Open Access

ARTICLE

Enhancing Heart Sound Classification with Iterative Clustering and Silhouette Analysis: An Effective Preprocessing Selective Method to Diagnose Rare and Difficult Cardiovascular Cases

Sami Alrabie^#,*, Ahmed Barnawi^#

Information Technology, Faculty of Computing and Information Technology (FCIT), King Abdulaziz University, Jeddah, 21589, Saudi Arabia

* Corresponding Author: Sami Alrabie. Email:
# These authors contributed equally to this work

(This article belongs to the Special Issue: Exploring the Impact of Artificial Intelligence on Healthcare: Insights into Data Management, Integration, and Ethical Considerations)

Computer Modeling in Engineering & Sciences 2025, 144(2), 2481-2519. https://doi.org/10.32604/cmes.2025.067977

Received 17 May 2025; Accepted 25 July 2025; Issue published 31 August 2025

Abstract

In the effort to enhance cardiovascular diagnostics, deep learning-based heart sound classification presents a promising solution. This research introduces a novel preprocessing method: iterative k-means clustering combined with silhouette score analysis, aimed at downsampling. This approach ensures optimal cluster formation and improves data quality for deep learning models. The process involves applying k-means clustering to the dataset, calculating the average silhouette score for each cluster, and selecting the cluster with the highest score. We evaluated this method using 10-fold cross-validation across various transfer learning models from different families and architectures. The evaluation was conducted on four datasets: a binary dataset, an augmented binary dataset, a multiclass dataset, and an augmented multiclass dataset. All datasets were derived from the HeartWave heart sounds dataset, a novel multiclass dataset introduced by our research group. To increase dataset sizes and improve model training, data augmentation was performed using heartbeat cycle segmentation. Our findings highlight the significant impact of the proposed preprocessing approach on the HeartWave datasets. Across all datasets, model performance improved notably with the application of our method. In augmented multiclass classification, the MobileNetV2 model showed an average weighted F1-score improvement of 27.10%. In binary classification, ResNet50 demonstrated an average accuracy improvement of 8.70%, reaching 92.40% compared to its baseline performance. These results underscore the effectiveness of clustering with silhouette score analysis as a preprocessing step, significantly enhancing model accuracy and robustness. They also emphasize the critical role of preprocessing in addressing class imbalance and advancing precision medicine in cardiovascular diagnostics.

---

Keywords

---