Abstract
<jats:p>The process of finding suitable kidney transplant donors stands as a crucial problem because of the shortage of available organs as well as complicated matching procedures. The implementation of traditional matching systems produces allocation errors that result in fewer successful organ transplant results. The analysts propose an Enhanced Artificial Neural Network (EANN) model to enhance kidney allocation efficiency by combining ABO compatibility information with HLA genotyping analysis using survival prediction models. One thousand patient records comprise the dataset where EANN runs concurrently with Random Forest, Naïve Bayes, and K-Nearest Neighbors (KNN). According to experimental outcomes, EANN delivered accuracy levels of 92%, which surpassed Random Forest's88%, Naïve Bayes's84%, and KNN's 86%. The proposed model improved transplant survival rates by increasing them to 88% while decreasing mismatch rates from 20% in 2022 to 8% in 2024.</jats:p>