A Decision Tree Model-Based System for Categorizing Aberrant Red Blood Cells

Identifying and classifying abnormal red blood cells (RBCs) are crucial in diagnosing various hematological disorders. In recent years, image analysis has developed as a promising tool for the automated identification and classification of RBCs. In this study, we propose a decision tree algorithm for classifying abnormal RBCs based on their microscopic images. The algorithm uses size, shape, and color to differentiatebetween normal and abnormal RBCs. We used a dataset of microscopic images of RBCs with various abnormalities to evaluate the algorithm's performance. The dataset was divided into two. One is training and other is testing sets, and the decision tree algorithm was trained on the training set. The results show that the algorithm achieved high accuracy in classifying abnormal RBCs with a precision of 94.5% and recall of 93.2%. The proposed decision tree algorithm is efficient approach for the automatic classification of abnormal RBCs. It may help in the detection of hematological illnesses and enhance the effectiveness of blood analysis in medical environments.