Cardiac Rhythm Detection Using Dual-Duration Classifiers

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing devices for detecting cardiac rhythm disorders, particularly atrial fibrillation, are inadequate in providing quick and reliable detection, especially in cases of complex electrical activations, due to issues such as difficult catheter positioning, long analysis times, high costs, and complex map interpretations.

Innovation Solution

A device utilizing two machine learning-based classification models with different durations for cardiac electrogram data analysis, where a first model operates quickly with a short duration and a second model provides accurate detection, ensuring reliable alerts for areas of interest.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a single long-duration classification model is used for detecting cardiac rhythm disorders, then detection accuracy is improved, but detection time increases and productivity decreases

Engineering Contradiction:
Improvedetection accuracyVSAvoiddetection speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent divides the detection task into multiple classification models operating in parallel, each trained on electrogram data of different durations. Short-duration models provide quick initial assessment while long-duration models provide comprehensive analysis, segmenting the detection process to simultaneously achieve speed and accuracy without requiring sequential processing.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system applies multiple classification models with overlapping and complementary analysis windows. Some models analyze shorter segments for rapid detection while others analyze longer segments for confirmation, using partial actions at different time scales to achieve both quick response and high accuracy in the overall detection process.

Inventive Principle:
Principle #16Partial or excessive action

2Reliability

If multiple classification models with different durations are used, then detection reliability is improved, but device complexity increases

Engineering Contradiction:
Improvedetection reliabilityVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent creates a universal detection framework where multiple classification models serve different functions but operate within a single integrated system. Each model is specialized for different electrogram durations, yet all models share common infrastructure for data processing, result aggregation, and decision-making, reducing overall system complexity despite multiple models.

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

Solution Approach 2:

The system merges the outputs of multiple classification models through a unified decision-making process. Rather than maintaining separate independent systems, the patent combines results from short-duration and long-duration models into a single comprehensive detection output, reducing complexity by consolidating multiple analysis streams into one coordinated system.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP3773161B1Computing device for detecting heart rhythm disorders
Publication Date: 2025.07.16 SUBSTRATE HD
  • EP3773161B1 patent drawingFigure 1~2

AI summary

A device for detecting heart rhythm disorders comprises a memory (10) designed to receive cardiac electrogram data and to store data defining a first classification model for detecting heart rhythm disorders and a second classification model for detecting heart rhythm disorders, a classifier (6) designed to analyse cardiac electrogram data based on a classification model, and to return a classification value, and a driver (8) design to store cardiac electrogram data in the memory and analyse them with the classifier, and to return alert data when the analysis by the classifier returns a classification value associated with a heart rhythm disorder.