Pseudo-EGM Generation From ECG for Non-Invasive Cardiac Mapping

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Intracardiac electrograms (EGMs) provide precise electrical activity recordings but require invasive procedures, causing discomfort and risk to patients.

Innovation Solution

An apparatus and method to generate pseudo-EGM data from electrocardiogram (ECG) data using a processor and machine-learning model, trained on synchronized ECG and EGM data pairs, to predict EGM data without invasive procedures.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If intracardiac electrograms (EGMs) are used to provide precise electrical activity recordings, then measurement precision is improved, but the procedure becomes invasive causing discomfort and risk to patients

Engineering Contradiction:

Improveelectrical activity recording precisionVSAvoidpatient discomfort and risk

Core Design Contradiction:

Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent creates a copy of the invasive EGM measurement process by training a machine learning model on synchronized ECG-EGM data pairs. The model learns to generate pseudo-EGM signals that replicate the characteristics of actual invasive measurements, allowing non-invasive acquisition of precise electrical activity data through ECG inputs alone

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent introduces ECG data as an intermediary that bridges the gap between non-invasive surface measurements and invasive internal recordings. By using ECG as input to the machine learning model, the system indirectly captures electrical activity information without requiring direct intracardiac electrode contact

Inventive Principle:

Principle #24Intermediary (Mediator)

2Loss of information

If intracardiac electrograms (EGMs) are used to provide detailed electrical conduction pathways, then information completeness is improved, but the procedure requires invasive catheter insertion

Engineering Contradiction:

Improveelectrical conduction pathway informationVSAvoidcatheter insertion procedure

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The machine learning model creates a computational copy of the invasive EGM measurement system. By training on paired ECG-EGM data, the model learns to reproduce the information content of invasive measurements, including electrical conduction pathway details, without requiring physical catheter insertion

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent replaces the mechanical intrusion of catheter insertion with an information processing system. Instead of physically inserting electrodes into the heart chambers, the system uses machine learning algorithms to process ECG data and generate equivalent EGM information computationally

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Reliability

If pseudo-EGM data is generated from ECG data using machine learning, then patient safety and comfort are improved, but measurement precision may be compromised

Engineering Contradiction:

Improvepatient safetyVSAvoidelectrical activity recording accuracy

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent performs preliminary training of the machine learning model using synchronized ECG-EGM data pairs before actual use. This pre-training phase allows the model to learn the complex relationship between surface ECG and intracardiac EGM signals, optimizing its ability to generate accurate pseudo-EGM data from ECG inputs

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system uses feedback from the training data, where actual EGM measurements serve as ground truth to evaluate and refine the model's predictions. This feedback mechanism ensures the model learns to generate pseudo-EGM data that accurately reflects true intracardiac electrical activity patterns

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20260031242A1Apparatus and method for generating pseudo-electrogram (EGM) data from electrocardiogram (ECG) data

Publication Date: 2026.01.29 ANUMANA INC

AI summary

Apparatus and method for generating pseudo-EGM data from ECG data are disclosed. The apparatus includes at least a processor and a memory communicatively connected to the at least a processor, wherein the memory contains instructions configuring the at least a processor to generate EGM model training data, wherein generating the EGM model training data includes receiving the EGM model training data, wherein the EGM model training data includes exemplary ECG data correlated to exemplary EGM data and time synchronizing the exemplary ECG data and the exemplary EGM data, train an EGM machine-learning model using the EGM model training data, receive subject data, wherein the subject data includes subject ECG data and generate subject EGM data as a function of the subject ECG data using the trained EGM machine-learning model.