Anonymized Donor–Recipient Clinical Dataset for Artificial Intelligence Models in Liver Transplantation (São Paulo State, 2007–2022)

This repository contains an anonymized clinical dataset used in the study “A Study on the Use of Artificial Intelligence in Predicting the Life Expectancy of Liver Graft Recipients”. The data originate from the liver transplant registry of the State of São Paulo, Brazil, and include donor–recipient pairs collected between 2007 and 2022. The dataset was constructed to support the development and evaluation of machine learning models for predicting 12-month post-transplant survival. It includes demographic, clinical, laboratory, and transplant-related variables that are typically available to transplant teams at the time of organ allocation. After data cleaning, cohort construction, and exclusion criteria, the final dataset comprises 7,098 liver transplant cases. All personal identifiers were removed, and the data were fully anonymized in compliance with Brazil’s General Data Protection Law (LGPD). The study was approved by the appropriate ethics committee, with a waiver of informed consent due to the use of anonymized registry data. The dataset can be used for: Development and benchmarking of predictive models for post-transplant survival Research on donor–recipient matching and graft allocation Studies on class imbalance and clinical decision support systems Reproducibility and validation of results reported in the associated publication This dataset is provided for research and educational purposes only and is not intended for direct clinical decision-making without appropriate validation.