Machine Learning Cardiac Mapping Annotation Selection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing cardiac mapping systems struggle to select and detect the optimal heartbeat at each spatial location for accurate cardiac mapping annotations, often relying on manual corrections by physicians due to the acquisition of heartbeats with poor characteristics.

Innovation Solution

A system utilizing a machine learning algorithm to compare attribute information of multiple heartbeats at the same spatial location, determining which heartbeat has optimal characteristics for use as a mapping annotation, thereby improving the accuracy and efficiency of cardiac mapping.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional EP mapping systems acquire and record a first heartbeat at every spatial location, then complete mapping data is obtained, but heartbeats with poor characteristics are included requiring manual corrections

Engineering Contradiction:

Improvemapping annotation accuracyVSAvoidmanual correction requirement

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The system performs self-correction by using machine learning algorithms to automatically identify and select optimal heartbeats at each spatial location, replacing the need for physician manual corrections. The algorithm compares multiple heartbeats and autonomously determines which ones have optimal characteristics for mapping annotations.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The manual mechanical process of physician review and correction is replaced with an automated machine learning system. The ML algorithm processes heartbeat data, compares attributes, and makes selection decisions without human intervention, substituting the mechanical workflow with an intelligent automated system.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If multiple heartbeats are acquired at each spatial location, then optimal heartbeat selection is possible, but data processing complexity increases

Engineering Contradiction:

Improveheartbeat characteristic detectionVSAvoiddata processing system

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system changes the parameter of heartbeat selection from single-heartbeat acquisition to multi-heartbeat acquisition with comparative analysis. By acquiring multiple heartbeats and comparing their attributes (amplitude, morphology, timing), the system achieves more precise detection of optimal heartbeats while managing complexity through systematic attribute comparison.

Inventive Principle:

Principle #35Parameter changes

3Reliability

If manual correction of mapping annotations is performed, then annotation accuracy is improved, but procedure time increases

Engineering Contradiction:

Improvemapping annotation accuracyVSAvoidprocedure time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary action by automatically selecting optimal heartbeats during the data acquisition phase itself, rather than requiring post-acquisition manual correction. The machine learning algorithm identifies and flags optimal heartbeats in real-time, preparing the data for mapping before the physician needs to review it, thus eliminating time-wasting manual corrections later.

Inventive Principle:

Principle #10Preliminary action

4Extent of automation

If rules-based algorithms are used for mapping annotations, then automated processing is achieved, but accuracy is insufficient requiring manual intervention

Engineering Contradiction:

Improveannotation processing automationVSAvoidmapping annotation accuracy

Core Design Contradiction:

Extent of automationVSReliability

Solution Approach 1:

The system replaces rules-based algorithms with machine learning-based intelligent processing. Instead of following predetermined rigid rules, the ML algorithm learns from data patterns and makes nuanced decisions about heartbeat quality, achieving both high automation and high accuracy by substituting mechanical rule-following with intelligent adaptive processing.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12239449B2System and method to detect stable arrhythmia heartbeat and to calculate and detect cardiac mapping annotations

Publication Date: 2025.03.04 BIOSENSE WEBSTER (ISRAEL) LTD

AI summary

A system and method for detecting a mapping annotation for an electrophysiological (EP) mapping system. The system includes a processor comprising a machine learning algorithm configured to receive a first heartbeat at an identified cardiac spatial location including a first set of attributes information corresponding to the first heartbeat; receive a second heartbeat at the identified cardiac spatial location including a second set of attributes information corresponding to the second heartbeat; compare the first set of attributes information with the second set of attributes information; and determine which of the first heartbeat and the second heartbeat has optimal characteristics based on the compared attribute information.