Probabilistic Seizure Activity Measures From Multiple Algorithms

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The lack of a universal and objective definition of seizures complicates the validation and comparison of seizure detection algorithms, leading to inconsistent and biased results due to cognitive biases in expert-based methods, and there is a need for a common database for performance comparisons.

Innovation Solution

A probabilistic measure of seizure activity (PMSA) is determined using multiple seizure detection algorithms, such as wavelet transform maximum modulus-stepwise approximation, to provide a probabilistic measure based on the outputs of these algorithms, addressing the non-stationary and fractal nature of seizures.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If expert-based rules are used for seizure detection, then clinical knowledge is utilized, but cognitive biases propagate into the architecture leading to inconsistent results

Engineering Contradiction:

Improveseizure detection consistencyVSAvoidalgorithm architecture complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces expert-based mechanical decision-making with an automated computational system that uses signal processing algorithms (wavelet transform, autoregression, STA/LTA) to objectively detect seizures, eliminating cognitive biases while maintaining clinical relevance through validated detection criteria

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent transforms subjective expert judgments into objective quantitative parameters by measuring signal features (power spectrum, fractal dimensions, autocorrelation coefficients) that can be consistently computed and compared across different cases and experts

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If visual analysis is used for seizure detection, then expert interpretation is obtained, but objectivity and reproducibility are compromised

Engineering Contradiction:

Improveseizure detection objectivityVSAvoiddetection method simplicity

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent enables the system to automatically perform seizure detection without requiring expert visual analysis, with the algorithm independently processing signals and generating detections based on predefined objective criteria, thereby improving measurement precision while maintaining operational simplicity

Inventive Principle:

Principle #25Self-service

3Reliability

If multiple detection algorithms are used, then detection accuracy is improved, but system complexity increases

Engineering Contradiction:

Improveseizure detection accuracyVSAvoidalgorithm system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent combines multiple detection algorithms (wavelet transform, autoregression, STA/LTA) into a unified system where their outputs are integrated through logical operations, achieving improved detection accuracy while managing complexity through systematic combination rather than independent parallel systems

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS12414742B2Apparatus and systems for event detection using probabilistic measures

Publication Date: 2025.09.16 FLINT HILLS SCIENTIFIC LLC

AI summary

Methods, systems, and apparatus for determining probabilistic measures of seizure activity (PMSA) values based on a plurality of seizure detection algorithms and/or body signals used as inputs by the seizure detection algorithms. Use of the PMSA values to detect seizure activity based on a consensus of the algorithms and/or body signals, and/or warn, log, administer a therapy, or assess the efficacy of a therapy.