Leveraging Machine Learning to Strengthen Network Security and Improve Threat Detection in Blockchain for Healthcare systems
Rianat Abbas, Victoria Abosede Ogunsanya, Sunday Jacob Nwanyim, Rasheed Afolabi, Richard Kagame, Ahmed Akinsola, Tosin Clement · International Journal of Scientific and Management Research · 2025
This study investigates the integration of blockchain technology and machine learning to enhance network security and improve threat detection in healthcare systems. With healthcare systems increasingly vulnerable to cyberattacks, the study explores how blockchain’s decentralized nature can secure electronic health records (EHRs) and improve interoperability among healthcare systems. Additionally, it examines how machine learning algorithms can identify anomalies and predict potential security breaches in real time. The findings highlight key factors, such as blockchain familiarity and machine learning effectiveness, that influence the successful adoption of these technologies. The model's evaluation metrics, including an AUC-ROC of 0.97 and accuracy of 80%, indicate that integrating blockchain and machine learning provides an effective solution for enhancing security. However, challenges such as multicollinearity, data imbalance, and integration complexities were identified. The study concludes with recommendations for addressing these challenges, emphasizing the need for continuous improvement in machine learning models, blockchain integration, and staff training to effectively safeguard healthcare systems.