Secure Integration of Electronic Health Data Using Advanced Machine Learning and Blockchain Technology

Articles in Press

Document Type : Original Article

Authors

1 Department of Health Information Technology, Sirjan School of Medical Sciences, Sirjan, Iran.

2 Sirjan School of Medical Sciences, Sirjan, Iran.

3 Department of Occupational Health Engineering, Sirjan School of Medical Sciences, Sirjan, Iran.

10.30476/jhmi.2025.108377.1309

Abstract

Background : Data integration and privacy preservation in electronic health record (EHR) systems are critical challenges in modern healthcare. This study explores innovative solutions for managing heterogeneous data and enhancing security in EHRs using advanced machine learning models and blockchain technology.
Methods: A synthetic dataset comprising patient records, visits, diagnoses, medications, clinical observations, and procedures was used to evaluate the Irregular Fuzzy Cellular Automata (IFCA) model against XGBoost and LightGBM. Data preprocessing included complete anonymization and 98.5% imputation of missing values. Data exchange standards like HL7 FHIR and blockchain technology were employed to improve integration and security. Analyses were conducted using Python 3.10 and R version 4.2, aligning with CONSORT-AI and STROBE standards.
Results: IFCA outperformed XGBoost (89% accuracy) and LightGBM (90% accuracy) with 92% accuracy, an F1-score of 0.90, and an AUC-ROC of 0.92. A 94% data exchange success rate and 95% security were achieved using blockchain and privacy-preserving methods. ANOVA tests (p<0.05) confirmed significant differences.
Conclusion: This study provides effective solutions for data integration and privacy preservation in EHR systems. Future research should focus on real-world datasets and scalable methods.

Keywords

Main Subjects

Health Management & Information Science

Articles in Press, Accepted Manuscript
Available Online from 11 October 2025

Files

Share

How to cite

Statistics