Privacy-preserving computation can help hospitals and researchers use sensitive health data without exposing it. Farinaz Koushanfar, Ph.D., UC San Diego, explains how secure computation and distributed learning make it possible to collaborate on medical data while protecting patient privacy. Koushanfar examines secure multi-party computation, zero-knowledge proofs, and federated and split learning, helping clarify how health systems can work together despite data silos, incompatibility, security threats, and re-identification risk. This work helps explain how medical AI can learn from private data more safely and points toward more secure, robust, and trustworthy healthcare systems. Series: "Exploring Ethics" [Health and Medicine] [Humanities] [Science] [Show ID: 41367]