Using big data to develop and validate clinical prediction models for survival outcomes in kidney transplant

Kidney transplantation is the organ transplant of a kidney to a patient with end-stage kidney disease. When a donor kidney is offered to a waitlisted patient, the clinical team responsible for the care of the potential recipient must make the decision to accept or decline the offer based upon complex and variable information about the donor, the recipient and the process of transplantation. Predicting graft and patient survival following transplantation is important to support this decision-making process. While research has been conducted to predict graft failure following kidney transplantation, they did not focus on patient survival and were based on a limited set of variables. There is a clinical need to develop new statistical methods using big data to better predict graft and patient survival in transplant recipients.

This project brings the opportunity to seek to use the linked registry data from national databases to develop and validate clinical prediction models for survival outcomes. The project will aim to integrate data from multiple sources, develop models to predict risks of graft failure and death over time, and conduct an internal and external validation of the developed prediction models.