ItemArticle

Privacy-Preserving Federated Learning for Prognostic Modeling in Rare Diseases: A Scalable Case Study on Kawasaki Disease

Title
Privacy-Preserving Federated Learning for Prognostic Modeling in Rare Diseases: A Scalable Case Study on Kawasaki Disease
Creator
Namitha, T.N.; Raghavendra, S.; Vinith, R.
Description
Predictive modeling in rare diseases faces major challenges, including data scarcity, class imbalance, and strict privacy regulations that limit cross-border collaboration. These challenges are particularly critical in Kawasaki disease (KD)a rare vasculitis in childrenwhere 10% to 20% of patients are resistant to intravenous immunoglobulin (IVIG), the standard first-line treatment. This significantly increases the risk of coronary artery abnormalities (CAA), making early and accurate prediction of resistance to IVIG essential for improving patient outcomes. Our work proposes a federated learning (FL) approach to address the constraints imposed by security and privacy concerns. We investigate convolutional neural networks (CNN) as the shared model, collaboratively trained across clients. Coupled with strategies to address class imbalance resulting from the rarity of the condition, the federated approach yielded promising results when evaluated against conventional machine learning (ML) models. The proposed approach demonstrated strong performance, achieving 94% accuracy, 93% precision, 89% recall, and 91% F1 score. To ensure robustness and generalizability, an independent dataset was also used, where the proposed model excelled similarly. These results highlight the potential of FL to overcome data privacy barriers and provide a scalable, secure solution for predictive modeling in rare diseases, supporting its integration into medical prediction workflows. 2025 by the authors of this article.
Source
International Journal of Online and Biomedical Engineering;Volume;21;Issue;11;pp.66-80
Date
01-01-2025
Publisher
International Federation of Engineering Education Societies (IFEES)
Subject
adaptive synthetic sampling; convolutional neural network (CNN); federated learning (FL); flower framework; intravenous immunoglobulin resistance; Kawasaki disease (KD); rare disease
Coverage
Namitha T.N., Department of CSE, Christ (Deemed to be University), Karnataka, Bangalore, India; Raghavendra S., Department of AIML and Data Science, Christ (Deemed to be University), Karnataka, Bangalore, India; Vinith R., Amrita Vishwa Vidyapeetham, Tamil Nadu, Coimbatore, India
Rights
All Open Access; Gold Open Access
Relation
ISSN: 26268493;
Format
online
Language
English
Type
Article

Citation

Namitha, T.N.; Raghavendra, S.; Vinith, R., “Privacy-Preserving Federated Learning for Prognostic Modeling in Rare Diseases: A Scalable Case Study on Kawasaki Disease,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 18, 2026, https://archives.christuniversity.in/items/show/23597.

Output Formats