Related Experiment Video
Updated: Jun 30, 2026
Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
Published on: October 11, 2018
Automated detection of myocardial infarction using binary Harry Hawks feature selection and ensemble KNN classifier
M Krishna Chaitanya1, Lakhan Dev Sharma1
1School of Electronics Engineering, VIT-AP University, Amaravati, India.
Insights
This study introduces an efficient method for diagnosing myocardial infarction (MI) using electrocardiogram (ECG) data. The novel approach achieves high accuracy in detecting heart attacks, improving diagnostic speed and reliability.
Area of Science:
- Biomedical Engineering
- Cardiology
- Signal Processing
Background:
- Myocardial infarction (MI) diagnosis relies heavily on electrocardiograms (ECG), but signal noise and complexity hinder accurate, timely detection.
- Manual ECG analysis is time-consuming and labor-intensive, necessitating automated diagnostic techniques.
- Existing automated methods often require significant computational resources for empirical data analysis.
Purpose of the Study:
- To develop an efficient and reliable automated method for identifying MI from ECG signals.
- To address the challenges of noise and complexity in ECG data for improved MI diagnosis.
- To compare the performance of the proposed method using both class-wise and subject-wise validation strategies.
Main Methods:
- ECG signal preprocessing involved baseline wander removal using circulant singular spectrum analysis (CSSA) and powerline interference elimination with a Savitzky-Golay (SG) filter.
- Decomposition of preprocessed ECG segments using CSSA, followed by extraction of entropy-based features.
- Feature selection was performed using binary Harris hawk optimization (BHHO), with selected features fed into various machine learning classifiers (Naive Bayes, Decision Tree, KNN, SVM, Ensemble Subspace KNN).
Main Results:
- The proposed method achieved a high accuracy of 99.8%, sensitivity of 99%, and 100% specificity under the class-oriented approach.
- For the subject-wise strategy, the method attained mean accuracy, sensitivity, and specificity of 85.2%, 83.1%, and 84.5%, respectively.
- The study demonstrated the effectiveness of CSSA, SG filtering, BHHO, and ML classifiers in robust MI detection from ECG data.
Conclusions:
- The developed automated method offers an efficient and reliable approach for myocardial infarction detection using ECG.
- The proposed signal processing and feature selection techniques significantly enhance diagnostic performance.
- The findings suggest a promising tool for improving the speed and accuracy of MI diagnosis in clinical settings.
Abstract:
Myocardial infarction (MI), referred to as a heart attack, is a life-threatening condition that happens due to blood clots, typically, blood flow to a portion of the heart muscle is blocked. The cardiac muscle may become permanently damaged if there is insufficient oxygen and blood flow to the affected area. It's crucial to treat MI as soon as possible because even a small delay might have serious effects. The primary diagnostic tool to track and identify the signs of MI is the electrocardiogram (ECG). The complexity of MI signals combined with noise makes it difficult for clinicians to make a precise and prompt diagnosis. It might be laborious and time-consuming to manually analyse an enormous quantity of ECG data. Therefore, techniques for autonomously diagnosing from the ECG data are required. There have been numerous research on the topic of MI espial, but the majority of the algorithms are cognitively intensive when working with empirical data. The current study suggests a unique method for the efficient and reliable identification of MI. We employed circulant singular spectrum analysis (CSSA) for baseline wander removal, a 4-stage Savitzky-Golay (SG) filter to expunge powerline interference from the ECG signal and segmented in the preprocessing stage. Thus segmented ECG has been decomposed using CSSA, entropy based features are extracted. The best features are selected by using binary Harris hawk optimization (BHHO) and to machine learning (ML) classifiers like Naive Bayes, Decision tree, K-nearest neighbor (KNN), Support vector machine (SVM), and Ensemble subspace KNN. Our suggested method has been examined from both class as well as subject oriented perspectives. While the subject-oriented technique uses data from one patient for testing while using data from the other subjects for training, the class-wise strategy divides data as test data as well as training data regardless of subjects. We succeeded in achieving accuracy () of 99.8, sensitivity () of 99, and 100 specificity (S%) under the class-oriented approach. Similarly, for the subject wise strategy we achieved a mean S%, and S% of 85.2, 83.1, and 84.5, respectively.
