Federated Explainable Deep Learning Framework for PrivacyPreserving Heart Disease Prediction
International Journal of Drug Delivery Technology · 02.06.2026 · 16 (44s)
DOI: 10.25258/ijddt.16.44s.76 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 02.06.2026. Verfasst von N. Sakthivel und 2 weiteren Autor:innen.
Abstract (Originalsprache)
The worldwide death toll from cardiovascular diseases ranks as the highest among all health problems which creates a demand for healthcare facilities to develop precise tools that assess patient risk at an early stage. Deep learning models excel in predicting heart disease but current methods use centralized data collection which creates serious issues for protecting patient information and securing data and following legal requirements. The paper introduces a new Federated Explainable Deep Learning (FEDL) framework which allows healthcare organizations to predict heart disease while protecting patient privacy through distributed medical systems. The proposed system enables multiple hospitals to collaboratively train a deep neural network model without sharing raw patient data. Each institution conducts its own model development process but only the model parameters get sent to the central server which uses the Federated Averaging (FedAvg) algorithm to build a universal predictive system. The framework uses Shapley Additive explanations (SHAP) to show how different clinical characteristics affect prediction results which helps doctors understand the system better and trust its results. The final system functions as a clinical decision support tool which delivers risk assessment results together with understandable explanations. The experimental analysis shows that the proposed method achieves excellent predictive results while safeguarding data and maintaining interpretability and fairness. The framework provides an artificial intelligence solution that protects data through its deployment process in distributed healthcare environments
Zitieren
APA
Sakthivel, N., Adhithya, A., & Alosius, A. (2026). Federated Explainable Deep Learning Framework for PrivacyPreserving Heart Disease Prediction. International Journal of Drug Delivery Technology, 16(44s). https://doi.org/10.25258/ijddt.16.44s.76
Vancouver
Sakthivel N, Adhithya A, Alosius A. Federated Explainable Deep Learning Framework for PrivacyPreserving Heart Disease Prediction. International Journal of Drug Delivery Technology. 2026;16(44s). doi:10.25258/ijddt.16.44s.76
BibTeX
@article{Sakthivel2026,
author = {Sakthivel, N. and Adhithya, A. and Alosius, A.},
title = {Federated Explainable Deep Learning Framework for PrivacyPreserving Heart Disease Prediction},
journal = {International Journal of Drug Delivery Technology},
year = {2026},
volume = {16},
number = {44s},
doi = {10.25258/ijddt.16.44s.76}
}
EUVIMED