EUVIMEDEUVIMED entdecken
Crossref

Heart Disease Prediction Using Machine Learning and Federated Learning Approach

Nabiha Fatma, Mohammad Suaib, Jameel Ahmad

International Journal of Science and Research (IJSR) · 05.05.2026 · 109-116

DOI: 10.21275/mr26501144519 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Science and Research (IJSR), erschienen am 05.05.2026. Verfasst von Nabiha Fatma und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Heart disease remains one of the leading causes of mortality worldwide, making early prediction and diagnosis crucial for improving patient outcomes. This research explores an integrated approach combining Machine Learning (ML) techniques with Federated Learning (FL) to develop a robust and privacy-preserving heart disease prediction system. Traditional ML models rely on centralized data collection, which often raises concerns related to data privacy, security, and regulatory compliance. To address these challenges, this study proposes a federated learning framework that enables multiple healthcare institutions to collaboratively train predictive models without sharing sensitive patient data. The proposed system utilizes clinical and demographic features such as age, blood pressure, cholesterol levels, and electrocardiographic results to train various machine learning algorithms, including decision trees, support vector machines, and ensemble models. These models are evaluated based on accuracy, precision, recall, and F1-score. The federated learning approach ensures that data remains localized while model updates are securely aggregated, thereby maintaining data confidentiality. Experimental results indicate that the hybrid ML-FL model achieves competitive prediction performance while significantly enhancing data privacy. This approach not only improves the scalability of predictive systems across distributed environments but also aligns with modern data protection requirements. The study demonstrates that integrating federated learning with traditional machine learning techniques can be an effective solution for building secure, efficient, and reliable healthcare prediction systems. Overall, this research contributes to the advancement of intelligent healthcare systems by offering a privacy-aware predictive framework for early heart disease detection.

Zitieren

APA

Fatma, N., Suaib, M., & Ahmad, J. (2026). Heart Disease Prediction Using Machine Learning and Federated Learning Approach. International Journal of Science and Research (IJSR), 109-116. https://doi.org/10.21275/mr26501144519

Vancouver

Fatma N, Suaib M, Ahmad J. Heart Disease Prediction Using Machine Learning and Federated Learning Approach. International Journal of Science and Research (IJSR). 2026:109-116. doi:10.21275/mr26501144519

BibTeX
@article{Fatma2026,
  author = {Fatma, Nabiha and Suaib, Mohammad and Ahmad, Jameel},
  title = {Heart Disease Prediction Using Machine Learning and Federated Learning Approach},
  journal = {International Journal of Science and Research (IJSR)},
  year = {2026},
  pages = {109--116},
  doi = {10.21275/mr26501144519}
}
Kostenlos starten →