Estimation of the tissue damage after MI through time-frequency analysis of the electromechanical signals
Hamid Ebrahimi Orimi1, Leila Abrishami Shokooh, Ali Ghaffari
1CardioVascular Research Group (CVRG), Department of Mechanical Engineering, K. N. Toosi University of Technology , Tehran , Iran and.
Insights
This study quantifies heart tissue damage from myocardial infarction (MI) in rats using ECG and blood pressure signals. Artificial neural networks accurately estimated damaged tissue with an average error of 2.91%.
Area of Science:
- Biomedical Engineering
- Cardiovascular Research
- Computational Biology
Background:
- Coronary artery disease, including ischaemia and myocardial infarction (MI), poses significant health risks.
- Accurate assessment of heart tissue damage is crucial for understanding disease progression and treatment efficacy.
- Current methods for evaluating MI extent can be invasive or lack precision.
Purpose of the Study:
- To develop and validate a non-invasive method for quantifying myocardial infarction-induced tissue damage.
- To assess the efficacy of using synchronic electrocardiogram (ECG) and atrial blood pressure (ABP) signals for damage estimation.
- To investigate the performance of artificial neural networks (ANNs) in predicting the extent of heart tissue damage.
Main Methods:
- Myocardial infarction was induced in laboratory rats (Wistar, 200-300g) via left anterior descending (LAD) coronary artery blockage.
- ECG and ABP signals were recorded for 30 minutes in normal, ischaemia, and MI states.
- A 50-dimensional feature vector was extracted using wavelet packet transform (WPT) and wavelet coefficient entropy from ECG and ABP signals.
- Heart tissue damage was quantified using image processing, and ANNs were employed for damage estimation.
Main Results:
- The study successfully simulated ischaemia and myocardial infarction in rats.
- Wavelet packet transform and entropy analysis of ECG and ABP signals provided robust features for damage assessment.
- Four different artificial neural network structures, combined with an averaging criterion, estimated ischaemic and normal tissue with an average error of 2.91% across various vasopressin (AVP) doses and control groups.
Conclusions:
- Synchronic ECG and ABP signal analysis, coupled with WPT and ANNs, offers a reliable method for estimating heart tissue damage extent.
- This computational approach demonstrates high accuracy in differentiating normal, ischaemic, and infarcted cardiac tissues.
- The findings suggest a potential for a non-invasive, quantitative diagnostic tool for cardiovascular injury assessment.
Abstract:
Abstract Coronary congestion is a heart disease that puts many lives at risk each year. The task of coronary arteries is to distribute blood to the heart tissue and any blockage in them can cause the tissue to absorb less oxygen and nutrients than needed (ischaemia disease). This imbalance will continue until the first cell is destroyed (myocardial infarction). Simulating the myocardial infarction in the laboratory rats, this study tries to determine the extent of tissue damage through the electrocardiogram (ECG) and atrial blood pressure (ABP) synchronic signals. The signals of 50 wistar rats with a weight range of 200-300 g were recorded at 30 min in the normal case and 30 min in the ischaemia and myocardial infarction (MI) case (the artificial complete blockage was in the left anterior descending coronary artery (LAD)). For a different injury in the rats' heart, the vasopressin (AVP) with different doses was injected to 40 rats. After that the images of the heart sections and the data were extracted, the 50-dimensional feature vector was generated by using the wavelet packet transform (WPT) on the ECG and ABP signals and also by obtaining the entropy of the wavelet coefficients. The extent of tissue damage on the images of the heart tissue was extracted by using the image processing method. Finally, the amount of the damaged tissue was estimated by four artificial neural networks (ANN) (with different structures) with an averaging criterion. The intelligent machine estimated the ischaemia and normal tissues with the average error of 2.91% for all the AVP doses and control cases.
Related Concept Videos
01:29Electrocardiogram
Three major waveforms are present in a typical ECG recording: the P wave, the QRS complex, and...
01:20Blood Studies for Cardiovascular System I: Cardiac Biomarkers
The essential diagnostic tools for detecting myocardial necrosis and monitoring individuals suspected of having acute coronary syndrome (ACS) include:
Troponins
Troponins, particularly cardiac troponins I and T, are the most precise and sensitive markers of myocardial injury. They are detectable within 4-6 hours of myocardial injury and remain...