Abstract

The rapid adoption of cloud-native platforms in healthcare has intensified the need for robust data security and privacy-preserving analytics. This study presents a privacy-aware machine learning and generative AI framework for securing healthcare data using SAP-integrated Databricks platforms. The proposed approach leverages scalable lakehouse architecture, advanced machine learning pipelines, and generative AI techniques to enable secure data processing, real-time analytics, and intelligent decision support while maintaining regulatory compliance. Privacy-aware mechanisms such as secure data isolation, access control, and governance are incorporated to protect sensitive patient information across distributed environments. By integrating SAP systems with Databricks, the framework ensures interoperability, performance optimization, and enterprise-grade security for healthcare applications. Experimental observations demonstrate improved data security, scalability, and analytical efficiency, making the proposed architecture suitable for modern, cloud-native healthcare ecosystems.