Related Experiment Video
Updated: Jun 26, 2026
12:09
Patient-specific Modeling of the Heart: Estimation of Ventricular Fiber Orientations
Published on: January 8, 2013
Modelling temporal evolution of cardiac electrophysiological features using Hidden Semi-Markov Models
Jerome Dumont1, Alfredo I Hernández, Julien Fleureau
1INSERM, U642, and Université de Rennes, Rennes, F-35000, France. jerome.dumont@univ-rennes1.fr
Summary
This study introduces a novel method using Continuous Density Hidden Semi-Markovian Models (CDHSMM) to analyze cardiac electrophysiological dynamics for patient classification. The approach achieved a 71% accuracy in identifying ischemic episodes, offering a new tool for cardiovascular research.
Area of Science:
- Cardiology
- Biomedical Engineering
- Data Science
Background:
- Cardiac electrophysiological dynamics are complex and challenging to analyze.
- Current methods may lack the ability to characterize continuous multivariate time series without prior information.
- Accurate patient classification is crucial for understanding and managing cardiovascular conditions like ischemia.
Purpose of the Study:
- To develop and apply a novel method for analyzing cardiac electrophysiological dynamics.
- To classify and cluster patients based on ECG feature dynamics.
- To investigate the utility of Continuous Density Hidden Semi-Markovian Models (CDHSMM) for this purpose.
Main Methods:
- Utilized Continuous Density Hidden Semi-Markovian Models (CDHSMM) to model the dynamics of ECG features.
- Developed a fuzzy Expectation Maximisation (EM) algorithm for patient clustering.
- Applied both classification and clustering approaches to analyze ischemic episodes.
Main Results:
- The CDHSMM approach effectively characterized continuous multivariate time series of ECG features.
- The fuzzy EM algorithm provided a method for clustering patients based on these dynamics.
- Achieved a classification accuracy of 71% for identifying ischemic episodes.
Conclusions:
- Continuous Density Hidden Semi-Markovian Models are a promising tool for analyzing cardiac electrophysiological dynamics.
- The proposed fuzzy EM clustering method offers a novel approach for patient stratification.
- This methodology shows encouraging results for the detection and analysis of ischemic events.
Related Concept Videos
01:19Electrophysiology of Normal Cardiac Rhythm
The normal cardiac rhythm is a synchronized electrical activity that facilitates the regular and coordinated contraction of the heart muscle. This process is essential for efficient blood circulation throughout the body. The fundamental elements involved in establishing and maintaining this rhythm include the unique electrical properties of cardiac muscle cells, the sinoatrial (SA) node's pacemaker function, the specialized conducting system, and the ionic mechanisms underlying each phase of...
01:25Correlation between ECG and Cardiac Cycle
The electrical signals recorded on an electrocardiogram (ECG) occur before the mechanical processes of contraction and relaxation during the cardiac cycle.
A cardiac action potential originates in the SA node and spreads throughout the atria and the AV node in approximately 0.03 seconds. This results in the P wave in an ECG and triggers atrial contraction. The action potential is then briefly slowed at the AV node, allowing the atria to contract and fill the ventricles with blood before...
A cardiac action potential originates in the SA node and spreads throughout the atria and the AV node in approximately 0.03 seconds. This results in the P wave in an ECG and triggers atrial contraction. The action potential is then briefly slowed at the AV node, allowing the atria to contract and fill the ventricles with blood before...