Method and apparatus for detecting seizures

• US 8,983,591 B2
• Filed: 10/17/2011
• Issued: 03/17/2015
• Est. Priority Date: 10/15/2010
• Status: Active Grant

• Current Assignee: Novela Neurotechnologies, Inc.
• Original Assignee: Brain Sentinel, Inc.
• Inventors: Leininger, James R., Herring, Russell M., Girouard, Michael R., Cavazos, Jose E.
• Primary Examiner(s): Dvorak, Linda
• Assistant Examiner(s): LLOYD, EMILY M
• Application Number:
  US13/275,309
• Publication Number:
  US 20120108999A1
• Time in Patent Office: 1,247 Days
• Field of Search: 600/546
• US Class Current: 600/546
• CPC Class Codes: A61B 2505/07 Home care
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/0004 characterised by the type of physiological signal transmitted
• CPC Class Codes: A61B 5/01 Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue clinical contact thermometers G01K13/20
• CPC Class Codes: A61B 5/11 Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb for measuring pulse A61B5/02 ;A61B5/1038 takes precedence; motion detection to correct for motion artifacts in physiological signals A61B5/721
• CPC Class Codes: A61B 5/25 Bioelectric electrodes therefor
• CPC Class Codes: A61B 5/296 for electromyography [EMG]
• CPC Class Codes: A61B 5/316 Modalities, i.e. specific diagnostic methods
• CPC Class Codes: A61B 5/318 Heart-related electrical modalities, e.g. electrocardiography [ECG]
• CPC Class Codes: A61B 5/389 Electromyography [EMG]
• CPC Class Codes: A61B 5/4094 Diagnosing or monitoring seizure diseases, e.g. epilepsy
• CPC Class Codes: A61B 5/6804 Garments; Clothes
• CPC Class Codes: A61B 5/6831 Straps, bands or harnesses
• CPC Class Codes: A61B 5/6833 Adhesive patches
• CPC Class Codes: A61B 5/6844 Monitoring or controlling distance between sensor and tissue
• CPC Class Codes: A61B 5/7282 Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence

Abstract

A method of detecting seizures may comprise receiving an EMG signal and processing the received EMG signal to determine whether a seizure characteristic is present in the EMG signal during a time window. An apparatus for detecting seizures with motor manifestations may comprise one or more EMG electrodes capable of providing an EMG signal substantially representing seizure-related muscle activity; and a processor configured to receive the EMG signal, process the EMG signal to determine whether a seizure may be occurring, and generate an alert if a seizure is determined to be occurring based on the EMG signal.

Claims

1. An apparatus for detecting seizures with motor manifestations, the apparatus comprising:

one or more electromyography electrodes configured to provide an electromyography signal representing seizure-related muscle activity;

a processor configured to receive the electromyography signal and process the electromyography signal to determine when a seizure is occurring based on the electromyography signal;

said processor configured to detect bursts of the electromyography signal, assign certainty values to individual bursts among said detected bursts, and determine a burst count contribution to seizure detection based on a number of said detected bursts weighted as a function of the certainty values assigned to said individual bursts;

said processor configured to qualify bursts against a minimum threshold duration and maximum threshold duration;

said processor configured to determine said certainty values based on how well the individual bursts compare to a reference burst in terms of one or more burst characteristics selected from the group of characteristics including burst signal-to-noise ratio, burst width, and burst amplitude;

said processor configured to identify the presence of a plurality of bursts over a time window, determine the periodicity of bursts over said time window, and determine a periodicity contribution to seizure detection;

said processor further configured to combine said burst count contribution and said periodicity contribution using a supervisory algorithm to determine a seizure detection value, and compare said seizure detection value to a threshold seizure detection value indicative of when a seizure is occurring; and

said processor further configured to generate an alert if a seizure is occurring.

2. The apparatus of claim 1 wherein the processor is configured to determine said periodicity contribution by calculating an average deviation for times between bursts included among said plurality of bursts and identifying if said average deviation is less than or greater than a threshold average deviation.

3. The apparatus of claim 2 wherein the processor is further configured to negatively weight said periodicity contribution against seizure detection if said average deviation is less than said threshold average deviation.

4. The apparatus of claim 1 wherein the processor is further configured to eliminate bursts from said plurality of bursts when bursts among said plurality of bursts are too close together or too far apart;

and

wherein the processor is further configured to determine said periodicity contribution by comparing the periodicity of the bursts over said time window to a minimum uniformity threshold and a maximum uniformity threshold.

5. A method of monitoring a patient for motor manifestations of seizure activity comprising:

monitoring the patient by collecting an electromyography signal using electromyography electrodes;

processing, with a processor the electromyography signal to detect bursts, assign certainty values to individual bursts among said detected bursts, and determine a burst count contribution to seizure detection based on a number of said detected bursts weighted as a function of the certainty values assigned to said individual bursts;

processing to qualify bursts against a minimum threshold duration and maximum threshold duration;

wherein said certainty values are based on how well the individual bursts compare to a reference burst in terms of one or more burst characteristics selected from the group of characteristics including burst signal-to-noise ratio, burst width, and burst amplitude;

identifying the presence of a plurality of bursts over a time window, determining the periodicity of bursts over said time window, and determining a periodicity contribution to seizure detection;

integrating said burst count contribution and said periodicity contribution into a supervisory algorithm to determine if said seizure activity is occurring; and

initiating an alert if a seizure is occurring.

6. The method of claim 5 the determining of said periodicity contribution includes calculating an average deviation for times between bursts included among said plurality of bursts and identifying if said average deviation is less than a threshold average deviation.

7. The method of claim 6, further comprising negatively weighting said periodicity contribution against seizure detection if said average deviation is less than the threshold average deviation.

8. The method of claim 5 further comprising eliminating bursts from said plurality of bursts if bursts among said plurality of bursts are too close together or too far apart;

and

wherein the determining of said periodicity contribution includes comparison of the periodicity of bursts over said time window to a minimum uniformity threshold and a maximum uniformity threshold.