Longitudinal ECG Interpretation for LBBB and LVH Differentiation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing ECG analysis models struggle to differentiate between similar cardiac conditions like left bundle branch block (LBBB) and left ventricular hypertrophy (LVH) due to similar features in single ECGs, leading to potential erroneous diagnoses when longitudinal data is not adequately considered.

Innovation Solution

A system and method for generating and utilizing longitudinal ECG features by comparing current and historical ECGs, incorporating both single-ECG and longitudinal criteria to enhance diagnostic accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If single ECG criteria are used for diagnosis, then the diagnosis process is simple and fast, but the diagnostic accuracy is insufficient when differentiating between similar conditions like LBBB and LVH

Engineering Contradiction:
Improvediagnostic accuracyVSAvoidanalysis complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent transitions from analyzing single ECG snapshots to analyzing longitudinal ECG trajectories over time. By adding the time dimension and comparing multiple ECGs taken at different time points, the system can differentiate between conditions that appear similar at a single point in time, such as distinguishing LBBB from LVH through their distinct patterns of change over time.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The system performs preliminary analysis by comparing current ECG with historical ECGs before finalizing the diagnosis. This preliminary action of examining longitudinal trends allows the system to identify characteristic patterns of change that precede or accompany the development of cardiac conditions, improving diagnostic accuracy before a final determination is made.

Inventive Principle:
Principle #10Preliminary action

2Reliability

If longitudinal ECG analysis is performed to improve diagnostic accuracy, then differentiation between similar conditions improves, but the analysis time and computational resources increase

Engineering Contradiction:
Improvediagnosis reliabilityVSAvoidanalysis time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces manual longitudinal ECG comparison with an automated computer-based analysis system. The processor automatically retrieves historical ECGs, compares them with current ECGs, and applies diagnostic algorithms to identify patterns, thereby maintaining high diagnostic reliability while significantly reducing the time required for analysis compared to manual methods.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system changes the analytical parameters from static single-timepoint measurements to dynamic longitudinal trajectories. By analyzing how ECG parameters change over time rather than their absolute values at a single moment, the system achieves more reliable diagnoses with automated processing that can efficiently handle the increased data volume.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If multiple ECGs are compared to identify longitudinal trends, then diagnostic precision improves, but the complexity of data processing increases

Engineering Contradiction:
Improvediagnostic precisionVSAvoiddata processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts and compares specific relevant ECG parameters across multiple time points rather than analyzing entire ECG datasets. By identifying and focusing on key diagnostic parameters that exhibit characteristic longitudinal patterns for different cardiac conditions, the system achieves high diagnostic precision while managing data processing complexity through selective parameter extraction and comparison.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentEP4699537A1Systems and methods for ECG interpretation based on longitudinal criteria
Publication Date: 2026.02.25 GE PRECISION HEALTHCARE LLC
  • EP4699537A1 patent drawingFigure 1
  • EP4699537A1 patent drawingFigure 2
  • EP4699537A1 patent drawingFigure 3

AI summary

Methods and systems for electrocardiogram (ECG) interpretation based on longitudinal medical data are here presented. In one example, a method, comprises, during a development phase of an ECG analysis model, generating a bank of longitudinal electrocardiogram (ECG) features from a plurality of ECGs with known diagnoses (306); extracting longitudinal criteria from the plurality of ECGs (410); during a deployment phase of the ECG analysis model, obtaining a plurality of ECGs of a patient (502, 506), wherein the plurality of ECGs includes a current ECG and one or more historical ECGs; determining, based on the longitudinal criteria, a diagnosis (510); and transmitting the diagnosis to a user device (514).