EUVIMEDEUVIMED entdecken
Crossref

An Attention‐Driven Hybrid Deep Neural Network for Enhanced Heart Disease Classification

Umesh Kumar Lilhore, Sarita Simaiya, Musaed Alhussein, Surjeet Dalal, Khursheed Aurangzeb, Amir Hussain

Expert Systems · 2025-02 · 42 (2)

DOI: 10.1111/exsy.13791 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Expert Systems, online erschienen am 19.11.2024. Verfasst von Umesh Kumar Lilhore und 5 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: King Saud University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Heart disease continues to be a primary cause of mortality globally, highlighting the critical necessity for efficient early prediction and classification techniques. This study presents a new hybrid model attention‐based CNN‐Bi‐LSTM that integrates the SMOTE with an attention‐driven improved convolutional neural network‐recurrent neural network architecture to improve the classification of heart sounds, especially from imbalanced datasets. Heart sounds are difficult to classify because of their complex acoustic properties and the variability of their characteristics across frequency and temporal domains. The proposed model utilises an advanced CNN to effectively extract global and local features, in conjunction with a bidirectional long short‐term memory network to improve the architecture by capturing contextual information from both preceding and subsequent time sequences. The incorporation of spatial attention within the CNN and temporal attention in the RNN enables the model to concentrate on the most pertinent audio segments. To address the challenges presented by imbalanced and noisy datasets that may impede the efficacy of deep learning algorithms, our model employs SMOTE to improve data representation. The hybrid model outperformed popular models such as CNN, LSTM and CNN‐LSTM, achieving a classification accuracy of more than 97% on the PCG and PASCAL heart sound datasets. The findings demonstrate the model's reliability as an initial evaluation tool in clinical settings, thereby improving support for cardiovascular disease diagnosis.

Förderung

  • King Saud University

Zitieren

APA

Lilhore, U. K., Simaiya, S., Alhussein, M., Dalal, S., Aurangzeb, K., & Hussain, A. (2025). An Attention‐Driven Hybrid Deep Neural Network for Enhanced Heart Disease Classification. Expert Systems, 42(2). https://doi.org/10.1111/exsy.13791

Vancouver

Lilhore UK, Simaiya S, Alhussein M, Dalal S, Aurangzeb K, Hussain A. An Attention‐Driven Hybrid Deep Neural Network for Enhanced Heart Disease Classification. Expert Systems. 2025;42(2). doi:10.1111/exsy.13791

BibTeX
@article{Lilhore2025,
  author = {Lilhore, Umesh Kumar and Simaiya, Sarita and Alhussein, Musaed and Dalal, Surjeet and Aurangzeb, Khursheed and Hussain, Amir},
  title = {An Attention‐Driven Hybrid Deep Neural Network for Enhanced Heart Disease Classification},
  journal = {Expert Systems},
  year = {2025},
  volume = {42},
  number = {2},
  doi = {10.1111/exsy.13791}
}
Kostenlos starten →