Predicting kidney transplant survival using multiple feature representations for HLAs

Mohammadreza Nemati, Haonan Zhang, Michael Sloma, Dulat Bekbolsynov, Hong Wang, Stanislaw Stepkowski, Kevin S. Xu

Abstract: Highlights•We propose novel feature representations for Human Leukocyte Antigen (HLA) compatibility between kidney transplant donors and recipients.•We incorporate these HLA feature representations into machine learning-based survival analysis algorithms to predict the time until a transplant will fail.•We demonstrate that our HLA feature representations improve prediction accuracy on a database of over 100,000 transplants.