Detecting, quantifying, and/or classifying seizures using multimodal data

• US 8,337,404 B2
• Filed: 10/01/2010
• Issued: 12/25/2012
• Est. Priority Date: 10/01/2010
• Status: Active Grant

• Current Assignee: Flint Hills Scientific, LLC
• Original Assignee: Flint Hills Scientific, LLC
• Inventors: Osorio, Ivan
• Primary Examiner(s): Gedeon, Brian T
• Application Number:
  US12/896,525
• Publication Number:
  US 20120083700A1
• Time in Patent Office: 816 Days
• Field of Search: 600/301, 600/510, 600/511, 600517-519
• US Class Current: 600/301
• CPC Class Codes: A61B 3/113 for determining or recording eye movement
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/02055 Simultaneously evaluating both cardiovascular condition and temperature
• CPC Class Codes: A61B 5/02405 Determining heart rate variability
• CPC Class Codes: A61B 5/0245 by using sensing means generating electric signals, i.e. ECG signals
• CPC Class Codes: A61B 5/0531 Measuring skin impedance
• CPC Class Codes: A61B 5/08 Detecting, measuring or recording devices for evaluating the respiratory organs A61B5/0205 takes precedence
• 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 5/1117 Fall detection
• CPC Class Codes: A61B 5/14539 for measuring pH
• CPC Class Codes: A61B 5/14542 for measuring blood gases A61B5/14551 takes precedence
• CPC Class Codes: A61B 5/165 Evaluating the state of mind, e.g. depression, anxiety
• CPC Class Codes: A61B 5/364 Detecting abnormal ECG interval, e.g. extrasystoles, ectopic heartbeats
• CPC Class Codes: A61B 5/366 Detecting abnormal QRS complex, e.g. widening
• CPC Class Codes: A61B 5/369 Electroencephalography [EEG] devices for psychotechnics A61B5/16
• 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 5/686 Permanently implanted devices, e.g. pacemakers, other stimulators, biochips A61B5/6861 takes precedence
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• 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
• CPC Class Codes: A61B 7/003 : Detecting lung or respiration noise
• CPC Class Codes: A61N 1/36064 : Epilepsy
• CPC Class Codes: A61N 1/36135 : using physiological parameters
• CPC Class Codes: A61N 1/36585 : controlled by two or more physical parameters
• CPC Class Codes: G16H 50/20 : for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

Methods, systems, and apparatus for detecting an epileptic event, for example, a seizure in a patient using a medical device. The determination is performed by providing an autonomic signal indicative of the patient'"'"'s autonomic activity; providing a neurologic signal indicative of the patient'"'"'s neurological activity; and detecting an epileptic event based upon the autonomic signal and the neurologic signal.

Claims

1. A method for detecting an epileptic event based upon a patient'"'"'s cardiac signal and kinetic activity, comprising:

providing a cardiac signal indicative of the patient'"'"'s heart beats;

providing a kinetic signal indicative of a body movement of the patient; and

detecting an epileptic event based upon the cardiac signal and the kinetic signal, wherein said detecting is based upon the temporal relationship between the cardiac signal and the kinetic signal.

2. The method of claim 1, wherein said detecting is based upon changes in the cardiac signal, changes in the kinetic signal, or both.

3. The method of claim 1, wherein detecting comprises detecting a possible epileptic event using said cardiac signal and confirming the detecting of the possible epileptic event with said kinetic signal.

4. The method of claim 1, wherein detecting comprises detecting a possible epileptic event using said kinetic signal and confirming the detecting of the possible epileptic event with said cardiac signal.

5. The method of claim 1, wherein said detecting comprises determining at least one cardiac parameter from said cardiac signal, characterizing said cardiac parameter as either indicative of an epileptic seizure or not indicative of an epileptic seizure, determining at least one kinetic parameter from said kinetic signal, characterizing said kinetic parameter as either indicative of an epileptic seizure or not indicative of an epileptic seizure, and determining the occurrence of an epileptic event only if at least one of said cardiac parameter and said kinetic parameter is indicative of an epileptic seizure.

6. The method of claim 1, further comprising classifying said epileptic event based upon said cardiac signal, said kinetic signal, one or more other body signals, or two or more thereof.

