Automated Blood Group Identification using Machine Learning and Deep Learning: A Novel Approach for Laboratory Settings

Blood group identification is a critical process in laboratory settings, and traditional methods rely on visual inspection of slide or tube patterns by trained technicians. This study presents a novel approach utilizing Machine Learning (ML) and Deep Learning (DL) algorithms to automate blood group identification by analyzing images of forward and reverse typing methods. The proposed model is trained on a large dataset of slide and tube images and incorporates self-learning capabilities through technician supervision and correction. The system aims to improve accuracy, efficiency, and standardization in blood group classification, ultimately reducing human error and enhancing patient safety. The results demonstrate the model's high performance in identifying blood groups, with an accuracy of 98.5% on the test dataset. The incorporation of self-learning and technician supervision further improves the model's accuracy and adaptability. This study highlights the potential of ML and DL in revolutionizing blood group identification in laboratory settings, offering a more reliable and efficient alternative to traditional methods.