2023-06-22 11:57:17
One in four patients with colon cancer will experience complications following colon cancer surgery, leading to readmission, permanent damage and, in some cases, premature death. The new research project FLORENCE aims to improve the diagnosis, prognosis and treatment of patients with colorectal cancer. The project will develop an AI (artificial intelligence) tool to give doctors a better basis for patient treatment decisions.
Understanding disease patterns
In addition to AI, the FLORENCE project uses the OMOP Common Data model. This model allows health data from different research institutions (such as European hospitals) to be uniformly structured, making it easier for researchers and clinicians to share, compare and analyze data. This allows them to better understand the effectiveness of treatments, safety of medicines and understand disease patterns on a large scale. The OMOP model has developed a common language in which different types of health information such as diagnoses, treatments, laboratory results and medication data can be coded and stored. All necessary to compare and link data from different research institutions.
For the first time on a global scale, the project links the AI model directly to the clinics through federated learning. That is why the project is unique in its approach because decision support in the treatment of colorectal cancer patients directly benefits patients.
Partners
The main partner of the project is the Center for Surgical Science and the research department of the University Hospital Zeeland in Køge (Denmark). Partners are Oslo University Hospital (Norway’s Oncology Pelvic Surgery Unit and Cancer Registry, respectively), Lund University (Sweden) and Denmark’s Technical University. IKNL is also a partner in the project. IKNL will help provide the software for federated learning: the vantage6 infrastructure. In addition, IKNL contributes knowledge in the field of the OMOP common data model. The ambition is to test the insights and results from FLORENCE on the Dutch patient population via the Dutch Cancer Registry (NKR).
Federated learning met vantage6
Within IKNL we use federated learning in many projects, the term Personal Health Train is also often used for this. IKNL has developed software for federated learning with other partners: vantage6. This software ensures that various parties, such as hospitals and researchers, can talk to each other: you can set up queries and you will receive the answers. In this case, patient data remains decentrally stored, for example in the EHR of the hospital, and only the algorithms ‘travel’ like a train along data sources with a specific, well-defined assignment.
More information
Project period: December 1, 2022 to December 1, 2025.
For questions, please contact: Gijs Geleijnse, senior clinical data scientist IKNL and Anja van Gestel, clinical data scientist IKNL.
#improve #colon #cancer #treatment