Predicting Donor Selection and Multi-Organ Transplantation within Organ Procurement Organizations Using Machine Learning

Organ procurement organizations (OPOs) play a crucial role in the field of organ transplantation, serving as key intermediaries in the process of organ donation. However, despite their vital function, there exists a pressing issue of transparency within the organ allocation process. This opacity not only impedes the overall effectiveness of OPOs but also raises ethical and societal concerns regarding organ distribution. This study utilizes the recently published ORCHID dataset, containing 133,101 records of organ donor referrals, to understand organ procurement and donor selection strategies in OPOs using machine learning (ML). We developed seven ML classification models to predict donor selection and the likelihood of at least four organs being suitable for transplantation, in line with established definitions of multi-organ transplantation. The models demonstrated variable recall values for donor selection, ranging between 0.62 and 0.80, while achieving consistently high performance across other evaluation metrics, notably with AUC values exceeding 0.95. Particularly in the context of multi-organ transplant predictions, the models exhibited remarkable effectiveness, with recall values spanning from 0.88 to 0.98 and AUC metrics consistently above 0.97. Administrative milestones and particular organ transplants were identified as key determinants in the organ allocation process. This studys findings suggest significant opportunities to improve organ allocation strategies by focusing on the optimization of administrative practices, highlighting their substantial impact on transplantation success rates.