Biomarker fusion system and method

• US 9,662,034 B2
• Filed: 09/09/2011
• Issued: 05/30/2017
• Est. Priority Date: 09/10/2010
• Status: Active Grant

• Current Assignee: Neuronetrix Solutions LLC
• Original Assignee: Neuronetrix Solutions LLC
• Inventors: Kulkarni, Mauktik V., Fadem, Kalford C.
• Primary Examiner(s): UDDIN, MD I
• Application Number:
  US13/228,626
• Publication Number:
  US 20120066238A1
• Time in Patent Office: 2,090 Days
• Field of Search: 707736, 707737, 707755, 707758
• CPC Class Codes: A61B 5/291 for electroencephalography [EEG]
• CPC Class Codes: A61B 5/377 using evoked responses
• CPC Class Codes: A61B 5/38 Acoustic or auditory stimuli
• CPC Class Codes: A61B 5/4088 Diagnosing of monitoring cognitive diseases, e.g. Alzheimer, prion diseases or dementia
• CPC Class Codes: A61B 5/6814 Head

Abstract

An apparatus comprises an ERP testing system that is configured to administer an ERP test. The apparatus further comprises a computer in communication with the ERP testing system. The computer is operable to access a database of biomarkers. The computer is further operable to define at least one class set relating to biomarkers and at least one feature set relating to biomarkers. The computer is further operable to classify a test subject into at least one of the defined class sets based on information in the feature set relating to biomarkers of the test subject. The biomarker processing may be carried out in association with or completely independent of ERP testing.

Claims

1. An apparatus comprising:

(a) a ERP testing system, wherein the ERP testing system is configured to administer an ERP test;

(b) a computer in communication with the ERP testing system, wherein the computer is configured to access a database of biomarkers, wherein the computer is configured to select at least one class set definition and at least one feature set definition, wherein the at least one class set definition includes a class set based on a variable present in the database of biomarkers, wherein the feature set definition comprises a biomarker based on additional biomarker criteria, wherein the computer is configured to form at least one training set definition from the at least one class set definition and the at least one feature set definition;

wherein the computer is further configured to automatically render an original diagnosis by fusing biomarker data using the training set definition, wherein at least some of the fused biomarker data is acquired through the ERP testing system.

2. The apparatus of claim 1, wherein the computer is configured to make the training set definition available to multiple users.

3. The apparatus of claim 1, wherein the computer is configured to store the training set definition and export the training set definition.

4. The apparatus of claim 1, wherein the class set definition and the feature set definition each comprise a distinct biomarker.

5. The apparatus of claim 1, wherein the computer comprises a validation module operable to validate the at least one training set definition.

6. The apparatus of claim 1, wherein the computer is configured to connect to an online database to retrieve lab test codes for selecting the at least one class set definition.

7. The apparatus of claim 1, wherein the computer is configured to select a class set definition based on feature set information.

8. The apparatus of claim 1, wherein the computer is further configured to perform preprocessing to the database of biomarkers prior to selecting a feature set definition.

9. The apparatus of claim 1, wherein the computer is in communication with external software operable to perform image analysis to the database of biomarkers.

10. The apparatus of claim 1, wherein the computer is configured to display a dynamically updating selection box for selecting the at least one class set definition.

11. The apparatus of claim 1, wherein the computer is configured to display a dynamically updating selection box for selecting the at least one feature set definition.

12. The apparatus of claim 1, wherein the database of biomarkers comprises a SQL database.

13. The apparatus of claim 1, wherein the computer is configured to use a plurality of training set definitions to form a meta-model.

14. The apparatus of claim 1, wherein the computer further comprises an expert classifier module.

15. A system for constructing a meta-model, the system comprising:

(a) a computer configured to output a selection dialog for defining a class set, wherein the computer is further configured to output a second selection dialog for defining a feature set, wherein the computer is configured to combine the class set definition and the feature set definition into a training set definition, wherein the class set definition comprises a class set based on a first selected biomarker, wherein the feature set definition comprises a feature set based on a second biomarker, wherein the first biomarker and the second biomarker have no known relationship, wherein the training set definition is transmitted to an expert classifier module; and

(b) a storage device configured to store a database of biomarker information, wherein the computer and the storage device are in communication with each other, wherein the computer is operable to retrieve biomarker information from the storage device in association with the expert classifier module;

wherein the computer is further configured to execute the expert classifier module to thereby automatically generate an original diagnosis of a patient exhibiting a biomarker used in at least one of the class set definition or the feature set definition.

16. The system of claim 15, wherein the storage device is configured to encrypt a portion of the biomarker information.

17. The system of claim 15, wherein the computer is configured to access the storage device to construct a list of possible class set definitions.

18. The system of claim 15, wherein the computer comprises a validation module operable to validate the training set definition.

19. The system of claim 15, wherein the storage device is configured to perform preprocessing to the biomarker information contained on the storage device.