7. The method of claim 1, wherein the cardiac signal is provided by an electrocardiogram (EKG).

8. The method of claim 1, wherein the kinetic signal is provided by an accelerometer, an inclinometer, an actigraph, or two or more thereof.

9. The method of claim 1, further comprising providing a responsiveness signal indicative of the patient'"'"'s responsiveness following said detecting, and characterizing the epileptic event based upon the responsiveness signal.

10. The method of claim 1, further comprising providing an awareness signal indicative of the patient'"'"'s awareness following said detecting, and characterizing the epileptic event based upon the awareness signal.

11. A computer readable program storage device encoded with instructions that, when executed by a computer, performs a method for detecting an epileptic seizure based upon a patient'"'"'s cardiac signal and kinetic activity, comprising:

providing a kinetic signal indicative of a body movement of the patient;

calculating at least one kinetic score for said kinetic signal, said at least one kinetic score being indicative of a correlation of said kinetic signal with an epileptic seizure;

providing a cardiac signal indicative of a heart beat sequence for said patient;

detecting a possible epileptic seizure based upon the patient'"'"'s heart beat sequence; and

providing an output indicative of an epileptic seizure if the kinetic score exceeds a first correlation reference value for an epileptic seizure.

12. The computer readable program storage unit of claim 11;

wherein the method further comprises not providing an output indicative of the occurrence of an epileptic event if the kinetic score does not exceed a second correlation reference value for an epileptic seizure.

13. A computer readable program storage device encoded with instructions that, when executed by a computer, performs a method for detecting an epileptic event based upon a patient'"'"'s cardiac signal and kinetic activity, comprising:

providing a kinetic signal indicative of a body movement of the patient;

calculating based on the kinetic signal a kinetic score indicative of a correlation of said kinetic signal with an epileptic event;

detecting an epileptic event based upon changes in the patient'"'"'s cardiac signal;

confirming the detecting if said kinetic score reflects a high correlation with an epileptic event;

overriding the detecting if said kinetic score reflects a low correlation with an epileptic event; and

providing an output indicative of an epileptic event only if the detecting is confirmed.

14. A method for detecting a generalized tonic-clonic epileptic seizure based upon two or more of a patient'"'"'s body signals, comprising:

providing a cardiac signal indicative of the patient'"'"'s heart beat sequence and an accelerometer signal indicative of the patient'"'"'s movement; and

detecting a generalized tonic-clonic epileptic seizure based upon the timewise correlation of at least one feature of the cardiac signal and at least one feature of the accelerometer signal, wherein;

the at least one feature of the cardiac signal is a heart rate above an interictal reference value; and

the at least one feature of the accelerometer signal is an indication of a clonic movement followed by an indication of a cessation of said clonic movement.

15. The method of claim 14, wherein the accelerometer signal further comprises an indication of a fall prior to said indication of said clonic movement.

16. The method of claim 14, further comprising characterizing the generalized tonic-clonic seizure as secondarily generalized if the accelerometer signal comprises at least one characteristic of movement outside an interictal reference value range prior to said indication of said clonic movement.

17. The method of claim 14, further comprising:

indicating the end of the generalized tonic-clonic epileptic seizure when each of the features is absent from its respective body signal.

18. The method of claim 14, further comprising:

indicating the beginning of a post-ictal period based upon the appearance of at least one post-ictal feature of the cardiac signal, the accelerometer signal, or both, wherein;

the cardiac signal is a heart rate below an ictal reference value; and

the accelerometer signal is a decrease in the patient'"'"'s movement below an ictal reference value.

19. The method of claim 18, further comprising providing a responsiveness signal and wherein the indicating is further based upon the responsiveness signal of the patient being below an inter-ictal reference value.

20. The method of claim 18, further comprising providing an awareness signal and wherein the indicating is further based upon the awareness signal of the patient being below an inter-ictal reference value.

21. The method of claim 18, further comprising:

indicating the end of the post-ictal period when each of the post-ictal features returns to a value within an inter-ictal range of values.

