article · Discover Artificial Intelligence
Early and accurate detection of chronic kidney disease is vital for preventing disease progression, yet standard machine learning methods usually rely on centralised datasets that pose serious privacy and logistical issues. To overcome these constraints in distributed healthcare environments, a decentralised prediction framework has been developed. The system combines federated learning, prediction-level aggregation, differential privacy, and explainable artificial intelligence using SHAP techniques. Tested across distributed setups, the model achieved a mean cross-validation accuracy of 98.85 percent, an F1-score of 98.58 percent, and maintained 97.50 percent accuracy even when subjected to differential privacy noise. In cross-client evaluations, accuracy reached 99.25 percent. Additionally, model compression and sparse update mechanisms reduced communication overhead from 0.82 MB to 0.25 MB, facilitating practical operation in settings with limited network and computing resources.
Hospitals frequently cannot share sensitive patient records due to strict privacy regulations and poor digital infrastructure. By training machine learning models across institutions without moving raw clinical data, healthcare providers can collaborate safely. This approach helps detect chronic kidney disease earlier while safeguarding patient privacy and working reliably even in clinics with low computing capacity or poor internet connectivity.
This research could enable privacy-preserving clinical decision-support software for hospitals, diagnostic centres, and health networks monitoring kidney disease. By minimising communication bandwidth and protecting patient data, the software suits multi-centre collaborations and resource-constrained clinics. The technology represents applied research that has undergone experimental simulation and cross-client testing, indicating it requires clinical validation and software integration before reaching operational, real-world deployment.
AI-generated from the published abstract. Always read the original work before citing.
Chronic kidney disease (CKD) is a major public health concern that requires early and reliable diagnosis to reduce disease progression and associated complications. Existing machine learning approaches often rely on centralized training, limiting their applicability in healthcare environments where data privacy, heterogeneity, and resource constraints are critical concerns. To address these challenges, this study proposes a privacy-preserving federated meta-ensemble stacking framework for CKD prediction. The proposed approach integrates a hybrid preprocessing pipeline, federated learning with prediction-level aggregation, differential privacy, and SHAP-based explainability to enable secure, interpretable, and decentralized model learning. Experimental evaluation demonstrates a mean cross-validation accuracy of 98.85% with an F1-score of 98.58%. The framework maintains robust performance under Gaussian noise, achieving 97.50% accuracy, while cross-client evaluation reaches 99.25%, demonstrating strong generalization across distributed healthcare institutions. The model also exhibits excellent discrimination and calibration, achieving a ROC-AUC of 0.998, PR-AUC of 0.997, and a Brier score of 0.00038. Furthermore, communication overhead is reduced from 0.82 MB to 0.25 MB through compression and sparse updates. These findings demonstrate that the proposed framework provides an accurate, privacy-aware, and interpretable solution for decentralized CKD prediction.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s44163-026-02143-w
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
