A BLOCKCHAIN-INTEGRATED PRIVACY-PRESERVING MACHINE LEARNING MODEL FOR CHRONIC KIDNEY DISEASE RISK ASSESSMENT

Authors

  • Mrs.Md. Parveen Begum1 ,Maddi Venkata Naga Anjani Sai Sanjana2 , Manam Srilakshmi3 , Meda Lakshmi Triveni4 ,Mogili Annamani5 Author

DOI:

https://doi.org/10.5281/zenodo.19452254

Keywords:

Chronic Kidney Disease (CKD), Machine Learning, Blockchain, InterPlanetary File System (IPFS), Healthcare Data Security, Decentralized Systems

Abstract

Chronic Kidney Disease (CKD) is a major global health concern that often progresses silently and leads to severe complications if not detected early. Machine learning techniques have shown promising results in predicting CKD; however, traditional systems rely on centralized data storage, which raises significant concerns regarding data privacy, security, and transparency. This research proposes a privacy-preserving decentralized framework for CKD prediction by integrating machine learning, blockchain technology, and the InterPlanetary File System (IPFS). In the proposed system, sensitive medical records are encrypted using AES and RSA algorithms before storage and processing to ensure confidentiality. Multiple machine learning algorithms, including Decision Tree, Random Forest, Logistic Regression, and K-Nearest Neighbors, are employed to analyze clinical parameters and predict CKD risk accurately. Blockchain technology ensures immutability, transparency, and secure transaction logging, while IPFS provides decentralized and reliable storage of encrypted medical data. Experimental evaluation demonstrates improved prediction accuracy, enhanced data security, and scalable healthcare analytics for trustworthy AI-driven medical diagnosis.

Downloads

Published

07-04-2026

How to Cite

A BLOCKCHAIN-INTEGRATED PRIVACY-PRESERVING MACHINE LEARNING MODEL FOR CHRONIC KIDNEY DISEASE RISK ASSESSMENT. (2026). International Journal of Engineering Research and Science & Technology, 22(2), 1825-1832. https://doi.org/10.5281/zenodo.19452254