Method and apparatus for prediction and detection of seizure activity

• US 10,426,365 B1
• Filed: 09/05/2014
• Issued: 10/01/2019
• Est. Priority Date: 08/30/2013
• Status: Active Grant

• Current Assignee: Keshab K. Parhi
• Original Assignee: Keshab K. Parhi
• Inventors: Parhi, Keshab K, Zhang, Zisheng
• Primary Examiner(s): Matter, Kristen
• Application Number:
  US14/121,426
• Time in Patent Office: 1,852 Days
• Field of Search: 600544, 706 15, 706 22, 706 45
• CPC Class Codes: A61B 5/316 Modalities, i.e. specific diagnostic methods
• CPC Class Codes: A61B 5/374 Detecting the frequency distribution of signals, e.g. detecting delta, theta, alpha, beta or gamma waves
• CPC Class Codes: A61B 5/4094 Diagnosing or monitoring seizure diseases, e.g. epilepsy
• CPC Class Codes: A61B 5/4836 Diagnosis combined with treatment in closed-loop systems or methods A61B5/0036 takes precedence
• CPC Class Codes: A61B 5/7257 using Fourier transforms
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• 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

Abstract

The present invention relates to the design and implementation of a seizure detection or prediction system. The proposed invention computes and selects spectral power ratio features, cross-channel spectral power ratio features, cross spectral power features and cross spectral power ratio features in a patient-specific manner. The selected features are input to a classifier to detect or predict seizures. The proposed algorithm takes advantage of high sensitivity in detecting or predicting seizures and low complexity in implementation. The proposed scheme is general and is suitable for creating a trigger for therapy delivery in a closed-loop therapy system. The therapy could involve either delivery of an anti-epileptic drug or electrical or magnetic stimulation of the brain.

Claims

1. An apparatus for monitoring and treating seizure activity from electroencephalogram, the apparatus comprising:

a first electrode providing a first temporal signal and a second electrode providing a second temporal signal from a brain of a subject;

a digital processing unit performing steps comprising;

computing a cross-power spectral density for a band of frequencies using the first and second temporal signals;

computing a second cross-power spectral density for a second band of frequencies;

determining a ratio of the first cross-power spectral density to the second cross-power spectral density; and

using the ratio to determine the seizure status of the subject; and

in response to the seizure status of the subject, triggering delivery of a seizure treatment to the subject.

2. An apparatus for monitoring and treating seizure activity from electroencephalogram, the apparatus comprising:

a first electrode providing a signal detected from a brain of a subject;

a digital processing unit performing steps comprising;

computation of a first spectral power in a first frequency band of the signal;

computation of a second spectral power in a second frequency band of the signal;

computation of a ratio of the first spectral power and the second spectral power;

processing of the ratio for monitoring seizure activity of the subject; and

in response to the seizure status of the subject, triggering delivery of a seizure treatment to the subject.

3. The apparatus in claim 2 wherein the first and second frequency bands are selected using a ranking algorithm during a training phase.

4. The apparatus in claim 2 further comprising using band-pass filters to compute the first spectral power and the second spectral power.

5. The apparatus in claim 2 further comprising using a fast Fourier transform to compute the first spectral power and the second spectral power.

6. The apparatus of claim 2 wherein the apparatus is within an implantable device.

7. The apparatus of claim 2 wherein the apparatus is within a wearable device.

8. An apparatus for monitoring and treating seizure activity from electroencephalogram, the apparatus comprising:

a first electrode providing a first signal detected from a brain of a subject;

electronic circuitry performing steps comprising;

receiving the signal;

determining a spectral power for a first frequency band of the signal;

determining a spectral power for a second frequency band of the signal, the second frequency band different from the first frequency band;

determining a ratio of the spectral power of the first frequency band to the spectral power of the second frequency band;

applying the ratio to a classifier that uses the ratio to determine when a seizure is taking place;

when a seizure is determined to be taking place, triggering delivery of a seizure treatment to the subject.

9. The apparatus of claim 8 wherein determining the spectral power for the first frequency band and determining the spectral power for the second frequency band comprises determining the spectral power for the first frequency band in a temporal window of signal and determining the spectral power for the second frequency band in the same temporal window of the signal.

10. The apparatus of claim 8 wherein the apparatus is within an implantable device.

11. The apparatus of claim 8 wherein the apparatus is within a wearable device.