Systems and methods for seizure detection based on changes in electroencephalogram (EEG) non linearities

1. A seizure detection system comprising one or more circuits, the one or more circuits are configured to:

receive an electroencephalogram (EEG) signal generated based on electrical brain activity of a patient;

determine a plurality of different types of metrics based on the EEG signal, one type of metric of the plurality of different types of metrics being eigenvalues, the plurality of different types of metrics indicating one or more non-linear features of the EEG signal;

monitor a moving window of the eigenvalues of the EEG signal;

determine that the eigenvalues are decreasing;

determine that the EEG signal indicates a candidate seizure by determining that the eigenvalues are decreasing and that another one of the plurality of different types of metrics is changing in a set pattern; and

cause a display of a user interface device to display a visual indicator responsive to determining that the EEG signal indicates the candidate seizure.

2. The seizure detection system of claim 1 , wherein at least one of the moving window or the set pattern is based on a default parameter value.

3. The seizure detection system of claim 1 , wherein the one or more circuits are configured to determine, based on the plurality of different types of metrics, an increase in the one or more non-linear features over time.

4. The seizure detection system of claim 1 , wherein the plurality of different types of metrics comprise at least one of dimensionality, synchrony, Lyapunov exponents, entropy, global non-linearity, distance differences between recurrence trajectories, or self-similarity.

5. The seizure detection system of claim 1 , wherein the one or more circuits are configured to:

perform a preliminary analysis with the eigenvalues, wherein the preliminary analysis indicates whether the EEG signal is insignificant; and

perform a secondary analysis with one or more metrics of the plurality of different types of metrics to determine whether the EEG signal indicates the candidate seizure or that the EEG signal includes noise.

6. The seizure detection system of claim 1 , wherein the one or more circuits are configured to:

determine probabilities of an occurrence of a pattern of a trajectory of each of the plurality of different types of metrics at a plurality of points in time;

determine whether the probabilities of the occurrence of a pattern of the trajectory of each of the plurality of different types of metrics meet a predefined level of statistical significance based on the probabilities; and

map metrics that meet the predefined level of statistical significance of the plurality of different types of metrics to a category, wherein the category is a seizure category.

7. The seizure detection system of claim 1 , wherein the one or more circuits are configured to determine a dimensionality of the EEG signal by performing a phase space analysis by increasing a value of the dimensionality until a number of false neighbors reaches zero, wherein a starting value of the dimensionality is based on an age of the patient.

8. The seizure detection system of claim 1 , wherein the one or more circuits are configured to:

determine whether one or more of the plurality of different types of metrics exhibit changes over time that meet a predefined level of statistical significance;

generate a user interface, the user interface comprising:

a real-time trend of the EEG signal; and

the one or more of the plurality of different types of metrics; and

cause the user interface device to display the user interface.

9. The seizure detection system of claim 8 , wherein the user interface further comprises a historical window of the EEG signal, the historical window of the EEG signal associated with the candidate seizure.

10. The seizure detection system of claim 1 , wherein the one or more circuits are configured to:

determine Renyi permutation entropy values based on the EEG signal;

determine that the Renyi permutation entropy values are decreasing;

determine that the EEG signal indicates the candidate seizure in response to a determination that the eigenvalues are decreasing and a second determination that the Renyi permutation entropy values are decreasing; and

determine that the EEG signal indicates noise based at least in part on eigenvalues decreasing and the Renyi permutation entropy values decreasing.

11. The seizure detection system of claim 1 , wherein the one or more circuits are configured to:

determine Renyi permutation entropy values based on the EEG signal;

determine that the Renyi permutation entropy values are increasing;

determine sample entropy values based on the EEG signal in response to a first determination that the Renyi permutation entropy values are increasing;

determine that the EEG signal indicates the candidate seizure in response to a second determination that the sample entropy values are negative; and

determine that the EEG signal does not indicate the candidate seizure in response to a third determination that the sample entropy values are positive.

12. The seizure detection system of claim 1 , wherein at least one of a step size or an overlap of a window used in a secondary analysis with one metric of the different types of metrics is based on user input.

13. A seizure detection system comprising:

an interface configured to receive an electroencephalogram (EEG) signal from electrodes, the EEG signal being related to electrical brain activity of a patient; and

a processor configured to:

determine a plurality of different types of metrics based on the EEG signal, one type of metric of the plurality of different types of metrics being eigenvalues, the plurality of different types of metrics indicating one or more non-linear features of the EEG signal;

determine that the eigenvalues are decreasing;

determine that the EEG signal indicates a candidate seizure by determining that the eigenvalues are decreasing and that another one of the plurality of different types of metrics is changing in a set pattern; and

cause a display of a user interface device to display a visual indicator responsive to determining that the EEG signal indicates the candidate seizure.

14. The seizure detection system of claim 13 , wherein the set pattern is based on a default parameter value or a user defined parameter value.

15. The seizure detection system of claim 13 , wherein the processor is configured to determine, based on the plurality of different types of metrics, an increase in the one or more non-linear features over time.

16. The seizure detection system of claim 13 , wherein the plurality of different types of metrics comprise at least one of dimensionality, synchrony, Lyapunov exponents, entropy, global non-linearity, distance differences between recurrence trajectories, or self-similarity.

17. The seizure detection system of claim 13 , wherein the processor is disposed in bedside equipment coupled to the electrodes.

18. A seizure detection system comprising one or more circuits, the one or more circuits are configured to:

receive an electroencephalogram (EEG) signal generated based on electrical brain activity of a patient;

determine a plurality of different types of metrics based on the EEG signal, one type of metric of the plurality of different types of metrics being eigenvalues, the plurality of different types of metrics indicating one or more non-linear features of the EEG signal;

determine whether the eigenvalues are decreasing; and

determine that the EEG signal indicates a candidate seizure by determining that the eigenvalues are decreasing and that another one of the plurality of different types of metrics is changing in a set pattern; and

cause a display of a user interface device to display a visual indicator responsive to determining that the EEG signal indicates the candidate seizure.

19. The seizure detection system of claim 18 , wherein the one or more circuits are configured to determine a dimensionality of the EEG signal by performing a phase space analysis by increasing a value of the dimensionality until a number of false neighbors reaches zero, wherein a starting value of the dimensionality is based on an age of the patient.

20. The seizure detection system of claim 18 , wherein the one or more circuits are configured to:

generate a user interface, the user interface comprising:

a real-time trend of the EEG signal; and

the one or more of the plurality of different types of metrics; and

cause the user interface device to display the user interface.