Simulated Cardiogram Calibration Using Heart Electromagnetic Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for identifying the source locations of heart disorders, such as arrhythmias, are complex, cumbersome, and expensive, and can lead to complications, while existing technologies like electrophysiology catheters and body surface vests are costly and have limitations in accuracy and safety.
Innovation Solution
A machine learning-based system, MLMO, generates a classifier for classifying electromagnetic data from the heart using simulated cardiograms and computational models, enabling accurate identification of arrhythmia sources by training on a variety of source configurations and clinical data, including ECG and VCG, to guide targeted therapies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If electrophysiology catheters are used to identify arrhythmia sources, then measurement precision is improved, but device complexity and cost increase, and harmful factors are introduced
Solution Approach 1:
The patent introduces an intermediary computational model that processes body surface ECG measurements to infer arrhythmia source locations. This mediator translates non-invasive surface data into diagnostic information previously requiring invasive catheter measurements, thereby maintaining measurement precision while eliminating direct physical intrusion into the heart
Solution Approach 2:
The patent creates a virtual copy of the heart's electrical activity through computational modeling. By simulating the electromagnetic fields generated by cardiac sources and matching them against measured body surface potentials, the system reproduces diagnostic capability without physical catheter insertion, thus preserving accuracy while removing harmful invasive effects
2Ease of operation
If body surface vests with electrodes are used, then ease of operation is improved, but measurement precision deteriorates
Solution Approach 1:
The patent replaces direct mechanical/electrical contact measurements (catheters) with field-based measurements (body surface ECG). By substituting the measurement mechanism from intra-cardiac electrodes to surface electrodes combined with computational field modeling, the system achieves both ease of operation and maintained precision through mathematical reconstruction of source locations
Solution Approach 2:
The patent transforms the measurement approach by changing from direct voltage measurement at multiple heart locations to measuring potential distributions on the body surface and computationally deriving source parameters. This parameter transformation allows non-invasive measurement while recovering precise location information through inverse problem solving and model matching
3Measurement precision
If invasive procedures are used to identify arrhythmia sources, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent extracts the essential diagnostic information (arrhythmia source location) from the complex invasive procedure by using a simplified non-invasive measurement system. Through computational modeling and body surface ECG analysis, the system isolates and identifies source locations without requiring complex catheter deployment, navigation, and recording procedures
Solution Approach 2:
The patent creates a computational model that copies the diagnostic functionality of invasive procedures. By simulating cardiac electromagnetic fields and matching them to measured data, the system reproduces source localization capability without the procedural complexity of catheter-based methods
Data Source
AI summary
Systems are provided for generating data representing electromagnetic states of a heart for medical, scientific, research, and/or engineering purposes. The systems generate the data based on source configurations such as dimensions of, and scar or fibrosis or pro-arrhythmic substrate location within, a heart and a computational model of the electromagnetic output of the heart. The systems may dynamically generate the source configurations to provide representative source configurations that may be found in a population. For each source configuration of the electromagnetic source, the systems run a simulation of the functioning of the heart to generate modeled electromagnetic output (e.g., an electromagnetic mesh for each simulation step with a voltage at each point of the electromagnetic mesh) for that source configuration. The systems may generate a cardiogram for each source configuration from the modeled electromagnetic output of that source configuration for use in predicting the source location of an arrhythmia.


