Machine Learning Approaches for Potential Blood Donors Prediction

Abstract

Human blood is very important to save the life of other people. During blood donation process, blood is directly collected from donors, processed and stored in the blood bank. It must be managed effectively for the need during emergency in hospitals. The area of transfusion medicine, specifically blood donation services requires an intelligent system for automation of the process. Hence, an intelligent system that can integrate major operations involved in the blood bank, make efficient decisions and improve communication is required. A system of this sort would involve machine learning algorithms for efficient donor selection. Accurate prediction of the number of blood donors can help medical professionals know the future supply of blood and plan accordingly to entice voluntary blood donors to meet demand. In this research, the pattern of blood donors’ behaviors is based on factors influencing blood donation decision that is conducted using online questionnaire. To find out the potential individuals to become the blood donor the factors like altruistic values, knowledge in blood donation, perceived risks, attitudes toward blood donation, and intention to donate blood, are analyzed. To predict whether individual person is a donor or not from the data given by the person, Naive Bayes technique and K-nearest neighbors (KNN) algorithm are used. The results indicate that the accuracy value for KNN is higher than the Naive Bayes algorithm. The database can be used to track potential blood donors.