Assessment of 12-Lead ECG-based Noninvasive Electroanatomical Mapping Accuracy: Incorporating Fibrosis Data in Advanced Computational Algorithms
Year: 2024
Type: conference-paper
Abstract: Restoring cardiac activation maps using a 12-channel ECG is a promising field in digital medicine with the potential to improve the management of cardiac disorders.This study examines the effect of incorporating detailed fibrosis data into the reconstruction of cardiac activation maps.Using retrospective data from 15 non-ischemic heart disease patients, we compared activation maps and ECGs generated with and without fibrosis information.The methodology involved solving the forward ECG problem using the eikonal equation and the lead field approach, followed by machine learning-based reconstruction.Accuracy was assessed using Spearman correlation coefficients and the mean absolute difference in local activation times.Our results indicated that including fibrosis data enhanced the alignment of calculated ECGs with recorded signals, increasing the mean correlation coefficient from 0.74 to 0.78.However, this improvement was not statistically significant, indicating a limited impact on quantitative accuracy.In conclusion, while fibrosis data aids in visualizing delayed activation areas, it does not significantly improve ECG-based map accuracy.Further research with larger datasets and advanced imaging is required to fully explore its clinical potential.
Source: Computing in cardiology
Language: English
Topic: ECG Monitoring and Analysis
Subfield: Cardiology and Cardiovascular Medicine
Field: Medicine
Domain: Health Sciences
Open Access status: bronze
OpenAlex ID: W4405435059