Authors: Kavyansh Nath
Abstract: The exponential growth of data volume and complexity in the enterprise and healthcare sectors has rendered traditional data warehousing techniques insufficient for high-performance analytics. This review article investigates the emergence of AI-assisted data warehousing as a transformative paradigm for modern data management. We evaluate the integration of machine learning across the entire data lifecycle, specifically focusing on AI-driven ETL processes for automated schema mapping and the ingestion of unstructured clinical data. The study examines advanced performance optimization techniques, including reinforcement learning for autonomous query tuning and predictive resource scaling. In the context of healthcare, we analyze how these techniques facilitate longitudinal patient records, real-time clinical decision support, and accelerated drug discovery. Furthermore, we address the critical domains of security and compliance, highlighting AI-based data masking and anomaly detection for fraud prevention. By discussing emerging trends such as self-driving warehouses and generative AI interfaces, this article provides a strategic framework for organizations seeking to implement resilient, intelligent, and high-speed analytical cores. Ultimately, we demonstrate that AI-assisted warehousing is the essential foundation for turning massive datasets into actionable strategic and clinical intelligence.
DOI: http://doi.org/10.5281/zenodo.18229082
