Machine Learning Predictions for Assessing Hard-to-Place Deceased Donor Kidneys

Nearly 20% of deceased donor kidneys in the United States are placed “out-of-sequence” (ie, outside of standard alloca-
tion rules). The rationale for out-of-sequence placements is to expedite placement of kidneys at risk of nonuse. The research team, including Blueprint Co-Director Nikhil Agarwal and Research Affiliate Paulo Somaini, aimed to (1) develop machine learning (ML) models to predict the risk of kidney nonuse over time during the allocation process and (2) use the ML predictions to assess current out-of-sequence placements.