Neural Network Ventricular Activation Assessment from Standard ECG

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for assessing ventricular electrical activation patterns require ultra-high-frequency ECG recordings, which are time-consuming and not feasible with standard ECG equipment, limiting their clinical applicability.

Innovation Solution

A method using standard ECG signals processed by a neural network to estimate ventricular electrical activation parameters, including pre-processing steps to remove baseline wandering and normalize signals, and training a neural network with down-sampled ultra-high-frequency data to achieve accurate parameter estimation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If ultra-high-frequency ECG technique is used to describe ventricular activation patterns, then measurement precision is improved, but recording time increases and device complexity increases

Engineering Contradiction:

Improveventricular activation parameter accuracyVSAvoidrecording time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent creates a digital copy (neural network model) of the ultra-high-frequency ECG analysis capability. The neural network is trained on data from ultra-high-frequency ECG recordings but can process standard ECG signals, effectively copying the analytical function without requiring the expensive and time-consuming ultra-high-frequency recording equipment and procedures.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent changes the sampling frequency parameter from ultra-high-frequency (3-7 kHz) to standard ECG frequency (1 kHz). By training the neural network to recognize ventricular activation patterns at this lower frequency, the system maintains measurement precision while reducing recording time and equipment requirements.

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If ultra-high-frequency ECG technique is used to describe ventricular activation patterns, then measurement precision is improved, but device complexity increases

Engineering Contradiction:

Improveventricular activation parameter accuracyVSAvoidECG equipment requirements

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces complex ultra-high-frequency ECG equipment with a software-based neural network model. The model captures the essential analytical capability of expensive hardware through computational processing of standard ECG signals, eliminating the need for specialized equipment while maintaining measurement precision.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent substitutes the mechanical/electronic complexity of ultra-high-frequency ECG acquisition systems with a computational neural network. Instead of requiring sophisticated hardware to capture high-frequency signals, the system uses software algorithms trained on standard ECG data to achieve the same analytical results.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Device complexity

If standard ECG equipment is used, then device complexity is reduced, but measurement precision deteriorates

Engineering Contradiction:

ImproveECG equipment simplicityVSAvoidventricular activation parameter accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent creates a computational copy of the analysis function that was previously only available through complex hardware. The neural network model replicates the ventricular activation analysis capability, allowing standard ECG equipment to achieve previously unattainable measurement precision through software enhancement rather than hardware complexity.

Inventive Principle:

Principle #26Copying

4Loss of time

If standard ECG equipment with shorter recording times is used, then loss of time is reduced, but measurement precision deteriorates

Engineering Contradiction:

Improverecording timeVSAvoidventricular activation parameter accuracy

Core Design Contradiction:

Loss of timeVSMeasurement precision

Solution Approach 1:

The patent creates a digital twin (neural network) that can process standard ECG recordings of typical length (10 seconds) and produce accurate ventricular activation parameters. This copied analytical function eliminates the need for lengthy ultra-high-frequency recordings while maintaining precision, as the model has learned to extract accurate parameters from standard recording durations.

Inventive Principle:

Principle #26Copying

Data Source

PatentUS20250378928A1Method for Ventricular Activation Assessment from Regular Electrocardiogram Using Neural Network

Publication Date: 2025.12.11 VDI TECHNOLOGIES SRO

AI summary

In a method of obtaining ventricular electrical activation parameters from an electrocardiogram signal, the electrocardiogram signal is pre-processed to remove baseline wandering to normalize the signal and optionally to amplify oscillations. The pre-processed electrocardiogram signal is fed to a neural network trained to estimate ventricular electrical activation parameters from electrocardiogram signal pre-processed in the same manner. The e ventricular electrical activation parameters are obtained as an output from the trained neural network. A method of training a neural network is also provided.