Adaptive systems and methods for seizure detection and confidence indication
Inventors
Frankel, Mitchell A. • Kazen, Avidor • Newton, Tyler James • Tosi, Zoë Vera
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12239450-B2
Publication Date
2025-03-04
Expiration Date
Abstract
Disclosed electroencephalogram (EEG) monitoring and detection systems and methods can detect differentiated electrographic seizure characteristics of different seizure types across a diverse group of patients. Disclosed systems and methods can utilize EEG data collected by discrete wireless EEG sensors positioned on a scalp of a patient.
Core Innovation
The invention detects seizure events using electroencephalogram (EEG) signals by obtaining one or more EEG data segments collected by a plurality of EEG sensors positioned on a scalp of a patient. For each segment, the system processes the EEG data to obtain a plurality of probabilities of occurrence of one or more electrographic seizure characteristics, and these probabilities are used as the basis for downstream event interpretation and output.
The invention interprets the plurality of probabilities using a plurality of event identifiers to obtain a plurality of event interpretations. Each event interpretation reflects a confidence value that represents a confidence that the interpretation is a true positive event. An event interpretation is then selected from the plurality of event interpretations based on the confidence values.
Finally, the invention outputs a label indicating a seizure event based on the selected event interpretation and a confidence indicator determined based on the confidence value of the selected event interpretation. The confidence indicator reflects confidence in the seizure event being a true positive event, and the dependent claim refinements provide additional label forms such as start time and duration or prevalence over time.
Claims Coverage
The provided material includes two independent claims: clm-00001 (a method) and clm-00011 (a non-transitory computer readable medium). Both claims share the same central sequence: obtaining EEG segments, processing them into probabilities of electrographic seizure characteristics, interpreting those probabilities into confidence-valued event interpretations via multiple event identifiers, selecting an interpretation based on confidence, and outputting a seizure event label with a confidence indicator reflecting true-positive confidence.
Multiple event-identifier interpretations with confidence values for electrographic seizure characteristics
Interpreting, by each of a plurality of event identifiers, the plurality of probabilities to obtain a plurality of event interpretations, each event interpretation reflecting a confidence value that represents a confidence of the interpretation being a true positive event.
Selecting an event interpretation based on confidence values
Selecting an event interpretation from the plurality of event interpretations based on the confidence values.
Output label for seizure event with a true-positive confidence indicator
Outputting a label indicating a seizure event based on the selected event interpretation and a confidence indicator determined based on the confidence value of the selected event interpretation, the confidence indicator reflecting a confidence in the seizure event being a true positive event.
Processing EEG segments into probabilities of electrographic seizure characteristics
Processing each of the one or more EEG data segments to obtain a plurality of probabilities of occurrence of one or more electrographic seizure characteristics.
Across both independent claims, the inventive concept is the use of multiple event identifiers to interpret probabilities into confidence-valued event interpretations, selecting an interpretation using the confidence values, and outputting a seizure-event label together with a confidence indicator tied to confidence of a true positive event.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?