Apparatus and method for epileptic seizure detection using non-linear techniques

• US 5,743,860 A
• Filed: 03/20/1996
• Issued: 04/28/1998
• Est. Priority Date: 03/20/1996
• Status: Expired due to Fees

• Current Assignee: Lockheed Martin Energy Systems, Inc. (AES Corporation)
• Original Assignee: Lockheed Martin Energy Systems, Inc. (AES Corporation)
• Inventors: Hively, Lee M., Daw, C. Stuart, Clapp, Ned E., Lawkins, William F.
• Primary Examiner(s): Kamm, William E.
• Assistant Examiner(s): LAYNO, CARL HERNANDZ
• Application Number:
  US08/619,024
• Time in Patent Office: 769 Days
• Field of Search: 128/731, 128/732, 128/45, 607/45
• US Class Current: 600/544
• CPC Class Codes: A61B 5/316 Modalities, i.e. specific diagnostic methods
• CPC Class Codes: A61B 5/369 Electroencephalography [EEG] devices for psychotechnics A61B5/16
• CPC Class Codes: A61B 5/4094 Diagnosing or monitoring seizure diseases, e.g. epilepsy

Abstract

Methods and apparatus for automatically detecting epileptic seizures by monitoring and analyzing brain wave (EEG or MEG) signals. Steps include: acquiring the brain wave data from the patient; digitizing the data; obtaining nonlinear measures of the data via chaotic time series analysis; obtaining time serial trends in the nonlinear measures; determining that one or more trends in the nonlinear measures indicate a seizure, and providing notification of seizure occurrence.

Claims

1. A method for automatically detecting an epileptic seizure in a patient comprising the steps of:

(a) providing at least one channel of a patient'"'"'s raw brain wave data, called e-data, selected from the group consisting of electroencephalogram data and magnetoencephalogram data;

(b) separating the e-data into artifact data, called f-data, and artifact-free data, called g-data, while preventing phase distortions in the data;

(c) processing g-data through a low-pass filter to produce a low-pass-filtered version of g-data, called h-data;

(d) applying at least one nonlinear measure selected from the group consisting of time steps per cycle, kolmogorov entropy, first minimum in the mutual information function, and correlation dimension to at least one type of data selected from the group consisting of e-data, f-data, g-data, and h-data to provide at least one time serial sequence of nonlinear measures, from which at least one indicative trend selected from the group consisting of abrupt increases and abrupt decreases can be determined;

(e) comparing at least one indicative trend with at least one known seizure indicator; and

(f) determining from said comparison whether an epileptic seizure is occurring in the patient.

2. The method as described in claim 1 further comprising the step of selecting said at least one time serial sequence of nonlinear measures from the group consisting of:

time per wave cycle for e-data, time per wave cycle for f-data, time per wave cycle for g-data, time wave per cycle for h-data, Kolmogorov entropy for e-data, Kolmogorov entropy for f-data, Kolmogorov entropy for g-data, Kolmogorov entropy for h-data, first minimum in the mutual information function for e-data, first minimum in the mutual information function for f-data, first minimum in the mutual information function for g-data, first minimum in the mutual information function for h-data, correlation dimension for e-data, correlation dimension for f-data, correlation dimension for g-data, correlation dimension for h-data, and combinations thereof.

3. The method as described in claim 2 further comprising the step of selecting said at least one seizure indicator from the group consisting of:

an abrupt decrease in the number of timesteps per cycle for f-data;

an abrupt increase in the number of timesteps per cycle for g-data;

an abrupt increase in in the number of timesteps per cycle for h-data;

an abrupt increase in the entropy of e-data;

an abrupt increase in the entropy of f-data;

an abrupt increase in the entropy of g-data;

an abrupt increase in the entropy of h-data;

an abrupt decrease in the first minimum in the mutual information function for f-data;

an abrupt decrease in the first minimum in the mutual information function for h-data;

an abrupt increase in the correlation dimension of e-data;

an abrupt increase in the correlation dimension of f-data;

an abrupt increase in the correlation dimension of g-data;

an abrupt increase in the correlation dimension of h-data; and

combinations thereof.

