Published
XplOit data integration for predictive models in transplantation
AI and real-world clinical data
XplOit was a BMBF i:DSem consortium (2016–2021) coordinated by Fraunhofer IBMT. It built a platform for integrating clinical data and developing prediction models after allogeneic stem cell transplantation. University Hospital Essen contributed clinical expertise and data. This research group did not lead the consortium. A 2022 paper with Amin Turki as last author reports machine-learning prediction of mortality and CMV reactivation after transplantation.
What problem are we trying to solve?
How can heterogeneous clinical data be integrated, with privacy constraints, to support predictive models after allogeneic transplantation?
Why it matters
Predictive modeling in HCT is limited by fragmented hospital data. Ontology-based integration was a prerequisite for later machine-learning work.
Approach
BMBF i:DSem consortium, 1 March 2016 to 28 February 2021, coordinated by Fraunhofer IBMT. University Hospital Essen contributed clinical expertise and data. This group did not coordinate the consortium.
Who is working on it
Consortium source
The March 2019 Fraunhofer IBMT press release describes the consortium. Fraunhofer IBMT coordinated the platform. The Clinic for Bone Marrow Transplantation and the Institute for Virology at University Hospital Essen are named as clinical partners. That release does not describe this research group as the project lead.
Papers and abstracts
- XplOit: An Ontology-Based Data Integration Platform Supporting the Development of Predictive Models for Personalized Medicine Stud Health Technol Inform 2018
- Time-dependent prediction of mortality and cytomegalovirus reactivation after allogeneic hematopoietic cell transplantation using machine learning Am J Hematol 2022