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

1. A method of seizure detection, the method comprising:

receiving, by a processing circuit, an electroencephalogram (EEG) signal generated based on electrical brain activity of a patient;

determining, by the processing circuit, a plurality of metrics based on the EEG signal, the plurality of metrics indicating non-linear features of the EEG signal;

determining, by the processing circuit, a trajectory of each of the plurality of metrics at a plurality of points in time;

determining, by the processing circuit, that occurrences of particular patterns of trajectories of the plurality of metrics map to a seizure category by:

determining, by the processing circuit, whether an occurrence of a particular trajectory of each of the plurality of metrics meets a predefined level of statistical significance based on a probability of the occurrence of the particular trajectory of each of the plurality of metrics; and

determining, by the processing circuit, that particular trajectories that meet the predefined level of statistical significance map to the seizure category;

generating, by the processing circuit, a seizure alert indicating that the EEG signal indicates a candidate seizure responsive to determining that the occurrences of the particular patterns of the trajectories map to the seizure category; and

causing, by the processing circuit, a display of a user device to display a visual indicator responsive to generating the seizure alert.

2. The method of claim 1 , further comprising determining, by the processing circuit, that the EEG signal indicates the candidate seizure based on at least one of a default parameter value or a user defined parameter value.

3. The method of claim 1 , wherein the plurality of metrics comprise at least one of dimensionality, synchrony, Lyapunov exponents, entropy, global non-linearity, distance differences between recurrence trajectories, a complexity metric, or self-similarity.

4. The method of claim 1 , further comprising determining, by the processing circuit, 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.

5. The method of claim 1 , further comprising:

receiving, by the processing circuit, the EEG signal from a local EEG acquisition system via a network; and

providing, by the processing circuit, result data to the local EEG acquisition system via the network.

6. The method of claim 1 , wherein the processing circuit is included within a local seizure detection system, wherein the local seizure detection system is:

integrated with a local EEG system; or

connected locally to an EEG acquisition system.

7. The method of claim 1 , further comprising:

generating, by the processing circuit, a user interface, the user interface comprising:

a real-time trend of the EEG signal; and

one or more of the plurality of metrics; and

causing, by the processing circuit, the display of the user device to display the user interface.

8. The method of claim 7 , wherein one of the plurality of metrics is an eigenvalue, wherein the user interface further comprises a trend of the eigenvalue.

9. The method of claim 7 , 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. A seizure detection system comprising:

a processing circuit configured to:

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

determine a plurality of metrics based on the EEG signal, the plurality of metrics indicating non-linear features of the EEG signal;

determine probabilities of occurrences of particular patterns of trajectories of the plurality of metrics;

determine that the probabilities of the occurrences of the particular patterns of the trajectories of the plurality of metrics map to a category, wherein the category is a seizure category;

generate a seizure alert indicating that the EEG signal indicates a candidate seizure responsive to determining that the probabilities of the occurrences of the particular patterns of the trajectories map to the category; and

cause a display of a user device to display a visual indicator responsive to generating the seizure alert.

11. The seizure detection system of claim 10 , wherein the processing circuit is configured to determine that the EEG signal indicates the candidate seizure based on at least one of a default parameter value or a user defined parameter value.

12. The seizure detection system of claim 10 , wherein the plurality of metrics comprise at least one of dimensionality, synchrony, Lyapunov exponents, entropy, global non-linearity, distance differences between recurrence trajectories, a complexity metric, or self-similarity.

13. The seizure detection system of claim 10 , wherein the processing circuit is 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.

14. The seizure detection system of claim 10 , wherein the processing circuit is configured to:

receive the EEG signal from a local EEG acquisition system via a network; and

provide result data to the local EEG acquisition system via the network.