Abstract
The new advances in multiple types of devices and machine learning models provide opportunities for practical automatic computer-aided diagnosis (CAD) systems for ECG classification methods to be practicable in an actual clinical environment. This imposes the requirements for the ECG arrhythmia classification methods that are inter-patient. We aim in this paper to design and investigate an automatic classification system using a new comprehensive ECG database inter-patient paradigm separation to improve the minority arrhythmical classes detection without performing any features extraction. We investigated four supervised machine learning models: support vector machine (SVM), k-nearest neighbors (KNN), Random Forest (RF), and the ensemble of these three methods. We test the performance of these techniques in classifying: Normal beat (NOR), Left Bundle Branch Block Beat (LBBB), Right Bundle Branch Block Beat (RBBB), Premature Atrial Contraction (PAC), and Premature Ventricular Contraction (PVC), using inter-patient real ECG records from MIT-DB after segmentation and normalization of the data, and measuring four metrics: accuracy, precision, recall, and f1-score. The experimental results emphasized that with applying no complicated data pre-processing or feature engineering methods, the SVM classifier outperforms the other methods using our proposed inter-patient paradigm, in terms of all metrics used in experiments, achieving an accuracy of 0.83 and in terms of computational cost, which remains a very important factor in implementing classification models for ECG arrhythmia. This method is more realistic in a clinical environment, where varieties of ECG signals are collected from different patients.
Highlights
One of the most fundamental vital organs is the heart
We test the performance of these techniques in classifying: Normal beat (NOR), Left Bundle Branch Block Beat (LBBB), Right Bundle Branch Block Beat (RBBB), Premature Atrial Contraction (PAC), and Premature Ventricular Contraction (PVC), using inter-patient real electrocardiogram recording (ECG) records from MIT-DB after segmentation and normalization of the data, and measuring four metrics: accuracy, precision, recall, and f1-score
An automated arrhythmia detection system needs to be reliable, with high quality and performance in decision making, with less complexity, especially concerning the number of resources required to run it, and more realistic in a clinical environment. Considering these requirements and the metrics used in this paper, the results achieved with all the machine learning models we investigated in this paper, and using our proposed inter-patient paradigm separation method of the patient concerning the MIT-BIH DB, and applying no complicated data pre-processing or feature engineering methods, prove that the support vector machine (SVM) is the model that outperformed the other techniques, in predicting the most classes presented such as (NOR, RBBB, and PVC), and especially the minority ones such as the PAC, as it predicted one quarter of the data provided, which was the purpose of the inter-patient paradigm separation proposed
Summary
One of the most fundamental vital organs is the heart. It’s the engine that pumps blood to many networks of vessels. The heart moves constantly, beating 100,000 times a day by providing oxygen and nutrients while clearing away harmful waste matter. The beating of the heart produces electrical actions measured on the body surface by an electrocardiogram recording (ECG). The morphology and heart rate variability (HRV) extracted from the ECG signal reveal the cardiac behavior. The heart behavior analysis expressed by the electrocardiogram signal provides specific information about the heart. If the ECG is irregular or faster, or slower than normal, that means cardiac arrhythmia. Arrhythmia can cause several types of consequences; an imminent threat to a patient’s life (e.g., ventricular fibrillation and tachycardia), long-term threats, or even more causing death, the thing that made it the most common leading cause of deaths in the world
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
