a content based similarity search of the database to retrieve subjects who meet the selection criteria, presenting the selected subjects to a user, and receiving user feedback regarding the selected subjects. The feedback can concern whether each of the selected subjects presented to the user is suitable for the clinical study. The method also includes learning from the feedback to improve the content based similarity search, performing an improved content based similarity search of the database to retrieve additional subjects who meet the selection criteria, and presenting the additional subjects to the user.

Claims

1. A method for identifying a patient for a clinical study, said method comprising the steps of:

creating a database of patients and patient information;

providing a criteria for selecting one or more patients from the database;

performing a content based similarity search of the database to retrieve the one or more patients who meet the selection criteria; and

presenting said selected one or more patients to a user.

2. The method of claim 1, wherein said criteria for selecting one or more patients comprises providing an example patient suitable for said study to a search engine, and wherein said criteria is determined from characteristic feature values of said example patient.

3. The method of claim 1, wherein said criteria for selecting one or more patients comprises providing a plurality of example patients suitable for said study to a search engine, and wherein said criteria is determined from characteristic feature values of said plurality of example patients.

4. The method of claim 1, wherein said database is created by extracting features that support distance based comparisons from at least one of financial, demographic, image, clinical, and genomic data.

5. The method of claim 4, wherein said features include numerical data and discrete information represented by words.

6. The method of claim 4, wherein the similarity search comprises a distance measure performed on said selection criteria.

7. The method of claim 6, further comprising the steps of:

receiving user feedback regarding the one or more selected patients, wherein the feedback concerns whether each of the one or more selected patients presented to the user is suitable for the clinical study;

improving said content based similarity search based on said user feedback;

performing the improved content based similarity search of the database to retrieve one or more additional patients who meet the selection criteria; and

presenting said selected additional patients to the user.

8. The method of claim 7, wherein improving said content based similarity search comprises selecting and re-weighting distance measures of said features stored in said database.

9. The method of claim 7, wherein improving said content based similarity search comprises utilizing discriminative density estimators and kernel machine techniques.

10. The method of claim 9, wherein improving said content based similarity search comprises biased discriminant analysis.

11. The method of claim 1, further comprising the steps of selecting one or more additional patients wherein said content based similarity search is uncertain whether said additional patients meet the selection criteria.

12. The method of claim 1, further comprising using statistical analysis to determine consistent hidden information and dependencies among keywords and key-features within said database.

18. The computer readable program storage device of claim 1, wherein said database is created by extracting features that support distance based comparisons from at least one of financial, demographic, image, clinical, and genomic data.

19. The computer readable program storage device of claim 18, wherein said features include numerical data and discrete information represented by words.

20. The computer readable program storage device of claim 18, wherein the similarity search comprises a distance measure performed on said selection criteria.

21. The computer readable program storage device of claim 20, wherein the method further comprises the steps of:

receiving user feedback regarding the one or more selected patients, wherein the feedback concerns whether each of the one or more selected patients presented to the user is suitable for the clinical study;

improving said content based similarity search based on said user feedback;

performing the improved content based similarity search of the database to retrieve one or more additional patients who meet the selection criteria; and

presenting said selected additional patients to the user.

22. The computer readable program storage device of claim 21, wherein improving said content based similarity search comprises selecting and re-weighting distance measures of said features stored in said database.

23. The computer readable program storage device of claim 21, wherein improving said content based similarity search comprises utilizing discriminative density estimators and kernel machine techniques.

24. The computer readable program storage device of claim 23, wherein improving said content based similarity search comprises biased discriminant analysis.

13. A method for selecting a subject for a clinical study, said method comprising the steps of:

providing a criteria for selecting one or more subjects for said clinical study;

performing a content based similarity search of a database to retrieve the one or more subjects who meet the selection criteria;

receiving user feedback regarding the one or more selected subjects, wherein the feedback concerns whether each of the one or more selected subjects presented to the user is suitable for the clinical study;

learning from said feedback to improve the content based similarity search;

performing an improved content based similarity search of the database to retrieve one or more additional subjects who meet the selection criteria; and

presenting said selected additional subjects to the user.

14. The method of claim 13, wherein the steps of receiving user feedback, learning from said feedback, performing an improved content based similarity search, and presenting said selected additional subjects are repeated until a sufficient sample of subjects for said clinical study has been selected.

15. A program storage device readable by a computer, tangibly embodying a program of instructions executable by the computer to perform the method steps for identifying a patient for a clinical study, said method comprising the steps of:

creating a database of patients and patient information;

providing a criteria for selecting one or more patients from the database;

performing a content based similarity search of the database to retrieve the one or more patients who meet the selection criteria; and

presenting said selected one or more patients to a user.

16. The computer readable program storage device of claim 15, wherein said criteria for selecting one or more patients comprises providing an example patient suitable for said study to a search engine, and wherein said criteria is determined from characteristic feature values of said example patient.

17. The computer readable program storage device of claim 15, wherein said criteria for selecting one or more patients comprises providing a plurality of example patients suitable for said study to a search engine, and wherein said criteria is determined from characteristic feature values of said plurality of example patients.

25. The computer readable program storage device of claim 15, wherein the method further comprises the steps of selecting one or more additional patients wherein said content based similarity search is uncertain whether said additional patients meet the selection criteria.

26. The computer readable program storage device of claim 15, wherein the method further comprises using statistical analysis to determine consistent hidden information and dependencies among keywords and key-features within said database.