Related Experiment Video
Updated: Aug 27, 2025
Real-Time Cardiac Mapping with a Noninvasive Imageless Electrocardiographic Imaging System
Published on: April 11, 2025
The prediction of cardiac abnormality and enhancement in minority class accuracy from imbalanced ECG signals using
Hari Mohan Rai1, Kalyan Chatterjee2, Serhii Dashkevych3
1Department of Electrical Engineering, Indian Institute of Technology(ISM), Dhanbad, India; Department of Electronics and Communication Engineering, Dronacharya Group of Institutions, Greater Noida, India.
Insights
This study introduces a novel sequential ensemble technique using deep learning to accurately detect cardiac arrhythmias from imbalanced electrocardiogram (ECG) data. The method significantly improves detection accuracy and minority class recall, aiding early cardiovascular disease diagnosis.
Area of Science:
- Cardiology
- Artificial Intelligence
- Biomedical Engineering
Background:
- Cardiovascular disease (CVD) is a leading cause of mortality worldwide.
- Early and accurate detection of cardiac arrhythmias is crucial for timely medical intervention.
- Data imbalance in medical datasets, particularly ECGs, poses a significant challenge for automated detection models.
Purpose of the Study:
- To develop and validate a sequential ensemble technique for detecting 6 types of cardiac arrhythmias.
- To address the challenge of imbalanced ECG datasets using a hybrid data resampling approach.
- To improve the accuracy and reliability of automated arrhythmia detection systems.
Main Methods:
- A sequential ensemble technique combining Convolutional Neural Network (CNN) and CNN with Long Short-Term Memory (CNN-LSTM) models was proposed.
- A hybrid data resampling technique, Synthetically Minority Oversampling Technique and Tomek Link (SMOTE + Tomek), was employed to handle data imbalance.
- The models were validated on a combined dataset of 23,998 ECG beats from the MIT-BIH and PTB diagnostic databases, tested on original, randomly oversampled, SMOTE, and SMOTE + Tomek sampled data.
Main Results:
- The ensemble technique achieved an overall accuracy of 99.02% on the SMOTE + Tomek sampled dataset.
- The minority class accuracy (Recall) was improved by 20% compared to imbalanced data.
- The proposed method demonstrated superior performance in detecting cardiac arrhythmias on imbalanced ECG datasets.
Conclusions:
- The sequential ensemble technique effectively addresses data imbalance in ECG datasets for arrhythmia detection.
- The hybrid SMOTE + Tomek resampling method significantly enhances model performance.
- This approach offers a promising solution for accurate and automated early diagnosis of cardiovascular diseases.
Abstract:
Cardiovascular disease (CVD) is the most fatal disease in the world, so its accurate and automated detection in the early stages will certainly support the medical expert in timely diagnosis and treatment, which can save many lives. Many types of research have been carried out in this regard, but due to the problem of data imbalance in the medical and health care sector, it may not provide the desired results in all aspects. To overcome this problem, a sequential ensemble technique has been proposed that detects 6 types of cardiac arrhythmias on large ECG imbalanced datasets, and the data imbalanced issue of the ECG dataset has been addressed by using a hybrid data resampling technique called "Synthetically Minority Oversampling Technique and Tomek Link (SMOTE + Tomek)". The sequential ensemble technique employs two distinct deep learning models: Convolutional Neural Network (CNN) and a hybrid model, CNN with Long Short-Term Memory Network (CNN-LSTM). The two standard datasets "MIT-BIH arrhythmias database" (MITDB) and "PTB diagnostic database" (PTBDB) are combined and extracted 23, 998 ECG beats for the model validation. In this work, the three models CNN, CNN-LSTM, and ensemble approach were tested on four kinds of ECG datasets: the original data (imbalanced), the data sampled using a random oversampled technique, data sampled using SMOTE, and the dataset resampled using SMOTE + Tomek algorithm. The overall highest accuracy was obtained of 99.02% on the SMOTE + Tomek sampled dataset by ensemble technique and the minority class accuracy result (Recall) is improved by 20% as compared to the imbalanced data.
