What is the clinical evidence from this study?

Study design: Other. Population: Cardiac arrhythmias. Intervention: GLCM and GLRLM morphological features combined with XGBoost vs. Wavelet features with XGBoost. Primary outcome: Cardiac arrhythmia classification accuracy (AUC 0.982).

What does this research mean for the field?

Combining XGBoost with novel one-dimensional morphological features extracted from GLCM and GLRLM achieves high accuracy (90.46%) and AUC (0.982) in classifying cardiac arrhythmias, outperforming traditional wavelet features. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

October 12, 2021Open Access

Cardiac Arrhythmia Classification Based on One-Dimensional Morphological Features

Key Result

Combining XGBoost with novel 1D morphological features from GLCM and GLRLM yielded an accuracy of 90.46% and an AUC of 0.982 for classifying cardiac arrhythmias, outperforming wavelet features.

Structured PICO

Does a novel feature extraction method using GLCM and GLRLM combined with XGBoost improve the classification of cardiac arrhythmias on 12-lead ECGs compared to wavelet features?

Population

12-lead ECG database collected from Chapman University and Shaoxing People's Hospital for cardiac arrhythmia classification.

Intervention

Novel method generating gray-level co-occurrence matrix (GLCM) and gray-level run-length matrix (GLRLM) from one-dimensional signals, combined with XGBoost

Comparator

Wavelet features with XGBoost

Outcome

Classification of cardiac arrhythmias (accuracy, AUC, sensitivity, precision, F1 score)surrogate

A novel feature extraction method using GLCM and GLRLM combined with XGBoost provides highly accurate automatic classification of cardiac arrhythmias from 12-lead ECGs.

Main Result

Effect estimate: AUC 0.982

Abstract

The electrocardiogram (ECG) is the most commonly used tool for diagnosing cardiovascular diseases. Recently, there have been a number of attempts to classify cardiac arrhythmias using machine learning and deep learning techniques. In this study, we propose a novel method to generate the gray-level co-occurrence matrix (GLCM) and gray-level run-length matrix (GLRLM) from one-dimensional signals. From the GLCM and GLRLM, we extracted morphological features for automatic ECG signal classification. The extracted features were combined with six machine learning algorithms (decision tree, k-nearest neighbor, naïve Bayes, logistic regression, random forest, and XGBoost) to classify cardiac arrhythmias. Experiments were conducted on a 12-lead ECG database collected from Chapman University and Shaoxing People’s Hospital. Of the six machine learning algorithms, combining XGBoost with the proposed features yielded an accuracy of 90.46%, an AUC of 0.982, a sensitivity of 0.892, a precision of 0.900, and an F1 score of 0.895 and presented better results than wavelet features with XGBoost. The experimental results show the effectiveness of the proposed feature extraction algorithm.

Bookmark

View Full Paper