Working at UMCG means working in an inspiring and professional environment where development and innovation are central. Within the ADORABLE consortium, funded by the Dutch Kidney Foundation and NWO, you will contribute to groundbreaking research that has the potential to transform the future of kidney transplantation.
Background
Within the ADORABLE consortium, academic and clinical partners collaborate to improve the selection and assessment of donor kidneys for transplantation. Each year, more than 1,000 kidney transplants are performed in the Netherlands, half of which involve kidneys from deceased donors. The 10-year survival rate of kidneys from deceased donors is only 50%, compared with 70% for kidneys from living donors. At the same time, many potentially viable kidneys are discarded, partly due to the lack of reliable predictors of transplant outcomes.
The ADORABLE consortium focuses on developing an advanced, data-driven assessment system for donor kidneys. Central to this approach is the use of machine learning to evaluate the predictive value of biomarkers from multiple sources: donor-related clinical data, perfusion fluid, and kidney biopsies. Blood and urine samples may contain unique information about organ quality that is not visible from macroscopic characteristics. In this PhD project, the consortium aims to develop AI models that predict clinically relevant outcomes based on existing and novel biomarker data and outcome measures. The ultimate goal is to implement and use these algorithms directly in patient care.
This innovative approach will contribute to more reliable donor kidney selection, reduced rejection rates, and improved long-term outcomes for patients. The project offers a unique opportunity to contribute to socially relevant research with direct clinical impact.
What will you do
As a PhD student, you will contribute to the development of an advanced predictive model for donor kidney transplant outcomes. You will focus specifically on the analysis of large datasets using machine learning and deep learning techniques. You will:
- Contribute to the development of innovative methods for performing such analyses.
- Apply new and existing methods to make the most accurate possible predictions of transplant outcomes such as graft failure and mortality.
- Compare the predictive performance of AI-driven analyses with other epidemiological approaches.
- Collaborate with national and international experts in clinical data science.
- Present results at national and international conferences and publish in scientific journals.