Blepharometric Seizure Prediction Using Eyelid Movement Patterns
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies for analyzing neurological conditions using blepharometric data are limited in their ability to predict and detect complex seizure events, particularly non-convulsive seizures, due to the lack of effective methods for monitoring involuntary eyelid movements beyond drowsiness and alertness.
Innovation Solution
A computer-implemented method that utilizes blepharometric data from sensor devices, such as infrared reflectance oculography spectacles, to process eyelid movement parameters like negative Inter-Event Duration (IED) and Blink Total Duration (BTD), identifying threshold increases and deviations to predict future seizure events and detect myoclonic eyelid movements, providing alerts for potential seizures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If blepharometric data analysis is used to predict and detect complex seizure events, then the capability to detect non-convulsive seizures is improved, but the complexity of the analysis system increases
Solution Approach 1:
The patent segments the complex seizure detection task into distinct components: data collection from multiple sensors (accelerometers, gyroscopes, blepharometric sensors), feature extraction (separating convulsive from non-convulsive patterns), and classification. This segmentation allows the system to handle complex neurological conditions by breaking down the analysis into manageable, specialized modules that can be processed independently.
Solution Approach 2:
The patent introduces intermediate processing layers between raw sensor data and final seizure detection. These intermediaries include feature extraction algorithms that transform raw blepharometric and motion data into meaningful patterns, and classification systems that interpret these patterns. This intermediary processing enables the system to manage complexity by creating abstraction layers that simplify the relationship between diverse sensor inputs and diagnostic outputs.
2Measurement precision
If multiple sensor types and parameters are analyzed for comprehensive seizure detection, then the measurement precision is improved, but the device complexity increases
Solution Approach 1:
The patent merges data from multiple sensor types (accelerometers, gyroscopes, blepharometric sensors) and combines them with clinical expertise to create a comprehensive seizure detection system. By integrating these diverse data sources and processing them through unified algorithms, the system achieves high measurement precision for detecting both convulsive and non-convulsive seizures without requiring separate systems for each sensor type.
Solution Approach 2:
The patent creates a universal analysis platform that handles multiple seizure types and multiple sensor inputs through a single integrated system. The same core algorithms process data from accelerometers, gyroscopes, and blepharometric sensors, enabling the system to detect various neurological conditions (epileptic seizures, absence seizures, myoclonic jerks) with consistent precision. This multi-functionality reduces overall system complexity compared to having separate specialized systems for each sensor type.
Data Source
AI summary
Blepharometric data (data describing eyelid position as a function of time) is recorded and processed for the purposes of predicting a future risk and/or current occurrence of neurological events such as seizures. For example, in one embodiment, blepharometric data is recorded via infrared reflectance oculography spectacles, and processed in real time thereby to extract a set of blepharometric artifacts. Where those artifacts indicate prolonged spiking in blink calmness (for example, based on spiking in negative inter-event duration, or negative IED), an alert is able to be generated thereby to indicate that the subject is at risk of a seizure in a proximal time period. This provides an opportunity to implement mitigation measures, for example, to reduce the likelihood of the seizure manifesting, and/or to mitigate harm should the seizure occur.