Motion Sensor Avatar for Epilepsy Seizure Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for diagnosing and monitoring epilepsy are subjective and invasive, relying on patient recall and prolonged hospital-based video capturing, which limits their effectiveness and practicality for everyday life.

Innovation Solution

A method utilizing multiple motion sensors installed on the body to collect and record data for extended periods, combining sensor data to visualize movements through an avatar, allowing for real-time monitoring and differentiation of seizure patterns from daily activities, using three-axis accelerometers, gyroscopes, and other medical sensors, with data fusion and pattern recognition for precise analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If multiple motion sensors are installed on the body for continuous monitoring, then measurement precision and reliability are improved, but device complexity increases

Engineering Contradiction:
Improveseizure detection accuracyVSAvoidsensor system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system divides the monitoring task into multiple independent sensor units distributed across different body parts (head, torso, limbs). Each sensor independently captures motion data from its local position, and the central system integrates these segmented measurements to achieve comprehensive seizure detection with high precision while maintaining manageable complexity through modular architecture.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Multiple sensors measuring different physical quantities (acceleration, gyroscope, magnetometer) are merged into a unified sensor system. The data from all sensors are combined and processed together to detect seizure patterns, leveraging the complementary information from each sensor type to improve overall measurement precision and reliability.

Inventive Principle:
Principle #5Merging (Combining)

2Reliability

If data is collected for extended periods (at least 24 hours), then reliability of seizure detection is improved, but loss of time and patient burden increase

Engineering Contradiction:
Improveseizure detection reliabilityVSAvoidmonitoring duration
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary processing and filtering of sensor data in real-time during the monitoring period. Motion patterns are pre-analyzed and segmented, with potential seizure events flagged for detailed review. This preliminary action prepares the data in advance, making the actual diagnosis process faster and reducing the time burden on patients and physicians.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

Instead of continuous intensive processing, the system employs periodic analysis intervals where sensor data is collected continuously but evaluated at specific intervals or when threshold events occur. This periodic action maintains high reliability for detecting seizures that may happen infrequently while reducing overall processing time and patient burden during normal monitoring periods.

Inventive Principle:
Principle #19Periodic action

3Measurement precision

If multiple sensors are used for comprehensive monitoring, then measurement precision is improved, but ease of operation deteriorates

Engineering Contradiction:
Improvemotion recognition precisionVSAvoidsensor installation ease
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The sensor units are designed as universal, multi-functional components that can be attached to various body parts (head, torso, limbs) and perform multiple measurement functions (acceleration, rotation, magnetic field sensing). This universality simplifies installation and operation, as the same sensor type can be deployed anywhere on the body without requiring different specialized devices, while still achieving comprehensive motion recognition precision.

Inventive Principle:
Principle #6Universality (Multi-functionality)

4Measurement precision

If video capturing is used to observe seizures, then measurement precision is improved, but device complexity and patient burden increase

Engineering Contradiction:
Improveseizure observation accuracyVSAvoidvideo system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system replaces the mechanical video capturing approach with motion sensors that directly measure physical movement parameters. Instead of recording visual images that require complex processing and interpretation, the sensors directly detect the characteristic motion patterns of seizures through acceleration and rotation measurements, simplifying the overall system while maintaining or improving measurement precision for seizure detection.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

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

Enables effective, non-invasive, and continuous monitoring of movements, allowing for accurate detection of seizures and treatment evaluation with minimal disruption to daily life, providing valuable data for medical professionals to diagnose and assess epilepsy and other neurological diseases.

Implementation Method 1

the sensors are each three-axis motion sensors, in other words, accelerometer sensors, which detect an orientation as well as a change in velocity, thus an acceleration

Methodology Applied
Scientific EffectAccelerometer: Accelerometer

Implementation Method 2

In addition, the sensor can comprise a gyroscope

Methodology Applied
Scientific EffectGyroscope: Gyroscope

Data Source

PatentEP4140407A1A method and a device for retrieving sensor data for medical motion recognition
Publication Date: 2023.03.01 GAIA AG
  • EP4140407A1 patent drawingFigure 1~2
  • EP4140407A1 patent drawingFigure 3
  • EP4140407A1 patent drawing

AI summary

The present invention relates to a method for retrieving sensor data for medical motion recognition, wherein the method comprises retrieving and recording data from multiple motion sensors on a person for a period of time of at least 24 hours, and wherein the method further comprises displaying at least time segments of the retrieved and recorded data in the form of an avatar for visualizing movements of the person within the time segment.