Transforming Hospital Data into Real-World Evidence for Clinical Research: Insights into a Scalable Framework at...

The use of Real-World Data (RWD) is increasingly recognized as a critical driver for evidence generation in clinical research. At Fondazione Policlinico Universitario Agostino Gemelli IRCCS, within the Gemelli Generator Real World Data facility, a strategic targeted program has been developed to optimize the extraction, harmonization, and use of data collected in the hospital Data Warehouse and Data Lake, which currently include approximately 5 million patients across 50 information systems. This work describes the methodological framework adopted for data scouting, thematic library organization, and the implementation of standardized pipelines for data extraction and harmonization. The framework demonstrates how structured and unstructured hospital data can be integrated and transformed into scalable and reproducible Real-World Evidence (RWE), supporting and accelerating clinical research and multi-institutional collaboration.