QRS Complex Clustering for Accurate ECG Classification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing ECG signal analysis methods struggle with accurately classifying QRS complexes, leading to incorrect classifications and increased clinician burden due to false positives and false negatives, causing alert fatigue.

Innovation Solution

An automated ECG analysis system filters ECG signals, extracts features from QRS complexes, clusters them into normal and abnormal groups, generates a QRS cluster template, and calculates distances to correct misclassifications, using techniques like Gaussian mixture modeling and hierarchical clustering.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If rule-based and deep learning algorithms are used to classify QRS complexes, then automation is improved, but classification accuracy deteriorates due to incorrect classifications

Engineering Contradiction:

Improveautomation of QRS complex classificationVSAvoidclassification accuracy

Core Design Contradiction:

Extent of automationVSMeasurement precision

Solution Approach 1:

The system implements feedback by calculating the distance between each QRS complex and the cluster template, then using this distance information to iteratively refine classifications. The algorithm compares calculated distances against thresholds and adjusts classifications accordingly, creating a feedback loop that improves accuracy while maintaining automation.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent introduces an intermediary clustering mechanism that acts as a mediator between raw QRS complexes and final classifications. By introducing cluster templates as an intermediate representation, the system can more accurately classify QRS complexes without requiring direct complex decision rules, thus improving accuracy while maintaining automation.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Productivity

If algorithms classify all QRS complexes, then productivity is improved, but reliability deteriorates due to false positives and false negatives causing alert fatigue

Engineering Contradiction:

Improvethroughput of ECG analysisVSAvoidtrustworthiness of classifications

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system changes parameters by calculating distance metrics between QRS complexes and cluster templates, then using these distance parameters to dynamically adjust classifications. This parameter-based approach allows the system to maintain high throughput while improving reliability by base.ing classifications on quantitative distance measurements rather than fixed rules.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent applies partial action by focusing computational resources on classifying QRS complexes that fall into abnormal or dissimilar clusters, rather than uniformly processing all QRS complexes with the same intensity. This selective approach maintains productivity while improving reliability for critical cases.

Inventive Principle:

Principle #16Partial or excessive action

3Measurement precision

If clustering is used to group QRS complexes, then measurement precision is improved, but device complexity increases

Engineering Contradiction:

Improveaccuracy of QRS complex identificationVSAvoidcomplexity of analysis algorithm

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies segmentation by dividing QRS complexes into distinct clusters based on their characteristics. By segmenting the data into normal and abnormal/dissimilar groups, the system improves measurement precision while managing complexity through organized data structures and systematic processing of each segment.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system uses copying by creating cluster templates that represent typical QRS complexes. These templates serve as simplified copies that capture essential characteristics, allowing the system to achieve high measurement precision without requiring complex analysis of every individual QRS complex, thus managing algorithmic complexity.

Inventive Principle:

Principle #26Copying

Data Source

PatentUS20260069191A1Methods and systems for unsupervised analysis of QRS complex classifications in ECG signals

Publication Date: 2026.03.12 KONINKLIJKE PHILIPS NV

AI summary

A method for automated analysis of ECG signal classifications, comprising: receiving an ECG signal classification for a subject, comprising an ECG signal; analyzing the ECG signal classification to generate a final ECG signal classification, comprising: (i) filtering the received ECG signal; (ii) extracting features from each of a plurality of identified QRS complexes; (iii) clustering, using the extracted features, the identified QRS complexes into at least a first cluster of QRS complexes and abnormal or dissimilar QRS complexes; (iv) generating a QRS cluster template from the first cluster; (v) calculating a distance between each of the QRS complexes in the cluster of abnormal or dissimilar QRS complexes and the QRS cluster template; and (vi) classifying, based on the calculated distance, the QRS complexes in the cluster of abnormal or dissimilar QRS complexes as being normal or abnormal/dissimilar to generate the final ECG signal classification; and reporting the generated final ECG signal classification.