EEG recording and analysis

1 . A method, comprising:

collecting EEG data from at least two self-contained wireless single-channel EEG sensors disposed on a scalp of a patient, the EEG data comprising a plurality of single channel EEG time segments, the at least two EEG sensors configured to wirelessly transmit the EEG data;

classifying, without user input and using a pre-trained machine learning classifier, each of the plurality of single channel EEG time segments as one of normal or abnormal, wherein the pre-trained machine learning classifier has been trained using a training set of EEG data;

identifying a set of the plurality of single channel EEG time segments classified as abnormal to indicate a seizure event lasting longer than an individual single channel EEG time segment;

creating an annotation list comprising an ordered set of the plurality of single channel EEG time segments;

providing an indication of the seizure event and the annotation list to facilitate an expedited review of the EEG data; and

causing the indication along with a length of the seizure event to be displayed,

wherein the method is performed under control of one or more processors.

2 . The method of claim 1 , further comprising:

updating an abnormality list based on the classification of each of the plurality of single channel EEG time segments as one of normal or abnormal to facilitate automated recording of discrete seizure events; and

refining the pre-trained machine learning classifier using the abnormality list to tune the pre-trained machine learning classifier for automated recording of discrete seizure events in the patient.

3 . The method of claim 1 , further comprising creating a seizure forecast based on one or more of the EEG data, the classification of the EEG data as one of normal or abnormal, and an abnormality list.

4 . The method of claim 3 , wherein creating the seizure forecast comprises determining a likelihood that a seizure will occur for one or more time periods based on one or more of the EEG data, the classification of the EEG data as one of normal or abnormal, and the abnormality list.

5 . The method of claim 4 , wherein the one or more time periods comprise: a second, a minute, an hour, a day, and a week.

6 . The method of claim 3 , further comprising providing the seizure forecast to the patient.

7 . The method of claim 1 , wherein the training set of EEG data comprises one or more of: EEG data collected by at least two other self-contained wireless single-channel EEG sensor or EEG data collected by a wired EEG system.

8 . The method of claim 1 , further comprising:

receiving a seizure indication input from the patient; and

updating an abnormality list based on the seizure indication input.

9 . The method of claim 1 , further comprising:

creating a patient health report based on one or more of: the EEG data, the classification of EEG data, and the annotation list; and

providing the patient health report for being displayed.

10 . The method of claim 1 , further comprising:

classifying the seizure event as a type of seizure; and

updating the annotation list based on the classification of the seizure event as the type of seizure.

11 . An electroencephalogram (EEG) monitoring system comprising:

at least two self-contained wireless single-channel EEG sensors configured to be disposed on a scalp of a patient and collect EEG data, the EEG data comprising a plurality of single channel EEG time segments, the at least two self-contained wireless single-channel EEG sensors configured to wirelessly transmit the EEG data; and

a non-transitory computer readable medium storing program instructions that, when executed by at least one processor, cause the at least one processor to:

classify, without user input and using a pre-trained machine learning classifier, each of the plurality of single channel EEG time segments as one of normal or abnormal, wherein the pre-trained machine learning classifier has been trained using a training set of EEG data;

identify a set of the plurality of single channel EEG time segments classified as abnormal to indicate a seizure event lasting longer than an individual EEG time segment;

create an annotation list comprising an ordered set of the plurality of single channel EEG time segments;

provide an indication associated with the seizure event and the annotation list to facilitate an expedited review of the EEG data; and

cause the indication along with a length of the seizure event to be displayed.

12 . The EEG monitoring system of claim 11 , wherein the instructions are further configured to cause the at least one processor to:

update an abnormality list based on the classification of each of the plurality of single channel EEG time segments as one of normal or abnormal to facilitate automated recording of discrete seizure events; and

refine the pre-trained machine learning classifier using the abnormality list to tune the pre-trained machine learning classifier for automated recording of discrete seizure events in the patient.

13 . The EEG monitoring system of claim 11 , wherein the instructions are further configured to cause the at least one processor to create a seizure forecast based on one or more of: the EEG data, the classification of the EEG data as one of normal or abnormal, and an abnormality list.

14 . The EEG monitoring system of claim 11 , wherein the instructions are further configured to cause the at least one processor to determine a likelihood that a seizure will occur for one or more time periods based on one or more of: the classification of the EEG data as one of normal or abnormal and the abnormality list.

15 . The EEG monitoring system of claim 14 , wherein the one or more time periods comprise: a second, a minute, an hour, a day, and a week.

16 . The EEG monitoring system of claim 13 , wherein the instructions are further configured to cause the at least one processor to provide the seizure forecast to the patient.

17 . The EEG monitoring system of claim 11 , wherein the training set of EEG data comprises one or more of: EEG data collected by at least two other self-contained wireless single-channel EEG sensor or EEG data collected by a wired EEG system.

18 . The EEG monitoring system of claim 11 , wherein the instructions are further configured to cause the at least one processor to:

receive a seizure indication input from the patient; and

update an abnormality list based on the seizure indication input.

19 . The EEG monitoring system of claim 11 , wherein the instructions are further configured to cause the at least one processor to:

create a patient health report based on the EEG data, the classification of EEG data, and the annotation list; and

provide the patient health report for being displayed.

20 . The EEG monitoring system of claim 11 , wherein the instructions are further configured to cause the at least one processor to:

classify, the pre-trained classifier, the seizure event as a type of seizure; and

updating the annotation list based on the classification of the EEG data as the type of seizure.