This project explored novel automation approaches to leukemia diagnosis to addressing the subjectivity and inefficiency inherent in current techniques. Single-cell flow cytometry data was analyzed and organized using machine learning algorithms, particularly supervised and unsupervised models like logistic regression, random forests, and convolutional neural networks (CNNs), to enhance diagnostic accuracy. Dimension deduction and data visualization with UMAPs also improves system efficiency. The project outlines an end-to-end pipeline for data preprocessing, model programming, training, and post-processing