Machine-Learning Based Organ Matching Prediction System

Organ transplantation is one of the most effective treatments for end-stage organ failure, yet the shortage of compatible donors remains a major global healthcare challenge. Identifying a suitable donor-recipient pair requires evaluation of numerous medical parameters, including blood group compatibility, age, organ type, tissue matching, urgency level, and overall health condition. Traditional matching processes rely heavily on manual assessment by medical experts, which can be time-consuming and prone to human error. This paper presents a machine learning–based organ matching prediction system designed to automate compatibility analysis using historical transplant data. Multiple classification algorithms, including Logistic Regression, Decision Tree, Support Vector Machine, and Random Forest, are employed to determine the most accurate predictive model.