EEG monitoring system and method of monitoring an EEG

Patent metadata

Field	Value
Publication number	US-10413208-B2
Application number	US-201113335901-A
Country	US
Kind code	B2
Filing date	Dec 22, 2011
Priority date	Jun 26, 2009
Publication date	Sep 17, 2019
Grant date	Sep 17, 2019

Abstract

An EEG monitoring system (2) adapted to be carried continuously by a person to be monitored comprises electrodes for measuring at least one EEG signal from the person carrying the EEG monitoring system (2). The system also comprises signal processing means adapted to receive, process and analyze the EEG signal. Furthermore the system comprises data logging means adapted to log data relating to said EEG signal and a memory for storing said data relating to said EEG signal. A method of using the monitoring system is also provided.

First claim

We claim:

1. A portable EEG monitoring system, said system comprising:
electrodes for measuring an EEG signal from a person carrying the EEG monitoring system,
a signal processor adapted to receive, process and analyze at least a part of said EEG signal, wherein said signal processor comprises a feature extractor for extracting a feature vector from said EEG signal,
a classifier adapted for monitoring said feature vector for identifying an event and outputting an event signal to an event integrator adapted to integrate event signals over time, in order to produce an event level signal,
a data logger adapted to log data relating to said EEG signal, including the feature vector extracted from said EEG signal, and
a memory for storing said data relating to said EEG signal;
wherein said data logger includes a circular buffer for storing data over no more than a predetermined period of time, and said memory stores data logged in said data logger, including said feature vector, when said event level signal exceeds an event detection threshold.

2. The EEG monitoring system according to claim 1 , wherein said classifier comprises an event classifier for detecting important events based on said EEG signal.

3. The EEG monitoring system according to claim 2 , wherein said classifier detects an abnormal brain condition based on the detected important events, and initiates an alarm based on said detection of the abnormal brain condition.

4. The EEG monitoring system according to claim 1 , wherein the data logger is adapted to log information about a number of events.

5. The EEG monitoring system according to claim 1 , wherein the data logger is adapted to log the waveform of said EEG signal.

6. The EEG monitoring system according to claim 1 , wherein said classifier comprises a multi-dimensional classifier.

7. The EEG monitoring system according to claim 6 , wherein said classifier identifies the event as a function of a combination of a plurality of parameters.

8. The EEG monitoring system according to claim 6 , wherein said event corresponds to hypoglycaemia.

9. The EEG monitoring system according to claim 1 , wherein said classifier monitors said feature vector for patterns of signal characteristics indicative of an event of interest.

10. A portable EEG monitoring system, said system comprising:
electrodes for measuring an EEG signal from a person carrying the EEG monitoring system,
a signal processor adapted to receive, process and analyze at least a part of said EEG signal, wherein said signal processor comprises a feature extractor for extracting a feature vector from said EEG signal,
a classifier adapted for monitoring said feature vector for identifying an event and outputting an event signal to an event integrator adapted to integrate event signals over time, in order to produce an event level signal, wherein said classifier comprises an event classifier for detecting important events based on said EEG signal,
a data logger adapted to log data relating to said EEG signal, including the feature vector extracted from said EEG signal, and
a memory for storing said data relating to said EEG signal;
wherein said data logger includes a circular buffer for storing data over no more than a predetermined period of time, and said EEG monitoring system is configured to detect an abnormal brain condition when said event level signal exceeds an event detection threshold, and wherein said memory stores data logged in said data logger, including said feature vector, in response to said event level signal exceeding said event detection threshold.

11. A method for EEG monitoring using a portable EEG measuring system, said method comprising:
measuring an EEG signal from a person carrying the EEG monitoring system,
receiving, processing and analyzing at least a part of said EEG signal using a signal processor, said signal processing comprising the extraction of a feature vector from said EEG signal using a feature extractor,
monitoring said feature vector, identifying an event using a classifier and outputting an event signal to an event integrator and producing an event level signal by integrating event signals over time using said event integrator,
logging data relating to said EEG signal using a data logger, including the feature vector extracted from said EEG signal, and
storing said data relating to said EEG signal in a memory;
wherein said data logger includes a circular buffer for storing data over no more than a predetermined period of time, and said memory stores data logged in said data logger, including said feature vector, when said event level signal exceeds an event detection threshold.

12. The method according to claim 11 , wherein important events are detected based on said EEG signal, using an event classifier.

13. The method according to claim 12 , wherein an awareness condition is detected based on the important events, and an alarm initiated based on said detection of the awareness condition.

14. The method according to claim 11 , wherein information about a number of events is logged using said data logger.

15. The method according to claim 11 , wherein the waveform of said EEG signal is logged in said data logger.

16. The method according to claim 11 , wherein said classifier comprises a multi-dimensional classifier.

17. The method according to claim 16 , wherein said classifier identifies the event as a function of a combination of a plurality of parameters.

18. The method according to claim 11 , wherein said classifier monitors said feature vector for patterns of signal characteristics indicative of an event of interest.

19. The method according to claim 16 , wherein said event corresponds to hypoglycaemia.

20. A method for EEG monitoring using a portable EEG measuring system, said method comprising:
measuring an EEG signal from a person carrying the EEG monitoring system,
receiving, processing and analyzing at least a part of said EEG signal using a signal processor, said signal processing comprising the extraction of a feature vector from said EEG signal using a feature extractor,
monitoring said feature vector, identifying an event using a classifier and outputting an event signal to an event integrator and producing an event level signal by integrating event signals over time using said event integrator,
logging data relating to said EEG signal using a data logger, including the feature vector extracted from said EEG signal, and
storing said data relating to said EEG signal in a memory;
wherein important events are detected based on said EEG signal, using an event classifier;
wherein an awareness condition is detected based on the important events, and an alarm initiated based on said detection of the awareness condition, wherein said EEG monitoring system is configured to detect said awareness condition when said event level signal exceeds an event detection threshold; and
wherein said data logger includes a circular buffer for storing data over no more than a predetermined period of time, and said memory stores data logged in said data logger, including said feature vector, in response to said event level signal exceeding said event detection threshold indicating detection of said awareness condition.

Assignees

• Kidmose Preben
• Westermann Soren Erik
• Widex As

Inventors

• Kidmose Preben
• Westermann Soren Erik

Classifications

• A61B5/6838

  Clamps or clips · CPC title

• A61B5/6815 Primary

  Ear · CPC title

• A61B5/4094

  Diagnosing or monitoring seizure diseases, e.g. epilepsy · CPC title

• A61B5/0031

  Implanted circuitry · CPC title

• A61B5/7264 Primary

  Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems · CPC title