Performance Evaluation of Genetic Algorithm-Driven Blockchain Encryption for EHR Management and Validation

Abstract

In the realm of electronic health record (EHR) management, ensuring robust security and validation mechanisms is paramount due to the sensitive nature of healthcare data. This research focuses on the performance evaluation of a genetic algorithm-driven blockchain encryption approach for enhancing EHR security and validation. The proposed method leverages genetic algorithms to optimize encryption parameters within a blockchain framework, aiming to safeguard patient privacy and prevent unauthorized access. By integrating advanced cryptographic techniques like Elliptic Curve Cryptography (ECC) and Keyed-Hash Message Authentication Code (HMAC)-based authentication, along with machine learning for data classification. The evaluation of the approach holds significant promise in advancing secure EHR management practices, addressing critical challenges in data privacy and integrity within healthcare environments. Finally, as a result, this study presents a comparative analysis of cryptographic systems genetic algorithm-driven blockchain encryption (GADBE)+ECC and GADBE+ Advanced Encryption Standard (AES), focusing on the scaling of encryption and decryption times relative to key sizes and data volumes. Results show that both systems exhibit increasing times with larger key sizes and data sizes. ECC consistently demonstrates superior speed over AES, with decryption times ranging from 0.4 to 3.5 seconds for key sizes from 128 to 512 bits, indicating potential performance advantages of ECC in cryptographic applications.