Embedded Seizure Detection During Brain Stimulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current seizure detection methods for epilepsy, particularly for drug-resistant epilepsy, are inaccurate due to the reliance on patient diaries and the limited exploration of intracranial EEG signals for seizure detection in brain stimulation devices, leading to challenges in evaluating the efficacy of therapeutic brain stimulation.
Innovation Solution
A system and method for detecting seizures using intracranial EEG signals, segmenting them into time-frequency domains, and applying a classifier to determine seizure activity based on power thresholds, with adjustable parameters for different stimulation conditions, to create an electronic seizure log.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If patient diaries are used to track seizure outcomes, then seizure monitoring is implemented, but accuracy and reliability of seizure data are poor
Solution Approach 1:
The patent replaces the manual mechanical system of patient diaries with an automated electronic seizure detection system that uses implantable devices to sense brain electrical activity and automatically log seizure events, eliminating human error and improving measurement precision and reliability
Solution Approach 2:
The implantable device performs self-monitoring of seizure activity by automatically detecting and logging events without requiring patient intervention or manual diary keeping, enabling continuous objective monitoring
2Measurement precision
If intracranial EEG signals are used for seizure detection during brain stimulation, then seizure detection capability is improved, but false positive rate increases due to stimulation artifacts
Solution Approach 1:
The system performs preliminary classification of brain signals to distinguish seizure activity from stimulation artifacts before final seizure detection, using trained classifiers to predict whether detected events are true seizures or stimulation-related false positives
Solution Approach 2:
The system uses feedback from signal classification results to adjust detection thresholds and parameters, continuously optimizing the balance between seizure detection sensitivity and false positive reduction based on observed signal patterns
3Measurement precision
If fixed detection parameters are used across different stimulation conditions, then device complexity is reduced, but detection accuracy decreases when stimulation is present
Solution Approach 1:
The system dynamically adjusts detection parameters based on the presence and characteristics of brain stimulation, automatically modifying detection thresholds and signal processing settings to optimize performance under varying stimulation conditions without requiring manual reconfiguration
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Improves seizure detection accuracy with reduced false positives, providing a reliable electronic record of seizure history and enabling adjustments to brain stimulation therapy based on precise seizure data.
Implementation Method 1
The iEEG signals can be segmented into fixed time intervals, each segment converted from the time domain to the frequency domain (e.g., using a fast-Fourier transform (FFT))
Data Source
AI summary
This specification describes techniques for seizure detection in mammals. A first set of electrodes is used to stimulate a region of a brain of a mammal, and an electrical signal sensed by a second subset of electrodes is acquired during stimulation. The electrical signal is segmented into time-segmented portions according to a value of a time parameter. For each time-segmented portion of the electrical signal, a power is determined for the portion of the signal within a frequency band defined by a value of a frequency parameter. A classifier is used to classify the time-segmented portion of the signal as seizure positive or seizure negative based on the determined power within the frequency band. The values of the time and frequency parameters can result in the classifier achieving an effective level of performance defined by an area under a precision-recall curve (AU-PRC) for the classifier of at least 0.5.