22. A computer readable program storage device encoded with instructions that, when executed by a computer, performs a method for detecting a partial epileptic seizure based upon two or more of a patient'"'"'s body signals, comprising:

providing a cardiac signal indicative of the patient'"'"'s heart beat sequence; and

an accelerometer signal indicative of the patient'"'"'s movement; and

detecting the partial epileptic seizure based upon the timewise correlation of at least a first feature of said cardiac signal and at least a first feature of said accelerometer signal, wherein;

the first feature of the cardiac signal is a heart rate outside an interictal reference value range; and

the first feature of the accelerometer signal is a characteristic of movement outside an interictal reference value range and is not a generalized clonic movement.

23. The computer readable program storage device encoded with instructions that, when executed by a computer, perform the method of claim 22, wherein the method further comprises:

providing a responsiveness signal indicative of the patient'"'"'s responsiveness;

classifying the partial epileptic seizure as a complex partial seizure if a decrease in the patient'"'"'s responsiveness below a reference value is timewise correlated with the feature of the cardiac signal, the feature of the accelerometer signal, or both and with a decrease in awareness below a reference inter-ictal value; and

classifying the partial epileptic seizure as a simple partial seizure if a decrease in the patient'"'"'s responsiveness and in awareness are not observed.

24. The computer readable program storage device encoded with instructions that, when executed by a computer, perform the method of claim 22, wherein the method further comprising:

indicating the end of the partial epileptic seizure when both of the cardiac and accelerometer features are outside the range of ictal values for those features.

25. The computer readable program storage device encoded with instructions that, when executed by a computer, perform the method of claim 22, wherein the method further comprises:

indicating the beginning of a post-ictal period based upon the appearance of at least one post-ictal feature of at least one of said cardiac signal and said accelerometer signal, wherein;

the cardiac signal is a heart rate outside of an ictal range of values; and

the accelerometer signal is a characteristic of movement below outside of an ictal range of values.

26. The computer readable program storage device encoded with instructions that, when executed by a computer, perform the method of claim 25, wherein indicating the beginning of the post-ictal period is further based upon a responsiveness signal that increases to a value above an ictal reference value but remains below an inter-ictal reference value.

27. The computer readable program storage device encoded with instructions that, when executed by a computer, perform the method of claim 25, wherein indicating the beginning of the post-ictal period is further based upon an awareness signal that increases to a value above an ictal reference value but remains below an inter-ictal reference value.

28. The computer readable program storage device encoded with instructions that, when executed by a computer, perform the method of claim 25, wherein the method further comprising:

indicating the end of the post-ictal period when each of the cardiac and the accelerometer signals return to inter-ictal ranges.

29. A medical device system for detecting an epileptic event based upon multimodal signals, comprising:

a first sensor for detecting a first modal data and a second sensor for detecting a second modal data relating to a patient'"'"'s body, the first modal data comprising a kinetic signal and the second modal data comprising a cardiac signal of the patient'"'"'s body; and

an implantable medical device (IMD) operatively coupled to the first sensor and the second sensor;

the IMD comprising;

a kinetic signal module for receiving the kinetic signal;

a cardiac signal module for receiving the cardiac signal; and

a processing element for determining whether an epileptic event has occurred based, at least in part, upon the temporal relationship between the first and second modal data.

30. A computer readable program storage device encoded with instructions that, when executed by a computer, performs a method for detecting an epileptic seizure based upon two or more of a patient'"'"'s body signals, comprising:

providing a responsiveness signal indicative of the patient'"'"'s responsiveness;

detecting a seizure if there is a decrease in the patient'"'"'s responsiveness below a reference value that is timewise correlated with a feature of a cardiac signal, classifying the seizure as a generalized tonic-clonic seizure if the accelerometer signal is indicative of

     1) a loss of postural muscle tone outside an inter-ictal reference value,

     2) in increase in postural muscle tone outside an inter-ictal range of reference value, or

     3) a fall, correlated with the feature of the cardiac signal

classifying the seizure as a partial seizure if a decrease in the patient'"'"'s responsiveness is not associated with a change in the accelerometer signal indicative of a loss of postural muscle tone outside an inter-ictal reference value, an increase in postural muscle tone outside an inter-ictal reference value, or if a fall is observed;

classifying the seizure as a partial simple if a decrease in responsiveness is not correlated with a decrease in awareness below an inter-ictal reference value; and

classifying the seizure as a complex partial seizure if a decrease in responsiveness is associated with a decrease in awareness below an inter-ictal reference value.