An Intelligent Recommendation of Organ Transplantation System Machine Learning for Donor Recipient Matching

Organ transplantation refers to the transference of organs from donors to recipients for patients suffering from conditions such as kidney failure, liver disease, or heart failure. Despite the importance of organ transplantation, finding suitable donors for the recipients, organ availability, and geographic issues still continue to face extensive challenges. Moreover, a need for transparency heightens these problems. This project aims to propose a new approach of improvement in donor-recipient matching by using machine learning in providing predictive algorithms concerning more accurate compatibility assessments and reduced search times. In this scoring model on compatibility, utilizes a core Random Forest algorithm. The Random Forest algorithm allows us to bring into account blood and tissue matching features along with urgency levels to produce an approximation of the transplantation probability of having a good outcome. With the summing of the results for multiple decision trees, the Random Forest provides a highly robust and accurate matching score to enhance general compatibility assessments.