A holistic framework for strengthening security of healthcare data through encryption utilizing blockchain technology

Area of Science:

• Computer Science
• Medical Informatics
• Cybersecurity

Background:

• Healthcare data security is paramount due to sensitive patient information and increasing cyber threats.
• Existing security measures have limitations, necessitating innovative solutions for data protection.
• The need for secure, private, and immutable healthcare data management is critical.

Purpose of the Study:

• To propose a novel Blockchain-integrated Advanced Encryption Standard (BCT-AES) framework for enhancing healthcare data security.
• To improve the privacy, integrity, and overall security of sensitive patient information.
• To offer a practical and efficient solution for secure healthcare data management and predictive analytics.

Main Methods:

• A hybrid framework combining Convolutional Neural Networks (CNN) for feature extraction, Decision Tree (DT) and Logistic Regression (LR) for classification.
• Integration of Advanced Encryption Standard (AES) with blockchain technology for decentralized and tamper-proof data storage.
• Utilizing Python for implementation, ensuring practicality and real-world applicability.

Main Results:

• The BCT-AES framework achieved an average encryption time of 1.12 ms, significantly faster than existing methods.
• High classification accuracies were obtained: 99% for Decision Tree (DT) and 89% for Logistic Regression (LR).
• Demonstrated superior performance in encryption speed and predictive capabilities compared to AES-CP-IDABE, Enhanced AES, and AES-CBC.

Conclusions:

• The proposed BCT-AES framework offers a practical and efficient solution for secure healthcare data management.
• Integration of deep learning, advanced encryption, and blockchain technology enhances data security and privacy.
• The framework supports real-time analytics while ensuring robust protection of patient confidentiality.