Background The Kidney Donor Profile Index (KDPI) is a continuous metric used to estimate the risk of allograft failure for kidneys from deceased donors. Lower KDPI scores are associated with longer post-transplant kidney function. This study aims to evaluate the outcomes of kidney transplantation using high-KDPI kidneys (98–100%) compared to those with moderately high KDPI scores (85–97%), employing a novel case-matching approach using machine learning. Methods We conducted a retrospective analysis of the United Network for Organ Sharing (UNOS) database, examining kidney transplants performed in the United States between January 2000 and May 2020. An unsupervised machine learning algorithm was used to match recipients of KDPI 98–100% kidneys with recipients of KDPI 85–97% kidneys based on key baseline characteristics, including recipient age, body mass index (BMI), cold ischemia time, HLA mismatch, ethnicity, and gender. Results A total of 6,624 matched cases were selected for analysis. The mean follow-up duration was 4.5 years for the KDPI 98–100% cohort and 4.6 years for the KDPI 85–97% cohort. The five-year allograft survival was 51.7% for the KDPI 98–100% group versus 58% for the KDPI 85–97% group (P < 0.001). Asian recipients showed the highest survival in both cohorts (68% vs. 69%). Donation after circulatory death (DCD) status did not significantly impact outcomes. Across the full cohort, 1,819 cases of allograft failure were recorded, with chronic rejection being the leading cause (28.4% vs. 30%, P = 0.56). Conclusion Transplantation with high-KDPI kidneys, though associated with lower survival rates, remains a viable option for expanding the donor pool. With appropriate recipient selection, high-KDPI kidneys can improve patient quality of life, reduce wait times, and lower healthcare costs. Our findings support a more nuanced approach to organ allocation using advanced matching strategies.
Moein et al. (Tue,) studied this question.