ECG Morphology Matching Algorithm for Arrhythmia Identification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for mapping heart regions causing arrhythmia inaccurately include signals from ectopic beats and morphological changes, leading to distorted visualization and difficulty in identifying arrhythmia mechanisms.

Innovation Solution

An ECG morphology matching algorithm that selects an initial set of ECG signals as a template, performs cross-correlation with subsequent signals within defined time windows, and incorporates arrhythmia locations into a heart map when a correlation coefficient exceeds a threshold, distinguishing arrhythmia-caused heartbeats from others.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If all ECG signals are included in the arrhythmia map, then the map coverage is complete, but the accuracy of arrhythmia identification deteriorates due to inclusion of ectopic beats and morphological variations

Engineering Contradiction:
Improvearrhythmia identification accuracyVSAvoidsignal filtering complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies parameter changes by comparing morphological parameters of ECG signals against template signals. The system changes parameters such as correlation coefficients and morphological similarity metrics to distinguish arrhythmia-causing signals from ectopic beats and normal variations, thereby improving identification accuracy while maintaining manageable complexity through automated parameter-based filtering

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent uses copying by creating template ECG signals from representative arrhythmia beats and using these templates to compare against subsequent signals. This template-based approach allows the system to identify matching morphologies without manually analyzing each signal, resolving the contradiction between accuracy and complexity

Inventive Principle:
Principle #26Copying

2Measurement precision

If ECG signals are compared without time window constraints, then the morphological matching is more flexible, but the precision of arrhythmia localization deteriorates

Engineering Contradiction:
Improvearrhythmia localization precisionVSAvoidmorphological matching flexibility
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent applies segmentation by dividing the ECG signal comparison into specific time windows around key features such as QRS complexes. This segmentation allows precise localization of arrhythmia events while maintaining flexibility within each time window, resolving the contradiction between precision and adaptability

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent uses preliminary action by pre-defining time windows and template signals before comparing subsequent ECG signals. This preliminary setup enables both precise localization through fixed time windows and morphological flexibility through template matching, simultaneously achieving both measurement precision and adaptability

Inventive Principle:
Principle #10Preliminary action

3Productivity

If real-time ECG signal processing is performed, then the arrhythmia detection speed is improved, but the computational complexity increases

Engineering Contradiction:
Improvearrhythmia detection speedVSAvoidcomputational complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent applies taking out by extracting only the essential morphological features and comparing them against templates, rather than processing entire ECG signals in real-time. This extraction approach maintains fast detection speed while reducing computational complexity by focusing only on relevant signal characteristics

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent uses copying of template signals to enable rapid comparison without complex real-time analysis. By storing pre-processed templates and comparing against them, the system achieves real-time detection performance with reduced computational burden, resolving the contradiction between productivity and complexity

Inventive Principle:
Principle #26Copying

Data Source

PatentEP3281579B1Identifying ECG signals having the same morphology
Publication Date: 2024.03.13 BIOSENSE WEBSTER (ISRAEL) LTD
  • EP3281579B1 patent drawingFigure 1
  • EP3281579B1 patent drawingFigure 2
  • EP3281579B1 patent drawingFigure 3

AI summary

A method, including selecting an initial set of electrocardiograph (ECG) signals taken over a single heartbeat of a human subject, the set having respective morphologies to be used as a template for an arrhythmia of the subject, and receiving a subsequent set of ECG signals taken over a subsequent heartbeat of the human subject. The method also includes performing a cross-correlation between the initial set and the subsequent set, so as to generate a correlation coefficient that is a measure of a goodness of fit between geometries of the initial set and the subsequent set, and, when the correlation coefficient exceeds a threshold coefficient, accepting the subsequent heartbeat as having been caused by the arrhythmia.