4. The method as described in claim 1 further comprising the step of separating the e-data into f-data and g-data by use of a zero-phase filter.

5. The method as described in claim 1 wherein the step of processing data through a low-pass filter is preceded by the step of selecting a standard low-pass filter selected from the group consisting of second-order, third-order, and fourth-order low-pass filters at frequencies between about 35 Hz and about 60 Hz.

6. The method as described in claim 5 wherein the step of selecting a low-pass filter comprises the step of selecting a standard fourth-order low-pass filter at about 50 Hz.

7. Apparatus for automatically detecting an epileptic seizure in a patient comprising:

(a) data provision means for providing at least one channel of a patient'"'"'s raw brain wave data called e-data selected from the group consisting of electroencephalogram data and magnetoencephalogram data;

(b) separation means for separating e-data into artifact data, called f-data, and artifact-free data, called g-data, while preventing phase distortions in the data, communicably connected to the data provision means;

(c) low-pass filter means for filtering g-data to produce a low-pass filtered version of g-data, called h-data, communicably connected to the separation means;

(d) application means for applying at least one nonlinear measure selected from the group consisting of time steps per cycle, Kolmogorov entropy, first minimum in the mutual information function, and correlation dimension to at least one type of data selected from the group consisting of e-data, f-data, g-data, and h-data to provide at least one time serial sequence of nonlinear measures, from which at least one indicative trend selected from the group consisting of abrupt increases and abrupt decreases can be determined, communicably connected to the low-pass filter means;

(e) comparison means for comparing at least one indicative trend with known seizure indicators, communicably connected to the application means; and

(f) determination means for determining from the comparison whether an epileptic seizure is occurring in the patient, communicably connected to the comparison means.

8. The apparatus as described in claim 7 wherein said at least one time serial sequence of nonlinear measures comprises one from a group consisting of:

time per wave cycle for e-data, time per wave cycle for f-data, time per wave cycle for g-data, time wave per cycle for h-data, Kolmogorov entropy for e-data, Kolmogorov entropy for f-data, Kolmogorov entropy for g-data, Kolmogorov entropy for h-data, first minimum in the mutual information function for e-data, first minimum in the mutual information function for f data, first minimum in the mutual information function for g-data, first minimum in the mutual information function for h-data, correlation dimension for e-data, correlation dimension for f-data, correlation dimension for g-data, correlation dimension for h-data, and combinations thereof.

9. The apparatus as described in claim 8 wherein said at least one seizure indicator comprises one from a group consisting of:

an abrupt decrease in the number of timesteps per cycle for f-data;

an abrupt increase in the number of timesteps per cycle for g-data;

an abrupt increase in the number of timesteps per cycle for h-data;

an abrupt increase in the entropy of e-data;

an abrupt increase in the entropy of f-data;

an abrupt increase in the entropy of g-data;

an abrupt increase in the entropy of h-data;

an abrupt decrease in the first minimum in the mutual information function for f-data;

an abrupt decrease in the first minimum in the mutual information function for h-data;

an abrupt increase in the correlation dimension of e-data;

an abrupt increase in the correlation dimension of f-data;

an abrupt increase in the correlation dimension of g-data;

an abrupt increase in the correlation dimension of h-data; and

combinations thereof.

10. The apparatus as described in claim 7 wherein said separation means comprises a zero-phase filter.

11. The apparatus as described in claim 10 wherein said zero-phase filter comprises a programmed integrated circuit semiconductor chip.

12. The apparatus as described in claim 7 wherein said low-pass filter means comprises a standard low-pass filter selected from the group consisting of second-order, third-order, and fourth-order low-pass filters at frequencies between about 35 Hz and about 60 Hz.

13. The apparatus as described in claim 12 wherein said low-pass filter comprises a standard fourth-order low-pass filter at about 50 Hz.

14. The apparatus as described in claim 7 further comprising notification means for providing notification that a seizure is occurring in the patient, said notification means being communicably connected to said determination means.