Related Experiment Video
Updated: Sep 13, 2025
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
Published on: July 22, 2025
Investigating the Impact of the Stationarity Hypothesis on Heart Failure Detection using Deep Convolutional
Mohamed Elmehdi Ait Bourkha1, Dounia Nasir2
1Information Technology and Modeling Team Laboratory (LTIM), National School of Applied Sciences (ENSA) of Marrakech, Cadi Ayyad University (UCA), 40000, Marrakech, Morocco. mehdibourkha123@gmail.com.
Insights
A new deep learning model accurately detects cardiovascular diseases (CVDs) from ECG signals. This approach utilizes a Wavelet Scattering Network and the stationarity hypothesis for reliable early detection of heart conditions.
Area of Science:
- Cardiology
- Biomedical Engineering
- Machine Learning
Background:
- Cardiovascular diseases (CVDs) are a leading global cause of death, with increasing mortality rates.
- Early detection of CVDs is critical for effective management and improved patient outcomes.
- Existing methods for ECG signal analysis face challenges in accuracy and reliability.
Purpose of the Study:
- To develop a reliable model for the early detection of cardiovascular diseases (CVDs) using ECG signals.
- To classify ECG signals into Normal Sinus Rhythm (NSR), Arrhythmia Rhythm (ARR), and Congestive Heart Failure (CHF).
- To enhance automated CVD detection under the inter-patient paradigm.
Main Methods:
- A deep convolution Wavelet Scattering Network (WSN) was employed for ECG signal classification.
- The stationarity hypothesis of ECG rhythms within patients was integrated into the model.
- A Linear Discriminant (LD) classifier was used in conjunction with the WSN and stationarity hypothesis.
Main Results:
- The proposed model achieved high classification performance across all three classes (NSR, ARR, CHF).
- Achieved an overall accuracy of 99.61%, precision of 99.65%, sensitivity of 99.35%, specificity of 99.74%, and F1-score of 99.49%.
- Demonstrated the effectiveness of the WSN and stationarity hypothesis for inter-patient CVD detection.
Conclusions:
- The developed approach offers a reliable and accurate method for automated CVD detection from ECG signals.
- The integration of WSN, LD classifier, and stationarity hypothesis significantly improves classification results.
- This model holds promise for advancing early detection and management of cardiovascular diseases.
Abstract:
Detection of Cardiovascular Diseases (CVDs) has become crucial nowadays, as the World Health Organization (WHO) declares CVDs as the major leading causes of death in the globe. Moreover, the death rate due to CVDs is expected to rise in the next few upcoming years. One of the most valuable contributions that could be given to the cardiology field is developing a reliable model for early detection of CVDs. This paper presents a new approach aimed to classify ECG signals into: Normal Sinus Rhythm (NSR), Arrhythmia Rhythm (ARR), and Congestive Heart Failure (CHF). The proposed approach has been developed based on the stationarity hypothesis of rhythms within the same patient in ECG signals. The stationarity hypothesis assumes that if arrhythmias are found in one part of a long ECG signal, they are likely to occur in other parts of the same signal as well. In this paper, many contributions have been developed with the aim of enhancing automated detection of CVDs under the inter-patient paradigm, including using WSN in conjunction with different Machine Learning (ML) models and the stationarity hypothesis of ECG signals. A deep convolution Wavelet Scattering Network (WSN) in conjunction with a Linear Discriminant (LD) classifier and stationarity hypothesis was implemented with the aim of improving the classification results under inter-patient paradigm. The model achieved impressive results, with an overall accuracy of 99.61%, precision of 99.65%, sensitivity of 99.35%, specificity of 99.74%, and F1-score of 99.49%, across all the three classes.
