The utility of machine learning for predicting donor discard in abdominal transplantation

Abstract

Background Increasing access and better allocation of organs in the field of transplantation is a critical problem in clinical care. Limitations exist in accurately predicting allograft discard. Potential exists for machine learning to provide a balanced assessment of the potential for an organ to be used in a transplantation procedure. Methods We accessed and utilized all available deceased donor United Network for Organ Sharing data from 1987 to 2020. With these data, we evaluated the performance of multiple machine learning methods for predicting organ use. The machine learning methods trialed included XGBoost, random forest, Naïve Bayes (NB), logistic regression, and fully connected feedforward neural network classifier methods. The top two methods, XGBoost and random forest, were fully developed using 10‐fold cross‐validation and Bayesian optimization of hyperparameters. Results The top performing model at predicting liver organ use was an XGBoost model which achieved an AUC‐ROC of .925, an AUC‐PR of .868, and an F1 statistic of .756. The top performing model for predicting kidney organ use classification was an XGBoost model which achieved an AUC‐ROC of .952, and AUC‐PR of .883, and an F1 statistic of .786. Conclusions The XGBoost method demonstrated a significant improvement in predicting donor allograft discard for both kidney and livers in solid organ transplantation procedures. Machine learning methods are well suited to be incorporated into the clinical workflow; they can provide robust quantitative predictions and meaningful data insights for clinician consideration and transplantation decision‐making.

Revolutionizing Kidney Transplantation: Connecting Machine Learning and Artificial Intelligence with Next-Generation Healthcare—From Algorithms to Allografts

“…Other researchers have concentrated on predicting allograft or donor discards. Pettit et al [57] showed the efficacy of the XGBoost model at predicting organ use, while Barah et al [58] observed random forest's proficiency in identifying kidneys at risk of discard, with Price et al [59] having developed a kidney discard risk index, identifying 21 factors predictive of organ discard.…”

LightGBM outperforms other machine learning techniques in predicting graft failure after liver transplantation: Creation of a predictive model through large‐scale analysis

“…3 ML has been used for LTx to evaluate graft survival and donor discard rates, however the varying results could be attributed to model selection or testing procedures. 4,5 In order to implement ML algorithms that predict post-LTx out-…”

“…Quantifying the risks associated with recipient‐donor matching becomes a paramount priority in ensuring proper transplantation practices. When assessing the risk associated with a specific donor‐recipient pair, there exists a multitude of donor and recipient variables that could potentially be considered 3–6 . Developing methods that enable more precise prediction of graft survival following LTx can enhance physician decision‐making, improving organ utilization and graft outcomes.…”

“…ML techniques have been used to predict outcomes after cardiac transplant 2 and kidney transplant 3 . ML has been used for LTx to evaluate graft survival and donor discard rates, however the varying results could be attributed to model selection or testing procedures 4,5 …”