Table 1. Comparisons among ToPs/R, existing clinical risk scores, regression methods, and machine learning benchmarks for post-transplantation survival prediction using C-index and AUC (at horizons of 3-months, 1-year, 3-years, and 10-years).

Methods	AUC (Mean ± Std)				C-index (Mean ± Std)
	3-month	1-year	3-year	10-year
ToPs/R	.660 ± .003	.641 ± .005	.623 ± .005	.631 ± .003	.577 ± .003
DRI	.540 ± .007	.547 ± .004	.547 ± .003	.556 ± .005	.529 ± .002
IMPACT	.561 ± .005	.556 ± .006	.549 ± .007	.558 ± .005	.527 ± .003
RSS	.587 ± .006	.582 ± .006	.570 ± .004	.547 ± .003	.544 ± .003
Cox	.572 ± .006	.579 ± .005	.553 ± .005	.577 ± .004	.519 ± .003
Linear P	.632 ± .007	.617 ± .003	.596 ± .003	.612 ± .005	.554 ± .003
Logit R	.629 ± .007	.613 ± .007	.599 ± .006	.611 ± .007	.554 ± .004
AdaBoost	.605 ± .006	.605 ± .006	.588 ± .004	.596 ± .004	.551 ± .003
DeepBoost	.594 ± .009	.608 ± .004	.591 ± .006	.594 ± .004	.548 ± .003
LogitBoost	.621 ± .005	.614 ± .004	.596 ± .004	.611 ± .003	.554 ± .003
XGBoost	.565 ± .007	.553 ± .005	.548 ± .003	.584 ± .005	.530 ± .003
DT	.592 ± .007	.595 ± .004	.575 ± .004	.595 ± .003	.543 ± .003
RF	.625 ± .004	.610 ± .004	.597 ± .003	.607 ± .004	.555 ± .003
NN	.600 ± .003	.608 ± .007	.587 ± .004	.598 ± .003	.550 ± .003

Linear P: Linear Perceptron, Logit R: Logistic Regression, DT: Decision Tree, RF: Random Forest, NN: Neural Nets