System and Method for Disease Diagnosis from Patient Structural Deviation Data

• US 20090292557A1
• Filed: 05/20/2008
• Published: 11/26/2009
• Est. Priority Date: 05/20/2008
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Sirohey, Saad Ahmed, Avinash, Gopal B., Espinal, Fausto J., Lin, Zhongmin, Mohan, Ananth, Bembenek, Tamanna
• Granted Patent: US 8,010,381 B2
• Time in Patent Office: Days
• US Class Current: 705/3
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment
• 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
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

A data processing technique is provided. In one embodiment, a computer-implemented method includes accessing patient deviation data of a structural difference between a patient anatomical feature and a standardized anatomical feature. The method may also include comparing the patient deviation data to reference deviation data sets representative of multiple disease types. Each reference deviation data set may be representative of an expected deviation from the standardized anatomical feature for a particular disease type. The method may further include automatically identifying one or more potential patient disease types based at least in part on the comparison. Additional methods, systems, and manufactures are also disclosed.

Claims

1. A system to facilitate diagnosis of a patient, comprising:

a memory device having a plurality of routines stored therein;

a processor configured to execute the plurality of routines stored in the memory device, the plurality of routines comprising;

a routine configured to effect, when executed, accessing of a patient deviation map indicative of at least one difference between an anatomical feature of the patient and a standardized anatomical feature, the at least one difference including a structural difference;

a routine configured to effect, when executed, comparing of the patient deviation map to a plurality of reference deviation maps, wherein the plurality of reference deviation maps includes reference deviation maps representative of a plurality of different severity levels of a disease type;

a routine configured to effect, when executed, diagnosis of the patient as having a particular severity level of the disease type based at least in part on the comparison of the patient deviation map to the plurality of reference deviation maps; and

a routine configured to effect, when executed, at least one of storing of the diagnosis in the memory device or an additional memory device, or outputting of the diagnosis to a user.

2. The system of claim 1, wherein the plurality of reference deviation maps includes reference deviation maps representative of a plurality of disease types.

3. The system of claim 2, wherein the plurality of reference deviation maps includes reference deviation maps indicative of a plurality of different severity levels of the plurality of disease types.

4. The system of claim 1, wherein the standardized anatomical feature is selected from a group of standardized anatomical features based at least in part on a demographic characteristic of the patient.

5. The system of claim 4, wherein the patient deviation map includes a visual representation of the at least one difference between the anatomical feature of the patient and a standardized anatomical feature.

6. The system of claim 5, wherein the visual representation is generated from image data and non-image data.

7. A computer-implemented method comprising:

accessing patient deviation data indicative of a structural difference between a patient anatomical feature and a standardized anatomical feature;

comparing the patient deviation data to a plurality of reference deviation data sets representative of a plurality of disease types, wherein each reference deviation data set is representative of an expected deviation from the standardized anatomical feature for a particular disease type; and

automatically identifying a potential patient disease type based at least in part on the comparison.

8. The method of claim 7, wherein the standardized anatomical feature is standardized on the basis of a demographic characteristic.

9. The method of claim 8, wherein the demographic characteristic includes at least one of age, race, or gender.

10. The method of claim 8, wherein the plurality of reference deviation data sets includes a reference deviation data set that is standardized based on the demographic characteristic.

11. The method of claim 8, wherein the standardized anatomical feature represents an anatomical feature of a normal subject that does not exhibit any of the plurality of disease types.

12. The method of claim 7, further comprising accessing patient deviation data indicative of a functional difference between the patient anatomical feature and the standardized anatomical feature.

13. The method of claim 7, wherein the patient deviation data includes image data.

14. The method of claim 7, wherein the patient deviation data includes a visual representation of variance of the patient anatomical feature from the standardized anatomical feature.

15. The method of claim 14, wherein the visual representation is generated from image data and non-image data.

16. The method of claim 7, wherein the patient anatomical feature includes the cerebral cortex of the patient.

17. The method of claim 7, wherein the plurality of reference deviation data sets include reference deviation data sets representative of a plurality of severity levels of at least one disease type.

18. The method of claim 17, comprising automatically identifying a potential patient disease type severity level based at least in part on the comparison.

19. A computer-implemented method comprising:

accessing patient deviation data indicative of at least one difference between a patient anatomical feature and a standardized anatomical feature, wherein the at least one difference includes a structural difference;

comparing the patient deviation data to a plurality of reference deviation data sets representative of a plurality of severity levels of a disease type, wherein each reference deviation data set is representative of an expected deviation from the standardized anatomical feature for a particular severity level of the disease type; and

automatically identifying a potential patient disease type severity level based at least in part on the comparison.

20. The method of claim 19, wherein the at least one difference includes a functional difference.

21. The method of claim 19, comprising generating a disease severity score based at least in part on the identification of the potential patient disease type severity level.

22. The method of claim 19, comprising comparing the patient deviation data to an additional plurality of reference deviation data sets representative of an additional disease type.

23. The method of claim 22, wherein the additional plurality of reference deviation data sets include reference deviation data sets representative of a plurality of severity levels of the additional disease type.

24. The method of claim 23, comprising automatically identifying a potential severity level of the additional disease type for the patient.

25. The method of claim 24, comprising generating a combined disease severity score based at least in part on the identification of the potential patient disease type severity level and the identification of the potential severity level of the additional disease type for the patient.

26. The method of claim 24, wherein the patient exhibits a clinical condition in which both the disease type and the additional disease type are contributing causes, and wherein the method further comprises determining the relative impact of each of the disease type and the additional disease type on the clinical condition based at least in part on the identification of the potential patient disease type severity level and the identification of the potential severity level of the additional disease type for the patient.

27. A manufacture comprising:

a computer-readable medium having executable instructions stored thereon, the executable instructions comprising;

instructions adapted to access patient deviation data indicative of a structural difference between a patient anatomical feature and a standardized anatomical feature;

instructions adapted to compare the patient deviation data to a plurality of reference deviation data sets representative of a plurality of disease types, wherein each reference deviation data set is representative of an expected deviation from the standardized anatomical feature for a particular disease type; and

instructions adapted to automatically identify a potential patient disease type based at least in part on the comparison.

28. The manufacture of claim 27, wherein the computer-readable medium comprises a plurality of computer-readable media at least collectively having the executable instructions stored thereon.