Enhancing Donor Eligibility Criteria using Machine Learning to Maximize Blood Donation Efficiency

Abstract

Introduction: In todays healthcare scenarios, there is need to optimize blood donation processes, ensuring that only eligible donors are selected, thereby improving the efficiency and effectiveness of blood collection and transfusion services.

Objectives: This research aims to investigate the application of machine learning techniques in determining donor eligibility for blood donation based on critical factors such as the last donated month, recency, frequency, and volume of blood donated in CC units.

Methods: This work employs a comprehensive dataset, including historical donor information and various demographic factors, to train machine learning models. These models are designed to predict donor eligibility based on the aforementioned criteria, with the goal of enhancing the accuracy and reliability of donor screening processes.

Results: The findings of this research should significantly progress the field of managing blood donations by providing a way for evaluating a donor's eligibility based on data. Improved donor retention, more efficient blood collection processes, and eventually more lives saved by timely and successful blood transfusions could be the outcomes of this.

Conclusions: The research leverages advanced machine learning algorithms, including Random Forest (RF), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Decision Trees, and Linear Regression, to analyze the data and identify patterns that correlate with donor eligibility.