EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Cardiac Abnormalities Detection Among Malaysian Armed Forces (MAF) Using Deep Learning Techniques

Marini Binti Mansor, Nur Diyana Kamarudin, Aida Jaffar, Mohd Rizal Mohd Isa, Ashikin Rusly, Siti Noormiza Makhtar, Mohd Hazali Mohamed Halip, Melek Önen

JOIV : International Journal on Informatics Visualization · 30.07.2026 · 10 (4) · 1425

DOI: 10.62527/joiv.10.4.3457 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JOIV : International Journal on Informatics Visualization, online erschienen am 30.07.2026. Verfasst von Marini Binti Mansor und 7 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cardiac abnormalities among military personnel pose unique diagnostic challenges due to their physically and mentally demanding lifestyles, which can contribute to increased cardiovascular risks. This study investigates the use of supervised machine learning (ML) models to enhance the detection and classification of such abnormalities, aiming to determine the most effective approach in terms of predictive accuracy and clinical reliability. A dataset consisting of 35,564 electrocardiogram (ECG) readings and medical history records from 2,092 Malaysian military personnel was used. Each instance includes 17 clinical attributes, such as heart rate, QRS duration, and P-R interval. The data underwent comprehensive preprocessing steps, including normalization, handling missing values, and feature selection, to ensure robustness and model reliability. Three classification algorithms which are Neural Network, K-Nearest Neighbors (KNN), and Fine Tree—were implemented and evaluated. Model performance was assessed using accuracy, precision, recall, and confusion matrix analysis to determine its effectiveness in differentiating between normal and abnormal cardiac conditions. The results indicated that the Neural Network model achieved the highest accuracy, outperforming the KNN and Fine Tree models in capturing complex, non-linear patterns in the data. These findings suggest that deep learning-based models are particularly well-suited for detecting cardiac abnormalities in high-risk populations. This study underscores the value of machine learning in advancing cardiac diagnostics and offers a foundation for integrating AI-driven tools into routine clinical screening. Future research could explore real-time deployment and incorporate wearable sensor data for continuous monitoring and prediction.

Zitieren

APA

Mansor, M. B., Kamarudin, N. D., Jaffar, A., Isa, M. R. M., Rusly, A., Makhtar, S. N., Halip, M. H. M., & Önen, M. (2026). Cardiac Abnormalities Detection Among Malaysian Armed Forces (MAF) Using Deep Learning Techniques. JOIV : International Journal on Informatics Visualization, 10(4), 1425. https://doi.org/10.62527/joiv.10.4.3457

Vancouver

Mansor MB, Kamarudin ND, Jaffar A, Isa MRM, Rusly A, Makhtar SN, et al. Cardiac Abnormalities Detection Among Malaysian Armed Forces (MAF) Using Deep Learning Techniques. JOIV : International Journal on Informatics Visualization. 2026;10(4):1425. doi:10.62527/joiv.10.4.3457

BibTeX
@article{Mansor2026,
  author = {Mansor, Marini Binti and Kamarudin, Nur Diyana and Jaffar, Aida and Isa, Mohd Rizal Mohd and Rusly, Ashikin and Makhtar, Siti Noormiza and Halip, Mohd Hazali Mohamed and Önen, Melek},
  title = {Cardiac Abnormalities Detection Among Malaysian Armed Forces (MAF) Using Deep Learning Techniques},
  journal = {JOIV : International Journal on Informatics Visualization},
  year = {2026},
  volume = {10},
  number = {4},
  pages = {1425},
  doi = {10.62527/joiv.10.4.3457}
}
Kostenlos starten →