SYNTHEMA WP1 Update
The main purpose of WP1 is to develop a comprehensive strategy for two clinical use cases—Sickle Cell Disease (SCD) and Acute Myeloid Leukemia (AML)—to provide substantial high-quality data for training data anonymization and Synthetic Data Generation (SDG) pipelines (WP3), as well as for clinical validation and statistical utility assessment (WP4). Key objectives include identifying and defining the requirements of various end-user groups, establishing a harmonized data and metadata model that complies with GDPR and ethical standards, selecting suitable ICT standards, and coordinating ethics management, data collection, and processing across clinical sites.
For Sickle Cell Disease (SCD) and Acute Myeloid Leukemia (AML), data collection and integration are progressing, with specific Year 2 goals. For SCD, 1,253 patients are enrolled, with 904 having complete datasets from sites in France, Netherlands, Spain, and Italy.
The Year 2 objectives include releasing the RedCap platform for Portugal and Germany (managed by VHIR), assessing data quality, defining use contexts for data sharing with technical partners, sharing the data, and reviewing anonymization protocols.
For AML, data strategies leverage a public dataset from Charité and data from clinical partners (ICH, VHIR, UMCU, UNIPD, Hospital Da Luz, and Charité). Year 2 goals include integrating the AML dataset into RedCap, coordinating with Humanitas IT and CE for external access, and populating the dataset with real data. Both efforts support data quality and interoperability, with OMOP mapping collaboration underway with DATAWIZARD.