Source Code for a Study on the Use of Artificial Intelligence in Predicting the Life Expectancy of Liver Graft Recipients

The code developed in this research aims to implement, train, evaluate, and interpret Artificial Intelligence models capable of predicting whether liver transplant recipients will survive for more or less than twelve months, using exclusively the clinical data available to medical teams at the time an organ is offered. The entire development process was structured in a modular and reproducible manner, in accordance with the principles of the Design Science Research (DSR) methodology. The core component of the code corresponds to the implementation of supervised/unsupervised machine learning models, including linear models, decision trees and ensemble-based methods. Each model is trained to solve a binary classification problem, in which the target variable represents recipient survival beyond twelve months. The training process includes cross-validation and hyperparameter tuning to ensure robustness and to mitigate overfitting. To assess model performance, the code computes quantitative evaluation metrics the PR-ROC curve, Brier Sciore and Mean Net Benefit. These metrics enable systematic comparison across models and support the identification of those with the greatest potential for practical clinical application. In addition, the code incorporates interpretability and explainability techniques to identify the most relevant features for each trained model. This step is essential for aligning Artificial Intelligence outputs with clinical practice, allowing healthcare professionals to understand the factors that most strongly influence survival predictions and helping to reduce subjectivity in graft acceptance decisions. Please, do not forget to cite the database that are store in https://zenodo.org/records/18189988, with following DOI: https://doi.org/10.5281/zenodo.18189988. Full Citation (IEEE) [1]A. Galindo Leal, J. R. De Oliveira, B.-H. Ferraz Neto, R. L. Macacarie F. de A. Monteiro, “Anonymized Donor–Recipient Clinical Dataset for Artificial Intelligence Models in Liver Transplantation (São Paulo State, 2007–2022)”. Zenodo, jan. 08, 2026. doi: 10.5281/zenodo.18189988.