As of late 2019, there were nearly 800,000 people with end-stage kidney disease in the United States. Living donor kidney transplantation (LDKT) is the treatment of choice for such individuals, as it is associated with significantly improved long-term survival and quality of life compared to other renal replacement strategies. For any potential LDKT recipient, it is important to predict the risk of transplanted organ (graft) failure so as to inform selection of the best available donor kidney for said recipient. This is a challenging task, as graft failure results from many complex interactions between donor and recipient characteristics. Our team developed several predictive models of graft loss using survival analysis techniques and random forest and XGBoost algorithms. In all cases, we compared performance to an earlier model for graft loss risk created by our clinical mentors. We ultimately aim to develop a novel risk index which will facilitate the matching of potential living kidney donors to recipients so as to maximize transplant survival.

Team Members

[foreach 357]

• [if 397 not_equal=””][/if 397][395]

[/foreach 357]

Project Mentors, Sponsors, and Partners

• Allan Massie

• Dorry Segev

• Raimond L Winslow

• Joseph L Greenstein

Course Faculty

[foreach 429]

• [if 433 not_equal=””][/if 433][431]

[/foreach 429]

Project Links

• Project Poster Image

Additional Project Information