Healthcare capabilities have evolved throughout the years by integrating advanced technologies such as Artificial Intelligence (AI), Machine Learning (ML), Deep Learning (DL), and Cloud Computing. These technologies allow real-time remote monitoring, enhance diagnostic accuracy, and optimize resource utilization in e-health structures. Nevertheless, AI-based healthcare services add various privacy concerns, particularly regarding the handling of sensitive patient data in compliance with global regulations, such as General Data Protection Regulation (GDPR) and Health Insurance Portability and Accountability Act (HIPAA). Privacy-preserving techniques, including Homomorphic Encryption (HE), Secure Multi-Party Computation (SMPC), Zero-Knowledge Proofs (ZKP), and Federated Learning (FL), have been proposed to mitigate sensitive data challenges (for data at transit and at rest), by enabling secure data processing without data disclosure to none trusted parties, such as cloud-based AI analytic tools. This chapter aims at assisting healthcare service developers to comprehend the AI-based e-health framework, its security characteristics, and common privacy-enhancing mechanisms. This is achieved, first, by providing an in-depth analysis of AI-based e-health systems, their privacy vulnerabilities and threat models. Second, it analyzes the privacy-enhancing and anonymity mechanisms, their applicability in AI-driven healthcare systems, and their advantages and disadvantages. Finally, some future directions are highlighted for implementing robust and privacy-preserving AI solutions.