Back to results
US 12,708,320 B2Granted
EEG recording and analysis
AssigneeEpitel, Inc.
InventorsMichael K. Elwood, Mitchell A. Frankel, Mark J. Lehmkuhle, Jean M. Wheeler, Robert Lingstuyl, Erin M. West, Tyler D. McGrath
Life of this patent
Estimating the term…
Abstract
One embodiment provides a method, including: obtaining EEG data from one or more single channel EEG sensor worn by a user; classifying, using a processor, the EEG data as one of nominal and abnormal; and providing an indication associated with a classification of the EEG data. Other embodiments are described and claimed.
Claims20
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.
5 more elements
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.
6 more elements
Dependencies are inferred from the claim text.