COGNITIVE EFFICACY ESTIMATION SYSTEM AND METHOD

• US 20120130266A1
• Filed: 11/24/2010
• Published: 05/24/2012
• Est. Priority Date: 11/24/2010
• Status: Abandoned Application

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Mathan, Santosh, Ververs, Patricia May, Smart, Andrew
• Application Number:
  US12/953,763
• Publication Number:
  US 20120130266A1
• Time in Patent Office: Days
• US Class Current: 600/544
• CPC Class Codes: A61B 5/30 Input circuits therefor
• CPC Class Codes: A61B 5/313 for electromyography [EMG]
• CPC Class Codes: A61B 5/4088 Diagnosing of monitoring cognitive diseases, e.g. Alzheimer, prion diseases or dementia
• CPC Class Codes: A61B 5/4833 Assessment of subject's compliance to treatment
• CPC Class Codes: A61B 5/7267 involving training the classification device

Abstract

A system and method for estimating cognitive efficacy of an individual is provided. The individual is subjected to a plurality of tasks. Electroencephalogram (EEG) data from EEG sensors coupled to the individual are collected while the individual is performing the plurality of tasks. The EEG data are supplied to a trained classifier that generates an estimate of cognitive effort of the individual for each of the plurality of tasks performed by the individual.

Claims

1. A method for estimating cognitive efficacy of an individual, comprising the steps of:

collecting electroencephalogram (EEG) data from EEG sensors coupled to the individual, while the individual is performing a plurality of tasks;

supplying the EEG data to a trained classifier that generates an estimate of cognitive effort of the individual for each of the plurality of tasks performed by the individual;

generating baseline cognitive effort data for the individual, based on the plurality of tasks; and

comparing the estimates of cognitive effort to the baseline cognitive effort data to determine a change in cognitive efficacy of the individual.

2. The method of claim 1, further comprising:

preprocessing the EEG data; and

supplying the preprocessed EEG data to the trained classifier.

3. The method of claim 2, wherein the step of preprocessing comprises:

reducing artifacts in the EEG data; and

reducing non-informative features in the EEG data.

4. The method of claim 3, wherein the step of reducing artifacts in the EEG data comprises:

filtering the EEG data;

measuring artifacts at one or more artifact source; and

removing artifacts in the EEG data that coincide with the measured artifacts.

5. The method of claim 3, wherein the step of reducing non-informative features in the EEG data comprises subjecting the EEG data to one or more dimensionality reduction techniques.

6. The method of claim 1, wherein the trained classifier is configured to implement a logistic regression technique that follows a logistic model.

7. The method of claim 1, wherein the estimate of cognitive effort is a value between 0 and 1.

8. The method of claim 7, wherein 0 represents relatively low cognitive effort and 1 represents relatively high cognitive effort.

9. The method of claim 1, further comprising:

comparing updated estimates of cognitive effort to the baseline cognitive effort data to track changes in the cognitive efficacy of the individual.

10. A system for estimating cognitive efficacy of an individual performing a plurality of tasks, the system comprising:

a plurality of EEG sensors adapted to be coupled to the individual, each EEG sensor configured to collect EEG data from the individual, while the individual is performing the plurality of tasks, and supply the collected EEG data;

memory having baseline cognitive effort data for the individual stored therein, the baseline cognitive effort data based on the plurality of tasks; and

a processor in operable communication with the memory and coupled to receive the collected EEG data and configured, upon receipt of the EEG data, to (i) generate an estimate of cognitive effort of the individual for each of the plurality of tasks performed by the individual, (ii) selectively retrieve the baseline cognitive effort data from the memory, and (iii) compare the estimate of cognitive effort to the baseline cognitive effort data to determine a change in cognitive efficacy of the individual.

11. The system of claim 10, wherein the processor is configured to implement a trained classifier that generates the estimate of cognitive effort.

12. The system of claim 11, wherein the trained classifier is configured to implement a logistic regression technique that follows a logistic model:

13. The system of claim 10, wherein the estimate of cognitive effort is a value between 0 and 1.

14. The method of claim 13, wherein 0 represents relatively low cognitive effort and 1 represents relatively high cognitive effort.

15. The system of claim 10, further comprising:

one or more artifact sensors configured to measure artifacts at one or more artifact sources and supply artifact data representative thereof,

wherein the processor is further coupled to receive the artifact data, and is further configured to remove artifacts in the EEG data that coincide with the measured artifacts.

16. The system of claim 10, wherein the processor is further configured to implement one or more dimensionality reduction techniques to remove undesired features from the EEG data.

17. The system of claim 10, wherein the processor is further configured to compare updated estimates of cognitive effort to the baseline cognitive effort data to track changes in the cognitive efficacy of the individual.

18. A system for estimating cognitive efficacy of an individual performing a plurality of tasks, the system comprising:

a plurality of EEG sensors adapted to be coupled to the individual, each EEG sensor configured to collect EEG data from the individual, while the individual is performing the plurality of tasks, and supply the collected EEG data;

memory having baseline cognitive effort data for the individual stored therein, the baseline cognitive effort data based on the plurality of tasks; and

a processor configured to implement a trained classifier, the processor in operable communication with the memory and coupled to receive the collected EEG data and further configured, upon receipt of the EEG data, to;

generate an estimate of cognitive effort of the individual for each of the plurality of tasks performed by the individual,

selectively retrieve the baseline cognitive effort data from the memory,

compare the estimate of cognitive effort to the baseline cognitive effort data to determine a change in cognitive efficacy of the individual, and

compare updated estimates of cognitive effort to the baseline cognitive effort data to track changes in the cognitive efficacy of the individual.

19. The system of claim 18, wherein the trained classifier is configured to implement a logistic regression technique that follows a logistic model:

20. The system of claim 19, wherein the estimate of cognitive effort is a value between 0 and 1.