The increasing use of electronic health records (EHR) in e-health systems has increased the significant concerns with regards to the patient privacy and the data security. Despite the increasing adoption of advanced security protocols, cyberattacks on health data continue to surge, posing risks to patient confidentiality and the system integrity. To address these challenges, a privacy-preserving framework is proposed that integrates Automated Security Orchestration and the Response (ASOR) with advanced encryption and the access control mechanisms. This framework automates the detection and the response to security threats, enhancing both privacy and the operational efficiency within e-health systems. The methodology utilizes machine learning algorithms for real-time threat detection and the automated decision-making, ensuring rapid response and the minimal human intervention. Through a series of experiments conducted on a simulated e-health dataset, the framework has shown an improvement in the security response time by 32%, with a 40% reduction in the data breach incidents when it is compared with the conventional systems. In addition, the proposed framework achieved a 98.5% detection accuracy for unauthorized access attempts.