Comparative Evaluation of Machine Learning Models for Predicting Donor Kidney Discard

TL;DR

This study systematically compares various machine learning models for predicting donor kidney discard, emphasizing the importance of standardized data processing and evaluation over model choice.

Contribution

It provides a reproducible benchmarking framework and demonstrates that ensemble models outperform individual models in this prediction task.

Findings

Ensemble model achieved MCC=0.76, AUC=0.87, F1=0.90.

Standardized preprocessing and evaluation are crucial for fair comparison.

Donor age and renal markers are key predictors across models.

Abstract

A kidney transplant can improve the life expectancy and quality of life of patients with end-stage renal failure. Even more patients could be helped with a transplant if the rate of kidneys that are discarded and not transplanted could be reduced. Machine learning (ML) can support decision-making in this context by early identification of donor organs at high risk of discard, for instance to enable timely interventions to improve organ utilization such as rescue allocation. Although various ML models have been applied, their results are difficult to compare due to heterogenous datasets and differences in feature engineering and evaluation strategies. This study aims to provide a systematic and reproducible comparison of ML models for donor kidney discard prediction. We trained five commonly used ML models: Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, and Deep Learning along with an ensemble model on data from 4,080 deceased donors (death determined by neurologic criteria) in Germany. A unified benchmarking framework was implemented, including standardized feature engineering and selection, and Bayesian hyperparameter optimization. Model performance was assessed for discrimination (MCC, AUC, F1), calibration (Brier score), and explainability (SHAP). The ensemble achieved the highest discrimination performance (MCC=0.76, AUC=0.87, F1=0.90), while individual models such as Logistic Regression, Random Forest, and Deep Learning performed comparably and better than Decision Trees. Platt scaling improved calibration for tree-and neural network-based models. SHAP consistently identified donor age and renal markers as dominant predictors across models, reflecting clinical plausibility. This study demonstrates that consistent data preprocessing, feature selection, and evaluation can be more decisive for predictive success than the choice of the ML algorithm.