Analysis of ECG-based arrhythmia detection system using machine learning

Article Engineering, Biomedical

Arrhythmia disease classification utilizing ResRNN

Shikha Dhyani et al.

Summary: Automated electrocardiogram analysis using a deep neural network model called ResRNN showed promising results in identifying various anomalies in ECG data. Compared to other models, ResRNN achieved a higher accuracy rate of 91% in classifying ECG signals.

BIOMEDICAL SIGNAL PROCESSING AND CONTROL (2023)

Add to Collection

Article Mathematical & Computational Biology

Machine Algorithm for Heartbeat Monitoring and Arrhythmia Detection Based on ECG Systems

Ahmed I. Taloba et al.

Summary: Cardiac arrhythmia is a heart disease that can be identified through signal analysis to provide appropriate treatment. A new technique is proposed to better evaluate ECG signals through signal feature analysis, aiding researchers in detecting arrhythmia situations.

COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE (2021)

Add to Collection

Article Biophysics

Identification of 27 abnormalities from multi-lead ECG signals: an ensembled SE_ResNet framework with Sign Loss function

Zhaowei Zhu et al.

Summary: This study highlights the significance of early and accurate diagnosis of cardiovascular diseases through the development of an algorithm that automatically identifies 27 ECG abnormalities. By applying preprocessing methods and deep learning models, the performance of ECG abnormality classification was improved, and a method to address class imbalance was proposed. The proposed framework achieved remarkable results in experiments, demonstrating its effectiveness in automatic classification of multiple ECG abnormalities.

PHYSIOLOGICAL MEASUREMENT (2021)

Add to Collection

Article Biochemical Research Methods