The Multi-Branch Deep-Learning-Based Approach to Heart Dysfunction Classification
Cardiovascular diseases (CVDs), which remain globally one of the most common causes of death, are usually diagnosed based on the electrocardiogram (ECG) signal. To support human experts, modern deep-learning models are used for CVD classification problems as an early warning. This article proposes a...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/15/8765 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849405875677036544 |
|---|---|
| author | Krzysztof Hryniów Bartosz Puszkarski Marcin Iwanowski |
| author_facet | Krzysztof Hryniów Bartosz Puszkarski Marcin Iwanowski |
| author_sort | Krzysztof Hryniów |
| collection | DOAJ |
| description | Cardiovascular diseases (CVDs), which remain globally one of the most common causes of death, are usually diagnosed based on the electrocardiogram (ECG) signal. To support human experts, modern deep-learning models are used for CVD classification problems as an early warning. This article proposes a novel multi-branch architecture focused on processing various modalities of the ECG signal in parallel branches, replacing typical single-input architectures. Each branch is given separate input in the form of the raw signal, domain knowledge, the wavelet transform of the signal, or the signal with drift removed. The proposed method is based on deep-learning core models that can incorporate various modern neural networks. It was thoroughly tested on N-BEATS, LSTM, and GRU neural networks. The proposed architecture allows the retention of the speed of the neural network. At the same time, the combination of independently computed branches improves model performance, which finally exceeds the performance obtained by classical single-branch architectures. |
| format | Article |
| id | doaj-art-1b415e900ddb47f9800ffd0fe9a8394c |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-1b415e900ddb47f9800ffd0fe9a8394c2025-08-20T03:36:34ZengMDPI AGApplied Sciences2076-34172025-08-011515876510.3390/app15158765The Multi-Branch Deep-Learning-Based Approach to Heart Dysfunction ClassificationKrzysztof Hryniów0Bartosz Puszkarski1Marcin Iwanowski2Control Division, Institute of Control and Industrial Electronics, Faculty of Electrical Engineering, Warsaw University of Technology, ul. Koszykowa 75, 00-662 Warsaw, PolandControl Division, Institute of Control and Industrial Electronics, Faculty of Electrical Engineering, Warsaw University of Technology, ul. Koszykowa 75, 00-662 Warsaw, PolandControl Division, Institute of Control and Industrial Electronics, Faculty of Electrical Engineering, Warsaw University of Technology, ul. Koszykowa 75, 00-662 Warsaw, PolandCardiovascular diseases (CVDs), which remain globally one of the most common causes of death, are usually diagnosed based on the electrocardiogram (ECG) signal. To support human experts, modern deep-learning models are used for CVD classification problems as an early warning. This article proposes a novel multi-branch architecture focused on processing various modalities of the ECG signal in parallel branches, replacing typical single-input architectures. Each branch is given separate input in the form of the raw signal, domain knowledge, the wavelet transform of the signal, or the signal with drift removed. The proposed method is based on deep-learning core models that can incorporate various modern neural networks. It was thoroughly tested on N-BEATS, LSTM, and GRU neural networks. The proposed architecture allows the retention of the speed of the neural network. At the same time, the combination of independently computed branches improves model performance, which finally exceeds the performance obtained by classical single-branch architectures.https://www.mdpi.com/2076-3417/15/15/8765ECG classificationcardiovascular diseasesneural networkN-BEATSRNNGRU |
| spellingShingle | Krzysztof Hryniów Bartosz Puszkarski Marcin Iwanowski The Multi-Branch Deep-Learning-Based Approach to Heart Dysfunction Classification Applied Sciences ECG classification cardiovascular diseases neural network N-BEATS RNN GRU |
| title | The Multi-Branch Deep-Learning-Based Approach to Heart Dysfunction Classification |
| title_full | The Multi-Branch Deep-Learning-Based Approach to Heart Dysfunction Classification |
| title_fullStr | The Multi-Branch Deep-Learning-Based Approach to Heart Dysfunction Classification |
| title_full_unstemmed | The Multi-Branch Deep-Learning-Based Approach to Heart Dysfunction Classification |
| title_short | The Multi-Branch Deep-Learning-Based Approach to Heart Dysfunction Classification |
| title_sort | multi branch deep learning based approach to heart dysfunction classification |
| topic | ECG classification cardiovascular diseases neural network N-BEATS RNN GRU |
| url | https://www.mdpi.com/2076-3417/15/15/8765 |
| work_keys_str_mv | AT krzysztofhryniow themultibranchdeeplearningbasedapproachtoheartdysfunctionclassification AT bartoszpuszkarski themultibranchdeeplearningbasedapproachtoheartdysfunctionclassification AT marciniwanowski themultibranchdeeplearningbasedapproachtoheartdysfunctionclassification AT krzysztofhryniow multibranchdeeplearningbasedapproachtoheartdysfunctionclassification AT bartoszpuszkarski multibranchdeeplearningbasedapproachtoheartdysfunctionclassification AT marciniwanowski multibranchdeeplearningbasedapproachtoheartdysfunctionclassification |