PANCAIM project brings together 9 participating organisations with academic, clinical and technical expertise from across Europe which closely cooperate to improve outlook for pancreatic cancer patients with use of novel digital and AI tools. In the project, 6 clinical centers from 5 countries to gather and use real-life, multimodal pancreatic cancer data from almost 6000 patients for AI training and validation with the ultimate objective to assist clinicians in diagnosis an treatment of this aggressive disease.
However, it’s no easy task to bring together data from such different sources, each built to function in their own system. Some record the birthday of the patient, some only the age – and many more variables recorded in the clinical data differ. Each medical centre has a set of conventions and tools for capturing the clinical data which varies between institutions, making combining data in the source format unattainable. To make the data FAIR, especially interoperable and (re-)usable cross-center, all the clinical data will be harmonised and converted into a common data model (CDM) which will then be used for research.
For this reason, PANCAIM Partner the Hyve designed and developed a custom PANCAIM clinical data model, in close collaboration with remaining project partners, tailored to perfectly fit the research purposes of the PANCAIM project. Once combined across clinical centres, this data is an invaluable resource for training AI algorithms and making progress in helping rare cases and complex decisions.
A first step in the harmonisation of data into the CDM is the White Rabbit scan of the data intended for the project, an open-source tool providing information about what type of data, tables and sizes are available in the scanned dataset. This is done in a privacy-presevering way, without direct access to the source data. This step is followed by a mapping workshop with the representatives of each hospital to discuss results and any legal/technical constraints. The final step is to achieve consensus between all clinical data partners about the minimum variables and tables to include in the CDM given the objectives of the research and the shareability of the data.
The PANCAIM CDM is composed of 9 tables, with the patient table being at the centre of the model, complemented by tables for body measurements, past medical history, surgery, lab tests, follow-up/progression, chemotherapy, radiotherapy and time intervals. This makes the CDM a comprehensive framework that standardises a range of clinical observational measurements across European hospitals, specialised for PANCAIM and pancreatic cancer. The makes it easier for current and future data partners to organise their data in a way that enhances its accessibility to fellow clinicians, researchers, and other hospitals.
By enabling harmonisation of clinical observational data with other modalities such as radiological images, OMICs data, and pathological slide, the clinical data model streamlines data integration and improves interoperability. The PANCAIM CDM is a unique development in pancreatic cancer care – it is one of the first of its kind and helps address a unique challenge in combining multi-modal data across multiple European hospital sites to improve pancreatic cancer care and offers researchers and clinicians a unified platform to explore complex datasets and drive innovation in oncological research and patient care. The model thereby stands as a crucial milestone for the PANCAIM consortium and its objectives, and provides the foundation for improving advanced analytics and training machine learning algorithms, where multi-modal pancreatic cancer data is leveraged to build and improve cancer survival predictions, early diagnosis, subtyping or image segmentation.
With this, The Hyve and the PANCAIM consortium at large are strengthening the foundation for collaborative research and innovation in pancreatic cancer care, ultimately paving the way for more effective treatments and improved outcomes for patients worldwide.
For more information on the development of the PANCAIM CDM, see the article published by the HYVE: https://www.thehyve.nl/articles/custom-made-clinical-data-model
