An End-to-End Cardiac Arrhythmia Recognition Method with an Effective DenseNet Model on Imbalanced Datasets Using ECG Signal

Abstract

Electrocardiography (ECG) is a well-known noninvasive technique in medical science that provides information about the heart’s rhythm and current conditions. Automatic ECG arrhythmia diagnosis relieves doctors’ workload and improves diagnosis effectiveness and efficiency. This study proposes an automatic end-to-end 2D CNN (two-dimensional convolution neural networks) deep learning method with an effective DenseNet model for addressing arrhythmias recognition. To begin, the proposed model is trained and evaluated on the 97720 and 141404 beat images extracted from the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia and St. Petersburg Institute of Cardiological Technics (INCART) datasets (both are imbalanced class datasets) using a stratified 5-fold evaluation strategy. The data is classified into four groups: N (normal), V (ventricular ectopic), S (supraventricular ectopic), and F (fusion), based on the Association for the Advancement of Medical Instrumentation® (AAMI). The experimental results show that the proposed model outperforms state-of-the-art models for recognizing arrhythmias, with the accuracy of 99.80% and 99.63%, precision of 98.34% and 98.94%, and F1-score of 98.91% and 98.91% on the MIT-BIH arrhythmia and INCART datasets, respectively. Using a transfer learning mechanism, the proposed model is also evaluated with only five individuals of supraventricular MIT-BIH arrhythmia and five individuals of European ST-T datasets (both of which are also class imbalanced) and achieved satisfactory results. So, the proposed model is more generalized and could be a prosperous solution for arrhythmias recognition from class imbalance datasets in real-life applications.

Therapeutic Efficacy of a Formulation Prepared with Linum usitatissimum L., Plantago ovata Forssk., and Honey on Uncomplicated Pelvic Inflammatory Disease Analyzed with Machine Learning Techniques

“…For the classification, we used four machine learning techniques such as DT, RF, LR, and AB with three cross-validation models including 2-fold, 5-fold, and 10-fold to classify the pessary and standard groups ( Table 8 ). The standard mathematical expression of the performance evaluation methods such as sensitivity (SENS), specificity (SPEC), accuracy (ACC), and precision (PREC) [ 70 , 71 , 72 , 73 , 74 ] are mentioned in Equations (5)–(8):…”

Automated Lung-Related Pneumonia and COVID-19 Detection Based on Novel Feature Extraction Framework and Vision Transformer Approaches Using Chest X-ray Images

“…As illustrated in Figure 4 , this work combines deep features collected from DenseNet [ 56 , 57 ], VGG16 [ 58 ], and GoogleNet [ 59 ] using Ensembling algorithms [ 60 , 61 ]. DenseNet [ 41 ] architecture is a classification model that involves connecting layers in a feed-forward manner (with identical feature-map size), this design ensures knowledge transfer across network tiers.…”

A Novel Smart Belt for Anxiety Detection, Classification, and Reduction Using IIoMT on Students’ Cardiac Signal and MSY

“…Electrocardiogram (ECG) is the primary medical diagnostic tool for disease in practice and it provides a comprehensive picture of a patient’s cardiac conditions [ 34 , 35 ]. Currently, physicians usually use post hoc analysis through ECG waveforms to diagnose whether a patient is well or sick, which is inefficient, time-consuming, and unreliable due to physicians’ experience and expertise level [ 36 ].…”